DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Regarding Applicant’s comments regarding a requested Examiner Interview, the Examiner sincerely apologizes for any miscommunication which may have occurred. The Examiner received an interview request via voicemail on 05/11/2026 from Applicant’s representative, Xin Xie. The Examiner attempted to return the call twice on 05/12/2026, but was unable to place an outgoing call to the callback number provided by Applicant’s representative. In an effort to respond to Applicant’s request to schedule an interview, the Examiner emailed Xin Xie (xxie@sheppard.com) on 5/12/2026 indicating interview availability but did not receive a response.
Applicant’s arguments, see Pgs. 10-11, filed 05/11/2026, with respect to the 35 USC 112(b) rejection of claims 5, 11-12, 16, and 19 have been fully considered and are persuasive.
The Examiner is in agreement that the amendments to the claims correct the previously-raised indefiniteness concerns. Accordingly, the 35 USC 112(b) rejection of claims 5, 11-12, 16, and 19 has been withdrawn.
Applicant’s arguments, see Pgs. 12-18, filed 05/11/2026, with respect to the 35 USC 101 rejection of claims 1-20 have been fully considered and are persuasive.
The Examiner is in agreement with Applicant’s arguments that the amended independent claims now recite limitations directed towards causing recipient vehicles to perform one or more responsive actions in response to the predictive action. The Examiner is in further agreement that these features amount to significantly more than the abstract idea, and is supported by the written description in at least [000186], which discloses that “A negative effect may include a reaction made by another vehicle or driver of another vehicle from the action performed by the ego vehicle… For example, a reaction may include yelling, hand gestures, and accident preventative driving (i.e., changing lanes, slowing down, and speeding up).” Accordingly, the 35 USC 101 rejection of claims 1-20 has been withdrawn.
Applicant’s arguments, see Pgs. 18-19, filed 05/11/2026, with respect to the 35 USC 103 rejections of claims 1-20 have been fully considered but are not persuasive.
Applicant alleges that independent claims 1, 14, and 20 (and by extension their respective dependent claims) are allowable over the prior art of record, but does not provide any particular supporting argument. Applicant's arguments amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. Therefore, the Examiner is unpersuaded by Applicant’s arguments and maintains that Martinson and Ucar (503) teach the limitations of independent claims 1, 14, and 20.
Accordingly, the 35 USC 103 rejection of claims 1-20 has been maintained to account for the cancellation of claims 8-9 and 15-19 and the modified scope of the amended claims.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 25-27 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding claim 25, the claim recites “the comparison between the predictive action and an observed action is based on a Euclidean distance between an observed action vector corresponding to the observed action and a predictive action vector corresponding to the predictive action.” However, the written description fails to sufficiently describe these features. While paragraph [000138] does disclose that “the computing component 110 may determine the Euclidian distance between the actual next driving action and the predict next driving action. If the determined Euclidian distance is less than a threshold, the actual next driving action may be determined to be the same or similar to the predicted next driving action”, this disclosure fails to describe the claimed observed action vector and predictive action vector. Paragraph [000138] refers to an actual next driving action and a predicted next driving action, but these driving actions are not identified as being vector(s) here or anywhere else in the written description. As such, the above-recited features amount to new matter and the claim fails to comply with the written description requirement.
Claims 26-27 are dependent upon claim 25 and therefore inherit the above-described deficiencies. Accordingly, claims 26-27 are rejected under similar reasoning as claim 25 above.
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 1-7, 10-14, and 20-27 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.
Regarding claim 1, the claim recites “transmitting, via a vehicle-to-everything (V2X) communication interface, one or more V2X messages to one or more recipient vehicles, wherein: the one or more V2X messages identify the predictive action and cause one or more responsive actions to be performed by one or more recipient vehicles in response to the predictive action;” Here, the claim is rendered indefinite because it is unclear whether the second invocation of “one or more recipient vehicles” refers to the same vehicles as the first invocation of “one or more recipient vehicles”. For the purposes of this Examination, the first and second invocation of “one or more recipient vehicles” are being interpreted as being directed towards the same “one or more recipient vehicles”.
Claims 2-7, 10-13, and 21-27 are dependent upon claim 1 and therefore inherit the above-described deficiencies. Accordingly, claims 2-7, 10-13, and 21-27 are rejected under similar reasoning as claim 1 above.
Regarding independent claims 14 and 20, these claims include limitations parallel to those discussed above with respect to claim 1, each reciting two invocations of “one or more recipient vehicles”. Accordingly, claims 14 and 20 are rejected under similar reasoning as claim 1 above.
Regarding claim 25, as discussed in the corresponding 35 USC 112(a) rejection above, the written description fails to sufficiently describe that “the comparison between the predictive action and an observed action is based on a Euclidean distance between an observed action vector corresponding to the observed action and a predictive action vector corresponding to the predictive action.” Claim 25 is rendered indefinite because the observed action vector and the predictive action vector are undefined by the written description and the claim. In particular, it is unclear whether “vector” is being used to specifically refer to a mathematical vector, or if “vector” is being used to more generally describe a vehicle route, path, trajectory, and/or heading. For the purposes of this examination, “vector” is being interpreted under broadest reasonable interpretation as being at least one of a mathematical vector; a vehicle route, path, trajectory, and/or heading; or both.
Claims 26-27 are dependent upon claim 25 and therefore inherit the above-described deficiencies. Accordingly, claims 26-27 are rejected under similar reasoning as claim 25 above.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-7, 13-14, 20-21, and 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martinson et al. (US 2018/0053102 A1), hereinafter Martinson, in view of Ucar et al. (US 2022/0402503 A1), hereinafter Ucar (503).
Regarding claim 1, Martinson teaches a computer-implemented (“computing device 200”, [0070]) method for refining predictive driving actions, the method comprising:
electing a prediction model according to an inferred characteristic of a driving behavior associated with a vehicle;
Martinson teaches ([0013]): "According to one innovative aspect of the subject matter described in this disclosure, a method may include aggregating local sensor data from a plurality of vehicle system sensors during operation of vehicle by a driver; detecting, during the operation of the vehicle, a driver action using the local sensor data; and extracting, during the operation of the vehicle, features related to predicting driver action from the local sensor data. The method may include adapting, during operation of the vehicle, a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. Additionally, in some implementations, the method may include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features."
determining, using the prediction model, a predictive action of the vehicle according to environmental data of the vehicle;
Martinson teaches ([0013]): "The method may include adapting, during operation of the vehicle, a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. Additionally, in some implementations, the method may include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features."
transmitting, via a vehicle-to-everything (V2X) communication interface, one or more V2X messages to one or more recipient vehicles,
Martinson teaches ([0034]): "FIG. 1 is a block diagram of an example system 100. As illustrated, the system 100 may include a modeling server 121, a map server 131, client device(s) 117, and moving platform(s) 101. The entities of the system 100 may be communicatively coupled via a network 111. It should be understood that the system 100 depicted in FIG. 1 is provided by way of example and the system 100 and/or other systems contemplated by this disclosure may include additional and/or fewer components, may combine components, and/or divide one or more of the components into additional components, etc. For example, the system 100 may include any number of moving platforms 101, client devices 117, modeling servers 121, or map servers 131. For instance, additionally... the system 100 may include... vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) technologies, etc." Martinson further teaches ([0036]): "The network 111 may also be coupled to or include portions of a telecommunications network for sending data in a variety of different communication protocols. In some implementations, the network 111 includes Bluetooth® communication networks or a cellular communications network for sending and receiving data including via short messaging service (SMS), multimedia messaging service (MMS), hypertext transfer protocol (HTTP), direct data connection, WAP, email, etc. In some implementations, the network 111 is a wireless network using a connection such as DSRC, WAVE, 802.11p, a 3G, 4G, 5G+ network, WiFi™, or any other wireless networks. In some implementations, the network 111 may include a V2V and/or V2I communication network(s) for communicating data among moving platforms 101 and/or infrastructure external to the moving platforms 101 (e.g., traffic or road systems, etc.)."
wherein: the one or more V2X messages identify the predictive action and cause one or more responsive actions to be performed by one or more recipient vehicles in response to the predictive action;
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)."
However, while Martinson does teach determining a predictive action of the vehicle, Martinson does not outright teach refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle. Ucar (503) teaches a machine-learning model for predicting next driving maneuvers, comprising:
and refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle.
Ucar (503) teaches ([0123]): "The continuity system of the ego vehicle senses that the candidate vehicle left the vehicular micro cloud and modifies parameters of the machine-learning model in response to the sensing. Once the candidate vehicle leaves the vehicular micro cloud, the driving maneuver shape of the candidate vehicle is complete and the driving maneuver shape can be used as a source of data for the stored driving maneuver shapes. In addition, because the machine-learning model made a prediction about the next driving maneuver for the candidate vehicle, having the data about when the candidate vehicle actually left the vehicular micro cloud can be used as feedback for the machine-learning model to determine if the machine-learning model accurately predicted the next driving maneuver. If the machine-learning model did not accurately predict the next driving maneuver, the continuity system may update the parameters for the machine-learning model based on when and how the candidate vehicle left the vehicular micro cloud."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson to incorporate the teachings of Ucar (503) to provide refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle. Martinson and Ucar (503) are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Further, both Martinson and Ucar (503) are concerned with updating and improving their respective prediction models. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]).
Regarding claim 2, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. Martinson further teaches:
the inferred characteristic is based on an identity of a driver of the vehicle.
Martinson teaches ([0082]): "This wealth of sensor data about the driver, moving platform 101, and environment of the driver/moving platform 101 may be used by the advance driver assistance engine 105 to allow driver actions to be recognized in real-time, and/or be synchronized with further sensor data, e.g., from on-vehicle sensors 103 that sense the external environment (e.g. cameras, LIDAR, Radar, etc.), network sensors (via V2V, V2I interfaces sensing communication from other nodes of the network 111), etc. A multiplicity of sensor data may be used by the advance driver assistance engine 106 to perform real-time training data collection for training the driver action prediction model for a specific driver, so that the driver action prediction model can be adapted or customized to predict that specific driver's actions."
Regarding claim 3, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. Martinson further teaches:
the driving behavior associated with the vehicle comprises one or more actions performed by the vehicle while in motion.
Martinson teaches ([0013]): "According to one innovative aspect of the subject matter described in this disclosure, a method may include aggregating local sensor data from a plurality of vehicle system sensors during operation of vehicle by a driver; detecting, during the operation of the vehicle, a driver action using the local sensor data;" Martinson further teaches ([0046]): "For instance, in the context of a moving platform 101, the sensor(s) 103 may capture the user's operation of the moving platform 101 including moving forward, braking, turning left, turning right, changing to a left lane, changing to a right lane, making a U-turn, stopping, making an emergency stop, losing control on a slippery road, etc. "
Regarding claim 4, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. Martinson further teaches:
the inferred characteristic of the driving behavior comprises a type of action performed by the vehicle, a degree of repetition of the type of action, a motion pattern, a period of the motion pattern, or a degree of influence.
Martinson teaches ([0096]): "At 403, the advance driver assistance engine 105 may detect a driver action using the local sensor data during the operation of the vehicle. Detecting a driver action may include recognizing one or more driver actions based on sensor data and, in some instances, using the local sensor data to label the driver action." Martinson further teaches ([0097]): "For instance, some examples implementations for recognizing a driver's action may include recognizing braking actions by filtering and quantizing brake pressure data; recognizing acceleration actions from gas pedal pressure data; and recognizing merge and turn data using logistic regression on a combination of turn signal, steering angle, and road curvature data." Martinson even further teaches ([0099]): "At 405, the advance driver assistance engine 105 may extract features related to predicting driver action from the local sensor data during operation of the vehicle. In some implementations, extracting the features related to predicting driver action from the local sensor data includes generating one or more extracted features vectors including the extracted features. For example, sensor data may be processed to extract features related to predicting actions..." Martinson still further teaches ([0097]): "For instance, some examples implementations for recognizing a driver's action may include recognizing braking actions by filtering and quantizing brake pressure data; recognizing acceleration actions from gas pedal pressure data; and recognizing merge and turn data using logistic regression on a combination of turn signal, steering angle, and road curvature data."
Regarding claim 5, Martinson and Ucar (503) teach the aforementioned limitations of claim 4. Martinson further teaches:
the inferred characteristic of the driving behavior comprises the type of action performed by the vehicle,
Martinson teaches ([0096]): "At 403, the advance driver assistance engine 105 may detect a driver action using the local sensor data during the operation of the vehicle. Detecting a driver action may include recognizing one or more driver actions based on sensor data and, in some instances, using the local sensor data to label the driver action." Martinson further teaches ([0097]): "For instance, some examples implementations for recognizing a driver's action may include recognizing braking actions by filtering and quantizing brake pressure data; recognizing acceleration actions from gas pedal pressure data; and recognizing merge and turn data using logistic regression on a combination of turn signal, steering angle, and road curvature data." Martinson even further teaches ([0099]): "At 405, the advance driver assistance engine 105 may extract features related to predicting driver action from the local sensor data during operation of the vehicle. In some implementations, extracting the features related to predicting driver action from the local sensor data includes generating one or more extracted features vectors including the extracted features. For example, sensor data may be processed to extract features related to predicting actions..."
the type of action comprising a nudging action, an accelerating action, a decelerating action, a braking action, a weaving action, a swerving action, a failure-to-signal action, a tailgating action, a lane drifting action, a failure-to-stop action, a speeding action, a reduced speed action, a delayed stopping action, a delayed accelerating action, a honking action, a headlight flashing action, or a headlight non-activation action.
Martinson teaches ([0046]): "For instance, in the context of a moving platform 101, the sensor(s) 103 may capture the user's operation of the moving platform 101 including moving forward, braking, turning left, turning right, changing to a left lane, changing to a right lane, making a U-turn, stopping, making an emergency stop, losing control on a slippery road, etc." One of ordinary skill in the art would recognize braking as deceleration. Martinson further teaches ([0096]): "At 403, the advance driver assistance engine 105 may detect a driver action using the local sensor data during the operation of the vehicle. Detecting a driver action may include recognizing one or more driver actions based on sensor data and, in some instances, using the local sensor data to label the driver action." ([0097]): "For instance, some examples implementations for recognizing a driver's action may include recognizing braking actions by filtering and quantizing brake pressure data; recognizing acceleration actions from gas pedal pressure data; and recognizing merge and turn data using logistic regression on a combination of turn signal, steering angle, and road curvature data."
Regarding claim 6, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. However, Martinson does not outright teach that the prediction model comprises a reckless behavior prediction model, an aggressive behavior prediction model, or a distracted behavior prediction model. Ucar (503) further teaches:
the prediction model comprises a reckless behavior prediction model, an aggressive behavior prediction model, or a distracted behavior prediction model.
Ucar (503) ([0083]): "In some embodiments, the shapes data 133 is also associated with a class for each type of stored driving maneuver shape. For example, a stored driving maneuver shape may belong to a class of an aggressive driver that is likely to leave the vehicular micro cloud quickly, a driver that is changing between lanes but is likely to stay joined to the vehicular micro cloud, a driver that is changing lanes rapidly enough to indicate that the driver is likely to get off on an exit, the driver has a tendency to tailgate, the driver is distracted, etc." Ucar (503) further teaches ([0229]): "The machine-learning model may modify its parameters based on the training data. In some embodiments, the training data is supervised. For example, a user may label the different stored driving maneuver shapes with a class based on the movements, such as aggressive, calm, a tailgater, etc. In some embodiments, the training data is unsupervised and the machine-learning model performs clustering of the training data to identify characteristics between the different stored driving maneuver shapes."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson and Ucar (503) to further incorporate the teachings of Ucar (503) to provide that the prediction model comprises a reckless behavior prediction model, an aggressive behavior prediction model, or a distracted behavior prediction model. Martinson and Ucar (503) are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Further, both Martinson and Ucar (503) are concerned with updating and improving their respective prediction models. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]). With respect to the driving maneuver shapes of Ucar (503), incorporating such features advantageously allows for determination of whether a stored driving maneuver shape belongs to a class of aggressive driving, as recognized by Ucar (503) (see at least [0083]).
Regarding claim 7, Martinson and Ucar (503) teach the aforementioned limitations of claim 6. Martinson further teaches:
the prediction model is generated according to driving data of a plurality of vehicles.
Martinson teaches ([0013]): "The method may include adapting, during operation of the vehicle, a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. Additionally, in some implementations, the method may include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features." Martinson further teaches ([0087]): "Stock means the model was pre-trained using a collective of sensor data aggregated from a multiplicity of moving platforms 101 to identify general driver behavior."
Regarding claim 13, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. However, Martinson does not outright teach that the refining the prediction model comprises: generating a new rule on driving behavior characteristic inference that regulates an inference of the inferred characteristic of the driving behavior; and updating the prediction model to include the new rule for subsequent inference. Ucar (503) further teaches:
the refining the prediction model comprises: generating a new rule on driving behavior characteristic inference that regulates an inference of the inferred characteristic of the driving behavior; and updating the prediction model to include the new rule for subsequent inference.
Ucar (503) teaches ([0123]): "The continuity system of the ego vehicle senses that the candidate vehicle left the vehicular micro cloud and modifies parameters of the machine-learning model in response to the sensing. Once the candidate vehicle leaves the vehicular micro cloud, the driving maneuver shape of the candidate vehicle is complete and the driving maneuver shape can be used as a source of data for the stored driving maneuver shapes. In addition, because the machine-learning model made a prediction about the next driving maneuver for the candidate vehicle, having the data about when the candidate vehicle actually left the vehicular micro cloud can be used as feedback for the machine-learning model to determine if the machine-learning model accurately predicted the next driving maneuver. If the machine-learning model did not accurately predict the next driving maneuver, the continuity system may update the parameters for the machine-learning model based on when and how the candidate vehicle left the vehicular micro cloud." The Examiner has interpreted the updating of the parameters for the machine-learning model based on when and how the candidate vehicle left the vehicular micro cloud as generating a new rule on driving behavior characteristic inference and updating the prediction model to include the new rule for subsequent inference.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson and Ucar (503) to further incorporate the teachings of Ucar (503) to provide that the refining the prediction model comprises: generating a new rule on driving behavior characteristic inference that regulates an inference of the inferred characteristic of the driving behavior; and updating the prediction model to include the new rule for subsequent inference. Martinson and Ucar (503) are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Further, both Martinson and Ucar (503) are concerned with updating and improving their respective prediction models. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]).
Regarding claim 14, Martinson teaches a computing system, comprising:
one or more processors;
Martinson teaches ([0070]): "In some implementations, the computing device 200 may include an advance driver assistance engine 105. The advance driver assistance engine 105 may include a prediction engine 231 and a model adaptation engine 233, for example. The advance driver assistance engine 105 and/or its components may be implemented as software, hardware, or a combination of the foregoing... In some implementations, one or more of the components 231 and 233 are sets of instructions executable by the processor(s) 213. In further implementations, one or more of the components 231 and 233 are storable in the memory(ies) 215 and are accessible and executable by the processor(s) 213."
and memory coupled to the one or more processors to store instructions, which when executed by the one or more processors, cause at least one of the one or more processors to perform operations, the operations comprising:
Martinson teaches ([0070]): "In some implementations, the computing device 200 may include an advance driver assistance engine 105. The advance driver assistance engine 105 may include a prediction engine 231 and a model adaptation engine 233, for example. The advance driver assistance engine 105 and/or its components may be implemented as software, hardware, or a combination of the foregoing... In some implementations, one or more of the components 231 and 233 are sets of instructions executable by the processor(s) 213. In further implementations, one or more of the components 231 and 233 are storable in the memory(ies) 215 and are accessible and executable by the processor(s) 213."
electing a prediction model according to an inferred characteristic of a driving behavior associated with a vehicle;
Martinson teaches ([0013]): "According to one innovative aspect of the subject matter described in this disclosure, a method may include aggregating local sensor data from a plurality of vehicle system sensors during operation of vehicle by a driver; detecting, during the operation of the vehicle, a driver action using the local sensor data; and extracting, during the operation of the vehicle, features related to predicting driver action from the local sensor data. The method may include adapting, during operation of the vehicle, a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. Additionally, in some implementations, the method may include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features."
determining, using the prediction model, a predictive action of the vehicle according to environmental data of the vehicle;
Martinson teaches ([0013]): "The method may include adapting, during operation of the vehicle, a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. Additionally, in some implementations, the method may include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features."
transmitting, via a vehicle-to-everything (V2X) communication interface, one or more V2X messages to one or more recipient vehicles,
Martinson teaches ([0034]): "FIG. 1 is a block diagram of an example system 100. As illustrated, the system 100 may include a modeling server 121, a map server 131, client device(s) 117, and moving platform(s) 101. The entities of the system 100 may be communicatively coupled via a network 111. It should be understood that the system 100 depicted in FIG. 1 is provided by way of example and the system 100 and/or other systems contemplated by this disclosure may include additional and/or fewer components, may combine components, and/or divide one or more of the components into additional components, etc. For example, the system 100 may include any number of moving platforms 101, client devices 117, modeling servers 121, or map servers 131. For instance, additionally... the system 100 may include... vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) technologies, etc." Martinson further teaches ([0036]): "The network 111 may also be coupled to or include portions of a telecommunications network for sending data in a variety of different communication protocols. In some implementations, the network 111 includes Bluetooth® communication networks or a cellular communications network for sending and receiving data including via short messaging service (SMS), multimedia messaging service (MMS), hypertext transfer protocol (HTTP), direct data connection, WAP, email, etc. In some implementations, the network 111 is a wireless network using a connection such as DSRC, WAVE, 802.11p, a 3G, 4G, 5G+ network, WiFi™, or any other wireless networks. In some implementations, the network 111 may include a V2V and/or V2I communication network(s) for communicating data among moving platforms 101 and/or infrastructure external to the moving platforms 101 (e.g., traffic or road systems, etc.)."
wherein: the one or more V2X messages identify the predictive action and cause one or more responsive actions to be performed by one or more recipient vehicles in response to the predictive action;
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)."
However, while Martinson does teach determining a predictive action of the vehicle, Martinson does not outright teach refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle. Ucar (503) teaches a machine-learning model for predicting next driving maneuvers, comprising:
and refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle.
Ucar (503) teaches ([0123]): "The continuity system of the ego vehicle senses that the candidate vehicle left the vehicular micro cloud and modifies parameters of the machine-learning model in response to the sensing. Once the candidate vehicle leaves the vehicular micro cloud, the driving maneuver shape of the candidate vehicle is complete and the driving maneuver shape can be used as a source of data for the stored driving maneuver shapes. In addition, because the machine-learning model made a prediction about the next driving maneuver for the candidate vehicle, having the data about when the candidate vehicle actually left the vehicular micro cloud can be used as feedback for the machine-learning model to determine if the machine-learning model accurately predicted the next driving maneuver. If the machine-learning model did not accurately predict the next driving maneuver, the continuity system may update the parameters for the machine-learning model based on when and how the candidate vehicle left the vehicular micro cloud."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson to incorporate the teachings of Ucar (503) to provide refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle. Martinson and Ucar (503) are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Further, both Martinson and Ucar (503) are concerned with updating and improving their respective prediction models. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]).
Regarding claim 20, Martinson teaches a non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations (“one or more non-transitory memories storing instructions…”, see at least [0014]), the operations comprising:
electing a prediction model according to an inferred characteristic of a driving behavior associated with a vehicle;
Martinson teaches ([0013]): "According to one innovative aspect of the subject matter described in this disclosure, a method may include aggregating local sensor data from a plurality of vehicle system sensors during operation of vehicle by a driver; detecting, during the operation of the vehicle, a driver action using the local sensor data; and extracting, during the operation of the vehicle, features related to predicting driver action from the local sensor data. The method may include adapting, during operation of the vehicle, a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. Additionally, in some implementations, the method may include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features."
determining, using the prediction model, a predictive action of the vehicle according to environmental data of the vehicle;
Martinson teaches ([0013]): "The method may include adapting, during operation of the vehicle, a stock machine learning-based driver action prediction model to a customized machine learning-based driver action prediction model using one or more of the extracted features and the detected driver action, the stock machine learning-based driver action prediction model initially generated using a generic model configured to be applicable to a generalized driving populace. Additionally, in some implementations, the method may include predicting a driver action using the customized machine learning-based driver action prediction model and the extracted features."
transmitting, via a vehicle-to-everything (V2X) communication interface, one or more V2X messages to one or more recipient vehicles,
Martinson teaches ([0034]): "FIG. 1 is a block diagram of an example system 100. As illustrated, the system 100 may include a modeling server 121, a map server 131, client device(s) 117, and moving platform(s) 101. The entities of the system 100 may be communicatively coupled via a network 111. It should be understood that the system 100 depicted in FIG. 1 is provided by way of example and the system 100 and/or other systems contemplated by this disclosure may include additional and/or fewer components, may combine components, and/or divide one or more of the components into additional components, etc. For example, the system 100 may include any number of moving platforms 101, client devices 117, modeling servers 121, or map servers 131. For instance, additionally... the system 100 may include... vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) technologies, etc." Martinson further teaches ([0036]): "The network 111 may also be coupled to or include portions of a telecommunications network for sending data in a variety of different communication protocols. In some implementations, the network 111 includes Bluetooth® communication networks or a cellular communications network for sending and receiving data including via short messaging service (SMS), multimedia messaging service (MMS), hypertext transfer protocol (HTTP), direct data connection, WAP, email, etc. In some implementations, the network 111 is a wireless network using a connection such as DSRC, WAVE, 802.11p, a 3G, 4G, 5G+ network, WiFi™, or any other wireless networks. In some implementations, the network 111 may include a V2V and/or V2I communication network(s) for communicating data among moving platforms 101 and/or infrastructure external to the moving platforms 101 (e.g., traffic or road systems, etc.)."
wherein: the one or more V2X messages identify the predictive action and cause one or more responsive actions to be performed by one or more recipient vehicles in response to the predictive action;
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)."
However, while Martinson does teach determining a predictive action of the vehicle, Martinson does not outright refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle. Ucar (503) teaches a machine-learning model for predicting next driving maneuvers, comprising:
and refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle.
Ucar (503) teaches ([0123]): "The continuity system of the ego vehicle senses that the candidate vehicle left the vehicular micro cloud and modifies parameters of the machine-learning model in response to the sensing. Once the candidate vehicle leaves the vehicular micro cloud, the driving maneuver shape of the candidate vehicle is complete and the driving maneuver shape can be used as a source of data for the stored driving maneuver shapes. In addition, because the machine-learning model made a prediction about the next driving maneuver for the candidate vehicle, having the data about when the candidate vehicle actually left the vehicular micro cloud can be used as feedback for the machine-learning model to determine if the machine-learning model accurately predicted the next driving maneuver. If the machine-learning model did not accurately predict the next driving maneuver, the continuity system may update the parameters for the machine-learning model based on when and how the candidate vehicle left the vehicular micro cloud."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson to incorporate the teachings of Ucar (503) to provide refining the prediction model according to a comparison between the predictive action and an observed action of the vehicle. Martinson and Ucar (503) are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Further, both Martinson and Ucar (503) are concerned with updating and improving their respective prediction models. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]).
Regarding claim 21, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. Martinson further teaches:
the vehicle corresponds to a target vehicle, and at least a portion of the computer-implemented method is performed by a host vehicle system of a host vehicle,
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)." Here, the target vehicle corresponds to the vehicle 303, while the host vehicle corresponds to an adjacent vehicle having a predictive system.
the computer-implemented method further comprising: generating, based on the predictive action, a host control signal to a host ADAS of the host vehicle to cause the host ADAS to execute an evasive maneuver concurrent with transmitting the one or more V2X messages to the one or more recipient vehicles,
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)."
wherein the host vehicle is different from the target vehicle and different from the one or more recipient vehicles.
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)." Here, the target vehicle corresponds to the vehicle 303, while the host vehicle corresponds to an adjacent vehicle having a predictive system. The host vehicle is described as being one of "adjacent vehicles" (i.e., the host vehicle is a distinct and different vehicle among the adjacent vehicles).
Regarding claim 24, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. Martinson further teaches:
the one or more V2X messages are configured to cause one or more advanced driver assistance systems (ADAS) corresponding to the one or more recipient vehicles to generate one or more recipient-vehicle control signals to cause the one or more responsive actions to be performed.
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)."
Claim(s) 10-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martinson and Ucar (503) in view of Emanuel et al. (US 8,346,468 B2), hereinafter Emanuel.
Regarding claim 10, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. However, Martinson does not outright teach determining the predictive action of the vehicle is unsafe. Ucar (503) further teaches:
determining the predictive action of the vehicle is unsafe;
Ucar (503) teaches ([0112]): "In some embodiments, the continuity system determines that the next driving maneuver indicates that the candidate vehicle is predicted to leave the vehicular micro cloud within a predetermined time period." Ucar (503) further teaches ([0113]): "In some embodiments, the continuity system determines a reason with the prediction of the next driving maneuver. For example, the continuity system may associate the driving maneuver shape of the candidate vehicle with an aggressive driving technique (e.g., overtaking, lane cutting, etc.), a steady driving technique, a tailgating driving technique, etc." Ucar (503) even further teaches ([0299]): "Conversely, the driving maneuver shape for candidate vehicle 470 indicates that the driver is driving aggressively because the driving maneuver shape illustrates that that the candidate vehicle 470 changed lanes far too close to candidate vehicle 455 and candidate vehicle 460."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson and Ucar (503) to further incorporate the teachings of Ucar (503) to provide determining the predictive action of the vehicle is unsafe. Martinson and Ucar (503) are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Further, both Martinson and Ucar (503) are concerned with updating and improving their respective prediction models. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]). Identifying driver actions as unsafe actions provides the further benefit of excluding such aggressive vehicles from leadership vehicle status in vehicle platooning scenarios, as recognized by Ucar (503) (see at least [0299]).
However, neither Martinson nor Ucar (503) outright teach that transmitting the one or more V2X messages is in response to determining the predictive action is unsafe. Emanuel teaches a method and apparatus for collision avoidance, comprising:
and wherein transmitting the one or more V2X messages is in response to determining the predictive action is unsafe.
Emanuel teaches (Claim 5): "A collision avoidance apparatus for avoiding collisions between vehicles… the apparatus calculating the current predicted trajectory and safety zone of each manned vehicle and each automatically guided vehicle at each predetermined time interval to determine any areas of intersection of safety zones of other manned or automatically guided vehicles; the apparatus calculating a probability of collision of each manned vehicle and each automatically guided vehicle with other manned or automatically guided vehicles; the apparatus comparing each probability of collision with a predetermined threshold; the apparatus communicating each predicted collision with a probability above the threshold to the at least one server, the server issuing a command or a warning to the vehicles predicted to collide, the warned vehicles able to take appropriate action to avoid collision." Emanuel is modified such that the command/warning issued by the server is communicated via the V2X network of Martinson.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson and Ucar (503) to incorporate the teachings of Emanuel to provide that transmitting the one or more V2X messages is in response to determining the predictive action is unsafe. Martinson, Ucar (503), and Emanuel are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Emanuel, as doing so beneficially allows for warning other vehicles to dangerous predictive actions, thereby allowing the warned vehicles to take appropriate action to avoid a collision, as recognized by Emanuel (see at least Claim 5).
Regarding claim 11, Martinson, Ucar (503), and Emanuel teach the aforementioned limitations of claim 10. However, Martinson does not outright teach that the determining the predictive action of the vehicle is unsafe is based on a driving detection algorithm associated with the prediction model. Ucar (503) further teaches:
the determining the predictive action of the vehicle is unsafe is based on a driving detection algorithm associated with the prediction model.
Ucar (503) teaches ([0112]): "In some embodiments, the continuity system determines that the next driving maneuver indicates that the candidate vehicle is predicted to leave the vehicular micro cloud within a predetermined time period." Ucar (503) further teaches ([0113]): "In some embodiments, the continuity system determines a reason with the prediction of the next driving maneuver. For example, the continuity system may associate the driving maneuver shape of the candidate vehicle with an aggressive driving technique (e.g., overtaking, lane cutting, etc.), a steady driving technique, a tailgating driving technique, etc." Ucar (503) even further teaches ([0144]): "In some embodiments, a machine-learning model outputs an estimate of the next driving maneuver of the candidate vehicle." Ucar (503) still further teaches ([0299]): "Conversely, the driving maneuver shape for candidate vehicle 470 indicates that the driver is driving aggressively because the driving maneuver shape illustrates that that the candidate vehicle 470 changed lanes far too close to candidate vehicle 455 and candidate vehicle 460."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson, Ucar (503), and Emanuel to further incorporate the teachings of Ucar (503) to provide that the determining the predictive action of the vehicle is unsafe is based on a driving detection algorithm associated with the prediction model. Martinson, Ucar (503), and Emanuel are each directed towards similar pursuits in the field of vehicle behavior monitoring and driver action prediction. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]). Identifying driver actions as unsafe actions provides the further benefit of excluding such aggressive vehicles from leadership vehicle status in vehicle platooning scenarios, as recognized by Ucar (503) (see at least [0299]).
Regarding claim 12, Martinson, Ucar (503), and Emanuel teach the aforementioned limitations of claim 10. Martinson further teaches:
wherein the predictive action comprises a repetitive nudging action, a repetitive acceleration action, a repetitive deceleration action, a repetitive braking action, a repetitive weaving action, a repetitive weaving action, a repetitive swerving action, a repetitive headlight flashing action, a prolonged tailgating action, or an aggressive speeding action through an intersection.
Martinson teaches ([0097]): "For instance, some examples implementations for recognizing a driver's action may include recognizing braking actions by filtering and quantizing brake pressure data; recognizing acceleration actions from gas pedal pressure data; and recognizing merge and turn data using logistic regression on a combination of turn signal, steering angle, and road curvature data." The Examiner has interpreted "braking actions" as indicating either of a repetitive deceleration action or a repetitive braking action, as "actions" indicates that the act of braking has occurred more than once (i.e., the action has repeated). Under similar reasoning, "acceleration actions" has been interpreted as indicating a repetitive acceleration action.
Claim(s) 22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martinson and Ucar (503) in view of Durling et al. (US 2012/0158219 A1), hereinafter Durling.
Regarding claim 22, Martinson and Ucar (503) teach the aforementioned limitations of claim 21. Martinson further teaches:
transmitting the one or more V2X messages comprises transmitting a first V2X message prior to executing the evasive maneuver
Martinson teaches ([0084]): "Using the sensor data 301, the advance driver assistance engine 105 then predict driver actions and/or adapt a driver action prediction model, as described in further detail elsewhere herein, for example, in reference to FIGS. 3B and 4. In some implementations, the predicted future driver action may be returned to other systems of the vehicle 303 to provide actions (e.g., automatic steering, braking, signaling, etc.) or warnings (e.g., alarms for the driver), may be transmitted to adjacent vehicles and/or infrastructure to notify these nodes of impending predicted driver actions, and which may be processed by the predictive systems of those vehicles (e.g. instances of the advance driver assistance engine 105) and/or infrastructure to take counter actions (e.g., control the steering of those systems to swerve or make a turn, change a street light, route vehicles along other paths, provide visual, tactile, and/or audio notifications, etc.)." Here, the transmission of the predicted future driver action to the adjacent vehicles occurs prior to the execution of counter actions of the adjacent vehicles.
However, Martinson does not outright teach transmitting a second V2X message after executing the evasive maneuver, the second V2X message identifying updated host trajectory data of the host vehicle. Durling teaches trajectory based sensing and avoiding, comprising:
and transmitting a second V2X message after executing the evasive maneuver, the second V2X message identifying updated host trajectory data of the host vehicle.
Durling teaches ([0050]): "Returning to the UAS surveillance scenario, the UAS may initially negotiate with air traffic control 108 regarding a proposed loitering pattern. In this example, traffic in the airspace is low and UAS loitering pattern is approved. While en route, on-board sensors 162 detect an approaching object with a collision estimate of less than two minutes. The on-board tactical separation algorithm is activated and the on-board flight management system 180 generates a trajectory to avoid collision. Based on the new trajectory, the UAS changes trajectory to avoid collision. After collision avoidance is achieved, the UAS communicates its new trajectory to air traffic control 108 and the on-board flight management system 180 generates a trajectory to get back into original planned trajectory with minimum deviation."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson and Ucar (503) to incorporate the teachings of Durling to provide transmitting a second V2X message after executing the evasive maneuver, the second V2X message identifying updated host trajectory data of the host vehicle. Martinson, Ucar (503), and Durling are each directed towards similar pursuits in the field of vehicle control and maneuver analysis. Martinson and Ucar (503) are each directed towards ground vehicles; while Durling is directed towards UAS applications, one of ordinary skill in the art would nonetheless recognize that incorporating the communication logic of Durling would be advantageous, as doing so beneficially communicates a new trajectory of a vehicle to a central server and enables the generation of a trajectory for the vehicle to return to its original planned trajectory with minimum deviation subsequent to the collision avoidance maneuver, as recognized by Durling (see at least [0050]).
Claim(s) 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martinson and Ucar (503) in view of Park et al. (US 2018/0151071 A1), hereinafter Park.
Regarding claim 23, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. However, Martinson does not outright teach that the one or more V2X messages further identify: a time horizon associated with the predictive action; relative vehicle state data of the vehicle with respect to at least one of the one or more recipient vehicles, or a collision probability metric corresponding to a computed probability that, within the time horizon, the vehicle and at least one of the one or more recipient vehicles will satisfy a collision criteria if the vehicle performs the predictive action, wherein the collision criteria is based on a predicted separation between the vehicle and the at least one of the one or more recipient vehicles being less than a threshold separation. Park teaches an apparatus and method for recognizing position of a vehicle, comprising:
the one or more V2X messages further identify: a time horizon associated with the predictive action; relative vehicle state data of the vehicle with respect to at least one of the one or more recipient vehicles, or a collision probability metric corresponding to a computed probability that, within the time horizon, the vehicle and at least one of the one or more recipient vehicles will satisfy a collision criteria if the vehicle performs the predictive action, wherein the collision criteria is based on a predicted separation between the vehicle and the at least one of the one or more recipient vehicles being less than a threshold separation.
Park teaches ([0021]): "The transmitting of the relative position of the first neighboring vehicle and the absolute position of the own vehicle and receiving the absolute position of the another vehicle and the relative position of the second neighboring vehicle includes: generating a vehicle-to-everything (V2X) message including the relative position of the at least one first neighboring vehicle and the absolute position of the own vehicle, transmitting the V2X message to the another vehicle, and receiving the V2X message including the absolute position of the another vehicle and the relative position of the at least one second neighboring vehicle transmitted from the another vehicle."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson and Ucar (503) to incorporate the teachings of Park to provide that the one or more V2X messages further identify relative vehicle state data of the vehicle with respect to at least one of the one or more recipient vehicles. Martinson, Ucar (503), and Park are each directed towards similar pursuits in the field of vehicle control and maneuver analysis. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Park, as doing so beneficially improves positioning of the vehicle(s) by allowing for accurate recognizing of positions of the vehicle and neighboring vehicles by exchanging sensor information with the neighboring vehicles through V2X communication, as recognized by Park (see at least [0008] and [0021]).
Claim(s) 25-27 is/are rejected under 35 U.S.C. 103 as being unpatentable over Martinson and Ucar (503) in view of Omari et al. (US 2021/0200221 A1), hereinafter Omari.
Regarding claim 25, Martinson and Ucar (503) teach the aforementioned limitations of claim 1. However, Martinson does not outright teach that the comparison between the predictive action and an observed action is based on a Euclidean distance between an observed action vector corresponding to the observed action and a predictive action vector corresponding to the predictive action. Omari teaches resource prioritization based on travel path relevance, comprising:
the comparison between the predictive action and an observed action is based on a Euclidean distance between an observed action vector corresponding to the observed action and a predictive action vector corresponding to the predictive action.
Omari teaches ([0026]): "FIG. 4 illustrates an example trajectory comparison of agents. As described in more detail below, given the contextual environment at time t, the prioritization model may output a predicted position of each agent 104A-104D at future times t1, t2, etc. based on a predicted trajectory of agents 104A-104D. As described in more detail below, during the training of the prioritization model, a trajectory comparison module may compare the prediction of the position of agents 104A-104D at future times t.sub.1 and t.sub.2 to the ground truth (recorded position) at these times. The prioritization model may be updated based on the accuracy of the predicted position of agents 104A-104D relative to the recorded position of agents 104A-104D." Omari further teaches ([0034]): "The comparison may be quantified by a loss value or computed using a loss function. As an example and not by way of limitation, the loss value may correspond to the distance between the predicted position of the agents and actual recorded position of the agents. The loss value may be used (e.g., via back-propagation techniques) to update the configuration parameters of prioritization model 505 so that the loss value would be less if the prediction were to be made again." The Examiner has interpreted the determination of the distance between the predicted position of the agents and actual recorded position of the agents as the determination of Euclidean distance(s).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson and Ucar (503) to incorporate the teachings of Omari to provide that the comparison between the predictive action and an observed action is based on a Euclidean distance between an observed action vector corresponding to the observed action and a predictive action vector corresponding to the predictive action. Martinson, Ucar (503), and Omari are each directed towards similar pursuits in the field of vehicle behavior monitoring and prediction. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Omari, as incorporating the distance comparison of Omari beneficially allows for the determination of a loss value corresponding to the distance between the predicted position of the agents and the actual recorded position of the agents which may be used to update the prediction model to reduce the loss value in future predictions, as recognized by Omari (see at least [0026] and [0034]).
Regarding claim 26, Martinson, Ucar (503), and Omari teach the aforementioned limitations of claim 25. However, Martinson does not outright teach that refining the prediction model comprises updating the prediction model based on a magnitude of the Euclidean distance. Omari further teaches:
refining the prediction model comprises updating the prediction model based on a magnitude of the Euclidean distance.
Omari teaches ([0026]): "FIG. 4 illustrates an example trajectory comparison of agents. As described in more detail below, given the contextual environment at time t, the prioritization model may output a predicted position of each agent 104A-104D at future times t1, t2, etc. based on a predicted trajectory of agents 104A-104D. As described in more detail below, during the training of the prioritization model, a trajectory comparison module may compare the prediction of the position of agents 104A-104D at future times t.sub.1 and t.sub.2 to the ground truth (recorded position) at these times. The prioritization model may be updated based on the accuracy of the predicted position of agents 104A-104D relative to the recorded position of agents 104A-104D." Omari further teaches ([0034]): "The comparison may be quantified by a loss value or computed using a loss function. As an example and not by way of limitation, the loss value may correspond to the distance between the predicted position of the agents and actual recorded position of the agents. The loss value may be used (e.g., via back-propagation techniques) to update the configuration parameters of prioritization model 505 so that the loss value would be less if the prediction were to be made again."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson, Ucar (503), and Omari to further incorporate the teachings of Omari to provide that refining the prediction model comprises updating the prediction model based on a magnitude of the Euclidean distance. Martinson, Ucar (503), and Omari are each directed towards similar pursuits in the field of vehicle behavior monitoring and prediction. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Omari, as incorporating the distance comparison of Omari beneficially allows for the determination of a loss value corresponding to the distance between the predicted position of the agents and the actual recorded position of the agents which may be used to update the prediction model to reduce the loss value in future predictions, as recognized by Omari (see at least [0026] and [0034]).
Regarding claim 27, Martinson, Ucar (503), and Omari teach the aforementioned limitations of claim 25. However, Martinson does not outright teach that refining the prediction model comprises updating, within the prediction model: a potential-indicator characteristic of unsafe driving; an election criteria of electing the prediction model; one or more algorithms of the prediction model used to predict the predictive action; or unsafe driving detection logic. Ucar (503) further teaches:
refining the prediction model comprises updating, within the prediction model: a potential-indicator characteristic of unsafe driving; an election criteria of electing the prediction model; one or more algorithms of the prediction model used to predict the predictive action; or unsafe driving detection logic.
Ucar (503) teaches ([0123]): "The continuity system of the ego vehicle senses that the candidate vehicle left the vehicular micro cloud and modifies parameters of the machine-learning model in response to the sensing. Once the candidate vehicle leaves the vehicular micro cloud, the driving maneuver shape of the candidate vehicle is complete and the driving maneuver shape can be used as a source of data for the stored driving maneuver shapes. In addition, because the machine-learning model made a prediction about the next driving maneuver for the candidate vehicle, having the data about when the candidate vehicle actually left the vehicular micro cloud can be used as feedback for the machine-learning model to determine if the machine-learning model accurately predicted the next driving maneuver. If the machine-learning model did not accurately predict the next driving maneuver, the continuity system may update the parameters for the machine-learning model based on when and how the candidate vehicle left the vehicular micro cloud." The Examiner has interpreted the above updating of the parameters for the machine-learning model as updating one or more algorithms of the prediction model used to predict the predictive action.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Martinson, Ucar (503), and Omari to further incorporate the teachings of Ucar (503) to provide that refining the prediction model comprises updating, within the prediction model: one or more algorithms of the prediction model used to predict the predictive action. Martinson, Ucar (503), and Omari are each directed towards similar pursuits in the field of vehicle behavior monitoring and prediction. Further, both Martinson and Ucar (503) are concerned with updating and improving their respective prediction models. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Ucar (503), as incorporating the next action monitoring and analysis of Ucar (503) advantageously allows for updating the parameters of the prediction model if the prediction model did not accurately predict the next driving behavior, as recognized by Ucar (503) (see at least [0123]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Joshua et al. (US 2014/0279707 A1) teaches a system and method for vehicle data analysis, including determining whether a recommended action is followed by the vehicle, wherein the compliance information indicates that the driver is careful or careless (see at least [0163]). Olabiyi et al. (US 2018/0053108 A1) teaches an efficient driver action prediction system based on temporal fusion of sensor data, including labeling features for prediction, and determining error between a recognized label and a predicted label (see at least [0016]).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to FRANK T GLENN III whose telephone number is (571)272-5078. The examiner can normally be reached M-F 7:30AM - 4:30PM 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, Jelani Smith can be reached at 571-270-3969. 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.
/F.T.G./Examiner, Art Unit 3662
/DALE W HILGENDORF/Primary Examiner, Art Unit 3662
Prosecution Insights