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 .
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 1-21 are rejected under 35 U.S.C. 101 because they are directed towards a mental process or mathematical process without significantly more.
Claim 1 Cites:
A computer-implemented method for determining a target trajectory for a vehicle, the method comprising:
determining a respective score for each one of a plurality of trajectory candidates for the vehicle from a current ego pose to a target ego position;
for each trajectory candidate, generating one or more adjustment scores, the one or more adjustment scores including at least one of:
a first adjustment score indicative of a minimum distance between the vehicle and a given surrounding object of the vehicle as the vehicle moves along the given trajectory candidate;
a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
a third adjustment score indicative of a change in a longitudinal acceleration of the vehicle relative to the given surrounding object;
determining, based on the respective score and the plurality of adjustment scores, a modified respective score for each trajectory candidate;
ranking the plurality of trajectory candidates according to the modified respective scores; and
selecting, from the ranked trajectory candidates, a top trajectory candidate as being the target trajectory for navigating the vehicle from the current ego pose to the target ego position.
Step 2A prong one evaluation: Judicial Exception – Yes – Mental Processes
The Office submits that the foregoing bolded limitation(s) constitutes judicial exceptions in terms of “mental processes” because under its broadest reasonable interpretation, the claim covers performance using mental.
The claims recite determining a respective score for each of a plurality of trajectory candidates. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider different trajectories, and consider different scores for them. Thus this step is directed to a mental process.
The claims recite generating one or more adjustment scores, including minimum distances, time within an encroachment window, or lateral acceleration values. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different factors and create adjustment scores mentally for the trajectories. Thus this step is directed to a mental process.
The claims recite determining based on the respective score and the adjustment score a modified respective score. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different scores and combine them in some way to reach a new score. Thus this step is directed to a mental process.
The claims recite ranking the scores. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different scores and rank them. Thus this step is directed to a mental process.
The claims recite selecting a score. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different ranked scores and select a top ranking trajectory. Thus this step is directed to a mental process.
Step 2A Prong Two evaluations
Claims are evaluated whether as a whole it integrates the recited judicial exception into a practical application. As noted in the 2019 PEG, it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea or adding/performing insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.”
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the “additional limitations” while the bolded portions continue to represent the “abstract idea”).
The claims recite determining scores, generating adjustment scores, determining modified scores, ranking trajectories, and selecting trajectories using a device, a processor, a memory, a computer, processing circuitry, and a non-transitory computer readable storage medium. The above listed actions are recited at a high level of generality. The computer/circuitry that facilitate the steps are described by the specification at a high level of generality. The generically recited computer merely describes how to generally “apply” the otherwise mental/extra solution processes using a generic or general-purpose processor. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claim is not patent eligible.
2B Evaluation: Inventive Concept – No
Claims are evaluated as to whether the claims as a whole amount to significantly more than the recited exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim.
As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than possible uses for the output of the abstract idea. The same analysis applies here in 2B, i.e., possible uses for information or mere instructions to apply an exception on a generic computer cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Thus the claims are not patent eligible.
Claim 15 cites:
An electronic device for determining a target trajectory for a vehicle, the electronic device comprising at least processor and at least one non-transitory computer-readable memory storing instructions, which, when executed by the at least one processor, cause the electronic device to:
determine a respective score for each one of a plurality of trajectory candidates for the vehicle from a current ego pose to a target ego position;
for each trajectory candidate, generate one or more adjustment scores, the one or more adjustment scores including at least one of:
a first adjustment score indicative of a minimum distance between the vehicle and a given surrounding object of the vehicle as the vehicle moves along the given trajectory candidate;
a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
a third adjustment score indicative of a change in a longitudinal acceleration of the vehicle relative to the given surrounding object;
determine, based on the respective score and the plurality of adjustment scores, a modified respective score for each trajectory candidate;
rank the plurality of trajectory candidates according to the modified respective scores; and
select, from the ranked trajectory candidates, a top trajectory candidate as being the target trajectory for navigating the vehicle from the current ego pose to the target ego position.
Step 2A prong one evaluation: Judicial Exception – Yes – Mental Processes
The Office submits that the foregoing bolded limitation(s) constitutes judicial exceptions in terms of “mental processes” because under its broadest reasonable interpretation, the claim covers performance using mental.
The claims recite determining a respective score for each of a plurality of trajectory candidates. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider different trajectories, and consider different scores for them. Thus this step is directed to a mental process.
The claims recite generating one or more adjustment scores, including minimum distances, time within an encroachment window, or lateral acceleration values. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different factors and create adjustment scores mentally for the trajectories. Thus this step is directed to a mental process.
The claims recite determining based on the respective score and the adjustment score a modified respective score. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different scores and combine them in some way to reach a new score. Thus this step is directed to a mental process.
The claims recite ranking the scores. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different scores and rank them. Thus this step is directed to a mental process.
The claims recite selecting a score. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different ranked scores and select a top ranking trajectory. Thus this step is directed to a mental process.
Step 2A Prong Two evaluations
Claims are evaluated whether as a whole it integrates the recited judicial exception into a practical application. As noted in the 2019 PEG, it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea or adding/performing insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.”
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the “additional limitations” while the bolded portions continue to represent the “abstract idea”).
The claims recite determining scores, generating adjustment scores, determining modified scores, ranking trajectories, and selecting trajectories using a device, a processor, a memory, a computer, processing circuitry, and a non-transitory computer readable storage medium. The above listed actions are recited at a high level of generality. The computer/circuitry that facilitate the steps are described by the specification at a high level of generality. The generically recited computer merely describes how to generally “apply” the otherwise mental/extra solution processes using a generic or general-purpose processor. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claim is not patent eligible.
2B Evaluation: Inventive Concept – No
Claims are evaluated as to whether the claims as a whole amount to significantly more than the recited exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim.
As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than possible uses for the output of the abstract idea. The same analysis applies here in 2B, i.e., possible uses for information or mere instructions to apply an exception on a generic computer cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Thus the claims are not patent eligible.
Claim 21 cites:
A non-transient computer readable medium storing executable instructions for causing at least one computer processor to:
determine a respective score for each one of a plurality of trajectory candidates for the vehicle from a current ego pose to a target ego position;
for each trajectory candidate, generate one or more adjustment scores, the one or more adjustment scores including at least one of:
a first adjustment score indicative of a minimum distance between the vehicle and a given surrounding object of the vehicle as the vehicle moves along the given trajectory candidate;
a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
a third adjustment score indicative of a change in a longitudinal acceleration of the vehicle relative to the given surrounding object;
determine, based on the respective score and the plurality of adjustment scores, a modified respective score for each trajectory candidate;
rank the plurality of trajectory candidates according to the modified respective scores; and
select, from the ranked trajectory candidates, a top trajectory candidate as being the target trajectory for navigating the vehicle from the current ego pose to the target ego position.
Step 2A prong one evaluation: Judicial Exception – Yes – Mental Processes
The Office submits that the foregoing bolded limitation(s) constitutes judicial exceptions in terms of “mental processes” because under its broadest reasonable interpretation, the claim covers performance using mental.
The claims recite determining a respective score for each of a plurality of trajectory candidates. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider different trajectories, and consider different scores for them. Thus this step is directed to a mental process.
The claims recite generating one or more adjustment scores, including minimum distances, time within an encroachment window, or lateral acceleration values. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different factors and create adjustment scores mentally for the trajectories. Thus this step is directed to a mental process.
The claims recite determining based on the respective score and the adjustment score a modified respective score. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different scores and combine them in some way to reach a new score. Thus this step is directed to a mental process.
The claims recite ranking the scores. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different scores and rank them. Thus this step is directed to a mental process.
The claims recite selecting a score. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different ranked scores and select a top ranking trajectory. Thus this step is directed to a mental process.
Step 2A Prong Two evaluations
Claims are evaluated whether as a whole it integrates the recited judicial exception into a practical application. As noted in the 2019 PEG, it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea or adding/performing insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.”
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the “additional limitations” while the bolded portions continue to represent the “abstract idea”).
The claims recite determining scores, generating adjustment scores, determining modified scores, ranking trajectories, and selecting trajectories using a device, a processor, a memory, a computer, processing circuitry, and a non-transitory computer readable storage medium. The above listed actions are recited at a high level of generality. The computer/circuitry that facilitate the steps are described by the specification at a high level of generality. The generically recited computer merely describes how to generally “apply” the otherwise mental/extra solution processes using a generic or general-purpose processor. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
The claim is not patent eligible.
2B Evaluation: Inventive Concept – No
Claims are evaluated as to whether the claims as a whole amount to significantly more than the recited exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim.
As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than possible uses for the output of the abstract idea. The same analysis applies here in 2B, i.e., possible uses for information or mere instructions to apply an exception on a generic computer cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Thus the claims are not patent eligible.
Claim 2 cites:
The method of claim 1, wherein generating the first adjustment score comprises using a first prediction model that has been trained to determine a minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate.
Claim 3 cites:
The method of claim 2, wherein the first prediction model has been trained to determine a value of a distance cost function, expressed by a following equation:
Distance Cost = e^(-k(min(distance)))
where min (distance) is the minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate; and
k is a coefficient.
Claim 4 cites:
The method of claim 1, wherein generating the second adjustment score comprises using a second prediction model that has been trained to determine PETs for those ones of the plurality trajectory candidates of the vehicle that are intersected by an object trajectory of the given surrounding object.
Claim 5 cites:
The method of claim 4, wherein the second prediction model has been trained to determine a value of a PET cost function, expressed by a following equation:
PET Cost = (PET - desired PET)²,
where PET is a given PET for the given trajectory candidate of the vehicle; and
desired PET is a predetermined PET threshold value.
Claim 6 cites:
The method of claim 1, wherein generating the third adjustment score comprises using a third prediction model that has been trained to determine motion parameters of the vehicle causing the change in the longitudinal acceleration of the vehicle and relative to the given surrounding object.
Claim 7 cites:
The method of claim 6, wherein the third prediction model has been trained to determine a value of a follow cost function, expressed by a following equation:
PNG
media_image1.png
50
343
media_image1.png
Greyscale
where aₖ is a longitudinal acceleration value of the vehicle at a kth point defining the given trajectory candidate;
n is a total number of points defining the given trajectory candidate; and
follow_accel is a desired longitudinal acceleration of the vehicle relative to the given surrounding object.
Claim 8 cites:
The method of claim 7, wherein the given surrounding object moves immediately ahead of the vehicle, and wherein the method further comprises determining the desired longitudinal acceleration according to a following equation:
PNG
media_image2.png
52
405
media_image2.png
Greyscale
where v₁ is a vehicle velocity of the vehicle at a kth point defining the given trajectory candidate;
v₂ is an object current velocity of the given surrounding object while the vehicle is at the kth point defining the given trajectory candidate;
d is a current distance between the vehicle and the given surrounding object while the vehicle is at the kth point defining the given trajectory candidate;
kd, kv, do are constants; and
t is time.
Claim 9 cites:
The method of claim 1, wherein:
generating the first adjustment score comprises using a first prediction model that has been trained to determine a minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate;
generating the second adjustment score comprises using a second prediction model that has been trained to determine PETs for those ones of the plurality trajectory candidates of the vehicle that are intersected by an object trajectory of the given surrounding object; and
generating the third adjustment score comprises using a third prediction model that has been trained to determine motion parameters of the vehicle causing the change in the longitudinal acceleration of the vehicle relative to the given surrounding object.
Claim 10 cites:
The method of claim 9, wherein the determining the modified respective score for the given trajectory candidate further comprises determining an average adjustment score of the plurality of adjustment scores of the given trajectory candidate.
Claim 11 cites:
The method of claim 10, wherein the determining the modified respective score for the given trajectory candidate comprises multiplying the respective score thereof by a following multiplier:
(1 + average auxiliary score)⁻¹,
where average adjustment score is the average adjustment score of the plurality of adjustment scores.
Claim 12 cites:
The method of claim 9, wherein each one of the first, second, and third prediction models has been trained independently.
Claim 13 cites:
The method of claim 9, wherein each one of the first, second, and third prediction models is a Multilayer Perceptron prediction model.
Claim 14 cites:
The method of claim 1, wherein the given surrounding object comprises a plurality of surrounding objects; and wherein:
the first adjustment score is indicative of a minimum distance between the vehicle and a first surrounding object of the plurality of surrounding objects as the vehicle moves along the given trajectory candidate;
the second adjustment score is indicative of a PET for the vehicle and a second surrounding object of the plurality of surrounding objects; and
the third adjustment score is indicative of a change in a longitudinal acceleration of the vehicle relative to a third surrounding object of the plurality of surrounding objects as the third surrounding object moves immediately ahead of the vehicle.
Claim 16 cites:
The electronic device of claim 15, wherein to generate the first adjustment score, the at least one processor causes the electronic device to use a first prediction model that has been trained to determine a minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate.
Claim 17 cites:
The electronic device of claim 16, wherein the first prediction model has been trained to determine a value of a distance cost function, expressed by a following equation:
Distance Cost = e^ -k(min(distance))
where min (distance) is the minimum distance between the vehicle and the given surrounding
object as the vehicle moves along the given trajectory candidate; and
k is a coefficient.
Claim 18 cites:
The electronic device of claim 15, wherein to generate the second adjustment score, the at least one processor causes the electronic device to use a second prediction model that has been trained to determine PETs for those ones of the plurality trajectory candidates of the vehicle that are intersected by an object trajectory of the given surrounding object.
Claim 19 cites:
The electronic device of claim 18, wherein the second prediction model has been trained to determine a value of a PET cost function, expressed by a following equation:
PET Cost = (PET - desired PET)².
where PET is a given PET for the given trajectory candidate of the vehicle; and
desired PET is a predetermined PET threshold value.
Claim 20 cites:
The electronic device of claim 15, wherein to generate the third adjustment score, the at least one processor causes the electronic device to use a third prediction model that has been trained to determine motion parameters of the vehicle causing the change in the longitudinal acceleration of the vehicle relative to the given surrounding object.
Step 2A prong one evaluation: Judicial Exception – Yes – Mental Processes
The Office submits that the foregoing bolded limitation(s) constitutes judicial exceptions in terms of “mental processes” because under its broadest reasonable interpretation, the claim covers performance using mental.
Claim 8 recites determining the longitudinal acceleration according to an equation. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers mathematical operations, as it explicitly provides an equation for the task. Thus this step is directed to a mathematical process..
Claim 10 cites determining an average adjustment score. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind, but for the limitation that processing circuitry be programed to perform the task. That is, other than reciting “processor”, or “memory”, nothing in the claim precludes the element being done in the mind. A person could mentally consider the different scores and create an average. Thus this step is directed to a mental process.
Claim 11 cites multiplying the scores according to an equation. This limitation, as drafted, is a simple process that, under its broadest reasonable interpretation, covers mathematical process since an equation is provided to perform the task. Thus this step is directed to a mental process.
Step 2A Prong Two evaluations
Claims are evaluated whether as a whole it integrates the recited judicial exception into a practical application. As noted in the 2019 PEG, it must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea or adding/performing insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.”
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the “additional limitations” while the bolded portions continue to represent the “abstract idea”).
The claims recite determining scores, generating adjustment scores, determining modified scores, ranking trajectories, averaging values, determining accelerations and selecting trajectories using a device, a processor, a memory, a computer, processing circuitry, and a non-transitory computer readable storage medium. The above listed actions are recited at a high level of generality. The computer/circuitry that facilitate the steps are described by the specification at a high level of generality. The generically recited computer merely describes how to generally “apply” the otherwise mental/extra solution processes using a generic or general-purpose processor. Accordingly, even in combination, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Additionally, the models, or perceptron models, provided to perform the additional tasks are cited with a high level of generality. They may have been trained to perform tasks, but they do not explicitly tie this training to the outcome. Merely that they are used in some way.
The claim is not patent eligible.
2B Evaluation: Inventive Concept – No
Claims are evaluated as to whether the claims as a whole amount to significantly more than the recited exception, i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim.
As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than possible uses for the output of the abstract idea. The same analysis applies here in 2B, i.e., possible uses for information or mere instructions to apply an exception on a generic computer cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Thus the claims are not patent eligible.
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.
Claims 1-10, 12, and 14-21 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al (US Pub 2022/0227391 A1) in light of Omari et al (US Pub 2024/0025395 A1), hereafter known as Omari in light of Arora et al (US Pub 11,801,864 B1), hereafter known as Arora.
For Claim 1, Wang teaches A computer-implemented method for determining a target trajectory for a vehicle, the method comprising:
determining a respective score for each one of a plurality of trajectory candidates for the vehicle from a current ego pose to a target ego position; ([0061] As shown in FIG. 6, method 600 begins with 602 and continues with 604 where the computing device obtains candidate vehicle trajectory(ies) and context information from a data store (e.g., memory 312 of FIG. 3). The context information generally defines circumstances and/or conditions of an environment surrounding the autonomous vehicle. The context information can include, but is not limited to, predicted trajectories for detected objects, a map (e.g., 3D road map), traffic information (e.g., traffic flow, traffic jams, slow moving, delays, road closure, roadwork, construction, accident, etc.), environmental information (e.g., rain, snow, fog, etc.), and/or other information (e.g., information received over communication link(s) 150, 152, 154 of FIG. 1). A candidate vehicle trajectory is selected in 606. The selected candidate vehicle trajectory and the context information is used in 608 to generate a feature vector.
[0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0071] Once the final quality score s.sub.final for the given candidate trajectory has been generated, method 600 may return to 606 so that the process is repeated for a next candidate vehicle trajectory as shown by optional 624. In 626, a candidate vehicle trajectory is selected based on the final quality score(s) representing the quality of the candidate vehicle trajectory(ies). For example, the candidate vehicle trajectory with the highest or lowest final quality score is selected in 616. Alternatively or additionally, the candidate vehicle trajectory is selected as the one with the quality score that is greater than or less than a given threshold. If two or more candidate vehicle trajectories have a quality score that is greater than or less than the given threshold, then the candidate vehicle trajectory is selected as the one with the greatest or lowest quality score. A linear/non-linear function could be used to selected the candidate vehicle trajectory based on the final quality scores. Subsequently, 628 is performed where method 600 ends or other operations are performed. For example, the computing device may consider the selected candidate vehicle trajectory as a high quality vehicle trajectory, and therefore perform operations to cause the AV to follow the same (e.g., provided that there is no risk of collision with an object).
Figure 6)
for each trajectory candidate, generating one or more adjustment scores, the one or more adjustment scores including at least one of:
a first adjustment score indicative of a minimum distance between the vehicle and a given surrounding object of the vehicle as the vehicle moves along the given trajectory candidate; ([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).)
determining, based on the respective score and the plurality of adjustment scores, a modified respective score for each trajectory candidate; ([0069] If two or more quality scores were generated for at least one scenario class [616: YES], then method 600 continues with 620 where the quality scores are combined together to produce an aggregate quality score s.sub.aggregate for the given scenario class. For example, if two quality scores s.sub.1-class1 and s.sub.2-class2 where generated for a given class X, then the aggregate quality score for the given class may be defined by the following mathematical equation (5), mathematical equation (6), mathematical equation (7) or mathematical equation (8).)
selecting, from the ranked trajectory candidates, a top trajectory candidate as being the target trajectory for navigating the vehicle from the current ego pose to the target ego position. ([0071] Once the final quality score s.sub.final for the given candidate trajectory has been generated, method 600 may return to 606 so that the process is repeated for a next candidate vehicle trajectory as shown by optional 624. In 626, a candidate vehicle trajectory is selected based on the final quality score(s) representing the quality of the candidate vehicle trajectory(ies). For example, the candidate vehicle trajectory with the highest or lowest final quality score is selected in 616. Alternatively or additionally, the candidate vehicle trajectory is selected as the one with the quality score that is greater than or less than a given threshold. If two or more candidate vehicle trajectories have a quality score that is greater than or less than the given threshold, then the candidate vehicle trajectory is selected as the one with the greatest or lowest quality score. A linear/non-linear function could be used to selected the candidate vehicle trajectory based on the final quality scores. Subsequently, 628 is performed where method 600 ends or other operations are performed. For example, the computing device may consider the selected candidate vehicle trajectory as a high quality vehicle trajectory, and therefore perform operations to cause the AV to follow the same (e.g., provided that there is no risk of collision with an object).)
Wang does not explicitly teach a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
a third adjustment score indicative of a change in a longitudinal acceleration of the vehicle relative to the given surrounding object;
ranking the plurality of trajectory candidates according to the modified respective scores; and
Omari, however, does teach ranking the plurality of trajectory candidates according to the modified respective scores; and ([0111] The planning system 404 can identify primary actions and secondary actions in a variety of ways. In some cases, the primary actions can be actions (or predictions) that have a high likelihood of happening and the secondary actions can be actions that have a low likelihood of happening. In some examples, the high likelihood and low likelihood are determined with respect to each other. As such, primary actions can be a particular number of actions that are more likely to happen than a set number of secondary actions. For example, the top two or three ranked predictions for each agent can be identified as primary actions and the remaining actions for the respective agent can be identified as secondary actions. In some cases, the likelihood of an action happening can be based on a probability assigned to the action by the prediction engine or planning system 404 and/or a ranking assigned to the action by the prediction engine and/or planning system 404. For example, when the planning system receives predictions from the prediction engine, the prediction engine can include a probability that a particular prediction (or action) will occur and/or include a ranking of the different predictions for a particular agent. The planning system 404 can use the probabilities and/or rankings to determine primary and secondary actions.)
Therefore, it would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in light of Omari such that the scores are ranked before one is selected. It would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in this way because it would allow the system to know the best trajectories before making a selection. In a situation in which the normally highest ranked choice cannot be picked, the second or third would be readily available to be selected without further analysis.
Arora, however, does teach a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding collision zones; and
(Page 12, Column 7, Lines 14-34 (28) In some examples, the vehicle computing system may determine the occlusion cost based on a blocking penalty associated with the vehicle occupying space in front of the occlusion zone for a period of time. In some examples, the vehicle computing system may determine the blocking penalty by multiplying the vehicle speed by the time associated with the vehicle being within a collision zone between the vehicle and the occluded object. In various examples, the occlusion cost may include a sum of the progression penalty and the blocking penalty. In some examples, the occlusion cost may include the sum of the progression penalty and the blocking penalty multiplied by a probability that the action will affect the occluded object's travel. In some examples, the probability may be determined based on a distance between the occluded object (e.g., the occlusion zone) and the collision zone. In some examples, the probability may additionally be determined based on a predicted object trajectory of the occluded object. In various examples, the probability may be based in part on a time associated with the occluded object traveling from the occlusion zone to the collision zone.)
Therefore, it would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in light of Arora such that a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; .
It would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in this way because if there are areas that are dangerous (such as areas that are close to other objects) then it would be prudent to avoid getting too close, and to avoid spending too much time close to those other object. If every second in such an area is an opportunity for a collision to occur, then reducing the amount of time the vehicle spends in such an area would be likely to prevent collisions.
For Claim 2, Wang teaches The method of claim 1, wherein generating the first adjustment score comprises using a first prediction model that has been trained to determine a minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate. ([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0048] The high quality vehicle trajectory 420 may represent a smooth path that does not have abrupt changes that would otherwise provide passenger discomfort. For example, the vehicle trajectory is defined by a path of travel along a given lane of a road in which the object is not predicted travel within a given amount of time. The high quality vehicle trajectory 420 is then provided to block 408.
[0065] The machine-learning algorithm can employ supervised machine learning, semi-supervised machine learning, unsupervised machine learning, and/or reinforcement machine learning. Each of these listed types of machine-learning algorithms is well known in the art. In some scenarios, the machine-learning algorithm includes, but is not limited to, a decision tree learning algorithm, an association rule learning algorithm, an artificial neural network learning algorithm, a deep learning algorithm, an inductive logic programming based algorithm, a support vector machine based algorithm, a Bayesian network based algorithm, a representation learning algorithm, a similarity and metric learning algorithm, a sparse dictionary learning algorithm, a genetic algorithm, a rule-based machine-learning algorithm, and/or a learning classifier system based algorithm. The machine-learning process implemented by the present solution can be built using Commercial-Off-The-Shelf (COTS) tools (e.g., SAS available from SAS Institute Inc. of Cary, N.C.).)
For Claim 3, modified Wang teaches The method of claim 2, wherein the first prediction model has been trained to determine a value of a distance cost function, expressed by a following equation:
Distance Cost = e^(-k(min(distance)))
where min (distance) is the minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate; and
k is a coefficient.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 4, modified Wang teaches The method of claim 1, wherein generating the second adjustment score comprises using a second prediction model that has been trained to determine PETs for those ones of the plurality trajectory candidates of the vehicle that are intersected by an object trajectory of
the given surrounding object.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 5, modified Wang teaches The method of claim 4, wherein the second prediction model has been trained to determine a value of a PET cost function, expressed by a following equation:
PET Cost = (PET - desired PET)²,
where PET is a given PET for the given trajectory candidate of the vehicle; and
desired PET is a predetermined PET threshold value.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 6, modified Wang teaches The method of claim 1, wherein generating the third adjustment score comprises using a third prediction model that has been trained to determine motion parameters of the vehicle causing the change in the longitudinal acceleration of the vehicle and relative to the given
surrounding object.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 7, modified Wang teaches The method of claim 6, wherein the third prediction model has been trained to determine a value of a follow cost function, expressed by a following equation:
PNG
media_image3.png
41
333
media_image3.png
Greyscale
where aₖ is a longitudinal acceleration value of the vehicle at a kth point defining the given trajectory candidate;
n is a total number of points defining the given trajectory candidate; and
follow_accel is a desired longitudinal acceleration of the vehicle relative to the given surrounding object.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 8, modified Wang teaches The method of claim 7, wherein the given surrounding object moves immediately ahead of the vehicle, and wherein the method further comprises determining the desired longitudinal
acceleration according to a following equation:
PNG
media_image4.png
37
382
media_image4.png
Greyscale
where v₁ is a vehicle velocity of the vehicle at a kth point defining the given trajectory candidate;
v₂ is an object current velocity of the given surrounding object while the vehicle is at the kth point defining the given trajectory candidate;
d is a current distance between the vehicle and the given surrounding object while the vehicle is at the kth point defining the given trajectory candidate;
kd, kv, do are constants; and
t is time.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 9, Wang teaches The method of claim 1, wherein:
generating the first adjustment score comprises using a first prediction model that has been trained to determine a minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate; (([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0048] The high quality vehicle trajectory 420 may represent a smooth path that does not have abrupt changes that would otherwise provide passenger discomfort. For example, the vehicle trajectory is defined by a path of travel along a given lane of a road in which the object is not predicted travel within a given amount of time. The high quality vehicle trajectory 420 is then provided to block 408.
[0065] The machine-learning algorithm can employ supervised machine learning, semi-supervised machine learning, unsupervised machine learning, and/or reinforcement machine learning. Each of these listed types of machine-learning algorithms is well known in the art. In some scenarios, the machine-learning algorithm includes, but is not limited to, a decision tree learning algorithm, an association rule learning algorithm, an artificial neural network learning algorithm, a deep learning algorithm, an inductive logic programming based algorithm, a support vector machine based algorithm, a Bayesian network based algorithm, a representation learning algorithm, a similarity and metric learning algorithm, a sparse dictionary learning algorithm, a genetic algorithm, a rule-based machine-learning algorithm, and/or a learning classifier system based algorithm. The machine-learning process implemented by the present solution can be built using Commercial-Off-The-Shelf (COTS) tools (e.g., SAS available from SAS Institute Inc. of Cary, N.C.).))
generating the second adjustment score comprises using a second prediction model that has been trained to determine PETs for those ones of the plurality trajectory candidates of the vehicle that are intersected by an object trajectory of the given surrounding object; and
generating the third adjustment score comprises using a third prediction model that has been trained to determine motion parameters of the vehicle causing the change in the longitudinal acceleration of the vehicle relative to the given surrounding object.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 10, Wang teaches The method of claim 9, wherein the determining the modified respective score for the given trajectory candidate further comprises determining an average adjustment score of the plurality of adjustment scores of the given trajectory candidate. ([0069] If two or more quality scores were generated for at least one scenario class [616: YES], then method 600 continues with 620 where the quality scores are combined together to produce an aggregate quality score s.sub.aggregate for the given scenario class. For example, if two quality scores s.sub.1-class1 and s.sub.2-class2 where generated for a given class X, then the aggregate quality score for the given class may be defined by the following mathematical equation (5), mathematical equation (6), mathematical equation (7) or mathematical equation (8).
s.sub.aggregate-classX=s.sub.1-classX+s.sub.2-classX (5)
s.sub.aggregate-classX=avg (s.sub.1-classX+s.sub.2-classX) (6)
)
For Claim 12, Wang teaches The method of claim 9, wherein each one of the first, second, and third prediction models has been trained independently. ([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0063] The selected candidate vehicle trajectory and the context information is also used in 610 to classify a scenario specified thereby into one or more scenario classes. The scenario classification can be discrete or continuous. In the discrete case, the context is classified as one of the scenarios. In the continuous case, the scenario classifier given a probability of each possible scenario. The scenario space itself can be discrete or continuous. In the discrete case, there are a finite number of scenario. In the continuous case, the scenario space is a multi-dimensional vector space where each scenario is represented by a multi-dimensional real-valued vector.
[0064] The scenario classes can include, but are not limited to, a left turn scenario class, a right turn scenario, a passing scenario class, a driving scenario class, an acceleration scenario class, a deceleration scenario class, a stationary scenario class, a forward driving scenario class, a reverse driving scenario class, and/or a passenger pick-up scenario class. In some scenarios, a machine learning algorithm is employed in which machine learned models are used to determine scenario classifications. In those or other scenarios, the classification criteria is pre-defined to specify possible scenario classifications. For example, if the select candidate vehicle trajectory and map of the context information indicate that the AV is to take a left or right turn, then the scenario may be classified as a left or right turn scenario. If the selected candidate vehicle trajectory, a predicted trajectory for a detected object, road map and traffic information indicate that the AV is to pass the detected object, then the scenario may be classified as a passing scenario. If the selected candidate vehicle trajectory indicates that the AV is stationary and the context information indicates that individual(s) is(are) in proximity to the AV, then the scenario may be classified as a passenger pick-up scenario. The present solution is not limited to the particulars of this example.
[0065] The machine-learning algorithm can employ supervised machine learning, semi-supervised machine learning, unsupervised machine learning, and/or reinforcement machine learning. Each of these listed types of machine-learning algorithms is well known in the art. In some scenarios, the machine-learning algorithm includes, but is not limited to, a decision tree learning algorithm, an association rule learning algorithm, an artificial neural network learning algorithm, a deep learning algorithm, an inductive logic programming based algorithm, a support vector machine based algorithm, a Bayesian network based algorithm, a representation learning algorithm, a similarity and metric learning algorithm, a sparse dictionary learning algorithm, a genetic algorithm, a rule-based machine-learning algorithm, and/or a learning classifier system based algorithm. The machine-learning process implemented by the present solution can be built using Commercial-Off-The-Shelf (COTS) tools (e.g., SAS available from SAS Institute Inc. of Cary, N.C.).)
For Claim 14, Wang teaches The method of claim 1, wherein the given surrounding object comprises a plurality of surrounding objects; and wherein:
the first adjustment score is indicative of a minimum distance between the vehicle and a first surrounding object of the plurality of surrounding objects as the vehicle moves along the given trajectory candidate; (([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0048] The high quality vehicle trajectory 420 may represent a smooth path that does not have abrupt changes that would otherwise provide passenger discomfort. For example, the vehicle trajectory is defined by a path of travel along a given lane of a road in which the object is not predicted travel within a given amount of time. The high quality vehicle trajectory 420 is then provided to block 408.
[0065] The machine-learning algorithm can employ supervised machine learning, semi-supervised machine learning, unsupervised machine learning, and/or reinforcement machine learning. Each of these listed types of machine-learning algorithms is well known in the art. In some scenarios, the machine-learning algorithm includes, but is not limited to, a decision tree learning algorithm, an association rule learning algorithm, an artificial neural network learning algorithm, a deep learning algorithm, an inductive logic programming based algorithm, a support vector machine based algorithm, a Bayesian network based algorithm, a representation learning algorithm, a similarity and metric learning algorithm, a sparse dictionary learning algorithm, a genetic algorithm, a rule-based machine-learning algorithm, and/or a learning classifier system based algorithm. The machine-learning process implemented by the present solution can be built using Commercial-Off-The-Shelf (COTS) tools (e.g., SAS available from SAS Institute Inc. of Cary, N.C.).))
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
the second adjustment score is indicative of a PET for the vehicle and a second surrounding object of the plurality of surrounding objects; and
the third adjustment score is indicative of a change in a longitudinal acceleration of the vehicle relative to a third surrounding object of the plurality of surrounding objects as the third surrounding object moves immediately ahead of the vehicle.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 15, Wang teaches An electronic device for determining a target trajectory for a vehicle, the electronic device comprising at least processor and at least one non-transitory computer-readable memory storing instructions, which, when executed by the at least one processor, cause the electronic device to: ([0041] As shown in FIG. 3, the computing device 300 comprises a user interface 302, a Central Processing Unit (CPU) 306, a system bus 310, a memory 312 connected to and accessible by other portions of computing device 300 through system bus 310, a system interface 360, and hardware entities 314 connected to system bus 310. The user interface can include input devices and output devices, which facilitate user-software interactions for controlling operations of the computing device 300. The input devices include, but are not limited to, a physical and/or touch keyboard 350. The input devices can be connected to the computing device 300 via a wired or wireless connection (e.g., a Bluetooth® connection). The output devices include, but are not limited to, a speaker 352, a display 354, and/or light emitting diodes 356. System interface 360 is configured to facilitate wired or wireless communications to and from external devices (e.g., network nodes such as access points, etc.).)
determine a respective score for each one of a plurality of trajectory candidates for the vehicle from a current ego pose to a target ego position; (([0061] As shown in FIG. 6, method 600 begins with 602 and continues with 604 where the computing device obtains candidate vehicle trajectory(ies) and context information from a data store (e.g., memory 312 of FIG. 3). The context information generally defines circumstances and/or conditions of an environment surrounding the autonomous vehicle. The context information can include, but is not limited to, predicted trajectories for detected objects, a map (e.g., 3D road map), traffic information (e.g., traffic flow, traffic jams, slow moving, delays, road closure, roadwork, construction, accident, etc.), environmental information (e.g., rain, snow, fog, etc.), and/or other information (e.g., information received over communication link(s) 150, 152, 154 of FIG. 1). A candidate vehicle trajectory is selected in 606. The selected candidate vehicle trajectory and the context information is used in 608 to generate a feature vector.
[0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0071] Once the final quality score s.sub.final for the given candidate trajectory has been generated, method 600 may return to 606 so that the process is repeated for a next candidate vehicle trajectory as shown by optional 624. In 626, a candidate vehicle trajectory is selected based on the final quality score(s) representing the quality of the candidate vehicle trajectory(ies). For example, the candidate vehicle trajectory with the highest or lowest final quality score is selected in 616. Alternatively or additionally, the candidate vehicle trajectory is selected as the one with the quality score that is greater than or less than a given threshold. If two or more candidate vehicle trajectories have a quality score that is greater than or less than the given threshold, then the candidate vehicle trajectory is selected as the one with the greatest or lowest quality score. A linear/non-linear function could be used to selected the candidate vehicle trajectory based on the final quality scores. Subsequently, 628 is performed where method 600 ends or other operations are performed. For example, the computing device may consider the selected candidate vehicle trajectory as a high quality vehicle trajectory, and therefore perform operations to cause the AV to follow the same (e.g., provided that there is no risk of collision with an object).
Figure 6))
for each trajectory candidate, generate one or more adjustment scores, the one or more adjustment scores including at least one of:
a first adjustment score indicative of a minimum distance between the vehicle and a given surrounding object of the vehicle as the vehicle moves along the given trajectory candidate; (([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).))
determine, based on the respective score and the plurality of adjustment scores, a modified respective score for each trajectory candidate; (([0069] If two or more quality scores were generated for at least one scenario class [616: YES], then method 600 continues with 620 where the quality scores are combined together to produce an aggregate quality score s.sub.aggregate for the given scenario class. For example, if two quality scores s.sub.1-class1 and s.sub.2-class2 where generated for a given class X, then the aggregate quality score for the given class may be defined by the following mathematical equation (5), mathematical equation (6), mathematical equation (7) or mathematical equation (8).))
select, from the ranked trajectory candidates, a top trajectory candidate as being the target trajectory for navigating the vehicle from the current ego pose to the target ego position. (([0071] Once the final quality score s.sub.final for the given candidate trajectory has been generated, method 600 may return to 606 so that the process is repeated for a next candidate vehicle trajectory as shown by optional 624. In 626, a candidate vehicle trajectory is selected based on the final quality score(s) representing the quality of the candidate vehicle trajectory(ies). For example, the candidate vehicle trajectory with the highest or lowest final quality score is selected in 616. Alternatively or additionally, the candidate vehicle trajectory is selected as the one with the quality score that is greater than or less than a given threshold. If two or more candidate vehicle trajectories have a quality score that is greater than or less than the given threshold, then the candidate vehicle trajectory is selected as the one with the greatest or lowest quality score. A linear/non-linear function could be used to selected the candidate vehicle trajectory based on the final quality scores. Subsequently, 628 is performed where method 600 ends or other operations are performed. For example, the computing device may consider the selected candidate vehicle trajectory as a high quality vehicle trajectory, and therefore perform operations to cause the AV to follow the same (e.g., provided that there is no risk of collision with an object).))
Wang does not explicitly teach a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
a third adjustment score indicative of a change in a longitudinal acceleration of the vehicle relative to the given surrounding object;
rank the plurality of trajectory candidates according to the modified respective scores; and
Omari, however, does teach rank the plurality of trajectory candidates according to the modified respective scores; and
([0111] The planning system 404 can identify primary actions and secondary actions in a variety of ways. In some cases, the primary actions can be actions (or predictions) that have a high likelihood of happening and the secondary actions can be actions that have a low likelihood of happening. In some examples, the high likelihood and low likelihood are determined with respect to each other. As such, primary actions can be a particular number of actions that are more likely to happen than a set number of secondary actions. For example, the top two or three ranked predictions for each agent can be identified as primary actions and the remaining actions for the respective agent can be identified as secondary actions. In some cases, the likelihood of an action happening can be based on a probability assigned to the action by the prediction engine or planning system 404 and/or a ranking assigned to the action by the prediction engine and/or planning system 404. For example, when the planning system receives predictions from the prediction engine, the prediction engine can include a probability that a particular prediction (or action) will occur and/or include a ranking of the different predictions for a particular agent. The planning system 404 can use the probabilities and/or rankings to determine primary and secondary actions.)
Therefore, it would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in light of Omari such that the scores are ranked before one is selected. It would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in this way because it would allow the system to know the best trajectories before making a selection. In a situation in which the normally highest ranked choice cannot be picked, the second or third would be readily available to be selected without further analysis.
Arora, however, does teach a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding collision zone; and
(Page 12, Column 7, Lines 14-34 (28) In some examples, the vehicle computing system may determine the occlusion cost based on a blocking penalty associated with the vehicle occupying space in front of the occlusion zone for a period of time. In some examples, the vehicle computing system may determine the blocking penalty by multiplying the vehicle speed by the time associated with the vehicle being within a collision zone between the vehicle and the occluded object. In various examples, the occlusion cost may include a sum of the progression penalty and the blocking penalty. In some examples, the occlusion cost may include the sum of the progression penalty and the blocking penalty multiplied by a probability that the action will affect the occluded object's travel. In some examples, the probability may be determined based on a distance between the occluded object (e.g., the occlusion zone) and the collision zone. In some examples, the probability may additionally be determined based on a predicted object trajectory of the occluded object. In various examples, the probability may be based in part on a time associated with the occluded object traveling from the occlusion zone to the collision zone.)
Therefore, it would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in light of Arora such that a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
It would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in this way because if there are areas that are dangerous (such as areas that are close to other objects) then it would be prudent to avoid getting too close, and to avoid spending too much time close to those other object. If every second in such an area is an opportunity for a collision to occur, then reducing the amount of time the vehicle spends in such an area would be likely to prevent collisions.
For Claim 16, Wang teaches The electronic device of claim 15, wherein to generate the first adjustment score, the at least one processor causes the electronic device to use a first prediction model that has been trained to determine a minimum distance between the vehicle and the given surrounding object as the vehicle moves along the given trajectory candidate. (([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0048] The high quality vehicle trajectory 420 may represent a smooth path that does not have abrupt changes that would otherwise provide passenger discomfort. For example, the vehicle trajectory is defined by a path of travel along a given lane of a road in which the object is not predicted travel within a given amount of time. The high quality vehicle trajectory 420 is then provided to block 408.
[0065] The machine-learning algorithm can employ supervised machine learning, semi-supervised machine learning, unsupervised machine learning, and/or reinforcement machine learning. Each of these listed types of machine-learning algorithms is well known in the art. In some scenarios, the machine-learning algorithm includes, but is not limited to, a decision tree learning algorithm, an association rule learning algorithm, an artificial neural network learning algorithm, a deep learning algorithm, an inductive logic programming based algorithm, a support vector machine based algorithm, a Bayesian network based algorithm, a representation learning algorithm, a similarity and metric learning algorithm, a sparse dictionary learning algorithm, a genetic algorithm, a rule-based machine-learning algorithm, and/or a learning classifier system based algorithm. The machine-learning process implemented by the present solution can be built using Commercial-Off-The-Shelf (COTS) tools (e.g., SAS available from SAS Institute Inc. of Cary, N.C.).))
For Claim 17, modified Wang teaches The electronic device of claim 16, wherein the first prediction model has been trained to determine a value of a distance cost function, expressed by a following equation:
Distance Cost = e -k(min(distance))
where min (distance) is the minimum distance between the vehicle and the given surrounding
object as the vehicle moves along the given trajectory candidate; and
k is a coefficient.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 18, modified Wang teaches The electronic device of claim 15, wherein to generate the second adjustment score, the at least one processor causes the electronic device to use a second prediction model that has been trained to determine PETs for those ones of the plurality trajectory candidates of the
vehicle that are intersected by an object trajectory of the given surrounding object.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 19, modified Wang teaches The electronic device of claim 18, wherein the second prediction model has been trained to determine a value of a PET cost function, expressed by a following equation:
PET Cost = (PET - desired PET)².
where PET is a given PET for the given trajectory candidate of the vehicle; and
desired PET is a predetermined PET threshold value.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 20, modified Wang teaches The electronic device of claim 15, wherein to generate the third adjustment score, the at least one processor causes the electronic device to use a third prediction model that has been trained to determine motion parameters of the vehicle causing the change in the
longitudinal acceleration of the vehicle relative to the given surrounding object.
(It should be noted that while Wang does not teach the specific limitation provided in this claim, the independent claim is present in alternative form. According to the language of the independent claim, “at least one of” the adjustment scores are necessary, but not all of them. While this limitation provides additional limitations for one of them, because that adjustment score is optional, so is this limitation. If any two of the adjustment scores are rejectable in the independent form, all of the dependent claims that provide more limitations to any single adjustment score would be rejected by default.)
For Claim 21, Wang teaches A non-transient computer readable medium storing executable instructions for causing at least one computer processor to:
determine a respective score for each one of a plurality of trajectory candidates for the vehicle from a current ego pose to a target ego position; (([0061] As shown in FIG. 6, method 600 begins with 602 and continues with 604 where the computing device obtains candidate vehicle trajectory(ies) and context information from a data store (e.g., memory 312 of FIG. 3). The context information generally defines circumstances and/or conditions of an environment surrounding the autonomous vehicle. The context information can include, but is not limited to, predicted trajectories for detected objects, a map (e.g., 3D road map), traffic information (e.g., traffic flow, traffic jams, slow moving, delays, road closure, roadwork, construction, accident, etc.), environmental information (e.g., rain, snow, fog, etc.), and/or other information (e.g., information received over communication link(s) 150, 152, 154 of FIG. 1). A candidate vehicle trajectory is selected in 606. The selected candidate vehicle trajectory and the context information is used in 608 to generate a feature vector.
[0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).
[0071] Once the final quality score s.sub.final for the given candidate trajectory has been generated, method 600 may return to 606 so that the process is repeated for a next candidate vehicle trajectory as shown by optional 624. In 626, a candidate vehicle trajectory is selected based on the final quality score(s) representing the quality of the candidate vehicle trajectory(ies). For example, the candidate vehicle trajectory with the highest or lowest final quality score is selected in 616. Alternatively or additionally, the candidate vehicle trajectory is selected as the one with the quality score that is greater than or less than a given threshold. If two or more candidate vehicle trajectories have a quality score that is greater than or less than the given threshold, then the candidate vehicle trajectory is selected as the one with the greatest or lowest quality score. A linear/non-linear function could be used to selected the candidate vehicle trajectory based on the final quality scores. Subsequently, 628 is performed where method 600 ends or other operations are performed. For example, the computing device may consider the selected candidate vehicle trajectory as a high quality vehicle trajectory, and therefore perform operations to cause the AV to follow the same (e.g., provided that there is no risk of collision with an object).
Figure 6))
for each trajectory candidate, generate one or more adjustment scores, the one or more adjustment scores including at least one of:
a first adjustment score indicative of a minimum distance between the vehicle and a given surrounding object of the vehicle as the vehicle moves along the given trajectory candidate; (([0062] The feature vector is determined using known or to be known geometric algorithms, deep learning techniques (e.g., variational auto encoder), and/or other feature extraction algorithms. The feature vector can include, but is not limited to, a value specifying the closest detected object (e.g., pedestrian) to the vehicle, the closest distance from detected object (e.g., light, stop sign, etc.) to the vehicle, and/or whether the vehicle is blocking an intersection. The feature vector may also include, but is not limited to, the following information for a detected object: a foreground/background classification, a position, and a delta value (i.e., height above ground).))
determine, based on the respective score and the plurality of adjustment scores, a modified respective score for each trajectory candidate; (([0069] If two or more quality scores were generated for at least one scenario class [616: YES], then method 600 continues with 620 where the quality scores are combined together to produce an aggregate quality score s.sub.aggregate for the given scenario class. For example, if two quality scores s.sub.1-class1 and s.sub.2-class2 where generated for a given class X, then the aggregate quality score for the given class may be defined by the following mathematical equation (5), mathematical equation (6), mathematical equation (7) or mathematical equation (8).))
select, from the ranked trajectory candidates, a top trajectory candidate as being the target trajectory for navigating the vehicle from the current ego pose to the target ego position. (([0071] Once the final quality score s.sub.final for the given candidate trajectory has been generated, method 600 may return to 606 so that the process is repeated for a next candidate vehicle trajectory as shown by optional 624. In 626, a candidate vehicle trajectory is selected based on the final quality score(s) representing the quality of the candidate vehicle trajectory(ies). For example, the candidate vehicle trajectory with the highest or lowest final quality score is selected in 616. Alternatively or additionally, the candidate vehicle trajectory is selected as the one with the quality score that is greater than or less than a given threshold. If two or more candidate vehicle trajectories have a quality score that is greater than or less than the given threshold, then the candidate vehicle trajectory is selected as the one with the greatest or lowest quality score. A linear/non-linear function could be used to selected the candidate vehicle trajectory based on the final quality scores. Subsequently, 628 is performed where method 600 ends or other operations are performed. For example, the computing device may consider the selected candidate vehicle trajectory as a high quality vehicle trajectory, and therefore perform operations to cause the AV to follow the same (e.g., provided that there is no risk of collision with an object).))
Wang does not explicitly teach a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
a third adjustment score indicative of a change in a longitudinal acceleration of the vehicle relative to the given surrounding object;
rank the plurality of trajectory candidates according to the modified respective scores; and
Omari, however, does teach rank the plurality of trajectory candidates according to the modified respective scores; and
([0111] The planning system 404 can identify primary actions and secondary actions in a variety of ways. In some cases, the primary actions can be actions (or predictions) that have a high likelihood of happening and the secondary actions can be actions that have a low likelihood of happening. In some examples, the high likelihood and low likelihood are determined with respect to each other. As such, primary actions can be a particular number of actions that are more likely to happen than a set number of secondary actions. For example, the top two or three ranked predictions for each agent can be identified as primary actions and the remaining actions for the respective agent can be identified as secondary actions. In some cases, the likelihood of an action happening can be based on a probability assigned to the action by the prediction engine or planning system 404 and/or a ranking assigned to the action by the prediction engine and/or planning system 404. For example, when the planning system receives predictions from the prediction engine, the prediction engine can include a probability that a particular prediction (or action) will occur and/or include a ranking of the different predictions for a particular agent. The planning system 404 can use the probabilities and/or rankings to determine primary and secondary actions.)
Therefore, it would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in light of Omari such that the scores are ranked before one is selected. It would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in this way because it would allow the system to know the best trajectories before making a selection. In a situation in which the normally highest ranked choice cannot be picked, the second or third would be readily available to be selected without further analysis.
Arora, however, does teach a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding collision zone; and
(Page 12, Column 7, Lines 14-34 (28) In some examples, the vehicle computing system may determine the occlusion cost based on a blocking penalty associated with the vehicle occupying space in front of the occlusion zone for a period of time. In some examples, the vehicle computing system may determine the blocking penalty by multiplying the vehicle speed by the time associated with the vehicle being within a collision zone between the vehicle and the occluded object. In various examples, the occlusion cost may include a sum of the progression penalty and the blocking penalty. In some examples, the occlusion cost may include the sum of the progression penalty and the blocking penalty multiplied by a probability that the action will affect the occluded object's travel. In some examples, the probability may be determined based on a distance between the occluded object (e.g., the occlusion zone) and the collision zone. In some examples, the probability may additionally be determined based on a predicted object trajectory of the occluded object. In various examples, the probability may be based in part on a time associated with the occluded object traveling from the occlusion zone to the collision zone.)
Therefore, it would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in light of Arora such that a second adjustment score indicative of a Post-Encroachment Time (PET) for the vehicle and the given surrounding object; and
It would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in this way because if there are areas that are dangerous (such as areas that are close to other objects) then it would be prudent to avoid getting too close, and to avoid spending too much time close to those other object. If every second in such an area is an opportunity for a collision to occur, then reducing the amount of time the vehicle spends in such an area would be likely to prevent collisions.
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Wang in light of Omari in light of Arora in light of Mehdipour et al (US Pub 2023/0399014 A1), hereafter known as Mehdipour.
For Claim 13, Wang teaches The method of claim 9,
Wang does not teach wherein each one of the first, second, and third prediction models is a Multilayer Perceptron prediction model.
Mehdipour, however, does teach the use of multilayer perceptron prediction models for perception, planning, localization and control.
Therefore, it would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in light of Mehdipour such that wherein each one of the first, second, and third prediction models is a Multilayer Perceptron prediction model.
It would be obvious to one of ordinary skill in the art prior to the effective filing date to modify Wang in this way because multilayer peceptron models are expected to be useful at performing tasks such as this. Creating and analyzing trajectories is a known task they can perform. Therefore, it would be expected to be successful at the task.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Iglesias et al (US Pub 2023/0047336 A1), hereafter known as Iglesias relates to time within encroachment thresholds.
Narayanan et al (US Pub 2021/0276547 A1) relates to the use of perceptron neural networks.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TRISTAN J GREINER whose telephone number is (571)272-1382. The examiner can normally be reached Mon - Fri 7:30-4:30.
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, Tran Khoi can be reached Monday-Thursday. 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.
/T.J.G./Examiner, Art Unit 3656 /KHOI H TRAN/Supervisory Patent Examiner, Art Unit 3656