DETAILED ACTION
The amendments filed 1/20/2026 have been entered. Claims 1-6, 8-14, and 17-19 have been amended. Claims 1-20 remain pending in the application and are discussed on the merits below.
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
Applicant's arguments filed 1/20/2026 have been fully considered but they are considered moot because the amendments have necessitated a new grounds of rejection as outlined below.
Response to Amendment
Regarding the objections to the claims, amendments made to the claims have overcome the previously set forth objections. The previously set forth objections have been withdrawn. However, the amendments have necessitated new objections as outlined below.
Regarding the rejections under 35 USC §112, Applicant has amended the claims to overcome the rejections. The rejections under 35 USC §112 have been withdrawn.
Regarding the rejections under 35 USC §102 and 103, amendments made to the claims have necessitated a new grounds of rejection as outlined below.
Claim Objections
Claims 2, 4, 9, and 18 are objected to because of the following informalities:
Claim 2, line 2, “hardware processor is configured to” should read “hardware processor is further configured to”
Claim 4, lines 5-6, “hardware processor is configured to” should read “hardware processor is further configured to”
Claim 9, lines 11-12, “determined reference yaw angle the object” should read “determined reference yaw angle for the object”
Claim 18, lines 2-3, “hardware processor is configured to” should read “hardware processor is further configured to”
Appropriate correction is required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 7, 9-10, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Vijayan et al. (U.S. Patent Application Publication No. 2016/0347309 A1; hereinafter Vijayan) in view of Minh et al. (“Feasible and Optimal Trajectories Generation for Autonomous Driving Vehicles”; see reference U on PTO-892; hereinafter Minh).
Regarding claim 1, Vijayan discloses:
A system comprising: one or more sensors of an autonomous vehicle (autonomous vehicle system, automated operation of host vehicle 12, see at least [0010]-[0011]), the one or more sensors configured to collect sensing data for an environment of the autonomous vehicle (sensor 18 configured to detect other vehicle, see at least [0012]); and
a hardware processor of the autonomous vehicle, the hardware processor configured to: identify a heading direction of an object in the environment, based at least on the sensing data (detect other vehicle is off-center indicated by signals from sensor 18, see at least [0016]; determine orientation of other vehicle is not aligned with lane, see at least [0022]);
determine a yaw angle that the heading direction makes with a direction of travel of the object (orientation angle indicated by vehicle vector is substantially different from the direction of the lane vector, see at least [0023]);
determine, based at least on a speed of the object, a reference yaw angle for the object (difference threshold may be expressed in terms of instantaneous angle difference, yaw rate, lateral acceleration, or others and arising from a combination thereof, see at least [0024]; difference threshold is vector based including a combination of angle difference and linear speed, see at least [0024])
determine that the object is at risk of loss of control of a driving trajectory, based at least on the yaw angle and the determined reference yaw angle for the object (detect other vehicle has lost control when orientation of other vehicle 14 is not aligned with lane vector of roadway which indicates a direction of travel, see at least [0022]; when vector difference value violates the difference threshold such as other vehicle is classified as out-of-control, see at least [0025]); and
cause a control system of the autonomous vehicle to perform an avoidance action (when vector difference value violates the difference threshold such as other vehicle is classified as out-of-control, travel path may include changing lanes to avoid other vehicle, see at least [0025] and [0027]).
Furthermore, Minh teaches:
determine, based at least on a speed of the object, a reference yaw angle for the object (vehicle steering angles have upper limit angles based on vehicle speed, see Fig. 4 on page 5) *Examiner sets forth that steering angle and yaw angle are directly proportional and the same relational property of higher speeds requiring lower angles applies
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the out of control vehicle identification disclosed by Vijayan by adding the angle to speed relation taught by Minh with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to determine safe angles for vehicles (see page 5, col. 1, paragraph 3).
Regarding claim 2, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
wherein to determine that the object is at risk of loss of control, the hardware processor is to determine that the yaw angle exceeds the determined reference yaw angle (when vector difference value violates the difference threshold such as other vehicle is classified as out-of-control, see at least [0025] and [0027])
Vijayan does not disclose:
access a mapping of a plurality of speed values to a plurality of reference yaw angles, wherein higher speed values are mapped to smaller reference yaw angles
However, Minh teaches:
access a mapping of a plurality of speed values to a plurality of reference yaw angles, wherein higher speed values are mapped to smaller reference yaw angles (vehicle steering angles have upper limit angles based on vehicle speed, see Fig. 4 graph on page 5) *Examiner sets forth that steering angle and yaw angle are directly proportional and the same relational property of higher speeds requiring lower angles applies
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the out of control vehicle identification disclosed by Vijayan by adding the angle to speed relation taught by Minh with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to determine safe angles for vehicles (see page 5, col. 1, paragraph 3).
Regarding claim 7, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
the direction of travel of the object is obtained using at least one of: a roadgraph data for a portion of a roadway associated with a current location of the object, or a direction of a traffic lane occupied by the object determined by a computer vision model (lane vector 38 indicates direction of travel for a particular lane, see at least [0022]; sensor detects lane position of other vehicles relative to lane markings of roadway , see at least [0012])
Regarding claim 9, Vijayan discloses:
A method comprising: collecting, using a sensing system of an autonomous vehicle (autonomous vehicle system, automated operation of host vehicle 12, see at least [0010]-[0011]), sensing data for an environment of the autonomous vehicle (sensor 18 configured to detect other vehicle, see at least [0012]);
identifying a heading direction of an object in the environment, based at least on the sensing data (detect other vehicle is off-center indicated by signals from sensor 18, see at least [0016]; determine orientation of other vehicle is not aligned with lane, see at least [0022]);
determining a yaw angle that the heading direction makes with a direction of travel of the object (orientation angle indicated by vehicle vector is substantially different from the direction of the lane vector, see at least [0023]);
determining, based at least on a speed of the object, a reference yaw angle for the object (difference threshold may be expressed in terms of instantaneous angle difference, yaw rate, lateral acceleration, or others and arising from a combination thereof, see at least [0024]; difference threshold is vector based including a combination of angle difference and linear speed, see at least [0024]);
determining that the object is at risk of loss of control of a driving trajectory, based at least on the yaw angle and the determined reference yaw angle the object (detect other vehicle has lost control when orientation of other vehicle 14 is not aligned with lane vector of roadway which indicates a direction of travel, see at least [0022]; when vector difference value violates the difference threshold such as other vehicle is classified as out-of-control, see at least [0025]); and
causing a control system of the autonomous vehicle to perform an avoidance action (when vector difference value violates the difference threshold such as other vehicle is classified as out-of-control, travel path may include changing lanes to avoid other vehicle, see at least [0025] and [0027]).
Furthermore, Minh teaches:
determining, based at least on a speed of the object, a reference yaw angle for the object (vehicle steering angles have upper limit angles based on vehicle speed, see Fig. 4 on page 5) *Examiner sets forth that steering angle and yaw angle are directly proportional and the same relational property of higher speeds requiring lower angles applies
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the out of control vehicle identification disclosed by Vijayan by adding the angle to speed relation taught by Minh with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to determine safe angles for vehicles (see page 5, col. 1, paragraph 3).
Regarding claim 10, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
wherein to determining that the object is at risk of loss of control comprises determining that the yaw angle exceeds the determined reference yaw angle (when vector difference value violates the difference threshold such as other vehicle is classified as out-of-control, see at least [0025] and [0027])
Vijayan does not disclose:
accessing a mapping of a plurality of speed values to a plurality of reference yaw angles, wherein higher speed values are mapped to smaller reference yaw angles
However, Minh teaches:
accessing a mapping of a plurality of speed values to a plurality of reference yaw angles, wherein higher speed values are mapped to smaller reference yaw angles (vehicle steering angles have upper limit angles based on vehicle speed, see Fig. 4 graph on page 5) *Examiner sets forth that steering angle and yaw angle are directly proportional and the same relational property of higher speeds requiring lower angles applies
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the out of control vehicle identification disclosed by Vijayan by adding the angle to speed relation taught by Minh with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to determine safe angles for vehicles (see page 5, col. 1, paragraph 3).
Regarding claim 15, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
determining the direction of travel of the object using at least one of: a roadgraph data for a portion of a roadway associated with a current location of the object, or a direction of a traffic lane occupied by the object determined by a computer vision model (lane vector 38 indicates direction of travel for a particular lane, see at least [0022]; sensor detects lane position of other vehicles relative to lane markings of roadway , see at least [0012])
Claims 3 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Vijayan in view of Minh as applied to claims 1 and 9 above and further in view of Mande et al. (U.S. Patent Application Publication No. 2017/0344855 A1; hereinafter Mande).
Regarding claim 3, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
determine, based on the sensing data, a type of the object (sensor configured to detect other vehicle, see at least [0012]), and wherein the reference yaw angle is further determined based on the type of the object (determine a behavior classification of the other vehicle based on a lane keeping behavior, see at least [0014]; other vehicle may be classified as out of control when vector difference value is greater than difference threshold, see at least [0023])
Vijayan does not explicitly disclose:
a machine learning model
However, Mande teaches:
determine, based on the sensing data and using an object detection machine learning model, a type of the object (processing unit processes the image data to detect and classify a vehicle such as car, truck, bus, motorcycle, see at least [0059]; collision prediction system (CPS) learns motion patterns associated with vehicle of different classes and uses the learned motion patterns to generate an intersection model, see at least [0057])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the behavior classification disclosed by Vijayan and the angle to speed relation taught by Minh by adding the classification taught by Mande with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order to determine paths available for the given class (see [0016]).
Regarding claim 11, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
determining, based on the sensing data, a type of the object (sensor configured to detect other vehicle, see at least [0012]), and wherein the reference yaw angle is further determined based on the type of the object (determine a behavior classification of the other vehicle based on a lane keeping behavior, see at least [0014]; other vehicle may be classified as out of control when vector difference value is greater than difference threshold, see at least [0023])
Vijayan does not explicitly disclose:
a machine learning model
However, Mande teaches:
determine, based on the sensing data and using an object detection machine learning model, a type of the object (processing unit processes the image data to detect and classify a vehicle such as car, truck, bus, motorcycle, see at least [0059]; collision prediction system (CPS) learns motion patterns associated with vehicle of different classes and uses the learned motion patterns to generate an intersection model, see at least [0057])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the behavior classification disclosed by Vijayan and the angle to speed relation taught by Minh by adding the classification taught by Mande with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order to determine paths available for the given class (see [0016]).
Claims 4, 6, 12, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Vijayan in view of Minh as applied to claims 1 and 9 above and further in view of Harrison (U.S. Patent Application Publication No. 2021/0103027 A1) and further in view of Chemali et al. (U.S. Patent Application Publication No. 2024/0395049 A1; hereinafter Chemali) and Li (U.S. Patent No. 10,366,502 B1).
Regarding claim 4, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
the sensing data comprises: one or more camera images of the object (sensor may include camera 18A, see at least [0012]),
one or more lidar images of the object (sensor may include lidar unit 18C, see at least [0012]), and
one or more radar images of the object (sensor may include radar unit 18B, see at least [0012]); and
output the heading direction of the object, based on the camera, the lidar, and the radar (vehicle vector of other vehicle is used to indicate the speed, direction of travel, and orientation of other vehicle, see at least [0022]).
Vijayan does not disclose:
machine learning model
However, Harrison teaches:
wherein to identify the heading direction, the hardware processor is configured to process the sensing data using a heading detection machine learning model (MLM) comprising: a camera neural network configured to process the one or more camera images of the object (camera neural network to detect and identify objects in camera data, see at least abstract);
a lidar neural network configured to process the one or more lidar images of the object (lidar neural network to detect and identify objects in lidar data, see at least abstract);
a radar neural network configured to process the one or more radar images of the object (radar neural network to detect and identify objects in radar data, see at least abstract); and
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan and the angle to speed relation taught by Minh by adding the neural networks to identify objects taught by Harrison with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order “to detect and classify objects in the surrounding environment at the same or possibly at an even better level than humans” (see [0003]).
Furthermore, Chemali teaches:
wherein to identify the heading direction, the perception system is to process the sensing data using a heading detection machine learning model (MLM) comprising: a camera neural network configured to process the one or more camera images of the object and generate a camera feature vector (generate feature vectors of 2D bounding boxes in images, see at least [0044]);
a lidar neural network configured to process the one or more lidar images of the object and generate a lidar feature vector (generate feature vector of 3D bounding box, 3D data obtained from lidar point cloud data, see at least [0045]);
a radar neural network configured to process the one or more radar images of the object and generate a radar feature vector (generate feature vector of 3D bounding box, see at least [0045]); and
a classification neural network configured to output the heading direction of the object, based on the camera feature vector, the lidar feature vector, and the radar feature vector (neural network performs association of 2D bounding box and 3D bounding box, use first feature vector based on camera images and second feature vector that is representation of 3D data, see at least [0005]
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan, the angle to speed relation taught by Minh, and the neural networks to identify objects taught by Harrison by adding the feature vectors taught by Chemali with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order “to analyze images from a vehicle camera and detect objects in them” and train neural networks to do so (see [0019]).
Additionally, Li teaches:
a classification neural network configured to output the heading direction of the object, based on the camera feature vector, the lidar feature vector, and the radar feature vector (sensor subsystem includes combination of lidar, radar, and camera systems, see at least col. 4 lines 23-25; neural network trained to generated vehicle heading, see at least col. 3 lines 19-20; plurality of point cloud data as input to a neural network, see at least col. 2, lines 47-50; camera subnetwork that operates on camera image, output of point cloud and camera subnetwork, see at least col. 3 lines 7-13)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan, the angle to speed relation taught by Minh, the neural networks to identify objects taught by Harrison, and the feature vectors taught by Chemali by adding the combination of sensor systems taught by Li with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “for speed and real-time processing to quickly make vehicle heading predictions in a production system” (see col. 3 lines 27-39).
Regarding claim 6, the combination of Vijayan, Minh, Harrison, Chemali, and Li teaches the elements above but Vijayan does not disclose:
to identify the heading direction, the hardware processor is to process the sensing data using the heading detection MLM trained using: one or more first training inputs associated with a plurality of sensing modalities that comprises two or more of: a camera modality, a lidar modality, or a radar modality; and one or more second training inputs associated with one or more sensing modalities that lack at least one sensing modality of the plurality of sensing modalities
However, Harrison teaches:
to identify the heading direction, the hardware processor is to process the sensing data using the heading detection MLM trained using: one or more first training inputs associated with a plurality of sensing modalities that comprises two or more of: a camera modality, a lidar modality, or a radar modality (generate object detection labels with data acquired from camera and lidar sensors, see at least 704 of Fig. 7 and [0058]); and one or more second training inputs associated with one or more sensing modalities that lack at least one sensing modality of the plurality of sensing modalities (use labels to bootstrap training of radar network, see at least 706 of fig. 7 and [0058])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan and the angle to speed relation taught by Minh by adding the neural networks to identify objects taught by Harrison with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order “to detect and classify objects in the surrounding environment at the same or possibly at an even better level than humans” (see [0003]).
Regarding claim 12, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
the sensing data comprises: one or more camera images of the object (sensor may include camera 18A, see at least [0012]),
one or more lidar images of the object (sensor may include lidar unit 18C, see at least [0012]), and
one or more radar images of the object (sensor may include radar unit 18B, see at least [0012]); and
output the heading direction of the object, based on the camera, the lidar, and the radar (vehicle vector of other vehicle is used to indicate the speed, direction of travel, and orientation of other vehicle, see at least [0022]).
Vijayan does not disclose:
machine learning model
However, Harrison teaches:
wherein identifying the heading direction comprises processing the sensing data using a heading detection machine learning model (MLM) that comprises: a camera neural network configured to process the one or more camera images of the object (camera neural network to detect and identify objects in camera data, see at least abstract)
a lidar neural network configured to process the one or more lidar images of the object (lidar neural network to detect and identify objects in lidar data, see at least abstract);
a lidar neural network configured to process the one or more radar images of the object (radar neural network to detect and identify objects in radar data, see at least abstract); and
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan and the angle to speed relation taught by Minh by adding the neural networks to identify objects taught by Harrison with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order “to detect and classify objects in the surrounding environment at the same or possibly at an even better level than humans” (see [0003]).
Furthermore, Chemali teaches:
wherein identifying the heading direction comprises processing the sensing data using a heading detection machine learning model (MLM) that comprises: a camera neural network configured to process the one or more camera images of the object and generate a camera feature vector (generate feature vectors of 2D bounding boxes in images, see at least [0044]);
a lidar neural network configured to process the one or more lidar images of the object and generate a lidar feature vector (generate feature vector of 3D bounding box, see at least [0045]);
a lidar neural network configured to process the one or more radar images of the object and generate a radar feature vector (generate feature vector of 3D bounding box, see at least [0045]); and
a classification neural network configured to output the heading direction of the object, based on the camera feature vector, the lidar feature vector, and the radar feature vector (neural network performs association of 2D bounding box and 3D bounding box, use first feature vector based on camera images and second feature vector that is representation of 3D data, see at least [0005]
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan, the angle to speed relation taught by Minh, and the neural networks to identify objects taught by Harrison by adding the feature vectors taught by Chemali with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order “to analyze images from a vehicle camera and detect objects in them” and train neural networks to do so (see [0019]).
Additionally, Li teaches:
a classification neural network configured to process the camera feature vector, the lidar feature vector, and the radar feature vector and output the heading direction of the object (sensor subsystem includes combination of lidar, radar, and camera systems, see at least col. 4 lines 23-25; neural network trained to generated vehicle heading, see at least col. 3 lines 19-20; plurality of point cloud data as input to a neural network, see at least col. 2, lines 47-50; camera subnetwork that operates on camera image, output of point cloud and camera subnetwork, see at least col. 3 lines 7-13)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan, the angle to speed relation taught by Minh, the neural networks to identify objects taught by Harrison, and the feature vectors taught by Chemali by adding the combination of sensor systems taught by Li with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “for speed and real-time processing to quickly make vehicle heading predictions in a production system” (see col. 3 lines 27-39).
Regarding claim 14, the combination of Vijayan, Minh, Harrison, Chemali, and Li teaches the elements above but Vijayan does not disclose:
processing the sensing data using the heading detection machine learning model MLM trained using: one or more first training inputs associated with a plurality of sensing modalities that comprises two or more of: a camera modality, a lidar modality, or a radar modality, one or more second training inputs associated with one or more sensing modalities that lack at least one sensing modality of the plurality of sensing modalities
However, Harrison teaches:
processing the sensing data using the heading detection machine learning model MLM trained using: one or more first training inputs associated with a plurality of sensing modalities that comprises two or more of: a camera modality, a lidar modality, or a radar modality (generate object detection labels with data acquired from camera and lidar sensors, see at least 704 of Fig. 7 and [0058]), one or more second training inputs associated with one or more sensing modalities that lack at least one sensing modality of the plurality of sensing modalities (use labels to bootstrap training of radar network, see at least 706 of fig. 7 and [0058])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan and the angle to speed relation taught by Minh by adding the neural networks to identify objects taught by Harrison with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order “to detect and classify objects in the surrounding environment at the same or possibly at an even better level than humans” (see [0003]).
Claims 5 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Vijayan in view of Minh, Harrison, Chemali, and Li as applied to claim 4 above and further in view of Pertsel et al. (U.S. Patent No. 11,427,195 B1; hereinafter Pertsel).
Regarding claim 5, the combination of Vijayan, Minh, Harrison, Chemali, and Li teaches the elements above but does not teach:
Confidence
However, Pertsel teaches:
the heading detection machine learning model MLM is further to determine a confidence in the identified heading direction (confidence level of the predicted path 402 of moving object, see at least col. 40 lines 20-24), and wherein the hardware processor is to cause the control system of the autonomous vehicle to perform the avoidance action responsive to the confidence being above a threshold value (if amount of confidence level (e.g. certainty) is greater than the threshold, then the processors generate a control signal to autonomously move the ego vehicle, see at least col. 40 lines 17-39)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan, the angle to speed relation taught by Minh, the neural networks to identify objects taught by Harrison, the feature vectors taught by Chemali, and the combination of sensor systems taught by Li by adding the confidence level taught by Pertsel with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to be sure of a collision prior to carrying out an action.
Regarding claim 13, the combination of Vijayan, Minh, Harrison, Chemali, and Li teaches the elements above but does not teach:
Confidence
However, Pertsel teaches:
processing the sensing data using the heading detection machine learning model MLM comprises determining a confidence in the heading direction (confidence level of the predicted path 402 of moving object, see at least col. 40 lines 20-24); and wherein causing the control system of the autonomous vehicle to perform the avoidance action is responsive to the confidence being above a threshold value (if amount of confidence level (e.g. certainty) is greater than the threshold, then the processors generate a control signal to autonomously move the ego vehicle, see at least col. 40 lines 17-39)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan, the angle to speed relation taught by Minh, the neural networks to identify objects taught by Harrison, the feature vectors taught by Chemali, and the combination of sensor systems taught by Li by adding the confidence level taught by Pertsel with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to be sure of a collision prior to carrying out an action.
Claims 8 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Vijayan in view of Minh as applied to claims 1 and 9 above and further in view of Pertsel.
Regarding claim 8, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
the one or more sensors are further configured to collect second sensing data for a second object (other vehicles 14A, 14b, and 14C, see at least [0015] and Fig. 1); and wherein the hardware processor is further configured to:
identify a second heading direction for the second object based on the second sensing data (signal output by sensor may include position variation value for both other vehicle 14A and 14B, see at least [0016]);
determine that the second object is at risk of loss of control, based at least on a second difference between the second heading direction and a second direction of travel of the second object (other vehicle 14B may be classified as erratic when position variation value is not less than the variation threshold, see at least [0018]); and
abstain, responsive to presence of one or more mitigating conditions, from a second avoidance action (if vehicle 14B is erratic, the travel path 28 of host vehicle includes not passing the other vehicle 14B, see at least [0019]),
Vijayan does not disclose:
wherein the one or more mitigating conditions comprise at least one of: a second confidence in the second heading direction being below a threshold value, a field of view of the second object being at least partially obstructed, a distance to the second object being above a threshold distance, the second object being of an exempt object type, presence of one or more emergency vehicles, the second object exiting a highway, or the second object entering the highway
However, Pertsel teaches:
wherein the one or more mitigating conditions comprise at least one of: a second confidence in the second heading direction being below a threshold value (if amount of confidence level (e.g. certainty) is not greater than the threshold, then the processor does not generate an action, see at least col. 40 lines 17-39), a field of view of the second object being at least partially obstructed, a distance to the second object being above a threshold distance, the second object being of an exempt object type, presence of one or more emergency vehicles, the second object exiting a highway, or the second object entering the highway
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan and the angle to speed relation taught by Minh by adding the confidence level taught by Pertsel with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to be sure of a collision prior to carrying out an action.
Regarding claim 16, the combination of Vijayan and Minh teaches the elements above and Vijayan further discloses:
collecting second sensing data for a second object (other vehicles 14A, 14b, and 14C, see at least [0015] and Fig. 1); identifying a second heading direction for the second object based on the second sensing data (signal output by sensor may include position variation value for both other vehicle 14A and 14B, see at least [0016]); determining that the second object is at risk of loss of control, based at least on a second difference between the second heading direction and a second direction of travel of the second object (other vehicle 14B may be classified as erratic when position variation value is not less than the variation threshold, see at least [0018]); and abstaining, responsive to presence of one or more mitigating conditions, from a second avoidance action (if vehicle 14B is erratic, the travel path 28 of host vehicle includes not passing the other vehicle 14B, see at least [0019]);
Vijayan does not disclose:
wherein the one or more mitigating conditions comprise: a second confidence in the second heading direction being below a threshold value, a field of view of the second object being at least partially obstructed, a distance to the second object being above a threshold distance, the second object being of an exempt object type, presence of one or more emergency vehicles, the second object exiting a highway, or the second object entering the highway
However, Pertsel teaches:
wherein the one or more mitigating conditions comprise: a second confidence in the second heading direction being below a threshold value (if amount of confidence level (e.g. certainty) is not greater than the threshold, then the processor does not generate an action, see at least col. 40 lines 17-39), a field of view of the second object being at least partially obstructed, a distance to the second object being above a threshold distance, the second object being of an exempt object type, presence of one or more emergency vehicles, the second object exiting a highway, or the second object entering the highway
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan and the angle to speed relation taught by Minh by adding the confidence level taught by Pertsel with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to be sure of a collision prior to carrying out an action.
Claims 17-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Vijayan in view of Li and further in view of Minh.
Regarding claim 17, Vijayan discloses:
An autonomous vehicle comprising (autonomous vehicle system, automated operation of host vehicle 12, see at least [0010]-[0011]): a one or more sensors configured to acquire sensing data of a plurality of sensing modalities (sensor 18 configured to detect other vehicle, see at least [0012]), wherein the plurality of sensing modalities comprises at least two of a camera sensing modality (sensor may include camera 18A, see at least [0012]), a lidar sensing modality (sensor may include lidar unit 18C, see at least [0012]), or a radar sensing modality (sensor may include radar unit 18B, see at least [0012]);
a hardware processor configured to: identify a heading direction of an object in an environment of the autonomous vehicle, based at least on processing of the sensing data (detect other vehicle is off-center indicated by signals from sensor 18, see at least [0016]; determine orientation of other vehicle is not aligned with lane, see at least [0022]);
determine a yaw angle that the heading direction makes with a direction of travel of the object (orientation angle indicated by vehicle vector is substantially different from the direction of the lane vector, see at least [0023]);
determine based on at least a speed of the object, a reference yaw angle for the object (difference threshold may be expressed in terms of instantaneous angle difference, yaw rate, lateral acceleration, or others and arising from a combination thereof, see at least [0024]; difference threshold is vector based including a combination of angle difference and linear speed, see at least [0024]);
determine that the object is at risk of loss of control of a driving trajectory, based at least on the yaw angle and the determined yaw angle for the object (detect other vehicle has lost control when orientation of other vehicle 14 is not aligned with lane vector of roadway which indicates a direction of travel, see at least [0022]); and
select an avoidance action; and a driving control system configured to perform the selected avoidance action (when vector difference value violates the difference threshold such as other vehicle is classified as out-of-control, travel path may include changing lanes to avoid other vehicle, see at least [0025] and [0027]; avoidance scenario can range from lane change, passing, slowing, altering route, stop, and/or alerting authorities, see at least [0027])
Vijayan does not disclose:
machine learning model
However, Li teaches:
a heading detection machine learning model (MLM) (sensor subsystem includes combination of lidar, radar, and camera systems, see at least col. 4 lines 23-25; neural network trained to generated vehicle heading, see at least col. 3 lines 19-20; plurality of point cloud data as input to a neural network, see at least col. 2, lines 47-50; camera subnetwork that operates on camera image, output of point cloud and camera subnetwork, see at least col. 3 lines 7-13)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the sensors disclosed by Vijayan by adding the neural network taught by Li with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “for speed and real-time processing to quickly make vehicle heading predictions in a production system” (see col. 3 lines 27-39).
Furthermore, Minh teaches:
determine, based at least on a speed of the object, a reference yaw angle for the object (vehicle steering angles have upper limit angles based on vehicle speed, see Fig. 4 on page 5) *Examiner sets forth that steering angle and yaw angle are directly proportional and the same relational property of higher speeds requiring lower angles applies
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the out of control vehicle identification disclosed by Vijayan and the neural network taught by Li by adding the angle to speed relation taught by Minh with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to determine safe angles for vehicles (see page 5, col. 1, paragraph 3).
Regarding claim 18, the combination of Vijayan, Li, and Minh teaches the elements above and Vijayan further teaches:
wherein to determine that the object is at risk of loss of control, the hardware processor is to determine that the yaw angle exceeds the determined reference yaw angle
Vijayan does not disclose:
access a mapping of a plurality of speed values to a plurality of reference yaw angles, wherein higher speed values are mapped to smaller reference yaw angles
However, Minh teaches:
access a mapping of a plurality of speed values to a plurality of reference yaw angles, wherein higher speed values are mapped to smaller reference yaw angles (vehicle steering angles have upper limit angles based on vehicle speed, see Fig. 4 graph on page 5) *Examiner sets forth that steering angle and yaw angle are directly proportional and the same relational property of higher speeds requiring lower angles applies
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the out of control vehicle identification disclosed by Vijayan and the neural network taught by Li by adding the angle to speed relation taught by Minh with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification to determine safe angles for vehicles (see page 5, col. 1, paragraph 3).
Regarding claim 20, the combination of Vijayan, Li, and Minh teaches the elements above and Vijayan further discloses:
the direction of travel of the object is obtained using at least one of: a roadgraph data for a portion of a roadway associated with a current location of the object, or a direction of a traffic lane occupied by the object determined by a computer vision MLM (lane vector 38 indicates direction of travel for a particular lane, see at least [0022]; sensor detects lane position of other vehicles relative to lane markings of roadway , see at least [0012])
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Vijayan in view of Li and Minh as applied to claim 17 above and further in view of Mande.
Regarding claim 19, the combination of Vijayan, Li, and Minh teaches the elements above and Vijayan further teaches:
the hardware processor is further configured to: determine, based on the sensing data, a type of the object (sensor configured to detect other vehicle, see at least [0012]), and wherein the reference yaw angle is further determined based on the type of the object (determine a behavior classification of the other vehicle based on a lane keeping behavior, see at least [0014]; other vehicle may be classified as out of control when vector difference value is greater than difference threshold, see at least [0023])
Vijayan does not explicitly disclose:
a machine learning model
However, Mande teaches:
determine, based on the sensing data and using an object detection machine learning model, a type of the object (processing unit processes the image data to detect and classify a vehicle such as car, truck, bus, motorcycle, see at least [0059]; collision prediction system (CPS) learns motion patterns associated with vehicle of different classes and uses the learned motion patterns to generate an intersection model, see at least [0057])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the behavior classification disclosed by Vijayan, the neural network taught by Li, and the angle to speed relation taught by Minh by adding the classification taught by Mande with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification in order to determine paths available for the given class (see [0016]).
Conclusion
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 HANA LEE whose telephone number is (571)272-5277. The examiner can normally be reached Monday-Friday: 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.
/H.L./Examiner, Art Unit 3662
/DALE W HILGENDORF/Primary Examiner, Art Unit 3662