DETAILED ACTION
This action is in response to communications filed on 2/11/2026 in which claims 1, 5-7, and 9 -17 have been amended. No claims have been added nor cancelled. Claims 1-20 are presented for examination.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Specification Objections
Applicant has amended the title of the invention to “Decoupled Prediction Evaluation of Autonomous Vehicle Trajectories” in response to the previously set for objection to the non-descriptive title.
Examiner submits that this change is appropriate and the objection has been accordingly withdrawn.
Applicant has amended the specification for typographical errors.
The changes are appropriate and do not introduce new matter. The objections have been withdrawn.
Claim Objections
Applicant has amended the claims in response to informalities presented in the previous action.
The amendments are sufficient to overcome the previously set forth objections. Accordingly, the objections to claims 5-6, 10-14, 16, and 18-20 have been withdrawn.
Rejections under 35 U.S.C. § 112
Claims 7 and 15 have been amended in response to the previously set forth rejection under 35 U.S.C. § 112.
The amendment clarifies the intent of the claim and accordingly the rejections to claims 7 and 15 under 35 U.S.C. § 112 (and the corresponding dependent claims which incorporate such deficiencies) have been withdrawn.
Rejections under 35 U.S.C. § 101
Applicant disagrees with the previously set forth rejection under 35 U.S.C. § 101.
Arguments have been considered but are not persuasive. A detailed response has been provided below for each of the main arguments made.
Applicant argues that the present claims do not recite a mental process. The applicant argues that the apparatus, system and method of the claim contain physical characteristics of tangible physical objects, noting measurements by sensors, physical obstacles, an autonomous driving vehicle. The applicant further notes that the physical components are used to predict characteristics of the obstacle and then used to adjust the ADV’s kinematic response whereby there is a tangible physical result- the ADV operated according to its planned trajectory.
Many of the argued specific features of the invention are not claimed (map location, absolute and relative position, absolute and relative speed, throttle, brake, steering settings, etc.). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Furthermore, the applicant has admitted that a prediction is made within the claims, whereby a prediction is a process that can be practically performed in the human mind. There is no tangible physical result presented by the claims because the mechanism by which the ADV is operated within the claims is not so limited by any physical manipulations. Under broadest reasonable interpretation and when read in light of the specification (see spec ¶19), operating the ADV based on the planned trajectory may encompass sending a command over a network by which to operate the ADV. Sending data over a network has been found by the courts to be a well understood, routine, and conventional computer function when claimed in a merely generic manner such as in the claim. There are no required elements per the claim that would distinguish what “operating the ADV based on the planned trajectory determined by the planning module of the ADV” would entail otherwise beyond such interpretation.
Applicant further argues that the claimed invention cannot be performed in the human mind because the number of variables and the amount of data that must be kept in memory at the same time to predict and adjust trajectories is too great for the human mind. Applicant further argues that a human could not otherwise perform the computations required multiple times per second, as required by the amended claims.
The steps of the claims can be performed practically in the human mind, or using assistive physical aids. The courts do not distinguish between mental processes performed entirely in the human mind or using pen and paper as assistive aids, nor do the courts distinguish between mental processes performed using a computer. A generic computer would have the capacity to perform predictions multiple times per second as required by the claims and therefore the claim is still understood to recite a mental process except for the recitation of generic computing components as a tool to perform such process. The claims do not contain limitations that prohibit the methodology claimed from being performed in the human mind such as number of variables, amount of data in memory, etc, as argued by the applicant.
The applicant argues that the claims are directed to non-abstract improvements in ADV trajectory prediction and ADV operation, comfort, and safety.
An improvement in ADV trajectory prediction is an improvement to the steps which may be construed as a mental process. The judicial exception alone cannot provide the improvement but rather the improvement must be provided in the claims by additional element(s) or additional element(s) in conjunction with the judicial exception. There are no additional elements recited that present an inventive concept. The claims further do not recite any sort of improvement in ADV operation. Simply claiming that the ADV operates based on the prediction is the mere application of the optimized value (from the judicial exception) being applied in a non-descriptive and non-inventive way that would be distinguished from any existing technology. It is not claimed how the ADV operates in any inventive capacity. Merely using the data obtained as part of the prediction process (by “operating” and not explicitly specifying what “operating” entails) does not present an inventive concept or reflect any sort of alleged improvement to the technology.
Applicant further argues that a specific and novel procedure is applied to physical data collected about the obstacle to determine its kinematic/ physical response and once determined the kinematic response can have physical consequences.
These features are not claimed and therefore the claim does not recite any additional elements that would integrate the recited exceptions into any sort of practical application or provide an inventive concept.
Applicant argues that the claims recite significantly more than the abstract idea. Applicant first notes that the combinations of the claims utilize physical characteristics of tangible physical objects to predict physical characteristics and that such prediction results in physical kinematic responses of the ADV to account for the obstacle. Applicant highlights that there is an ultimate tangible physical response when the ADV is operated according to the planned and adjusted kinematic response.
Using characteristics of physical objects to make a prediction does not go beyond the capacity of the human mind. Characteristics of physical objects are merely data by which judgements can be made, such as in a mental process to make a prediction. No particular physical response is claimed per the operation of the ADV. There are no claimed physical elements that would demonstrate how the predicted value is applied for use by the ADV in any inventive capacity.
Applicant argues that the claimed combinations result in a technological improvement in two areas- ADC trajectory prediction and ADV operation, comfort, and safety.
Applicant has again admitted that the inventive concept is rooted in the prediction which is the recited mental process. There are no claim elements that demonstrate an improvement to ADV operation, comfort, or safety. Any purported improvement flows as a direct consequence to the improvements set forth within the mental process. The mechanism by which the prediction is applied is not specifically claimed such that it would be apparent to one having skill in the art that an improvement to the technology of ADV operation exists within the claimed elements.
Accordingly, for the reasons stated in this response, in conjunction with the updated rejection of this office action, the claims remain rejected under 35 U.S.C. § 101.
Rejections under 35 U.S.C. § 103
The claims have been amended in response to the previously set forth rejections under 35 U.S.C. § 103. The applicant argues that the prior art of record cannot render the claim obvious because the combination fails to disclose every element of the amended claim. Applicant argues that Lapin does not disclose, teach, or suggest that its weighted loss function includes one or more variables and a weight corresponding to each variable wherein each variable is based on a decomposition of an error in the predicted trajectory and each weight is based on the planned trajectory of the ADV. The applicant further argues that dependent claims incorporate such feature and would likewise be considered obvious over the prior art of record for the same rationale as given for the independent claims.
The argument has been considered but is not persuasive. Lapin does disclose a weighted loss function with one or more variables and a weight corresponding to each variable ((Lapin, ¶36) " The generated candidate trajectories 133 and the corresponding driving constraints 113 may be fed to the cost function 134 which evaluates/ranks the candidate trajectories based on a number of cost terms (also referred to as input terms) and a number of weights associated with these cost terms."). Lapin further discloses that the cost terms (as the variable) are derived from an evaluation (as an error), between (decomposition of) a predicted trajectory and an ideal trajectory ((Lapin, ¶41) “FIG. 4B illustrates an example process 400B for determining a total cost for an evaluated trajectory. As an example and not by way of limitation, the system may determine a number of cost terms corresponding to a number of parameters ( e.g., Pi, P 2 , P 3 ) associated with the evaluated trajectory. For each cost term, the system may determine a corresponding vector ( e.g., vector 411 for Pi, vector 413 for P 2 , vector 415 for P 3 ) for the evaluated trajectory. Then, the system may identify the scenario associated with the evaluated trajectory and access a reference model associated with this scenario. Then, the system may determine an ideal trajectory based on the reference model associated with this scenario. After that, for each cost term, the system may determine a vector ( e.g., vector 412 for Pi, vector 414 for P 2 , vector 414 for P3) for the ideal trajectory. Then, the system may calculate a cost associated for the evaluated trajectory based on each cost term ( e.g., 401 for P 1 , 402 for P 2 , 403 for P3). For example, the system may compare the corresponding elements of the vectors 411 and 412 to determine the difference of corresponding elements. Then, the system may determine the cost 401 by summing up the difference of all vector elements. As another example, the system may compare the corresponding elements of the vectors 413 and 413 to determine the difference of corresponding elements. Then, the system may determine the cost 402 by summing up the difference of all vector elements. As another example, the system may compare the corresponding elements of the vectors 415 and 416 to determine the difference of corresponding elements. Then, the system may determine the cost 403 by summing up the difference of all vector elements. After that, the system may determine the total cost 410 of the evaluated trajectory by summing up the costs determined based on respective cost terms as weighted by respective weights ( e.g., weights 421, 422, and 423). The total cost 410 may indicate an overall similarity level or disparity level of the evaluated trajectory with respect to the ideal trajectory determined based on a reference model associated with this scenario.”). Lapin further discloses that the weights are adjusted according to the planned trajectory ((Lapin, ¶34) " After that, the system may compare the two versions of planned trajectories and use the comparison result to optimize the constraint prediction algorithm or/and the cost function weights of the trajectory planner."). See also Lapin Figure 4B describing this concept. Accordingly, the prior art of record does disclose such feature.
Applicant has not particularly argued the newly added feature “multiple times per second” but nonetheless, explanation is provided herein regarding the rejection of the limitation. Examiner acknowledges that the prior art of record, particularly Burisch and Lapin, does not explicitly disclose “multiple times per second”; however, the amendment required further search and consideration by the examiner. During search, newly relied-upon reference Xu was found to teach the claimed limitation. Accordingly, the claims remain rejected over the prior art (35 U.S.C. § 103).
Claim Rejections - 35 USC § 112
Claims 2-4 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 2-4 recites the limitation "wherein the decomposing the loss function of the analysis model of the prediction module into the multiple components with the multiple weightings comprises" . There is insufficient antecedent basis for this limitation in the claim because the basis by which this limitation was constructed has been amended in the corresponding independent claim.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The following section follows the 2019 Patent Eligibility Guidance (PEG) for analyzing subject matter eligibility:
Step 1 - Statutory Category:
Step 1 of the PEG analysis entails considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101 (process, machine, manufacture, or composition of matter).
Step 2A Prong 1 - Judicial exception:
In Step 2A Prong 1, examiners evaluate whether the claim recites a judicial exception (an abstract idea, law of nature, or a natural phenomenon).
Step 2a Prong 2 - Integration into a practical application:
If claims recite a judicial exception, the claim requires further analysis in Step 2A Prong 2. In Step 2A Prong 2, examiners evaluate whether the claim as a whole integrates the exception into a practical application.
Step 2B - Significantly More:
If the additional elements identified in Step 2A Prong 2 do not integrate the exception into a practical application, then the claim is directed to the recited judicial exception and requires further analysis under Step 2B- Significantly More.
As noted in the MPEP 2106.05(II): The identification of the additional element(s) in the claim from Step 2A Prong 2, as well as the conclusions from Step 2A Prong 2 on the considerations discussed in MPEP 2106.05(a) -(c), (e), (f), and (h) are to be carried over. Claim limitations identified as Insignificant Extra-Solution Activities are further evaluated to determine if the elements are beyond what is well -understood, routine, and conventional (WURC) activity, as dictated by MPEP 2106.05(II).
Independent Claims:
Claim 1:
Step 1: Claim 1 and its dependent claims 2-8 are directed to a method which falls within one of the four statutory categories of a process.
Step 2A Prong 1: Claim 1 recites a judicial exception, noted in bold:
determining a predicted a trajectory of an obstacle The claim limitation can be reasonably read to entail evaluating the characteristics of an obstacle to predict the trajectory by which the obstacle will move. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
determining, [[…]] a planned a trajectory of the ADV based on the predicted trajectory of the obstacle The claim limitation can be reasonably read to entail evaluating the trajectory of the obstacle to make a judgement as to how the trajectory of the ADV should be planned. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
determining a weighted loss function, the weighted loss function including one or more variables and a weight corresponding to each variable, wherein each variable is based on a decomposition of an error in the predicted trajectory and each weight is based on the planned trajectory of the ADV; and The claim limitation can be reasonably read to entail making a judgment for a weighted loss function, wherein the function has cost terms and associated weights for each cost term and the cost terms and associated weights are derived according to the given requirements. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, the recitation of a weighted loss function with corresponding variables and weight values is a mathematical calculation and therefore the claim additionally recites the judicial exception of abstract ideas as a mathematical concepts
evaluating a performance of the prediction module based on the weighted loss function to improve the performance of the prediction module to increase a safety and comfort of the ADV. The claim limitation can be reasonably read to entail evaluating the weighted loss function to make a judgement of the performance of the prediction module. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because this claim limitation recites the utilization of the weighted loss function to determine a performance accuracy metric, the claim further recites the judicial exception of abstract ideas as a mathematical calculation, which is a mathematical concept.
Therefore, the claim recites a judicial exception.
Step 2A Prong 2: Additional elements were identified and are noted in italics.
by a prediction module of the ADV - This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
multiple times per second- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to execute the judicial exception.
by a planning module of the ADV - This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
operating the ADV based on the planned trajectory determined by the planning module of the ADV – This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) for amounting to the words “apply it” with regard to the value obtained as part of the judicial exception. The limitation has further been identified as Insignificant Extra Solution Activity (MPEP 2106.05(g))
The courts have found that merely including instructions to implement an abstract idea on a computer or merely using a computer as a tool to perform an abstract idea (Mere Instructions to Apply an Exception (MPEP 2106.05(f))) and appending insignificant extra solution activity (Insignificant Extra Solution Activity (MPEP 2106.05(g))) to the judicial exception does not integrate the judicial exception into a practical application.
When viewed independently and within the claim as a whole, the additional element does not appear to integrate the judicial exception into a practical application.
Step 2B: Additional elements identified and conclusions from Step 2A Prong 2 are carried over for evaluating if the claim, as a whole, amounts to an inventive concept that is significantly more than the judicial exception. Elements identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) as well as the combined elements are evaluated to determine if they are beyond well understood, routine, and conventional activities.
operating the ADV based on the planned trajectory determined by the planning module of the ADV – This limitation was identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)). When read in light of the specification and under broadest reasonable interpretation, controlling the ADV may encompass the transmission and receipt of data over a network (See spec [0019] describing the communication signals). Transmitting and receiving data over a network has been found by the courts to be a well understood, routine, and conventional activity when claimed in a merely generic manner such as in this claim.
This and the remaining additional elements were identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)), as stated previously. The courts have found that merely using a computer as a tool to perform an existing process does not qualify the limitations as “significantly more” than the recited judicial exception. The courts have also found that appending well understood, routine, and conventional activities to the judicial exception is not enough to qualify the limitation as significantly more than the recited judicial exception.
With the additional elements viewed independently and as part of the ordered combination, the claim as a whole does not appear to amount to significantly more than the recited judicial exception because the claim is using generic computing components recited at a high level of generality and functioning in their normal capacity to enable the performance of a task that can practically be performed within the human mind or using pen and paper (or a generic computer) as an assistive physical aid. Therefore, the claim does not include additional elements, alone or in combination that are sufficient to amount to significantly more than the recited judicial exception.
Conclusion: Based on this rationale, the claim has been deemed to be ineligible subject matter under 35 U.S.C. 101.
Claim 9:
Step 1: Claim 9 and its dependent claims 10-16 are directed to a non-transitory machine-readable medium having instructions stored therein which falls within one of the four statutory categories of a manufacture.
Step 2A Prong 1: Claim 1 recites a judicial exception, noted in bold:
determine a predicted trajectory of an obstacle The claim limitation can be reasonably read to entail evaluating the characteristics of an obstacle to predict the trajectory by which the obstacle will move. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
determine, [[…]], a planned trajectory of the ADV based on the trajectory of the obstacle The claim limitation can be reasonably read to entail evaluating the trajectory of the obstacle to make a judgement as to how the trajectory of the ADV should be planned. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
determine a weighted loss function, the weighted loss function including one or more variables and a weight corresponding to each variable, wherein each variable is based on a decomposition of an error in the predicted trajectory and each weight is based on the planned trajectory of the ADV; and The claim limitation can be reasonably read to entail making a judgment for a weighted loss function, wherein the function has cost terms and associated weights for each cost term and the cost terms and associated weights are derived according to the given requirements. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, the recitation of a weighted loss function with corresponding variables and weight values is a mathematical calculation and therefore the claim additionally recites the judicial exception of abstract ideas as a mathematical concepts
evaluate a performance of the prediction module based on the weighted loss function to improve the performance of the prediction module to increase a safety and comfort of the ADV. The claim limitation can be reasonably read to entail evaluating the weighted loss function to make a judgement of the performance of the prediction module. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because this claim limitation recites the utilization of the weighted loss function to determine a performance accuracy metric, the claim further recites the judicial exception of abstract ideas as a mathematical calculation, which is a mathematical concept.
Therefore, the claim recites a judicial exception.
Step 2A Prong 2: Additional elements were identified and are noted in italics.
which when executed by a processor, cause the processor to: - This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
by a prediction module of an autonomous driving vehicle (ADV);- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
multiple times per second- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to execute the judicial exception.
by a planning module of the ADV - This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
operate the ADV based on the planned trajectory determined by the planning module of the ADV;– This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) for amounting to the words “apply it” with regard to the value obtained as part of the judicial exception. The limitation has further been identified as Insignificant Extra Solution Activity (MPEP 2106.05(g))
The courts have found that merely including instructions to implement an abstract idea on a computer or merely using a computer as a tool to perform an abstract idea (Mere Instructions to Apply an Exception (MPEP 2106.05(f))) and appending insignificant extra solution activity (Insignificant Extra Solution Activity (MPEP 2106.05(g))) to the judicial exception does not integrate the judicial exception into a practical application.
When viewed independently and within the claim as a whole, the additional element does not appear to integrate the judicial exception into a practical application.
Step 2B: Additional elements identified and conclusions from Step 2A Prong 2 are carried over for evaluating if the claim, as a whole, amounts to an inventive concept that is significantly more than the judicial exception. Elements identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) as well as the combined elements are evaluated to determine if they are beyond well understood, routine, and conventional activities.
operate the ADV based on the planned trajectory determined by the planning module of the ADV;– This limitation was identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)). When read in light of the specification and under broadest reasonable interpretation, controlling the ADV may encompass the transmission and receipt of data over a network (See spec [0019] describing the communication signals). Transmitting and receiving data over a network has been found by the courts to be a well understood, routine, and conventional activity when claimed in a merely generic manner such as in this claim.
This and the remaining additional elements were identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)), as stated previously. The courts have found that merely using a computer as a tool to perform an existing process does not qualify the limitations as “significantly more” than the recited judicial exception. The courts have also found that appending well understood, routine, and conventional activities to the judicial exception is not enough to qualify the limitation as significantly more than the recited judicial exception.
With the additional elements viewed independently and as part of the ordered combination, the claim as a whole does not appear to amount to significantly more than the recited judicial exception because the claim is using generic computing components recited at a high level of generality and functioning in their normal capacity to enable the performance of a task that can practically be performed within the human mind or using pen and paper (or a generic computer) as an assistive physical aid. Therefore, the claim does not include additional elements, alone or in combination that are sufficient to amount to significantly more than the recited judicial exception.
Conclusion: Based on this rationale, the claim has been deemed to be ineligible subject matter under 35 U.S.C. 101.
Claim 17:
Step 1: Claim 17 and its dependent claims 18-20 are directed to a data processing system which falls within one of the four statutory categories of a machine.
Step 2A Prong 1: Claim 1 recites a judicial exception, noted in bold:
determine a predicted trajectory of an obstacle The claim limitation can be reasonably read to entail evaluating the characteristics of an obstacle to predict the trajectory by which the obstacle will move. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
determine, [[…]], a planned trajectory of the ADV based on the trajectory of the obstacle The claim limitation can be reasonably read to entail evaluating the trajectory of the obstacle to make a judgement as to how the trajectory of the ADV should be planned. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
determine a weighted loss function, the weighted loss function including one or more variables and a weight corresponding to each variable, wherein each variable is based on a decomposition of an error in the predicted trajectory and each weight is based on the planned trajectory of the ADV; andThe claim limitation can be reasonably read to entail making a judgment for a weighted loss function, wherein the function has cost terms and associated weights for each cost term and the cost terms and associated weights are derived according to the given requirements. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, the recitation of a weighted loss function with corresponding variables and weight values is a mathematical calculation and therefore the claim additionally recites the judicial exception of abstract ideas as a mathematical concepts
evaluate a performance of the prediction module based on the weighted loss function to improve the performance of the prediction module to increase a safety and comfort of the ADV. The claim limitation can be reasonably read to entail evaluating the weighted loss function to make a judgement of the performance of the prediction module. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because this claim limitation recites the utilization of the weighted loss function to determine a performance accuracy metric, the claim further recites the judicial exception of abstract ideas as a mathematical calculation, which is a mathematical concept.
Therefore, the claim recites a judicial exception.
Step 2A Prong 2: Additional elements were identified and are noted in italics.
a processor; and- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to: This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
by a prediction module of an autonomous driving vehicle (ADV);- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
multiple times per second- This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to execute the judicial exception.
by a planning module of the ADV - This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) because the limitation invokes the use of generic computing components as a tool to perform an existing process.
operate the ADV based on the planned trajectory determined by the planning module of the ADV;– This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) for amounting to the words “apply it” with regard to the value obtained as part of the judicial exception. The limitation has further been identified as Insignificant Extra Solution Activity (MPEP 2106.05(g))
The courts have found that merely including instructions to implement an abstract idea on a computer or merely using a computer as a tool to perform an abstract idea (Mere Instructions to Apply an Exception (MPEP 2106.05(f))) and appending insignificant extra solution activity (Insignificant Extra Solution Activity (MPEP 2106.05(g))) to the judicial exception does not integrate the judicial exception into a practical application.
When viewed independently and within the claim as a whole, the additional element does not appear to integrate the judicial exception into a practical application.
Step 2B: Additional elements identified and conclusions from Step 2A Prong 2 are carried over for evaluating if the claim, as a whole, amounts to an inventive concept that is significantly more than the judicial exception. Elements identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)) as well as the combined elements are evaluated to determine if they are beyond well understood, routine, and conventional activities.
operate the ADV based on the planned trajectory determined by the planning module of the ADV; – This limitation was identified as Insignificant Extra Solution Activity (MPEP 2106.05(g)). When read in light of the specification and under broadest reasonable interpretation, controlling the ADV may encompass the transmission and receipt of data over a network (See spec [0019] describing the communication signals). Transmitting and receiving data over a network has been found by the courts to be a well understood, routine, and conventional activity when claimed in a merely generic manner such as in this claim.
This and the remaining additional elements were identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)), as stated previously. The courts have found that merely using a computer as a tool to perform an existing process does not qualify the limitations as “significantly more” than the recited judicial exception. The courts have also found that appending well understood, routine, and conventional activities to the judicial exception is not enough to qualify the limitation as significantly more than the recited judicial exception.
With the additional elements viewed independently and as part of the ordered combination, the claim as a whole does not appear to amount to significantly more than the recited judicial exception because the claim is using generic computing components recited at a high level of generality and functioning in their normal capacity to enable the performance of a task that can practically be performed within the human mind or using pen and paper (or a generic computer) as an assistive physical aid. Therefore, the claim does not include additional elements, alone or in combination that are sufficient to amount to significantly more than the recited judicial exception.
Conclusion: Based on this rationale, the claim has been deemed to be ineligible subject matter under 35 U.S.C. 101.
Dependent Claims:
Examiner notes limitations identified as judicial exceptions are indicated in italicized bold and limitations identified as additional elements are indicated using italics.
Claim 2
Step 1: Regarding dependent claim 2, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 2 additionally recites the limitation and wherein the decomposing the loss function of the analysis model of the prediction module into the multiple components with the multiple weightings comprises decomposing the mean waypoint distance error into a first mean waypoint distance error perpendicular to a lane with a first weighting and a second mean waypoint distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting, which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 2 additionally recites the limitation wherein the loss function includes a mean waypoint distance error. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The courts have ruled generally linking the use of the judicial exception to a particular technological environment does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the judicial exception to a particular field of use or technological environment are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 3
Step 1: Regarding dependent claim 3, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 3 additionally recites the limitation and wherein the decomposing the loss function of the analysis model of the prediction module into the multiple components with the multiple weightings comprises decomposing the final point distance error into a first final point distance error perpendicular to a lane with a first weighting and a second final point distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 3 additionally recites the limitation wherein the loss function includes a final point distance error. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The courts have ruled generally linking the use of the judicial exception to a particular technological environment does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the judicial exception to a particular field of use or technological environment are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 4
Step 1: Regarding dependent claim 4, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 4 additionally recites the limitation and wherein the decomposing the loss function of the analysis model of the prediction module into the multiple components with the multiple weightings comprises decomposing the location error into a speed error with a first weighting and a heading error with a second weighting, wherein the first weighting is larger than the second weighting., which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 4 additionally recites the limitation wherein the loss function includes a location error This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The courts have ruled generally linking the use of the judicial exception to a particular technological environment does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the judicial exception to a particular field of use or technological environment are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 5
Step 1: Regarding dependent claim 5, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 5 additionally recites the limitation determining each weighting of the multiple weightings based on an impact of a weighting to the trajectory of the ADV, which can reasonably be read to entail evaluating the impact of a weighting value to the trajectory in order to make a judgment as to the appropriate weighting value for multiple weightings. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Additionally, this claim recites the mathematical relationships between weight values and their overall contribution to the trajectory, thereby indicating that the claim additionally recites the abstract idea of mathematical concepts.
Step 2A Prong 2 & Step 2B: This claim does not recite any additional elements that would integrate the judicial exceptions, nor amount to significantly more than the judicial exceptions.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 6
Step 1: Regarding dependent claim 6, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 6 additionally recites the limitation determining each weighting of the multiple weightings based on a performance of the planning module based on the trajectory of the ADV, which can reasonably be read to entail evaluating the impact of a weighting value to the performance of the planning module based on the trajectory of the ADV in order to make a judgment as to the appropriate weighting value for multiple weightings. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Additionally, this claim recites the mathematical relationships between weight values and their overall contribution to the performance of the planning module, thereby indicating that the claim additionally recites the abstract idea of mathematical concepts.
Step 2A Prong 2 & Step 2B: This claim does not recite any additional elements that would integrate the judicial exceptions, nor amount to significantly more than the judicial exceptions.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 7
Step 1: Regarding dependent claim 7, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 7 does not recite any additional judicial exceptions.
Step 2A Prong 2: Claim 7 additionally recites the limitation wherein the loss function includes a plurality of losses, each loss corresponding to a driving scenario that is one of a plurality of driving scenarios. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The courts have ruled generally linking the use of the judicial exception to a particular technological environment or field of use does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 8
Step 1: Regarding dependent claim 8, the judicial exception of independent claim 1 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 8 additionally recites the limitation determining a driving scenario from the plurality of driving scenarios, which can reasonably be read to entail evaluating driving scenarios to make a judgement as to an appropriate driving scenario. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Claim 8 further recites the limitation determining a corresponding loss from the plurality of losses in response to the driving scenario., which can reasonably be read to entail observing the driving scenarios and associated loss values to make a judgment as to the corresponding loss value associated with the driving scenario. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
Step 2A Prong 2 & Step 2B: This claim does not recite any additional elements that would integrate the judicial exceptions, nor amount to significantly more than the judicial exceptions.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 10
Step 1: Regarding dependent claim 10, the judicial exception of independent claim 9 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 10 additionally recites the limitation decompose the mean waypoint distance error into a first mean waypoint distance error perpendicular to a lane with a first weighting and a second mean waypoint distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting, which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 10 additionally recites the limitation wherein the loss function includes a mean waypoint distance error. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). Claim 10 additionally recites the limitation and wherein the instructions further cause the processor to. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled generally linking the use of the judicial exception to a particular technological environment or field of use and merely using a computer as a tool to perform an existing process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use and merely including instructions to implement a judicial exception on a computer are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 11
Step 1: Regarding dependent claim 11, the judicial exception of independent claim 9 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 11 additionally recites the limitation decompose the final point distance error into a first final point distance error perpendicular to a lane with a first weighting and a second final point distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 11 additionally recites the limitation wherein the loss function includes a final point distance error. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). Claim 11 additionally recites the limitation and wherein the instructions further cause the processor to: This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled generally linking the use of the judicial exception to a particular technological environment or field of use and merely using a computer as a tool to perform an existing process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use and merely including instructions to implement a judicial exception on a computer are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 12
Step 1: Regarding dependent claim 12, the judicial exception of independent claim 9 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 12 additionally recites the limitation decompose the location error into a speed error with a first weighting and a heading error with a second weighting, wherein the first weighting is larger than the second weighting., which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 12 additionally recites the limitation wherein the loss function includes a location error, This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). Claim 12 additionally recites the limitation and wherein the instructions further cause the processor to:. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled generally linking the use of the judicial exception to a particular technological environment or field of use and merely using a computer as a tool to perform an existing process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use and merely including instructions to implement a judicial exception on a computer are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 13
Step 1: Regarding dependent claim 13, the judicial exception of independent claim 9 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 13 additionally recites the limitation determine each weighing of the multiple weightings based on an impact of a weighting to the trajectory of the ADV. which can reasonably be read to entail evaluating the impact of a weighting value to the trajectory in order to make a judgment as to the appropriate weighting value for multiple weightings. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Additionally, this claim recites the mathematical relationships between weight values and their overall contribution to the trajectory, thereby indicating that the claim additionally recites the abstract idea of mathematical concepts.
Step 2A Prong 2: Claim 13 additionally recites the limitation wherein the instructions further cause the processor to:. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)).The courts have ruled merely including instructions to implement an abstract idea on a computer does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to invoking the use of a computer to perform an existing process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 14
Step 1: Regarding dependent claim 14, the judicial exception of independent claim 9 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 14 additionally recites the determine each weighing of the multiple weightings based on a performance of the planning module based on the trajectory of the ADV, which can reasonably be read to entail evaluating the impact of a weighting value to the performance of the planning module based on the trajectory of the ADV in order to make a judgment as to the appropriate weighting value for multiple weightings. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Additionally, this claim recites the mathematical relationships between weight values and their overall contribution to the performance of the planning module, thereby indicating that the claim additionally recites the abstract idea of mathematical concepts.
Step 2A Prong 2: Claim 14 additionally recites the limitation wherein the instructions further cause the processor to:. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)).The courts have ruled merely including instructions to implement an abstract idea on a computer does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to invoking the use of a computer to perform an existing process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 15
Step 1: Regarding dependent claim 15, the judicial exception of independent claim 9 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 15 does not recite any additional judicial exceptions
Step 2A Prong 2: Claim 15 additionally recites the limitation wherein the loss function includes a plurality of losses, each loss corresponding to a driving scenario that is one of a plurality of scenarios. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The courts have ruled generally linking the use of a judicial exception to a particular technological environment or field of use does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of a judicial exception to a particular technological environment or field of use are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 16
Step 1: Regarding dependent claim 16, the judicial exception of independent claim 9 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 16 additionally recites the limitation determine a driving scenario from the plurality of driving scenarios, which can reasonably be read to entail evaluating driving scenarios to make a judgement as to an appropriate driving scenario. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Claim 16 further recites the limitation determine a corresponding loss from the plurality of losses in response to the driving scenario. which can reasonably be read to entail observing the driving scenarios and associated loss values to make a judgment as to the corresponding loss value associated with the driving scenario. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process.
Step 2A Prong 2: Claim 16 additionally recites the limitation wherein the instructions futher cause the processor to:. This limitation has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)).The courts have ruled merely including instructions to implement an abstract idea on a computer does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to invoking the use of a computer to perform an existing process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 18
Step 1: Regarding dependent claim 18, the judicial exception of independent claim 17 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 18 additionally recites the limitation decompose the mean waypoint distance error into a first mean waypoint distance error perpendicular to a lane with a first weighting and a second mean waypoint distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting., which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 18 additionally recites the limitation wherein the loss function includes a mean waypoint distance error. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The claim further recites the limitation and wherein the processor is further to which has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled generally linking the judicial exception to a particular technological environment or field of use or merely invoking the use of computers as a tool to perform an existing process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use and invoking the use of computers as a tool to perform an existing process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 19
Step 1: Regarding dependent claim 19, the judicial exception of independent claim 17 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 19 additionally recites the limitation decompose the final point distance error into a first final point distance error perpendicular to a lane with a first weighting and a second final point distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting, which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 19 additionally recites the limitation wherein the loss function includes a final point distance error. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The claim further recites the limitation and wherein the processor is further to which has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled generally linking the judicial exception to a particular technological environment or field of use or merely invoking the use of computers as a tool to perform an existing process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use and invoking the use of computers as a tool to perform an existing process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim 20
Step 1: Regarding dependent claim 20, the judicial exception of independent claim 17 is further incorporated. The claim falls within the corresponding statutory category as stated previously.
Step 2A Prong 1: Claim 20 additionally recites the limitation decompose the location error into a speed error with a first weighting and a heading error with a second weighting, wherein the first weighting is larger than the second weighting which can reasonably be read to entail decomposing a function into its respective contributing components and weighing the contributing components such that the first weight is larger than the second weight. This task can be performed within the human mind or using a pen and paper as an assistive physical aid. Therefore, this claim limitation includes the recitation of the judicial exception of abstract ideas of a mental process. Furthermore, because the claim recites the mathematical calculations of decomposing an equation and further recites mathematical relationships of the contributions of the weightings and the comparison of weighting values, this claim limitation additionally includes the recitation of the judicial exception of abstract ideas as a mathematical concept.
Step 2A Prong 2: Claim 20 additionally recites the limitation wherein the loss function includes a location error. This limitation has been identified as Field of Use and Technological Environment (MPEP 2106.05(h)). The claim further recites the limitation and wherein the processor is further to which has been identified as Mere Instructions to Apply an Exception (MPEP 2106.05(f)). The courts have ruled generally linking the judicial exception to a particular technological environment or field of use or merely invoking the use of computers as a tool to perform an existing process does not integrate the judicial exception into a practical application. With the additional element viewed in conjunction with the other limitations, the claim as a whole does not appear to integrate the judicial exception into a practical application.
Step 2B: The courts have found that limitations that amount to generally linking the use of the judicial exception to a particular technological environment or field of use and invoking the use of computers as a tool to perform an existing process are not enough to qualify the claim as significantly more than the abstract idea. Therefore, the claim does not include additional elements, alone or in the ordered combination that are sufficient to amount to significantly more than the recited judicial exception.
This claim is not eligible subject matter under 35 U.S.C. 101.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1, 5- 9, and 13- 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Burisch et al (US 20220188667 A1), hereinafter referred to as Burisch, in view of Lapin et al (US 20210403034 A1), hereinafter referred to as Lapin, and in view of Xu et al (Xu, W., Wei, J., Dolan, J. M., Zhao, H., and Zha, H., “A Real-Time Motion Planner with Trajectory Optimization for Autonomous Vehicles”, 2012, 2012 IEEE International Conference on Robotics and Automation, pp 2061-2067), hereinafter referred to as Xu.
Regarding claim 1, Burisch discloses (except the limitations surrounded by brackets ([[..]])) A computer-implemented method of operating an autonomous driving vehicle (ADV), the method comprising: ((Burisch, ¶2) "For example, while operating in the autonomous-driving mode, the one or more systems or subsystems may generally include a perception system that generates perception data from data captured by sensors of the vehicle, a prediction system that may receive the perception data and generate prediction data with respect to one or more agents based on the perception data, and a trajectory planner that may generate a planned trajectory in response to the prediction data generated by the prediction system"); ((Burisch, ¶68) " FIG. 6A illustrates a flow diagram of a method 600A for generating known prediction data and providing to a planning module to generate a planned trajectory that may be utilized for the evaluation and training of the base prediction module, in accordance with the presently disclosed techniques. The method 600A may be performed utilizing one or more processing devices ( e.g., prediction training framework 200A, 200B) that may include hardware ( e.g., a general purpose processor, a graphic processing unit (GPU), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a visual processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), or any other processing device(s) that may be suitable for processing image data), software (e.g., instructions running/executing on one or more processors), firmware ( e.g., microcode), or some combination thereof.")
determining a predicted a trajectory of an obstacle by a prediction module of the ADV; ((Burisch, ¶61) "In certain embodiments, the vehicle 102A may generate predicted trajectories 114A, 114B, and 114C for the pedestrian agents 112A-112F each traveling straight and a constant velocity along the sidewalks 302, predicted trajectories 304A for the vehicle agents 104A-104F each traveling straight and at a constant velocity along the roadway 110A, and a predicted trajectory 310A for the cyclist 308A traveling straight and at a constant velocity within the bicycle lane 306.")
determining, [[multiple times per second]], a planned a trajectory of the ADV based on the predicted trajectory of the obstacle by a planning module of the ADV; ((Burisch, ¶62) "In certain embodiments, based on the predicted trajectories 114A, 114B, and 114C, the predicted trajectories 304A, and the predicted trajectory 310A, the vehicle 102A may generate a planned trajectory 106A, which may include a constant velocity and a varying steering angle to perform a lane change to overtake the vehicle agent 104E.")
operating the ADV based on the planned trajectory determined by the planning module of the ADV; ((Burisch, ¶39) " In certain embodiments, the planning module 208 may determine a planned trajectory 214A for the vehicle 102A, including navigation routes and particular driving operations ( e.g., slowing down, speeding up, stopping, swerving, and so forth), based on the predicted contextual representation generated by the prediction module 206."); ((Burisch, ¶44) " For example, in certain embodiments, while the vehicle 102A may be operating according to the planned trajectory generated based on the prediction data generated by the prediction module 206, additional sensor data 202 of the environment of the vehicle 102A may be captured.")
determining a [[weighted]] loss function, [[the weighted loss function including one or more variables and a weight corresponding to each variable, wherein each variable is based on a decomposition of an error in the predicted trajectory and each weight is based on the planned trajectory of the ADV; and]] A loss function is used to quantify a loss value by comparing the predicted trajectory and ground truth data ((Burisch, ¶37-38) "The predicted contextual representation may then be compared to the known second contextual representation (e.g., the ground truth at time T_1). In certain embodiments, the comparison may be quantified by a loss value, computed using a loss function. The loss value may be used (e.g., via back-propagation techniques) to update the configuration parameters of the ML model so that the loss would be less if the prediction were to be made again.") The planned trajectory of the vehicle may be utilized to evaluate the base prediction model, wherein the prediction model is evaluated by utilizing the loss function as stated previously ((Burisch, ¶64) "FIG. 4A, FIG. 4B, and FIG. 5 illustrate one or more running examples of driving scenarios 400A, 400B, and 500 in which known prediction data and one or more simulated agents may be generated by a known prediction module and provided to a planning module to generate a planned trajectory that may be utilized for the evaluation and training of the base prediction module. ")
evaluating a performance of the prediction module based on the [[weighted]] loss function to improve the performance of the prediction module to increase a safety and comfort of the ADV. ((Burisch, ¶30) "Thus, utilizing the determined deviation between the planned trajectory 108A and the planned trajectory 108B, the present techniques may allow the offline prediction training framework to evaluate the performance of the prediction module of the vehicle 102C, and to determine certain driving scenarios (e.g., driving scenario 100B corresponding to the predicted trajectory 108B with respect to the agent 104B) to be introduced to a prediction training dataset for the prediction module"); ((Burisch, ¶37-38) " In certain embodiments, the representation of the present contextual environment from the perception data 204A may be consumed by a prediction module 206 to generate one or more predictions of the future environment. [[..]] The predicted contextual representation may then be compared to the known second contextual representation (e.g., the ground truth at time T 1). In certain embodiments, the comparison may be quantified by a loss value, computed using a loss function. The loss value may be used (e.g., via back-propagation techniques) to update the configuration parameters of the ML model so that the loss would be less if the prediction were to be made again."); ((Burisch, ¶40) "While the example above used collision as an example, the disclosure herein contemplates the use of any suitable scoring criteria!, such as travel distance or time, fuel economy, changes to the estimated time of arrival at the destination, passenger comfort, proximity to other vehicles, the confidence score associated with the predicted contextual representation, and so forth.")
Burisch does not explicitly disclose; however, Burisch in view of Lapin discloses a weighted loss function, with the weighted loss function including one or more variables and a weight corresponding to each variable, ((Lapin, ¶36) " The generated candidate trajectories 133 and the corresponding driving constraints 113 may be fed to the cost function 134 which evaluates/ranks the candidate trajectories based on a number of cost terms (also referred to as input terms) and a number of weights associated with these cost terms."). wherein each variable is based on a decomposition of an error in the predicted trajectory The cost function is comprised of cost terms (each variable), wherein each cost term is calculated according to (composed of) the difference (error) between a vector corresponding to the evaluated (predicted) trajectory and a vector for the ideal trajectory (See Fig 4B);((Lapin, ¶41) “FIG. 4B illustrates an example process 400B for determining a total cost for an evaluated trajectory. As an example and not by way of limitation, the system may determine a number of cost terms corresponding to a number of parameters ( e.g., Pi, P 2 , P 3 ) associated with the evaluated trajectory. For each cost term, the system may determine a corresponding vector ( e.g., vector 411 for Pi, vector 413 for P 2 , vector 415 for P 3 ) for the evaluated trajectory. Then, the system may identify the scenario associated with the evaluated trajectory and access a reference model associated with this scenario. Then, the system may determine an ideal trajectory based on the reference model associated with this scenario. After that, for each cost term, the system may determine a vector ( e.g., vector 412 for Pi, vector 414 for P 2 , vector 414 for P3) for the ideal trajectory. Then, the system may calculate a cost associated for the evaluated trajectory based on each cost term ( e.g., 401 for P 1 , 402 for P 2 , 403 for P3). For example, the system may compare the corresponding elements of the vectors 411 and 412 to determine the difference of corresponding elements. Then, the system may determine the cost 401 by summing up the difference of all vector elements. As another example, the system may compare the corresponding elements of the vectors 413 and 413 to determine the difference of corresponding elements. Then, the system may determine the cost 402 by summing up the difference of all vector elements. As another example, the system may compare the corresponding elements of the vectors 415 and 416 to determine the difference of corresponding elements. Then, the system may determine the cost 403 by summing up the difference of all vector elements. After that, the system may determine the total cost 410 of the evaluated trajectory by summing up the costs determined based on respective cost terms as weighted by respective weights ( e.g., weights 421, 422, and 423). The total cost 410 may indicate an overall similarity level or disparity level of the evaluated trajectory with respect to the ideal trajectory determined based on a reference model associated with this scenario.”) and each weight is based on the planned trajectory of the ADV; and The weights of the cost function may be optimized according to the planned trajectory ((Lapin, ¶34) " After that, the system may compare the two versions of planned trajectories and use the comparison result to optimize the constraint prediction algorithm or/and the cost function weights of the trajectory planner.")
Burisch and Lapin are both analogous to the claimed invention because they are both related to the same field of endeavor of trajectory planning optimizations for autonomous vehicles. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have implemented a weighted loss function by which to evaluate the error of the prediction compared to the actual values because some teaching, suggestion, or motivation would have led one having ordinary skill in the art to combine the prior art references in order to arrive at the claimed invention. Burisch discloses the utilization of a loss function for quantifying the difference between a predicted representation and a ground truth representation of the contextual environment of the autonomous vehicle but does not particularly disclose the implementation details of the loss function. Lapin discloses the utilization of a cost function with weighted cost terms to evaluate candidate planned trajectories of an autonomous vehicle so as to improve the capabilities of the trajectory planner. Lapin suggests that optimizing the cost terms of the cost function enables tuning of the trajectory planner to more accurately reflect human driving behaviors ((Lapin, ¶17) "By testing and validating the trajectory planner with the optimized weights, the system may identify the scenarios that are not well handled by the trajectory planner and may send feedback information to the data collection module to collect more data for these scenarios and allow the trajectory planner to be trained to better handle these scenarios. By automatically tuning the cost function weights of the trajectory planner based on human driving behaviors, the output of the trajectory planner may be more similar to the human driving behaviors."). Accordingly, in order to realize the fine-tuned control of the planning module for generating the planned trajectory, it would have been obvious to leverage a weighted cost function as disclosed by Lapin as the particular implementation of the loss function disclosed by Burisch.
The proposed combination does not disclose performing planned trajectory determination multiple times per second; however, the proposed combination in light of the teachings of Xu discloses replanning a trajectory multiple times per second. ((Xu, Page 2065, Col 2, ¶4) " To react to a dynamically changing environment in the real world, the motion planner needs to replan continually. If the planner starts to plan from the current vehicle state, then when the planning is finished, usually around 100 milliseconds later, the vehicle will be at a different position, and the original plan will no longer be valid. ")
Xu is analogous to the claimed invention because it is related to the same field of endeavor of improvements in trajectory and motion planning for autonomous vehicles. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have imposed the trajectory planning update time to occur multiple times per second because some teaching, suggestion, or motivation would have led one having skill in the art to do so in order to arrive at the claimed invention. Burisch discloses performing steps of the methodology disclosed in real time but does not quantify the frequency which may be encompassed by real-time processing ((Burisch, ¶102) "For example, one or more computer systems 800 may perform in real time or in batch mode one or more steps of one or more methods described or illustrated herein."). Likewise, Lapin discloses performing methodologies in real time but does not quantify the speed by which real time entails ((Lapin, ¶54) " As an example and not by way of limitation, one or more computer systems 600 may perform in real
time or in batch mode one or more steps of one or more methods described or illustrated herein."). Xu describes the need for replanning motion in around 100 milliseconds in order to appropriately adjust to the dynamically changing environment as part of a real-time motion planner methodology ((Xu, Page 2065, Col 2, ¶4) " To react to a dynamically changing environment in the real world, the motion planner needs to replan continually. If the planner starts to plan from the current vehicle state, then when the planning is finished, usually around 100 milliseconds later, the vehicle will be at a different position, and the original plan will no longer be valid. "). Accordingly because both Burisch and Lapin suggest real-time execution and Xu provides an exemplary replanning period occurring around 100 milliseconds to adapt to a dynamically changing environment, the combination would have been obvious to one having skill in the art.
Regarding claim 5, the proposed combination discloses The method of claim 1, as stated previously.
The proposed combination in further view of Lapin discloses further comprising determining each weighting of the multiple weightings based on an impact of a weighting to the trajectory of the ADV. ((Lapin, ¶19) "During the automatic optimization process, one or more weights associated with one or more cost terms of the cost function may be adjusted based on the reference trajectory 114 ( e.g., a human driving trajectory) to adjust the values of the optimized weights 104."); ((Lapin, ¶37) "A higher cost may indicate a lower level of desirability attributed to a higher penalty for the associated candidate trajectory to be used for navigating the vehicle. A lower lost may indicate a higher level of desirability attributed to a lower penalty for the associated candidate trajectory to be used for navigating the vehicle.");((Lapin, ¶37) "As another example, the cost function for determining the total cost (also referred to as total cost function or overall cost function) of the evaluated trajectory may be sum function for summing up a number of cost terms as weighted by corresponding weights. In some examples, a maneuver associated with a high cost may be attributed to that which a human driver would be unlikely to perform due to impact on driving comfort, perceived safety, etc., whereas a maneuver associated with a lower cost may be attributed to that which a human would be more likely to perform"); ((Lapin, ¶44) "After that, the system may adjust the weight values in a weight vector to allow the weighted feature vector for the human driving trajectory to have a lower cost than the weighted feature vector of all candidate trajectories generated by the trajectory planner. ")
Regarding claim 6, the proposed combination discloses The method of claim 1, as stated previously. The proposed combination in further view of Lapin discloses further comprising determining each weighting of the multiple weightings based on a performance of the planning module based on the trajectory of the ADV. ((Lapin, ¶19) "After the weights have been optimized based on the reference trajectory 114, the trajectory planner 130 with the optimized weights 104 may be evaluated and tested using a validation platform ( e.g., a simulated validation platform or a vehicle test-running platform) to identify the scenarios that are not yet well handled by the trajectory planner 130 with the current weight values. Then, the system may send feedback information 115 to the data collection and storage module 102 to retrieve from a database more vehicle driving data related to these scenarios if the database includes more vehicle driving data related to these identified scenarios, or to collect more vehicle driving data related to these identified scenarios. After that, the system may use the newly retrieved or collected vehicle driving data related to these scenarios together with the existing vehicle driving data to further optimize the cost function weights of the trajectory planner 130.")
Regarding claim 7, the proposed combination discloses The method of claim 1, as stated previously. The proposed combination in further view of Lapin discloses wherein the loss function includes a plurality of losses, each loss corresponding to a driving scenario that is one of a plurality of driving scenarios. The cost function is comprised of a number of cost terms with associated weights (as a plurality of losses) and the relative importance of cost terms varies between scenarios faced by the vehicle ((Lapin, ¶15) " The cost function may have a number of cost terms and a number of weights associated with these cost terms.[[…]] For example, human engineers may need to evaluate and balance many different cost terms of the candidate trajectories across various different scenarios that could potentially be faced by the vehicle because the range of desirable values and the relative importance of such cost terms may vary from scenario-to-scenario."). A total cost function may be derived for a scenario which includes multiple cost functions for each trajectory parameter ((Lapin, ¶39) "In particular embodiments, the system may use one or more trajectory-evaluation functions ( e.g., cost functions) each being associated with a particular trajectory parameter ( e.g., velocity, acceleration, position, distance to lane boundary, distance to a closest object, etc.) to evaluate a trajectory with respect to an expected trajectory (e.g., generated from a reference model or previous driving data for a particular scenario).");((Lapin, ¶41) "After that, the system may determine the total cost 410 of the evaluated trajectory by summing up the costs determined based on respective cost terms as weighted by respective weights ( e.g., weights 421, 422, and 423). The total cost 410 may indicate an overall similarity level or disparity level of the evaluated trajectory with respect to the ideal trajectory determined based on a reference model associated with this scenario."). The weights of the cost function may be changed for a plurality of scenarios ((Lapin, ¶49) "In particular embodiments, the one or more weights may be adjusted using a gradient descent algorithm based on the vehicle driving data associated to a number of scenarios of the environment")
Regarding claim 8, the proposed combination discloses The method of claim 7, as stated previously. The proposed combination in further view of Lapin discloses further comprising determining a driving scenario from the plurality of driving scenarios; ((Lapin, ¶45) "The system may identify one or more scenarios that are not well handled by the trajectory planner based on the driving safety metric and the driving comfort metric ( e.g., being below respective thresholds) and send feedback information to the optimization pipeline to cause more vehicle driving data related to these identified scenarios to be fed to the optimization pipeline")
determining a corresponding loss from the plurality of losses in response to the driving scenario. Scenarios are evaluated using the cost function and identified to not be handled well. The methodology optimizes the cost function weights accordingly and the trajectory planner is evaluated for scenario criteria using the cost obtained from the cost function. ((Lapin, ¶45) "The system may determine that the trajectory planner cannot yet handle the nudging scenario well. The system may send feedback information to the optimization pipeline to cause more nudging data to be fed to the optimization pipeline. The system may access the database to access and retrieve more nudging data (if any) and feed this data to the optimization pipeline. Or, the system ma send feedback The system may determine that the trajectory planner cannot yet handle the nudging scenario well. The system may send feedback information to the optimization pipeline to cause more nudging data to be fed to the optimization pipeline. The system may access the database to access and retrieve more nudging data (if any) and feed this data to the optimization pipeline. Or, the system ma send feedback. The optimization process may be repeated to adjust the cost function weights of the trajectory planner until the trajectory planner meets the validation criteria (e.g., meeting criteria for the safety metric and comfort metric) with the output trajectory matching human driving trajectories.") ((Lapin, ¶15) "To generate vehicle trajectories for navigating AV in the autonomous driving mode, the AV may use a trajectory planner to generate a number of candidate trajectories and use a trajectory-evaluation function (e.g., a cost function) to evaluate these candidate trajectories to pick the best one. For example, the AV may use a cost function to determine a total cost for each evaluated trajectory and select the best trajectory based on the total cost values. The cost function may have a number of cost terms and a number of weights associated with these cost terms.")
Regarding claim 9, Burisch discloses A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to: ((Burisch, Claim 20) "A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors of a computing device, cause the one or more processors to:[[…]]")
The remaining limitations: determine a predicted trajectory of an obstacle by a prediction module of an autonomous driving vehicle (ADV);
determine, multiple times per second, a planned a trajectory of the ADV based on the trajectory of the obstacle by a planning module of the ADV;
operate the ADV based on the planned trajectory determined by the planning module of the ADV;
determine a weighted loss function, the weighted loss function including one or more variables and a weight corresponding to each variable, wherein each variable is based on a decomposition of an error in the predicted trajectory and each weight is based on the planned trajectory of the ADV; and
evaluate a performance of the prediction module based on the weighted loss function to improve the performance of the prediction module to increase a safety and
comfort of the ADV. are substantially similar to that recited in claim 1 and are therefore rejected under the same rationale.
Regarding claim 13, the proposed combination discloses The non-transitory machine-readable medium of claim 9, as stated previously.
The remaining limitations: wherein the instructions further cause the processor to:
determine each weighting of the multiple weightings based on an impact of a weighting to the trajectory of the ADV. are substantially similar to that recited in claim 5 and are therefore rejected under the same rationale.
Regarding claim 14, the proposed combination discloses The non-transitory machine-readable medium of claim 9, as stated previously.
The remaining limitations: wherein the instructions further cause the processor to:
determine each weighting of the multiple weightings based on a performance of the planning module based on the trajectory of the ADV. are substantially similar to that recited in claim 6 and are therefore rejected under the same rationale.
Regarding claim 15, the proposed combination discloses The non-transitory machine-readable medium of claim 9, as stated previously.
The remaining limitations: wherein the loss function includes a plurality of losses, each loss corresponding to a driving scenario that is one of a plurality of driving scenarios. are substantially similar to that recited in claim 7 and are therefore rejected under the same rationale.
Regarding claim 16, the proposed combination discloses The non-transitory machine-readable medium of claim 15, as stated previously.
The remaining limitations: wherein the instructions further cause the processor to: determine a driving scenario from the plurality of driving scenarios;
determine a corresponding loss from the plurality of losses in response to the driving scenario. are substantially similar to that recited in claim 8 and are therefore rejected under the same rationale.
Regarding claim 17, Burisch discloses A data processing system, comprising: ((Burisch, ¶101) "FIG. 8 illustrates an example computer system 800 that may be utilized to perform one or more of the forgoing embodiments as discussed herein.")
a processor; and ((Burisch, ¶103) "In certain embodiments, computer system 800 includes a processor 802, memory 804, storage 806, an input/output (I/O) interface 808, a communication interface 810, and a bus 812.")
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to: ((Burisch, ¶103) "In certain embodiments, computer system 800 includes a processor 802, memory 804, storage 806, an input/output (I/O) interface 808, a communication interface 810, and a bus 812. [[…]]In certain embodiments, processor 802 includes hardware for executing instructions, such as those making up a computer program. For example, to execute instructions, processor 802 may retrieve ( or fetch) the instructions from an internal register, an internal cache, memory 804, or storage 806; decode and execute them; and then write one or more results to an internal register, an internal cache, memory 804, or storage 806. In certain embodiments, processor 802 may include one or more internal caches for data, instructions, or addresses.")
The remaining limitations: determine a predicted trajectory of an obstacle by a prediction module of an autonomous driving vehicle (ADV);
determine, multiple times per second, a planned a trajectory of the ADV based on the trajectory of the obstacle by a planning module of the ADV;
operate the ADV based on the planned trajectory determined by the planning module of the ADV;
determine a weighted loss function, the weighted loss function including one or more variables and a weight corresponding to each variable, wherein each variable is based on a decomposition of an error in the predicted trajectory and each weight is based on the planned trajectory of the ADV; and
evaluate a performance of the prediction module based on the weighted loss
function to improve the performance of the prediction module to increase a safety and comfort of the ADV. are substantially similar to that recited in claim 1 and are therefore rejected under the same rationale.
Claims 2, 3, 10, 11, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Burisch in view of Lapin and Xu, as applied to claims 1, 9, and 17 above, and further in view of Ivanovic (Ivanovic, B., “Back to the Future: Planning-Aware Trajectory Forecasting for Autonomous Driving”, June 25, 2020, Stanford AI Lab, ai.stanford.edu), hereinafter referred to as Ivanovic, and in view of Salleh et al (Salleh, D., and Seignez, E., “Longitudinal error improvement by visual odometry trajectory trail and road segment matching”, October 29, 2018, IET Intelligent Transport Systems Volume 13, Issue 2, pp 313-322), hereinafter referred to as Salleh, and in view of Phillips et al (US 20210114617 A1), hereinafter referred to as Phillips.
Regarding claim 2, the proposed combination discloses The method of claim 1, as stated previously.
The proposed combination in further view of Lapin discloses (except the limitations surrounded by brackets ([[..]])) [[wherein the loss function includes a mean waypoint distance error, and ]]
wherein the decomposing the loss function of the analysis model of the prediction module into the multiple components with the multiple weightings comprises decomposing [[the mean waypoint distance error into a first mean waypoint distance error perpendicular to a lane]] with a first weighting and [[a second mean waypoint distance error along the lane]] with a second weighting, The total cost is decomposed into sub-costs with corresponding weights, as depicted in 4B and as stated previously ((Lapin, ¶38) " The system may use a total cost function to determine a total cost for the evaluated candidate trajectory based on the costs determined based on respective parameters ( cost terms), as illustrated in FIG. 4B and described in later section of this disclosure. The cost function for determining the total cost for the evaluated trajectory may have a number of cost terms ( corresponding to the cost values determined based on respective parameters) as weighted a number of weights ( e.g., a weight per cost term).").
[[wherein the first weighting is larger than the second weighting.]]
The proposed combination in further view of Lapin does not disclose; however, the proposed combination in further view of Ivanovic discloses wherein the loss function includes a mean waypoint distance error, and An average displacement error metric is disclosed for benchmarking performance in trajectory forecasting ((Ivanovic, ¶23) "Illustrated above, one of the most common ways is to directly compare them side-by-side, i.e., measure how far \(\widehat{y}_i\) is from \(y_i\) for each \(i\) and then average these distances to obtain the average error over the prediction horizon. This is commonly known as Average Displacement Error (ADE) and is usually reported in units of length, e.g., meters:")
Ivanovic is analogous to the claimed invention because it pertains to the same field of endeavor of optimizations in trajectory planning for autonomous vehicles with consideration to performance evaluations in terms of error. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have evaluated the planned trajectories of the proposed combination using the average displacement error as the evaluation metric because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to modify the prior art references in order to arrive at the claimed invention. Burisch discloses the utilization of a loss function to compare and evaluate predictions but does not particularly disclose what type of loss function is utilized. Lapin discloses the use of a position error for evaluating candidate trajectories but does not provide particulars as to which type of position is being evaluated. Ivanovic discloses the utilization of the average displacement error metric for evaluating forecasted trajectories and particularly notes that the ADE is a main metric used to evaluate deterministic regressors because they are east to implement, natural for the task, and interpretable ((Ivanovic, ¶26) "ADE and FDE are the two main metrics used to evaluate deterministic regressors. While these metrics are natural for the task, easy to implement, and interpretable, they generally fall short in capturing the nuances of more sophisticated methods (see more on this below)."). Accordingly, it would have been obvious to utilize the ADE as the particular cost function to evaluate the planned trajectory because it is commonly used and yields predictable results.
The proposed combination in further view of Ivanovic does not disclose; however, in view of Salleh discloses decomposing the mean waypoint distance error into a first mean waypoint distance error perpendicular to a lane … and a second mean waypoint distance error along the lane Distance error is described as being broken down into its lateral and longitudinal components for subsequent optimization ((Salleh, Page 314, Col 1, ¶3-4) "Vehicle localisation performance in accuracy and precision is generally measured by positioning error analysis which can be a relative distance error, heading error, lateral error, and longitudinal error. Distance error is the relative distance difference between ground truth data and fusion output while heading error is its angle difference. In order to reduce the distance error, we need to minimise the lateral and longitudinal errors. The position difference in the lateral axis (left/right of the object) is denoted as a lateral error and longitudinal error is the distance difference in the longitudinal axis, which makes the localisation to appear ahead or behind the ground truth data (Fig. 1). "); See also Salleh Figure 14.
Salleh is analogous art to the claimed invention because it is related to the same field of endeavor of autonomous/ intelligent vehicle route planning and error reduction techniques. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have decomposed the mean waypoint distance error, as disclosed by the proposed combination in view of Ivanovic, into its respective lateral and longitudinal error components as suggested by Salleh because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to modify the prior art references in order to arrive at the claimed invention. Lapin discloses the utilization of a weighted cost function wherein a total cost can be decomposed into weighted components. Lapin suggests that position errors are used as part of the cost function evaluation and further suggests that parameters of the trajectory planner may include distance from a leading vehicle and the distance to a lane boundary (Lapin, ¶43-44) but does not particularly disclose what position error or how the error may be decomposed according to particular parameters. The proposed combination in view of Ivanovic suggests utilization of the average displacement error as a cost function metric of interest for related applications. Salleh discloses the utilization of a positioning error that is decoupled into its lateral and longitudinal error components. Salleh explicitly notes that in order to reduce overall position error, errors need to be reduced in both the lateral and longitudinal components of the error (Salleh, Page 314, Col 1, ¶3). Accordingly, it would have been obvious to one having ordinary skill in the art to apply the decoupling of the error, as suggested by Salleh to the average displacement error of the proposed combination in order to achieve the greater control over reducing the overall error. By combining the prior art references in this way, one having skill in the art would arrive at the claimed invention.
The proposed combination in further view of Salleh does not disclose; however, in further view of Phillips discloses wherein the first weighting is larger than the second weighting. ((Phillips, ¶50) "For examples, the sub-cost value associated with a potential collision can be weighted more heavily than a sub-cost value associated with actor caution costs. In some examples, the weight of particular sub-cost value can depend on the current situation of the autonomous vehicle. Thus, overtaking buffer costs may be weighted more heavily on a single lane road than on a multi-lane highway.")
Phillips is analogous art to the claimed invention because it is related to the same field of endeavor of autonomous vehicle trajectory planning optimizations, particularly with regard for leveraging a weighted cost function for object avoidance. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have made the first weighing larger than the second weighting in the system of the proposed combination because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to make the modification in order to arrive at the claimed invention. Lapin discloses the adjustment of cost function weights but does not explicitly mention how the adjustments to the weights may be set. Ivanovic discloses the utilization of the average distance error as a particular metric by which to evaluate distance error. Phillips discloses that some parameters are weighted more heavily than others in a cost function, depending on the current situation of the vehicle but does not particularly note a weight corresponding to a lateral or longitudinal displacement error. Salleh discloses that the lateral component of a position error is minimized by considering road width and the longitudinal component of position error is difficult to reduce ((Salleh, Page 314, Col 1, ¶4) " While lateral error can be minimised by considering the road width factor, the longitudinal error remains difficult to be reduced especially for a drive with less heading variation and without intersection, stop or road markings. "). Accordingly, it would be obvious to weight the influence of the parameter with lessor error as part of the cost function so as to emphasize the more precise data points and de-emphasize the less precise ones. By applying the prior art references in this way, one having skill would arrive at the claimed invention.
Regarding claim 3, the proposed combination discloses The method of claim 1, as stated previously.
The proposed combination in further view of Lapin discloses (except the limitations surrounded by brackets ([[..]]))
[[wherein the loss function includes a final point distance error, and]]
wherein the decomposing the loss function of the analysis model of the prediction module into the multiple components with the multiple weightings comprises decomposing [[the final point distance error into a first final point distance error perpendicular to a lane]] with a first weighting and [[a second final point distance error along the lane]] with a second weighting, The total cost is decomposed into sub-costs with corresponding weights, as depicted in 4B and as stated previously ((Lapin, ¶38) " The system may use a total cost function to determine a total cost for the evaluated candidate trajectory based on the costs determined based on respective parameters ( cost terms), as illustrated in FIG. 4B and described in later section of this disclosure. The cost function for determining the total cost for the evaluated trajectory may have a number of cost terms ( corresponding to the cost values determined based on respective parameters) as weighted a number of weights ( e.g., a weight per cost term).").
[[wherein the first weighting is larger than the second weighting.]]
The proposed combination in further view of Lapin does not disclose; however, the proposed combination in further view of Ivanovic discloses wherein the loss function includes a final point distance error, and A final displacement error metric is disclosed for benchmarking performance in trajectory forecasting ((Ivanovic, ¶24-25) " Often, we are also interested in the displacement error of only the final predicted point, illustrated below (in particular, only \(\widehat{y}_3\) and \(y_3\) are compared. This provides a measure of a method’s error at the end of the prediction horizon, and is frequently referred to as Final Displacement Error (FDE). It is also usually reported in units of length.).
Ivanovic is analogous to the claimed invention because it pertains to the same field of endeavor of optimizations in trajectory planning for autonomous vehicles with consideration to performance evaluations in terms of error. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have evaluated the planned trajectories of the proposed combination using the final displacement error as the evaluation metric because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to modify the prior art references in order to arrive at the claimed invention. Burisch discloses the utilization of a loss function to compare and evaluate predictions but does not particularly disclose what type of loss function is utilized. Lapin discloses the use of a position error for evaluating candidate trajectories but does not provide particulars as to which type of position is being evaluated. Ivanovic discloses the utilization of the final displacement error metric for evaluating forecasted trajectories and particularly notes that the FDE is a main metric used to evaluate deterministic regressors because they are east to implement, natural for the task, and interpretable ((Ivanovic, ¶26) "ADE and FDE are the two main metrics used to evaluate deterministic regressors. While these metrics are natural for the task, easy to implement, and interpretable, they generally fall short in capturing the nuances of more sophisticated methods (see more on this below)."). Accordingly, it would have been obvious to utilize the ADE as the particular cost function to evaluate the planned trajectory because it is commonly used and yields predictable results.
The proposed combination in further view of Ivanovic does not disclose; however, in view of Salleh discloses decomposing the final point distance error into a first final point distance error perpendicular to a lane… and a second final point distance error along the lane. Distance error is described as being broken down into its lateral and longitudinal components for subsequent optimization ((Salleh, Page 314, Col 1, ¶3-4) "Vehicle localisation performance in accuracy and precision is generally measured by positioning error analysis which can be a relative distance error, heading error, lateral error, and longitudinal error. Distance error is the relative distance difference between ground truth data and fusion output while heading error is its angle difference. In order to reduce the distance error, we need to minimise the lateral and longitudinal errors. The position difference in the lateral axis (left/right of the object) is denoted as a lateral error and longitudinal error is the distance difference in the longitudinal axis, which makes the localisation to appear ahead or behind the ground truth data (Fig. 1). "); See also Salleh Figure 14.
Salleh is analogous art to the claimed invention because it is related to the same field of endeavor of autonomous/ intelligent vehicle route planning and error reduction techniques. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have decomposed the mean waypoint distance error, as disclosed by the proposed combination in view of Ivanovic, into its respective lateral and longitudinal error components as suggested by Salleh because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to modify the prior art references in order to arrive at the claimed invention. Lapin discloses the utilization of a weighted cost function wherein a total cost can be decomposed into weighted components. Lapin suggests that position errors are used as part of the cost function evaluation and further suggests that parameters of the trajectory planner may include distance from a leading vehicle and the distance to a lane boundary (Lapin, ¶43-44) but does not particularly disclose what position error or how the error may be decomposed according to particular parameters. The proposed combination in view of Ivanovic suggests utilization of the final displacement error as a cost function metric of interest for related applications. Salleh discloses the utilization of a positioning error that is decoupled into its lateral and longitudinal error components. Salleh explicitly notes that in order to reduce overall position error, errors need to be reduced in both the lateral and longitudinal components of the error (Salleh, Page 314, Col 1, ¶3). Accordingly, it would have been obvious to one having ordinary skill in the art to apply the decoupling of the error, as suggested by Salleh to the final displacement error of the proposed combination in order to achieve the greater control over reducing the overall error. By combining the prior art references in this way, one having skill in the art would arrive at the claimed invention.
The proposed combination in further view of Salleh does not disclose; however, in further view of Phillips discloses wherein the first weighting is larger than the second weighting. ((Phillips, ¶50) "For examples, the sub-cost value associated with a potential collision can be weighted more heavily than a sub-cost value associated with actor caution costs. In some examples, the weight of particular sub-cost value can depend on the current situation of the autonomous vehicle. Thus, overtaking buffer costs may be weighted more heavily on a single lane road than on a multi-lane highway.")
Phillips is analogous art to the claimed invention because it is related to the same field of endeavor of autonomous vehicle trajectory planning optimizations, particularly with regard for leveraging a weighted cost function for object avoidance. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have made the first weighing larger than the second weighting in the system of the proposed combination because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to make the modification in order to arrive at the claimed invention. Lapin discloses the adjustment of cost function weights but does not explicitly mention how the adjustments to the weights may be set. Ivanovic discloses the utilization of the final distance error as a particular metric by which to evaluate distance error. Phillips discloses that some parameters are weighted more heavily than others in a cost function, depending on the current situation of the vehicle but does not particularly note a weight corresponding to a lateral or longitudinal displacement error. Salleh discloses that the lateral component of a position error is minimized by considering road width and the longitudinal component of position error is difficult to reduce ((Salleh, Page 314, Col 1, ¶4) " While lateral error can be minimised by considering the road width factor, the longitudinal error remains difficult to be reduced especially for a drive with less heading variation and without intersection, stop or road markings. "). Accordingly, it would be obvious to weight the influence of the parameter with lessor error as part of the cost function so as to emphasize the more precise data points and de-emphasize the less precise ones. By applying the prior art references in this way, one having skill would arrive at the claimed invention.
Regarding claim 10, the proposed combination discloses The non-transitory machine-readable medium of claim 9, as stated previously.
The remaining limitations: wherein the loss function includes a mean waypoint distance error, and wherein the instructions further cause the processor to:
decompose the mean waypoint distance error into a first mean waypoint distance error perpendicular to a lane with a first weighting and a second mean waypoint distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting. are substantially similar to that recited in claim 2 and are therefore rejected under the same rationale.
Regarding claim 11, the proposed combination discloses The non-transitory machine-readable medium of claim 9 as stated previously.
The remaining limitations: wherein the loss function includes a final point distance error, and wherein the instructions further cause processor is further to:
decompose the final point distance error into a first final point distance error perpendicular to a lane with a first weighting and a second final point distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting. are substantially similar to that recited in claim 3 and are therefore rejected under the same rationale.
Regarding claim 18, the proposed combination discloses The data processing system of claim 17, as stated previously.
The remaining limitations: wherein the loss function includes a mean waypoint distance error, and wherein the processor is further to
decompose the mean waypoint distance error into a first mean waypoint distance error perpendicular to a lane with a first weighting and a second mean waypoint distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting. are substantially similar to that recited in claim 2 and are therefore rejected under the same rationale.
Regarding claim 19, the proposed combination discloses The data processing system of claim 17, as stated previously.
The remaining limitations: wherein the loss function includes a final point distance error, and wherein the processor is further to
decompose the final point distance error into a first final point distance error perpendicular to a lane with a first weighting and a second final point distance error along the lane with a second weighting, wherein the first weighting is larger than the second weighting. are substantially similar to that recited in claim 3 and are therefore rejected under the same rationale.
Claims 4, 12, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Burisch in view of Lapin and Xu as applied to claims 1, 9 and 17 above, and further in view of Santos et al (Santos, S., Azinheira, J., Botto, M., and Valerio, D., “Path Planning and Guidance Laws of a Formula Student Driverless Car”, June 9, 2022, World Electric Vehicle Journal, Volume 12, Issue 100), hereinafter referred to as Santos, and in view of Phillips et al (US 20210114617 A1), hereinafter referred to as Phillips.
Regarding claim 4, the proposed combination discloses The method of claim 1, as stated previously.
The proposed combination in further view of Lapin discloses (except the limitations surrounded by brackets ([[..]]))
wherein the loss function includes a location error, and ((Lapin, ¶43) "In particular embodiments, the system may analyze candidate trajectories that are very similar in terms of feature vectors, and determine their difference as measured by position errors to train a classification algorithm which optimizes the weights accordingly. ");((Lapin, ¶48) "In particular embodiments, the associated cost function with the adjusted one or more weights may allow a candidate trajectory having a minimum position-error vector with respect to the reference trajectory to have a smallest trajectory-evaluation metric value among the candidate trajectories.")
wherein the decomposing the loss function of the analysis model of the prediction module into the multiple components with the multiple weightings comprises decomposing the location error [[into a speed error]] with a first weighting [[and a heading error]] with a second weighting, [[wherein the first weighting is larger than the second weighting.]] The total cost is decomposed into sub-costs with corresponding weights, as depicted in 4B and as stated previously ((Lapin, ¶38) " The system may use a total cost function to determine a total cost for the evaluated candidate trajectory based on the costs determined based on respective parameters ( cost terms), as illustrated in FIG. 4B and described in later section of this disclosure. The cost function for determining the total cost for the evaluated trajectory may have a number of cost terms ( corresponding to the cost values determined based on respective parameters) as weighted a number of weights ( e.g., a weight per cost term)."). A position error is explicitly disclosed as a metric cost function to evaluate the difference for candidate trajectories ((Lapin, ¶43) " In particular embodiments, the system may analyze candidate trajectories that are very similar in terms of feature vectors, and determine their difference as measured by position errors to train a classification algorithm which optimizes the weights accordingly.")
The proposed combination in further view of Lapin does not explicitly disclose or suggest; however the proposed combination in view of Santos discloses decomposing position error …into a speed error… and a heading error The planned path (location) is decoupled into accounting for the boundaries of the track (which dictates the heading of the vehicle) and the speed ((Santos, Page 9, ¶5) " For path planning, the employed strategy consists of a decoupled approach, in the sense that one algorithm obtains the path, accounting for the boundaries of the track, and another one regulates its speed. Both algorithms will be described next. "). The path is obtained so as to define the heading error in terms of the bounds of the track ((Santos, Page 15, ¶6) " In autonomous driving, it is essential to know the vehicle pose in relation to the track in order to allow the control algorithm to correct eventual errors. These can be related to a distance (such as the cross-track error) or an angle (of which the heading error is an example). While it is possible to define such errors in different manners, in this paper, it was assumed that the vehicle has the waypoints in its front, provided by the perception and planning algorithms, and would then curve-fit them with a second-order polynomial in order to obtain a reference path."); ((Santos, Page 19, ¶2) "Considering that the reference path is intended to represent a solution close to an optimal one, the root mean square (RMS) of the cross-track error was used as an evaluation parameter. This error was computed separately from the one used for path-following, in order to guarantee an independent method to measure the distance to the reference path to be tracked")
Santos is analogous art to the claimed invention because it pertains to the same field of endeavor of autonomous vehicle optimizations, particularly for obstacle avoidance scenarios. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have implemented the decoupling of the planned path into speed and heading because some teaching, suggestion or motivation in the prior art references would have led one having ordinary skill in the art to do so in order to arrive at the claimed invention. Lapin discloses the utilization of a weighted cost function to characterize the overall cost of a planned path for an autonomous vehicle and discloses that the total cost can be decomposed into sub-costs wherein each contributing parameter has a corresponding weight. Lapin discloses that the system can evaluate trajectories using position errors to optimize weights of parameters accordingly (Lapin, ¶43) and further suggests that the parameters for evaluating the output may include velocity and turning radius (Lapin, ¶44) but does explicitly discloses breaking down the location error into speed and heading parameters. Santos discloses the decoupling of the path into speed and heading errors. Santos further notes that the autonomous vehicle operates usings lateral and longitudinal subsystems and the decoupling of the parameters for path planning enables decoupled and more simplified control of the subsystems that is reflective of human behavior ((Santos, Page 21, ¶3) "The results showed that, while the adopted approaches did not guarantee optimality, they were able to portray the expected behaviour of a human driver, and the controllers and path-following strategies provided enabled an FS vehicle to follow a given path, shortening the travelled distance and thus improving energy efficiency."). The approach demonstrates a satisfactory solution for control of the vehicle; and accordingly, the combination of the prior art references would have been obvious.
The proposed combination in further view of Lapin and Santos does not explicitly disclose; however, the proposed combination in view of Phillips discloses wherein the first weighting is larger than the second weighting. ((Phillips, ¶50) "For examples, the sub-cost value associated with a potential collision can be weighted more heavily than a sub-cost value associated with actor caution costs. In some examples, the weight of particular sub-cost value can depend on the current situation of the autonomous vehicle. Thus, overtaking buffer costs may be weighted more heavily on a single lane road than on a multi-lane highway.")
Phillips is analogous art to the claimed invention because it is related to the same field of endeavor of autonomous vehicle trajectory planning optimizations, particularly with regard for leveraging a weighted cost function for object avoidance. It would have been obvious to one of ordinary skill to which said subject matter pertains at the time the invention was filed to have made the first weighing larger than the second weighting in the system of the proposed combination because some teaching, suggestion, or motivation in the prior art references would have led one having ordinary skill in the art to make the modification in order to arrive at the claimed invention. Lapin discloses the adjustment of cost function weights but does not explicitly mention how the adjustments to the weights may be set. Phillips discloses that some parameters are weighted more heavily than others in a cost function, depending on the current situation of the vehicle but does not particularly note a weight corresponding to a speed or a heading. Santos suggests that the speed component is critical for safety and avoiding obstacle collision ((Santos, Page 13, ¶5) "This approach takes into account that any electromechanical system has an inherent response time, so the ability of a system to respond to a sudden obstacle can be derived from the concept of vehicle safety [33] and translated into the definition of multiple zones within the system observable environment. Such zones are four, as represented in Figure 8, and are responsible for the velocity adjustment needed to avoid obstacle collision. Figure 8. Schematic of the detection zones.") and further describes the heading error as being dependent on the speed ((Santos, Page 16, ¶1) " Thus, the mathematical expression for the cross-track error ey and the heading error ey is the same regardless of the situation. These errors are given by [[equation]] (51) [[equation]] (52) where the heading error ey was defined as the angle between the referenced tangent and the vehicle’s velocity vector v to take into account eventual sideslip. Because both errors are a cross-product of vectors in the xy plane, only the z component of ey and ey will be different from zero. "). Accordingly, it would have been obvious to set a higher weight on the speed because Santos suggests that the speed has a greater influence on avoiding obstacle collision and Phillips discloses that weights should be more heavily for those parameters associated with a potential collision.
Regarding claim 12, the proposed combination discloses The non-transitory machine-readable medium of claim 9, as stated previously.
The remaining limitations wherein the loss function includes a location error, and wherein the instructions further cause the processor to:
decompose the location error into a speed error with a first weighting and a heading error with a second weighting, wherein the first weighting is larger than the second weighting. are substantially similar to that recited in claim 4 and are therefore rejected under the same rationale.
Regarding claim 20, the proposed combination discloses The data processing system of claim 17, as stated previously.
The remaining limitations: wherein the loss function includes a location error, and
wherein the processor is further to decompose the location error into a speed error with a first weighting and a heading error with a second weighting, wherein the first weighting is larger than the second weighting. are substantially similar to that recited in claim 4 and are therefore rejected under the same rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20180164822 A1 discloses a trajectory planning methodology that is reactive to dynamic objects on the road. The methodology describes using decoupled lateral and longitudinal data in the trajectory planning process and further describes updating the motion planner in increments of every 100 ms.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EMILY GORMAN LEATHERS whose telephone number is (571)272-1880. The examiner can normally be reached Monday-Friday, 9:00 am-5:00 pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, EMERSON PUENTE can be reached at (571) 272-3652. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/E.G.L./Examiner, Art Unit 2187
/EMERSON C PUENTE/Supervisory Patent Examiner, Art Unit 2187
Prosecution Insights