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
Applicant’s arguments, see pages 9 and 10, filed 04/28/2026, with respect to the double patenting rejection and rejection under 35 USC 112(a) have been fully considered and are persuasive. The rejections of 02/27/2026 have been withdrawn.
In light of the IDS submitted with fee on 04/28/2026, the indication of allowable subject matter made on 02/27/2026 has been withdrawn. Accordingly, the claims are rejected as discussed in further detail below.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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, 2, 4-7, 9, 13, 14, 16, 17, and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Gray (US 20180373263, cited in applicant IDS) in view of Beaurepaire et al. (US 20230400312, cited in previous applicant IDS) in view of Picard et al. (WO 2020165544, previously cited).
Claim 1.
Gray teaches:
one or more processors
(Gray – [0094]) “The computer system 700 includes at least one processor 710 for processing information stored in the main memory 720, such as provided by a random access memory (RAM) or other dynamic storage device, for storing information and instructions which are executable by the processor.”
one or more non-transitory computer-readable media storing instructions
(Gray – [0094]) “The computer system 700 includes at least one processor 710 for processing information stored in the main memory 720, such as provided by a random access memory (RAM) or other dynamic storage device, for storing information and instructions which are executable by the processor.”
receiving sensor data from a sensor associated with an autonomous vehicle
(Gray – [0065]) “an associated set of sensor data 378, which can include LIDAR, sonar, radar measurements taken by sensors of the training data collection vehicle 375 at the time the particular training image frame 377 was captured.”
receiving map data of an environment
(Gray – [0066]) “The image analyzer (location data) 340 can query a location or mapping database using the precise location and heading of the training image collection vehicle 375”
determining, based on the sensor data, a dynamic object in the environment
(Gray – [0065]) “The image analyzer (sensor data) 335 can be used to identify pedestrians, other vehicles, walls, or moving objects on the road”
determining, based on the sensor data and the map data, a representation of the environment, wherein at least road marking and velocity information associated with the dynamic object is
(Gray – [0067]) “the label reconciler 350 can begin with a depiction of the stationary or mapped features such as paved road surfaces (drivable space) and can subsequently overlay identified moving features such as another vehicle to arrive at the preliminary training results 351.”
inputting the representation that comprises at least the road marking and velocity information associated with the dynamic object into a machine learned model
(Gray – [0015]) “the collision-avoidance system can determine regions of drivable space in a forward direction of the vehicle by analyzing the image frames”
[Examiner’s Note: Paragraph [0092] of Gray recites that velocity information of the dynamic object is extractable from the image data; therefore, the representation comprises road marking data and velocity information obtainable from the representation.]
receiving, from the machine learned model, a first output comprising a first probability that a first environment of the first output represents a drivable area and a second output comprising a second probability that a second element of the second output represents a non-drivable area
(Gray – [0015]) “the collision-avoidance system can determine a corresponding probability that each pixel of an image frame is representative of drivable space.”
[Examiner’s Note: As each pixel can either be drivable or non-drivable space, it is trivial to determine the probability that a particular area is non-drivable based on a known probability that the particular area is drivable.]
controlling the autonomous vehicle to traverse the environment based on the trajectory
(Gray – [0020]) “the collision-avoidance system can also generate a steering output to alter the trajectory of the vehicle”
While Gray teaches velocity information associated with the dynamic object, Gray does not explicitly teach storing velocity information; however, Beaurepaire et al. teaches:
wherein the at least road marking and velocity information associated with the dynamic object is stored in semantic data associated with the representation
(Beaurepaire – [0068]) “the machine learning module 307 can apply a machine learning data matrix/table on contextual features including road feature(s) (e.g., speed limit, guard rail (e.g., poles, beacon/sensor, etc.), signs, map features associated with additional roadway furniture, navigable or non-navigable, etc.) … mode of transport feature(s) (e.g., make, model, sensors, speed, sensor operations, autonomous vehicle (AV)/manual mode, etc.)”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the collision-avoidance system of Gray with the contextual data of Beaurepaire et al. One would have been motivated to do this because the use of contextual data can provide information as to why and how a particular detected event is occurring (Beaurepaire – [0056]).
While Gray teaches altering a vehicle trajectory based on a non-drivable area probability, Gray does not explicitly teach the generation of a trajectory; however, Picard et al. teaches:
generating a trajectory based on the first output and the second output
(Picard – [0037]) “calculation of a trajectory and/or a vehicle speed instruction by the processing unit based on the probability of the presence of a drivable zone.”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the collision-avoidance system of Gray with the generated trajectory of Picard et al. Both Gray and Picard are directed towards navigation based on a probability of a drivable area; therefore, a person of ordinary skill in the art would have recognized that this modification could be made with predictable results. One would have been motivated to do this because the pre-determination of a trajectory would allow for smoother navigation than an abrupt generation of a steering command would.
Claim 2.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 1, as discussed above. Beaurepaire et al. further teaches:
triggering operation of the autonomous vehicle by determining that there are at least one of dividers or cones on a roadway
(Beaurepaire – [0032]) “the infrastructure elements 111 (e.g., a fixture or structure on the road or within the road reserve intended to provide information, shelter, or safety to a road user, such as a… divider, fence, etc.)”
It would have been obvious to one possessing ordinary skill in the art to combine these teachings for the reasons given in discussion of claim 1.
Claim 4.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 1, as discussed above. Gray further teaches:
wherein the sensor data is received from one or more of a lidar sensor, a radar sensor, or an image sensor
(Gray – [0065]) “an associated set of sensor data 378, which can include LIDAR, sonar, radar measurements taken by sensors of the training data collection vehicle 375 at the time the particular training image frame 377 was captured.”
Claim 5.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 1, as discussed above. Beaurepaire et al. further teaches:
determining perception data that comprises previous road marking and velocity information, the previous road marking and velocity information comprising velocity information associated with objects in the environment
(Beaurepaire – [0068]) “the machine learning module 307 can apply a machine learning data matrix/table on contextual features including road feature(s) (e.g., speed limit, guard rail (e.g., poles, beacon/sensor, etc.), signs, map features associated with additional roadway furniture, navigable or non-navigable, etc.) … mode of transport feature(s) (e.g., make, model, sensors, speed, sensor operations, autonomous vehicle (AV)/manual mode, etc.)”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings for the reasons given in discussion of claim 1.
Claim 6.
Gray teaches:
determining, based at least in part on the map data and the dynamic object, a representation of the environment, wherein at least road marking and velocity information associated with the dynamic object is
(Gray – [0067]) “the label reconciler 350 can begin with a depiction of the stationary or mapped features such as paved road surfaces (drivable space) and can subsequently overlay identified moving features such as another vehicle to arrive at the preliminary training results 351.”
receiving, from the machine learned model, a first output comprising a first probability that a first element of the first output represents a first area comprising at least one of a drivable area, an expandable driving area, or a non-incident area, and a second output comprising a second probability that a second element of the second output represents a second area comprising at least one of a non-drivable area, an expanded non-drivable area, or an incident area
(Gray – [0015]) “the collision-avoidance system can determine a corresponding probability that each pixel of an image frame is representative of drivable space.”
[Examiner’s Note: As each pixel can either be drivable or non-drivable space, it is trivial to determine the probability that a particular area is non-drivable based on a known probability that the particular area is drivable.]
While Gray teaches velocity information associated with the dynamic object, Gray does not explicitly teach storing velocity information; however, Beaurepaire et al. teaches:
at least road marking and velocity information associated with the dynamic object is stored in semantic data associated with the representation
(Beaurepaire – [0068]) “the machine learning module 307 can apply a machine learning data matrix/table on contextual features including road feature(s) (e.g., speed limit, guard rail (e.g., poles, beacon/sensor, etc.), signs, map features associated with additional roadway furniture, navigable or non-navigable, etc.) … mode of transport feature(s) (e.g., make, model, sensors, speed, sensor operations, autonomous vehicle (AV)/manual mode, etc.)”
The rest of the claim is rejected by the same rationale as claim 1.
Claim 7.
Rejected by the same rationale as claim 2.
Claim 9.
Rejected by the same rationale as claim 5.
Claim 13.
Rejected by the same rationale as claim 6.
Claim 14.
Rejected by the same rationale as claim 2.
Claim 16.
Rejected by the same rationale as claim 4.
Claim 17.
Rejected by the same rationale as claim 5.
Claim 19.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 13, as discussed above. Picard et al. further teaches:
determining that the first probability is greater than a threshold probability and the second probability is less than the threshold probability
(Picard – [0038]) “calculating the instruction depends on a predetermined threshold value, the threshold value being a level of risk to be taken corresponding to a probability that a pixel of an acquired image belongs to a rolling zone.”
generating a trajectory through the drivable area based at least in part on the first probability being greater than a threshold probability and the second probability being less than the threshold probability
(Picard – [0038]) “calculating the instruction depends on a predetermined threshold value, the threshold value being a level of risk to be taken corresponding to a probability that a pixel of an acquired image belongs to a rolling zone.”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings for the reasons given in discussion of claim 1.
Claim 20.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 13, as discussed above. Beaurepaire et al. further teaches:
receiving from the machine learned model, a boundary line associated with the drivable area, and determining the trajectory based at least in part on the boundary line
(Beaurepaire – [0115]) “The mapping data records 611 also include lane models that provide the precise lane geometry with lane boundaries”
It would have been obvious to one possessing ordinary skill in the art to combine these teachings for the reasons given in discussion of claim 1.
Claim(s) 3, 8, and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Gray, Beaurepaire et al., and Picard et al. as applied to claims 1, 6, and 13 above, and further in view of Kudrynski et al. (US 20180202814).
Claim 3.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 1, as discussed above. None of the aforementioned references explicitly teach a multi-channel image; however, Kudrynski et al. teaches:
wherein the representation comprises a multi-channel image
(Kudrynski – [0046]) “In this way, a multi-channel depth map, e.g. raster image, is provided.”
It would have been obvious to one possessing ordinary skill in the art to combine these teachings, modifying the input images of Gray with the multi-channel images of Kudrynski et al. Both Gray and Kudrynski et al. are directed towards fusion of map and sensor data; therefore, a person of ordinary skill in the art would have recognized that this combination could be made with predictable results. One would have been motivated to do this because the multi-channel image allows for more efficient compression of a larger amount of data related to the environment (Kudrynski – [0046]).
Claim 8.
Rejected by the same rationale as claim 3.
Claim 15.
Rejected by the same rationale as claim 3.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Gray, Beaurepaire et al., and Picard et al. as applied to claim 6 above, and further in view of Woodbury (US 20240317232, previously cited).
Claim 10.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 6, as discussed above. While Gray teaches determination of an imminent impact based on the speed of the dynamic object (Gray – [0092]), Gray does not explicitly teach avoiding following the dynamic object; however, Woodbury teaches:
determining, by the machine learned model, to avoid following the dynamic object, based at least in part on the speed of the dynamic object being below a threshold speed
(Woodbury – [0038]) “the narrow track vehicle may determine that the object is moving below the speed limit, below a threshold speed, or is moving erratically. In examples, the narrow track vehicle 102 may perform a virtual change operation in order to position itself in a staggered (i.e., offset) formation relative to the other object”
in response to determining to avoid following the dynamic object, controlling the vehicle to not follow the dynamic object
(Woodbury – [0038]) “the narrow track vehicle may determine that the object is moving below the speed limit, below a threshold speed, or is moving erratically. In examples, the narrow track vehicle 102 may perform a virtual change operation in order to position itself in a staggered (i.e., offset) formation relative to the other object”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the collision-avoidance system of Gray with the automatic lane change of Woodbury. Both Gray and Woodbury are directed towards control of a vehicle based on the speed of objects in the environment; therefore, a person of ordinary skill in the art would have recognized that they could be combined in this fashion with predictable results. One would have been motivated to do this because the lane-level operation of Woodbury improves the efficiency of route planning (Woodbury – [0008]).
Claim(s) 11 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Gray, Beaurepaire et al., and Picard et al. as applied to claims 6 and 13 above, and further in view of Kaplan et al. (US 12013256, previously cited).
Claim 11.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 6, as discussed above. None of the aforementioned references explicitly teach an output drivable area differing from map data; however, Kaplan et al. teaches:
wherein the drivable area output by the machine learned model is different than a drivable area indicated by the map data
(Kaplan – Col. 28, lines 34-42) “a discrepancy may be determined between the mapped lines 552, 554 and a perceived lane 594 that is effectively defined by perceived boundaries 584, 586, e.g., as a result of attempting to match perceived boundaries 584, 586 with the mapped boundaries 566, 568, and 570. Based on the identified discrepancy, the map data may be augmented, e.g., using a centerline 596 and/or left or right boundaries or guides 598, 600 to define a pathway along the roadway”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the collision-avoidance system of Gray with the dynamic augmentation of map data of Kaplan et al. Both Gray and Kaplan et al. are directed towards the reconciliation of map data and sensor data; therefore, a person of ordinary skill in the art would have recognized that they could be combined in this fashion with predictable results. One would have been motivated to do this because even rapid updates to map data may not reflect changes which suddenly arise in an environment (Kaplan – Col. 1, lines 64-67).
Claim 12.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 6, as discussed above. While Beaurepaire et al. teaches detection of signs, Beaurepaire et al. does not explicitly teach specific traffic control indications; however, Kaplan et al. teaches:
detecting one or more of traffic control indications as input to the machine learned model, the traffic control indications comprising at least one of a lanes ahead merge sign, an entering construction zone sign, a do not enter sign, a construction zone ahead sign, or a flagger sign
(Kaplan – Col. 19, lines 29-34) “Perception component 358 may also include a sign classifier component 366 that receives the objects detected as being signs by object classifier component 360 and determines the logical significance of such signs, e.g., the type of sign (speed limit, warning, road closure, construction notification, etc.)”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings for the reasons given in discussion of claim 11.
Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Gray, Beaurepaire et al., and Picard et al. as applied to claim 13 above, and further in view of Green et al. (US 20240140487, previously cited).
Claim 18.
The combination of Gray, Beaurepaire et al., and Picard et al. teaches all the limitations of claim 13, as discussed above.
determining log data of another vehicle under control of a driver and traversing a construction zone
(Green – [0159]) “The training data 162 can include, for example log data annotated with yield labels. The log data can describe yield behaviors performed by vehicles (e.g., autonomous vehicles and/or humanly-operated vehicles) during previously conducted real-world driving sessions.”
training the machine learned model based at least in part on the log data
(Green – [0159]) “The training data 162 can include, for example log data annotated with yield labels. The log data can describe yield behaviors performed by vehicles (e.g., autonomous vehicles and/or humanly-operated vehicles) during previously conducted real-world driving sessions.”
It would have been obvious to one possessing ordinary skill in the art before the effective filing date to combine these teachings, modifying the input images of Gray with the annotated log data of Green et al. One would have been motivated to combine these teachings in order to assist in making decisions as to whether it is appropriate to yield to a detected object (Green – [0007]).
Conclusion
Applicant's submission of an information disclosure statement under 37 CFR 1.97(c) with the timing fee set forth in 37 CFR 1.17(p) on 04/28/2026 prompted the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 609.04(b). 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 SARAH A MUELLER whose telephone number is (703)756-4722. The examiner can normally be reached M-Th 7:30-12:00, 1:00-5:30; F 8:00-12:00.
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, Navid Mehdizadeh can be reached at (571)272-7691. 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.
/S.A.M./Examiner, Art Unit 3669
/NAVID Z. MEHDIZADEH/Supervisory Patent Examiner, Art Unit 3669
Prosecution Insights