DETAILED ACTION
This nonfinal office action is responsive to claims filed on March 18, 2024. Claims 1-11 are pending, claims 1 and 11 are independent.
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 .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on March 18, 2024 and April 23, 2024 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
"a computer-implemented system configured to predict a behavior..." in claim 11.
“the system being configured to predict, using at least one AI-based prediction component…” in claim 11.
“the system being configured to… determine, in parallel to the prediction of the individual behavior options…” in claim 11.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 6 and 11 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 6 states “the predicted individual behavior options are generated based on the currently aggregated scene-specific information by modifying weights of the prediction component for the different predictions with a predetermined probability and, by setting them to zero.” It’s unclear how the weights are being modified and also being set to zero. If the weights are all set to zero then the method would not provide any meaningful results. The specification states on page 5, lines 23-27 “According to a further possibility, any or specific weights of the AI-based prediction component could be modified, and in particular deactivated, for the different predictions by modifying them with a predetermined probability p or by setting them to 0.” Therefore, examiner is interpreting “the predicted individual behavior options are generated based on the currently aggregated scene-specific information by modifying weights of the prediction component for the different predictions with a predetermined probability and, by setting them to zero” to be “the predicted individual behavior options are generated based on the currently aggregated scene-specific information by modifying weights of the prediction component for the different predictions with a predetermined probability or, by setting them to zero.”
Regarding claim 11,
Claim limitation "a computer-implemented system configured to predict a behavior...", “the system being configured to predict, using at least one AI-based prediction component…”, and “the system being configured to… determine, in parallel to the prediction of the individual behavior options…” invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function.
The only mention of “a computer-implemented system” within the specification is on page 8, lines 7-11: “Fig. 1 illustrates the functionality of a computer-implemented system according to an example embodiment of the present invention for carrying out a prediction method in connection with a perception component and a planning component of an automated vehicle using a block diagram.” It is unclear what each of the components are or the structure of the computer-implemented system. Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-4, and 7-11 is/are rejected under 35 U.S.C. 102(a)(1) and (a)(2) as being anticipated by Probst et al. (US20220315047), hereinafter Probst.
Regarding claim 1, Probst teaches the computer-implemented method:
predicting, using at least one AI-based prediction component, a specified number of individual behavior options of the at least one participant for at least one future time segment based on scene-specific information which are aggregated at a current time point, wherein each of the at least one future time segment includes a specified number of consecutive time points; and (Probst, paragraph 0052: “The ego-trajectory 4 consists of lateral and longitudinal positions over time or similar spatio-temporal parameters such as velocity-/acceleration profile over time and steering-/curvature-/lane offset over time. The prediction can cover a fixed constant future time, or, alternatively, the duration can be adjusted based on driving conditions like weather, ego velocity, current maneuver (e.g. lane change, vehicle following), autonomy state of vehicle (e.g. full driver controlled, lateral control—LKAS/longitudinal control—ACC only, fully automated, etc.), traffic amount or uncertainty of its prediction.“ And paragraph 0053: “In step S4, at least one ego-trajectory alternative is generated by applying a lateral shift to the ego-trajectory 4 predicted in step S4. One possibility for the system to generate alternative lateral shifts for the ego-trajectory 4 is to move the original predicted ego-trajectory 4 laterally (i.e. in orthogonal direction to the lane center) by a number of fixed values or values that are fractions of the overall lane width. Alternatively the shifts can be generated by moving the shape of the lane center line laterally (i.e. in orthogonal direction to the lane center) by a number of predefined values or values that are fractions of the overall lane width.“ – The ego-trajectory and ego-trajectory alternative are analogous to the individual behavior options of the at least one participant for at least one future time segment. The trajectories being based off the velocity, steering, lane-offset, as well as a lateral shift is analogous to the scene-specific information.)
determining, in parallel to the prediction of the individual behavior options, at least one current overall uncertainty value that quantifies an epistemic uncertainty of all of the predicted individual behavior options for the at least one future time segment. (Probst, paragraph 0056: “The spatio-temporal uncertainty of the ego-trajectory alternative is estimated by, for example, copying the uncertainties of the predicted ego-trajectory, computing uncertainties using similar parameters as described for ego-trajectory prediction, adapting the ego-trajectory prediction uncertainties to include additional factors scaling with e.g. curvature or distance to lane center/current position of the shifted trajectory.“ – The spatio-temporal uncertainty is analogous to the overall uncertainty value.)
Regarding claim 2, Probst teaches the method of claim 1, as cited above.
Probst further teaches:
for each of the predicted individual behavior options, at least one respective current uncertainty value that quantifies an epistemic uncertainty of the predicted individual behavior option is determined, and that the current overall uncertainty value is determined based on all of the current uncertainty values. (Probst, paragraph 0061: “The modeled positional uncertainties for the combination of the original predicted ego-trajectory 4 and the ego-trajectory alternative(s) can be used as an input for each cost part.“ – The modeled positional uncertainties being a combination of the original predicted ego-trajectory and the ego-trajectory alternative(s) is analogous to the uncertainty value being an overall uncertainty value based on all of the current uncertainty values since, as noted above in claim 1, the original predicted ego-trajectory and the ego-trajectory alternative(s) each have their own uncertainty value.)
Regarding claim 3, Probst teaches the method of claim 2, as cited above.
Probst further teaches:
for each of the predicted individual behavior options, several different predictions are generated based on currently aggregated scene-specific information, and, for each of the predicted behavior options, the respective current uncertainty value is determined based on the different predictions. (Probst, paragraph 0045: “When predicting future positions of scene elements, the uncertainty of the position of an element at the current time can additionally be modified by the accuracy of the prediction method (which could also be a static function as in directly using the closest map path; and which in itself could depend on factors from the previous point, such as weather, element type, . . . ), and/or the estimated probability of a specific future trajectory leading to the future positions, and/or a factor that increases with temporal distance to the current time, and/or a factor that is based on the type of object, and/or based on the variance of the history of estimated positions of a specific element, and/or a factor that depends on current state of the element (velocity, yaw rate, acceleration, etc.).“ and paragraph 0052: “In step S3, the future ego-trajectory 4 is determined based on predefined map positions, a current or previous trajectory planning step of an automated system, an extrapolation of the past vehicle trajectory and/or based on a module that estimates such trajectory from current and previous actions of a human driver (including steering maneuvers, gas/brake pedal usage, gaze patterns, etc.).” – The predicted future positions of scene elements is analogous to the different predictions, where the trajectory being determined based on predefined map positions, current or previous trajectories, etc. is analogous to the predictions being generated based on currently aggregated scene-specific information as all of those elements are current scene specific information that is being used for the predicted trajectories.)
Regarding claim 4, Probst teaches the method of claim 3, as cited above.
Probst further teaches:
for each of the predicted individual behavior options, the respective current uncertainty value is determined as a mean value of variances between the different predictions over all time points of the at least one future time segment. (Probst, paragraph 0045: “When predicting future positions of scene elements, the uncertainty of the position of an element at the current time can additionally be modified by the accuracy of the prediction method (which could also be a static function as in directly using the closest map path; and which in itself could depend on factors from the previous point, such as weather, element type, . . . ), and/or the estimated probability of a specific future trajectory leading to the future positions, and/or a factor that increases with temporal distance to the current time, and/or a factor that is based on the type of object, and/or based on the variance of the history of estimated positions of a specific element, and/or a factor that depends on current state of the element (velocity, yaw rate, acceleration, etc.).“ – the uncertainty being modified based on the variance of the history of estimated positions of a specific element is analogous to the uncertainty value determined as a mean value of variances between the different predicitons over all time points.)
Regarding claim 7, Probst teaches the method of claim 3, as cited above.
Probst further teaches:
the several different predictions for each of the predicted individual behavior options are generated based on the currently aggregated scene-specific information by using several different prediction components including several architecturally equivalent prediction components, which differ in parameters learned. (Probst, paragraph 0052: “The ego-trajectory 4 consists of lateral and longitudinal positions over time or similar spatio-temporal parameters such as velocity-/acceleration profile over time and steering-/curvature-/lane offset over time. The prediction can cover a fixed constant future time, or, alternatively, the duration can be adjusted based on driving conditions like weather, ego velocity, current maneuver (e.g. lane change, vehicle following), autonomy state of vehicle (e.g. full driver controlled, lateral control—LKAS/longitudinal control—ACC only, fully automated, etc.), traffic amount or uncertainty of its prediction. Further, spatio-temporal uncertainty of the ego-trajectory is estimated based on, for example, ego position sensor or lane detection uncertainty, ego-trajectory prediction method, history of human driving inputs or ego-vehicle positions, prediction distance from current time, accuracy of vehicle control in following a target trajectory, etc.“ And paragraph 0053: "In step S4, at least one ego-trajectory alternative is generated by applying a lateral shift to the ego-trajectory 4 predicted in step S4. One possibility for the system to generate alternative lateral shifts for the ego-trajectory 4 is to move the original predicted ego-trajectory 4 laterally (i.e. in orthogonal direction to the lane center) by a number of fixed values or values that are fractions of the overall lane width.“ – The predicitons being based on driving conditions like weather, velocity, maneuver, autonomy, or traffic is analogous to the aggregated scene-specific information. The lateral and longitudinal positions over time and the spatio-temporal parameters are analoogus to the prediciton components. Thus, the ego-trajectory alternatives being generated by a lateral shift would indicate that the parameters are shifted and thus different parameters are used to generate the predictions while the architecture of the components of the prediction module remain the equivalent.)
Regarding claim 8, Probst teaches the method of claim 2, as cited above.
Probst further teaches:
for each of the predicted individual behavior options, a behavior of the at least one participant in a future time segment i+1 is predicted starting from an actual or predicted behavior of the participant in a previous time segment i, wherein: the behavior of the participant in the previous time segment i is reconstructed based on a behavior predicted for the future time segment i+1, (Probst, paragraph 0045: “When predicting future positions of scene elements, the uncertainty of the position of an element at the current time can additionally be modified by the accuracy of the prediction method (which could also be a static function as in directly using the closest map path; and which in itself could depend on factors from the previous point, such as weather, element type, . . . ), and/or the estimated probability of a specific future trajectory leading to the future positions,...“ – the current, previous, and future time points is analogous to the time segments. The uncertainty of the element in the current time point being modified by the estimated probability of a specific future trajectory is analogous to the behavior of the previous time segment i being reconstructed based on a behavior of the time segment i+1.)
the behavior reconstructed for the time segment i is compared either to the actual behavior of the participant in the time segment i if the time segment i is in the past, or to the predicted behavior of the participant for the time segment i if the time segment i is in the future, and a current uncertainty value for the time segment i+1 is determined based on the comparison. (Probst, paragraph 0010: “…calculating an ego-trajectory of the ego-vehicle, generating at least one ego-trajectory alternative by applying a lateral shift to the calculated ego-trajectory to generate a plurality of ego-trajectories including the calculated ego-trajectory and the at least one ego-trajectory alternative, selecting, for each trajectory of the plurality of ego-trajectories and the trajectory of the at least one traffic participant, a position on the trajectory that corresponds to a common point in time, determining, for each selected position, an uncertainty area at least with respect to a lateral direction, evaluating, for each of the plurality of ego-trajectories, at least a spatio-temporal closeness of the uncertainty area of the respective ego-trajectory and the uncertainty area of the trajectory of the at least one traffic participant...“ – The ego-trajectory and ego-trajectory alternatives is analogous to the behavior of time segment i being compared to the predicted behavior of time segment i since they are both in the future, the uncertainty area of the trajectory being determined based off the trajectories is analogous to the current uncertainty value for time segment i+1 being determined based off the comparison.)
Regarding claim 9, Probst teaches the method of claim 8, as cited above.
Probst further teaches:
further data aggregated and/or predicted in the past are taken into account in the reconstruction of the behavior of the participant in the previous time segment i. (Probst, paragraph 0052: “In step S3, the future ego-trajectory 4 is determined based on predefined map positions, a current or previous trajectory planning step of an automated system, an extrapolation of the past vehicle trajectory and/or based on a module that estimates such trajectory from current and previous actions of a human driver (including steering maneuvers, gas/brake pedal usage, gaze patterns, etc.).“ – The ego-trajectory being based on an extrapolation of the past vehicle trajectory and/or based on a moduel that estimates such trajectory from current and previous actions is analogous to the data aggregated and/or predicted in the past being taken into account in the reconstruction of the behavior.)
Regarding claim 10, Probst teaches the method of claim 1, as cited above.
Probst further teaches:
the predicted behavior options are predicted in the form of trajectory data including position data and/or movement data and/or orientation data, for each time point of the at least one future time segment. (Probst, paragraph 0052: “The ego-trajectory 4 consists of lateral and longitudinal positions over time or similar spatio-temporal parameters such as velocity-/acceleration profile over time and steering-/curvature-/lane offset over time. The prediction can cover a fixed constant future time, or, alternatively, the duration can be adjusted based on driving conditions like weather, ego velocity, current maneuver (e.g. lane change, vehicle following), autonomy state of vehicle (e.g. full driver controlled, lateral control—LKAS/longitudinal control—ACC only, fully automated, etc.), traffic amount or uncertainty of its prediction.“)
Regarding claim 11, Claim 11 has the same limitations of claim 1 which are taught by Probst – see claim 1 above.
Probst further teaches:
the system being configured to: (Probst, paragraph 0034: “The driver assistance system according to the disclosure comprises a processing unit configured to carry out the steps described above.“)
Claim Rejections - 35 USC § 103
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.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Probst in view of Schulz et al. (EP3552904), hereinafter Schulz.
Regarding claim 5, Probst teaches the method of claim 3, as cited above.
Probst does not explicitly teach:
the several different predictions for each of the predicted individual behavior options are generated based on the currently aggregated scene-specific information by applying different types of noise to the currently aggregated scene-specific information for the different predictions.
However, Schulz teaches:
the several different predictions for each of the predicted individual behavior options are generated based on the currently aggregated scene-specific information by applying different types of noise to the currently aggregated scene-specific information for the different predictions. (Schulz, paragraph 0007: “According to an embodiment of the present invention, for predicting the development of a traffic scene involving several participants a map with corresponding map related information is provided. Each participant is characterized by a participant tuple and the participant tuple comprises a state tuple of several state properties, a route intention characterization, a maneuver intention characterization and an action intention characterization. The state tuple of several state properties for each participant represents a global position and a heading and an absolute velocity of the participant. The traffic scene is characterized by a scene tuple comprising one participant tuple for each participant. A noisy measurement is obtained, wherein the noisy measurement comprises for each participant a position measurement and a heading measurement and an absolute velocity measurement of the participant.“ – Predicting the development of the traffic scene involving serveral participants is analogous to the trajectories taught by Probst. The traffic scene characterized by a scene tuple comprising a participant tuple for each participant is analogous to the aggregated scene-specific information, the noisy measurement for each participant that is obtained using the participant tuples is analogous to the different types of noise.)
Schulz is considered analogous to the claimed invention as it is in the same field of endeavor, artificial intelligence and autonomous driving. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to have modified Probst, which already teaches several different predictions for each predicted individual behavior option generated based on the current aggregated scene-specific information but does not explicitly teach applying noise to the scene-specific information for the different predictions, to include the teachings of Schulz which does teach applying noise to the scene-specific information for the different predictions as “the interaction-aware model outperforms both CTRV and map-based models.” (Schulz, paragraph 0082)
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Probst in view of Milanés-Hermosilla (Monte Carlo Dropout for Uncertainty Estimation and Motor Imagery Classification), hereinafter Milanés-Hermosilla.
Regarding claim 6, Probst teaches the method of claim 3, as cited above.
Probst does not explicitly teach:
the several different predictions for each of the predicted individual behavior options are generated based on the currently aggregated scene-specific information by modifying weights of the prediction component for the different predictions with a predetermined probability and, by setting them to zero.
However, Milanés-Hermosilla teaches:
the several different predictions for each of the predicted individual behavior options are generated based on the currently aggregated scene-specific information by modifying weights of the prediction component for the different predictions with a predetermined probability and, by setting them to zero. (Milanés-Hermosilla, section 2.4, paragraph 1: “A dropout layer multiplies the output of each neuron by a binary mask that is drawn following a Bernoulli distribution, randomly setting some neurons to zero in the neural network, during the training time. Then, the non-dropped trained neural network is used at test time. Gal and Ghahramani [23] demonstrated that dropout used at test time is an approximation of probabilistic Bayesian models in deep Gaussian processes. Monte Carlo dropout (MCD) quantifies the uncertainty of network outputs from its predictive distribution by sampling 𝑇 new dropout masks for each forward pass. As a result, instead of one output model, 𝑇 model outputs {Pt; 1 ≤ t ≤ T} for each input sample x are obtained.“ – Randomly setting some neurons to zero and performing Monte Carlo dropout to obtain a probability for the predictive distribution is analogous to the different predictions based on the currently aggregated scene-specific information, which is taught by Probst in claim 3. The specification states on page 5, lines 23-27: “According to a further possibility, any or specific weights of the AI-based prediciton component could be modified, and in particular deactivated, for the different predicitons by modifyin gthem with a predetermined probability p or by setting them to 0. This process is referred to as Monte-Carlo dropout.“)
Milanés-Hermosilla is considered analogous to the claimed invention as it is in the same field of endeavor, artificial intelligence. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to have modified Probst, which already teaches the several different predictions for each of the predicted individual behavior options based on the currently aggregated scene-specific information but does not explicitly teach that the predictions are obtained by modifying weights of the prediction component or by setting them to zero, to include the teachings of Milanés-Hermosilla which does teach that the predictions are obtained by modifying weights of the prediction component or by setting them to zero in order to “reduce the model complexity and also avoid overfitting [24].” (Milanés-Hermosilla, section 2.4, paragraph 1)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Zhang et al. (US 20200175691)
Oh et al. (US 20210276594)
Golgiri et al. (US 11530933)
Schulz et al. (Interaction-Aware Probabilistic Behavior Prediction in Urban Environments)
Damerow et al. (US 20150344030)
Hu et al. (Probabilistic Future Prediction for Video Scene Understanding)
Lee et al. (US 20210380099)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JACQUELINE MEYER whose telephone number is (703)756-5676. The examiner can normally be reached M-F 8:00 am - 4:30 pm EST.
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, Tamara Kyle can be reached at 571-272-4241. 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.
/J.C.M./Examiner, Art Unit 2144
/TAMARA T KYLE/Supervisory Patent Examiner, Art Unit 2144
Prosecution Insights