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 .
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.
Effective Filing Date
The effective filing date is 12/27/2022.
Status of Claims
The present application is being examined under the claims filed on 01/02/2026.
Claims 1-20 are rejected and pending.
Claims 1, 13 and 19 are independent claims.
Claims 1-13, 16-17 and 19-20 are amended.
Prior Art References
The short names that are used to identify the references of prior art in the analysis that follows are:
Short Name
Reference
Intel
US 20220126864 A1 - AUTONOMOUS VEHICLE SYSTEM
Xerox
US 20170286774 A1 - DEEP DATA ASSOCIATION FOR ONLINE MULTI-CLASS MULTI-OBJECT TRACKING
UATC
US 20210049378 A1 - Association And Tracking For Autonomous Devices
Li
US 20180374359 A1 - EVALUATION FRAMEWORK FOR PREDICTED TRAJECTORIES IN AUTONOMOUS DRIVING VEHICLE TRAFFIC PREDICTION
LGN
US 20220227379 A1 - NETWORK FOR DETECTING EDGE CASES FOR USE IN TRAINING AUTONOMOUS VEHICLE CONTROL SYSTEMS
Toyota
US 20190287079 A1 - SENSOR-BASED DIGITAL TWIN SYSTEM FOR VEHICULAR ANALYSIS
7D
US 10235601 B1 - Method For Image Analysis
Google
US 20120331061 A1 - Collaborative Development Of A Model On A Network
Arm
US 11138812 B1 - Image Processing For Updating A Model Of An Environment
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract idea without significantly more. This judicial exception is not integrated into a practical application as outlined in the 2-step analyses for each claim that follows.
In reference to claim 1.
Step 1:
Yes, a machine - "1. A processor comprising: one or more circuits to:".
Step 2A Prong 1:
- “determine a predicted state of an object detected in an environment of a machine” which is an evaluation that may be performed mentally by a human with the aid of pen and paper. Thus, the limitation recites a mental process and therefore an abstract idea.
Step 2A Prong 2:
- “obtain one or more inputs using: one or more values for one or more input parameters corresponding to the predicted state of the object, and sensor data corresponding to the object and including measurements from a plurality of sensors” which amount to mere extra solution activity of obtaining and/or gathering data over a network, see MPEP §2106.05(g)
-“generate, based at least on one or more neural network model processing the one or more inputs, a score indicative of an association between the predicted state of the object and one or more representations of the object in the sensor data” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
- “and update data corresponding to the environment according to whether the score exceeds an association threshold;” which amounts to insignificant extra-solution activity mere data gathering or outputting per MPEP2106.05(g).
- “generate a control signal based at least on the updated data” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
- “provide the control signal to a physical component of the machine to cause the machine to begin, cease, perform, or change one or more operations thereof” which amounts to insignificant extra-solution activity mere data gathering or outputting per MPEP2106.05(g).
Step 2B:
- “obtain one or more inputs using: one or more values for one or more input parameters corresponding to the predicted state of the object, and sensor data corresponding to the object and including measurements from a plurality of sensors” which is merely well understood, routine, and conventional activity of “transmitting or receiving data over a network" (see MPEP 2106.05(d)(II)(i) using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362).
-“generate, based at least on one or more neural network model processing the one or more inputs, a score indicative of an association between the predicted state of the object and one or more representations of the object in the sensor data” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
- “and update data corresponding to the environment according to whether the score exceeds an association threshold;” which amounts to insignificant extra-solution activity per MPEP2106.05(g). This is well-understood, routine, conventional computer functionality as recognized by MPEP2106.05(d)(II) iv. Storing and retrieving information in memory.
- “generate a control signal based at least on the updated data” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
- “provide the control signal to a physical component of the machine to cause the machine to begin, cease, perform, or change one or more operations thereof” which is merely well understood, routine, and conventional activity of “transmitting or receiving data over a network" (see MPEP 2106.05(d)(II)(i) using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362).
In reference to claim 2.
Step 1:
Yes, a machine - "2. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the one or more neural network models comprise a multi-layer perceptron (MLP) model." which only provides further details regarding the structure of neural network and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 3.
Step 1:
Yes, a machine - "3. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the one or more input parameters comprise at least one of: (i) the predicted state or (ii) an identification of a sensor." which only provides further details regarding the structure of the input parameters and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 4.
Step 1:
Yes, a machine - "4. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the plurality of sensors are part of a system, and wherein the one or more circuits generate an instruction to cause a change in the system in response to the updated data corresponding to the environment." which, but for the inclusion of generic computing equipment (i.e., circuits), is an evaluation that may be performed mentally by a human with the aid of pen and paper (refer to MPEP 2106.04(a)(2)(III)(C) for more information about mental processes being performed on a computer).
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 5.
Step 1:
Yes, a machine - "5. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the plurality of sensors are part of a system, and wherein the data is updated to indicate a change in a position of the object in the environment relative to the system." which, but for the inclusion of generic computing equipment, is an evaluation that may be performed mentally by a human with the aid of pen and paper (refer to MPEP 2106.04(a)(2)(III)(C) for more information about mental processes being performed on a computer).
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 6.
Step 1:
Yes, a machine - "6. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the one or more circuits are to normalize output from the respective plurality of sensors to obtain the sensor data." which, but for the inclusion of generic computing equipment (i.e., circuits), is an evaluation that may be performed mentally by a human with the aid of pen and paper (refer to MPEP 2106.04(a)(2)(III)(C) for more information about mental processes being performed on a computer).
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 7.
Step 1:
Yes, a machine - "7. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the one or more neural network models are generated, at least, using modeling data comprising (i) a plurality of predicted states of objects, and (ii) a plurality of sensor data each corresponding to a respective one of the plurality of predicted states and obtained from a respective plurality of sensors." which only provides further details regarding the structure of neural network and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 8.
Step 1:
Yes, a machine - "8. The one or more processors of claim 7,".
Step 2A Prong 1:
- "wherein a first portion of the modeling data corresponds to positive samples and a second portion of the modeling data corresponds to negative samples." which only provides further details regarding the structure of training samples and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 9.
Step 1:
Yes, a machine - "9. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the data corresponds to one or more object tracks corresponding to one or more objects in the environment, and the data is updated to include an updated object track corresponding to the object based at least on the score." which only provides further details regarding the structure of training data and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 10.
Step 1:
Yes, a machine - "10. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the one or more neural network models are generated, at least, by generating the modeling data, and updating one or more parameters of the one or more neural network models using the modeling data." which only provides further details regarding the structure of how the neural network is generated and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 11.
Step 1:
Yes, a machine - "11. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein, during training, the one or more neural network models are updated to receive input comprising (a) a first predicted state of a first object and (b) an identification of a first sensor, and to provide an output score indicative of an association between one or more first object representations corresponding to sensor data from the first sensor and the first predicted state." which only provides further details regarding the structure of the neural network and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 12.
Step 1:
Yes, a machine - "12. The one or more processors of claim 1,".
Step 2A Prong 1:
- "wherein the one or more processor are comprised in at least one of. a control system for an autonomous or semi-autonomous machine; a perception system for an autonomous or semi-autonomous machine; a system for performing simulation operations; a system for performing digital twin operations; a system for performing light transport simulation; a system for performing collaborative content creation for 3D assets; a system for performing deep learning operations; a system implemented using an edge device; a system for generating or presenting at least one of virtual reality, augmented reality, or mixed reality content; a system implemented using a robot; a system for performing conversational Al operations; a system for generating synthetic data; a system incorporating one or more virtual machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources." which, but for the inclusion of generic computing equipment, is an evaluation that may be performed mentally by a human with the aid of pen and paper (refer to MPEP 2106.04(a)(2)(III)(C) for more information about mental processes being performed on a computer).
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 13.
Step 1:
Yes, a method - "13. A method comprising:".
Step 2A Prong 1:
- "determining a predicted state of an object detected in an environment of a machine corresponding to a time" which is an evaluation that may be performed mentally by a human with the aid of pen and paper. Thus, the limitation recites a mental process and therefore an abstract idea.
- “generating…a score indicative of an association between the predicted state of the object and a detected state of the object at the time” which is an evaluation that may be performed mentally by a human with the aid of pen and paper. Thus, the limitation recites a mental process and therefore an abstract idea.
Step 2A Prong 2:
- “obtaining inputs data using: sensor data comprising measurements corresponding to the object from a plurality of sensors, and one or more values of one or more input parameters corresponding to the predicted state” which amount to mere extra solution activity of obtaining and/or gathering data over a network, see MPEP §2106.05(g)
-“generate, based at least on one or more neural network model processing the one or more inputs, a score indicative of an association between the predicted state of the object and one or more representations of the object in the sensor data” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
- “updating an object track corresponding to the object based at least on the score;” which amounts to insignificant extra-solution activity mere data gathering or outputting per MPEP2106.05(g).
-“causing the machine to begin, cease, perform, or change one or more operations thereof based on at least the object track as updates” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
Step 2B:
- “obtaining inputs data using: sensor data comprising measurements corresponding to the object from a plurality of sensors, and one or more values of one or more input parameters corresponding to the predicted state” which is merely well understood, routine, and conventional activity of “transmitting or receiving data over a network" (see MPEP 2106.05(d)(II)(i) using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362). which amount to mere extra solution activity of obtaining and/or gathering data over a network, see MPEP §2106.05(g)
-“generate, based at least on one or more neural network model processing the one or more inputs, a score indicative of an association between the predicted state of the object and one or more representations of the object in the sensor data” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
- “updating an object track corresponding to the object based at least on the score;” which amounts to insignificant extra-solution activity per MPEP2106.05(g). This is well-understood, routine, conventional computer functionality as recognized by MPEP2106.05(d)(II) iv. Storing and retrieving information in memory.
-“causing the machine to begin, cease, perform, or change one or more operations thereof based on at least the object track as updates” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
In reference to claim 14.
Step 1:
Yes, a method - "14. The method of claim 13,".
Step 2A Prong 1:
- "wherein the one or more neural network models comprise a multi-layer perceptron (MLP) model, and the MLP model is generated using data comprising (i) a plurality of predicted states of objects, and (ii) a plurality of sensor data each corresponding to a respective one of the plurality of predicted states and obtained from a respective plurality of sensors." which only provides further details regarding the structure of neural network and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 15.
Step 1:
Yes, a method - "15. The method of claim 13,".
Step 2A Prong 1:
- "wherein the one or more input parameters comprise at least one of (i) the predicted state and (ii) an identification of a sensor." which only provides further details regarding the structure of input parameters and thus is still a mental process based on the parent claim.
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
In reference to claim 16.
Step 1:
Yes, a method - "16. The method of claim 13,".
Step 2A Prong 1:
No elements are recited for Step 2a Prong 1.
Step 2A Prong 2:
- "wherein the plurality of sensors comprises a radar sensor, a light detection and ranging(LIDAR) sensor, or an ultrasonic sensor." which amount to mere extra solution activity of obtaining and/or gathering data over a network, see MPEP §2106.05(g)
Steps 2B:
- “wherein the plurality of sensors comprises a radar sensor, a light detection and ranging(LIDAR) sensor, or an ultrasonic sensor” which is merely well understood, routine, and conventional activity of “transmitting or receiving data over a network" (see MPEP 2106.05(d)(II)(i) using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362) as it further specifies the type of sensor that is obtained from.
In reference to claim 17.
Step 1:
Yes, a method - "17. The method of claim 13,".
Step 2A Prong 1:
- "wherein updating the object track indicates a change in a position of the object in the environment relative to the machine" which, but for the inclusion of generic computing equipment, is an evaluation that may be performed mentally by a human with the aid of pen and paper (refer to MPEP 2106.04(a)(2)(III)(C) for more information about mental processes being performed on a computer).
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more
In reference to claim 18.
Step 1:
Yes, a method - "18. The method of claim 13,".
Step 2A Prong 1:
- "further comprising generating the one or more neural network models, at least, by: generating modeling data;" which is an evaluation that may be performed mentally by a human with the aid of pen and paper. Thus, the limitation recites a mental process and therefore an abstract idea.
Step 2A Prong 2:
- “and updating the one or more neural network models using the modeling data, to: receive input comprising (a) a first predicted state of a first object and (b) an identification of a first sensor, and provide an output score indicative of an association between a first detected state of the object and the first predicted state.” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
Step 2B:
- “and updating the one or more neural network models using the modeling data, to: receive input comprising (a) a first predicted state of a first object and (b) an identification of a first sensor, and provide an output score indicative of an association between a first detected state of the object and the first predicted state.” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
In reference to claim 19.
Step 1:
Yes, a machine - "19. A processor comprising: one more circuits ".
Step 2A Prong 1:
The claim does not contain elements that would warrant a Step 2A Prong 1 analysis.
Step 2A Prong 2:
-“to provide one or more control signals to a physical component of a machine to cause the machine to perform one or more operations, the one or more controls signals generated based at least on an object track corresponding to an object at a time as determined using one or more association scores computed using one or more neural network models, the one or more association scores computed based at last on: ” which amount to mere extra solution activity of obtaining and/or gathering data over a network, see MPEP §2106.05(g)
-“obtaining one or more inputs generated based at least on: sensor data comprising measurements corresponding to the object from a plurality of sensors, and data representative of one or more values of one or more parameters corresponding to a predicted state of the object at the time” which amount to mere extra solution activity of obtaining and/or gathering data over a network, see MPEP §2106.05(g)
-“causing processing, using the one or more neural network models, of the one or more inputs” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
Step 2B:
- “to provide one or more control signals to a physical component of a machine to cause the machine to perform one or more operations, the one or more controls signals generated based at least on an object track corresponding to an object at a time as determined using one or more association scores computed using one or more neural network models, the one or more association scores computed based at last on” which is merely well understood, routine, and conventional activity of “transmitting or receiving data over a network" (see MPEP 2106.05(d)(II)(i) using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362).
-“obtaining one or more inputs generated based at least on: sensor data comprising measurements corresponding to the object from a plurality of sensors, and data representative of one or more values of one or more parameters corresponding to a predicted state of the object at the time, and causing processing, using the one or more neural network models, of the one or more inputs” which is merely well understood, routine, and conventional activity of “transmitting or receiving data over a network" (see MPEP 2106.05(d)(II)(i) using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362).
-“causing processing, using the one or more neural network models, of the one or more inputs” which merely recites the words apply it (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f).
In reference to claim 20.
Step 1:
Yes, a machine - "20. The one or more processors of claim 19,".
Step 2A Prong 1:
- "wherein, at each iteration of the one or more neural network models, the one or more neural network models output an association score between each detected object in the sensor data and the object." which, but for the inclusion of generic computing equipment (i.e., processor), is an evaluation that may be performed mentally by a human with the aid of pen and paper (refer to MPEP 2106.04(a)(2)(III)(C) for more information about mental processes being performed on a computer).
Steps 2A Prong 2 and 2B:
No further elements are recited. Thus, the claim is directed to an abstract idea without significantly more.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim Rejections - 35 USC § 103 - 1,2,4,5,6,9,13,16,17
Claims 1,2,4,5,6,9,13,16,17 are rejected under 35 U.S.C. 103 as being unpatentable over Intel in view of Xerox in further view of UATC.
In reference to claim 1.
“1. A processor comprising: one or more circuits to:” (preamble)
Intel teaches:
“determine a predicted state of an object”(Intel [0177], “Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory”, Object tracking teaches the predicted state of an object with a machine performing) “detected in an environment of machine;” (Intel [0257], “In the example shown, the sensing/perception system 1902 consists of either a singular type or a multi-modal combination of sensors (e.g., LIDAR, radar, camera(s), HD map as shown, or other types of sensors) that allow a digital construction (via sensor fusion) of the environment, including moving and non-moving agents and their current position in relation to the sensing element. This allows an autonomous vehicle to construct an internal representation of its surroundings and place itself within that representation (which may be referred to as an environment model” where the object tracking from the perspective of machine teaches an detection in an environment of machine)
“generate, based on at least on one or more neural network models, a score [indicative of an association between the predicted state and one or more representations of the object in the sensor data];” (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning, such as through one or more convolutional neural networks and other machine learning models 256. Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory. For instance, after a given object is recognized, a perception engine 238 may detect how the given object moves in relation to the vehicle.”, Deep learning teaches the neural network. Object tracking teaches the predicted state. The neural network is used for object recognition and the result thereof is then used for object tracking.)
“generate a control signal based at least on the updated data; and provide the control signal to a physical component of the machine to cause the machine to begin, cease, perform, or change one or more operations thereof”(Intel, Figure 59, where Figure 59 describes an acceleration-to-control converter that converts an acceleration value to a control signal then send the control signal to an actuation system that operates the vehicle corresponds to generate a control signal based at least on the updated data; and provide the control signal to a physical component of the machine to cause the machine to begin, cease, perform, or change one or more operations thereof )
Xerox teaches:
“[generate, based on at least on one or more neural network models], a score indicative of an association between the predicted state of the object and one or more representations of the object in the sensor data;” (Xerox [0037], “In other words, the neural network 56 takes the candidate objects—which can be associated with a target object being tracked in a given previous frame and a new or existing object in a current frame—and creates a data association matrix—a number of targets by a number of detections. The neural network 56 generates a probability (“association score”)”, The association score is indicative of an association between the predicted state (i.e., the tracked object state) and each candidate object.)
Motivation to combine Intel, Xerox.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel and Xerox. Intel discloses a system of object tracking in a multi-sensor autonomous vehicle system. Xerox discloses the generation of a probability of association with respect to tracked object. One would be motivated to combine these references because the disclosure of Xerox enables multiple objects to be tracked which would be applicable to the driving environment of Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (E) Obvious to try – choosing from a finite number of identified, predictable solutions, with a reasonable expectation of success.
UATC teaches:
“obtain one or more inputs using: one or more values for one or more input parameters corresponding to the predicted state of the object”(UATC, Fig. 3 and [0044], “…the association computing system can determine one or more object states and/or one or more object state uncertainties for the detected object…For example, the one or more machine-learned models can use the association data (which includes multiple measurements of the position of a detected object) as an input” where the tracked object state corresponds to a predicted state of the object and the detection corresponds to sensor data corresponding to the object with support UATC [0103] “The object state and uncertainty 324 can include a prediction of the state of an object associated with the detected object 312 (e.g., a location, velocity, physical dimensions, and/or acceleration of a detected object) and the probability that the prediction of the state of the object is accurate”) “, and sensor data corresponding to the object and including measurements from a plurality of sensors” (UATC, [0096], “The tracked objects 302 can include a set of tracked objects that are being tracked over a plurality of time intervals. The tracked object 308 can be part of the set of tracked objects included in the tracked objects 302. The detections 304 can be a set of sensor outputs that is associated with the detection of one or more objects in an environment that are detected by one or more sensors. For example, the detections 304 can include one or more sensor outputs generated by the one or more sensors 114 for use by the vehicle computing system 112. The tracked objects 302 and the detections 304 can be used as an input to the association tracker 306" where the association tracker tracking in the tracked object and sensor outputs describing the objects corresponds to values corresponding to the predicted state the object and sensor data corresponding to the object and including measurements from a plurality of sensors)
“and update data corresponding to the environment according to whether the score exceeds an association threshold.” (UATC [0034], “when the association score for a detected object is less than a predetermined association score threshold, the detected object can be determined not to be associated with an object track” where the determination of an object not being associated with an object track corresponds to update data corresponding to the environment and where checking whether an association score is less than an association score threshold corresponds to according to whether the score exceeds an association threshold)
Motivation to combine Intel, Xerox, UATC.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox and UATC. Intel, Xerox discloses a system of object tracking in a multi-sensor autonomous vehicle system. UATC discloses a utilization of the previously computed association score for filtering predicted object tracks. One would be motivated to combine these references because the disclosure of UATC would provide a method for discarding junk data generated in the system of the combination of Intel and Xerox. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (E) Obvious to try – choosing from a finite number of identified, predictable solutions, with a reasonable expectation of success.
In reference to claim 2.
“2. The one or more processors of claim 1,” (preamble)
Intel teaches:
“wherein the one or more neural network models comprise a multi-layer perceptron (MLP) model.” (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning, such as through one or more convolutional neural networks”, CNNs are a variant of MLP)
In reference to claim 4.
“4. The one or more processors of claim 1,” (preamble)
Intel teaches:
“wherein the plurality of sensors are part of a system (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning”, The sensors are part of the perception engine), and wherein the one or more circuits generate an instruction to cause a change in the system in response to the updated data corresponding to the environment.” (Intel [0199], “Based on the path plan and decisions of the planning and decision stage 510, a control and action stage 515 may convert these determinations into actions, through actuators to manipulate driving controls including steering, acceleration, and braking”)
In reference to claim 5.
“5. The one or more processors of claim 1,” (preamble)
Intel teaches:
“wherein the plurality of sensors are part of a system (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning”, The sensors are part of the perception engine), and wherein the data is updated to indicate a change in a position of the object in the environment relative to the system (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning, such as through one or more convolutional neural networks and other machine learning models 256. Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory. For instance, after a given object is recognized, a perception engine 238 may detect how the given object moves in relation to the vehicle.”).”
In reference to claim 6.
“6. The processor of claim 1,” (preamble)
Intel teaches:
“wherein the one or more circuits are to normalize output from the respective plurality of sensors to obtain the sensor data.” (Intel [0832], “sensor data may be abstracted away from the raw physical characteristics that both camera data and LIDAR data possess, into a more normalized format that enables processing of the data in a more uniform manner.”)
In reference to claim 9.
“9. The processor of claim 1,” (preamble)
Intel teaches:
“wherein the data corresponds to one or more object tracks corresponding to one or more objects in the environment, and the data is updated to include an updated object track corresponding to the object based at least on the score.” (Intel [0177], “Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory.”, The trajectory teaches the object track.)
In reference to claim 13.
“13. A method comprising:” (preamble)
Intel teaches:
“determining a predicted state of an object”(Intel [0177], “Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory”, Object tracking teaches the predicted state of an object with a machine performing) “detected in an environment of machine;” (Intel [0177], “In the example shown, the sensing/perception system 1902 consists of either a singular type or a multi-modal combination of sensors (e.g., LIDAR, radar, camera(s), HD map as shown, or other types of sensors) that allow a digital construction (via sensor fusion) of the environment, including moving and non-moving agents and their current position in relation to the sensing element. This allows an autonomous vehicle to construct an internal representation of its surroundings and place itself within that representation (which may be referred to as an environment model” where the object tracking from the perspective of machine teaches an detection in an environment of machine) corresponding to a time;” (Intel [0177]-[0179],“Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory… For instance, a path planner 242 may utilize these inputs and one or more machine learning models to determine probabilities of various events within a driving environment to determine effective real-time plans to act within the environment.”, Object tracking teaches the predicted state of an object within real-time to determine an effective plan (See also [0199] and [0216] ))
“generating, based on at least on one or more neural network models processing the input data, a score [indicative of an association between the predicted state and a detected state of the object at the time];” (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning, such as through one or more convolutional neural networks and other machine learning models 256. Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory. For instance, after a given object is recognized, a perception engine 238 may detect how the given object moves in relation to the vehicle.”, Deep learning teaches the neural network. Object tracking teaches the predicted state. The neural network is used for object recognition and the result thereof is then used for object tracking.)
Xerox teaches:
“[generating, based on at least on one or more neural network models processing the input data, a score], a score indicative of an association between the predicted state and a detected state of the object at the time;” (Xerox [0037], “In other words, the neural network 56 takes the candidate objects—which can be associated with a target object being tracked in a given previous frame and a new or existing object in a current frame—and creates a data association matrix—a number of targets by a number of detections. The neural network 56 generates a probability (“association score”)”, The association score is indicative of an association between the predicted state (i.e., the tracked object state) and each candidate object.)
obtaining input data using: sensor data comprising measurements corresponding to the object from a plurality of sensors(UATC, [0096], “The tracked objects 302 can include a set of tracked objects that are being tracked over a plurality of time intervals. The tracked object 308 can be part of the set of tracked objects included in the tracked objects 302. The detections 304 can be a set of sensor outputs that is associated with the detection of one or more objects in an environment that are detected by one or more sensors. For example, the detections 304 can include one or more sensor outputs generated by the one or more sensors 114 for use by the vehicle computing system 112. The tracked objects 302 and the detections 304 can be used as an input to the association tracker 306" where the association tracker tracking in the tracked object and sensor outputs describing the objects corresponds to values corresponding to the predicted state the object and sensor data corresponding to the object and including measurements from a plurality of sensors), and one or more values of one or more input parameters corresponding to the predicted state(UATC, Fig. 3 and [0044], “…the association computing system can determine one or more object states and/or one or more object state uncertainties for the detected object…For example, the one or more machine-learned models can use the association data (which includes multiple measurements of the position of a detected object) as an input” where the tracked object state corresponds to a predicted state of the object and the detection corresponds to sensor data corresponding to the object with support UATC [0103] “The object state and uncertainty 324 can include a prediction of the state of an object associated with the detected object 312 (e.g., a location, velocity, physical dimensions, and/or acceleration of a detected object) and the probability that the prediction of the state of the object is accurate”)
Motivation to combine Intel, Xerox.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel and Xerox. Intel discloses a system of object tracking in a multi-sensor autonomous vehicle system. Xerox discloses the generation of a probability of association with respect to tracked object. One would be motivated to combine these references because the disclosure of Xerox enables multiple objects to be tracked which would be applicable to the driving environment of Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (E) Obvious to try – choosing from a finite number of identified, predictable solutions, with a reasonable expectation of success.
UATC teaches:
“and updating an object track corresponding to the object based at least on the score.”(UATC [0034], “when the association score for a detected object is less than a predetermined association score threshold, the detected object can be determined not to be associated with an object track”) and causing the machine to begin, cease, perform, or change one or more operations thereof based at least on the object track as updated.”(UATC. [0134], “In some embodiments, the one or more motion state probabilities for the detected object can be determined based at least in part on one or more changes in the one or more object tracks over the plurality of time intervals. For example, the changes in location of the one or more object tracks associated with the detected object can be used to determine acceleration and/or velocity of the detected object, and in turn, the one or more motion state probabilities” where the changes in track are used to determine the objects velocity/accelerations correspond to causing the machine to….change one or more operations thereof based at least on the object track as updated)
Motivation to combine Intel, Xerox, UATC.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox and UATC. Intel, Xerox discloses a system of object tracking in a multi-sensor autonomous vehicle system. UATC discloses a utilization of the previously computed association score for filtering predicted object tracks. One would be motivated to combine these references because the disclosure of UATC would provide a method for discarding junk data generated in the system of the combination of Intel and Xerox. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (E) Obvious to try – choosing from a finite number of identified, predictable solutions, with a reasonable expectation of success.
In reference to claim 16.
“16. The method of claim 13,” (preamble)
Intel teaches:
“wherein the plurality of sensors of a system (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning”, The sensors are part of the perception engine), comprises a radar sensor, a light detection and ranging(LIDAR) sensor or an ultrasonic sensor (Intel [0184], “As discussed above, the autonomous driving stack of a vehicle may utilize a variety of sensor data (e.g., 258) generated by various sensors provided on and external to the vehicle. As an example, a vehicle 105 may possess an array of sensors 225 to collect various information relating to the exterior of the vehicle and the surrounding environment, vehicle system status, conditions within the vehicle, and other information usable by the modules of the vehicle's processing system 210. For instance, such sensors 225 may include global positioning (GPS) sensors 268, light detection and ranging (LIDAR) sensors”)
In reference to claim 17.
“17. The method of claim 13,” (preamble)
Intel teaches:
“wherein the updating the object track indicates a change in a position of the object in the environment relative to the machine (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning, such as through one or more convolutional neural networks and other machine learning models 256. Object tracking may also be performed to autonomously estimate, from sensor data inputs, whether an object is moving and, if so, along what trajectory. For instance, after a given object is recognized, a perception engine 238 may detect how the given object moves in relation to the vehicle.”).”
Claim Rejections - 35 USC § 103 - 3,11,15,18
Claims 3,11,18 are rejected under 35 U.S.C. 103 as being unpatentable over Intel in view of Xerox in further view of UATC in further view of Li in further view of LGN.
In reference to claim 3.
“3. The one or more processors of claim 1,” (preamble)
Li teaches:
“wherein the one or more input parameters comprise at least one of: (i) the predicted state or” (Li [0064], “FIG. 7 is a flow diagram illustrating a process of training a deep neural network for evaluating predicted trajectories according to one embodiment.”, The predicted state(s) is/are the predicted trajectories used for training the DNN.)
PNG
media_image1.png
708
794
media_image1.png
Greyscale
Motivation to combine Intel, Xerox, UATC, Li.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox, UATC and Li. Intel, Xerox, UATC discloses a system of object tracking in a multi-sensor autonomous vehicle system. Li discloses an evaluation procedure for computed trajectories. One would be motivated to combine these references because the disclosure of Li provides a means for evaluating the computed trajectories of the object tracking in Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (E) Obvious to try – choosing from a finite number of identified, predictable solutions, with a reasonable expectation of success.
LGN teaches:
“(ii) an identification of a sensor.” (LGN [0219], “The neural network may also receive one or more sensor identifiers (ID) (one for each sensor) and a time-stamp. The sensor ID uniquely identifies the corresponding sensor.”)
Motivation to combine Intel, Xerox, UATC, Li, LGN.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox, UATC, Li and LGN. Intel, Xerox, UATC, Li discloses a system of object tracking in a multi-sensor autonomous vehicle system. LGN discloses parameterizing the input of a multi-sensor neural network with an identification of the sensor in the input layer. One would be motivated to combine these references because the disclosure of LGN provides a specific neural network architecture for the system of Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (F) Known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art.
In reference to claim 11.
“11. The one or more processors of claim 1,” (preamble)
Xerox teaches:
“and to provide an output score indicative of an association between one or more first object representations corresponding to sensor data from the first sensor and the first predicted state.” (Xerox [0037], “In other words, the neural network 56 takes the candidate objects—which can be associated with a target object being tracked in a given previous frame and a new or existing object in a current frame—and creates a data association matrix—a number of targets by a number of detections. The neural network 56 generates a probability (“association score”)” The association score is indicative of an association between the predicted state (i.e., the tracked object state) and each candidate object.)
Li teaches:
“wherein, during training, the one or more neural network models are updated to receive input comprising (a) a first predicted state of a first object and” (Li [0064], “FIG. 7 is a flow diagram illustrating a process of training a deep neural network for evaluating predicted trajectories according to one embodiment.”, The predicted state(s) is/are the predicted trajectories used for training the DNN.)
LGN teaches:
“(b) an identification of a first sensor,” (LGN [0219], “The neural network may also receive one or more sensor identifiers (ID) (one for each sensor) and a time-stamp. The sensor ID uniquely identifies the corresponding sensor.”)
In reference to claim 15.
“15. The method of claim 13,” (preamble)
Li teaches:
“wherein the one or more input parameters comprise at least one of (i) the predicted state (Li [0064], “FIG. 7 is a flow diagram illustrating a process of training a deep neural network for evaluating predicted trajectories according to one embodiment.”, The predicted state(s) is/are the predicted trajectories used for training the DNN.)”
LGN teaches:
“and (ii) an identification of a sensor (LGN [0219], “The neural network may also receive one or more sensor identifiers (ID) (one for each sensor) and a time-stamp. The sensor ID uniquely identifies the corresponding sensor.”).”
In reference to claim 18.
“18. The method of claim 13, further comprising generating the one or more neural network models, at least, by:” (preamble)
Xerox teaches:
“and provide an output score indicative of an association between a first detected state of the object and the first predicted state.” (Xerox [0037], “In other words, the neural network 56 takes the candidate objects—which can be associated with a target object being tracked in a given previous frame and a new or existing object in a current frame—and creates a data association matrix—a number of targets by a number of detections. The neural network 56 generates a probability (“association score”)” The association score is indicative of an association between the predicted state (i.e., the tracked object state) and each candidate object.)
Li teaches:
“generating modeling data; and updating the one or more neural network models using the modeling data, to: receive input comprising (a) a first predicted state of a first object and” (Li [0064], “FIG. 7 is a flow diagram illustrating a process of training a deep neural network for evaluating predicted trajectories according to one embodiment.”, The predicted state(s) is/are the predicted trajectories used for training the DNN.)
LGN teaches:
“(b) an identification of a first sensor,” (LGN [0219], “The neural network may also receive one or more sensor identifiers (ID) (one for each sensor) and a time-stamp. The sensor ID uniquely identifies the corresponding sensor.”)
Claim Rejections - 35 USC § 103 - 7,8,10,14
Claims 7,8,10,14 are rejected under 35 U.S.C. 103 as being unpatentable over Intel in view of Xerox in further view of UATC in further view of Li.
In reference to claim 7.
“7. The one or more processors of claim 1,” (preamble)
Intel teaches:
“(ii) a plurality of sensor data each corresponding to a respective one of the plurality of predicted states and obtained from a respective plurality of sensors” (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning”)
Li teaches:
“wherein the one or more neural network models are generated, at least, using modeling data comprising (i) a plurality of predicted states of objects, and” (Li [0064], “FIG. 7 is a flow diagram illustrating a process of training a deep neural network for evaluating predicted trajectories according to one embodiment.”, The predicted state(s) is/are the predicted trajectories used for training the DNN.)
In reference to claim 8.
“8. The one or more processors of claim 7,” (preamble)
Li teaches:
“wherein a first portion of the modeling data corresponds to positive samples and a second portion of the modeling data corresponds to negative samples.” (Li [0064], “In operation 705, processing logic trains a DNN model based on the extracted predicted features as negative examples and the actual features as positive examples.”)
In reference to claim 10.
“10. The one or more processors of claim 1,” (preamble)
Li teaches:
“wherein the one or more neural network models are generated, at least, by generating the modeling data, and updating one or more parameters of the one or more neural network models using the modeling data.” (Li [0052], “For example, data collector 307 collects actual trajectories from perception module 302 and store the collected actual trajectories in persistent storage device 352 as part of actual trajectories 313. Data collector 307 may further collect predicted trajectories from prediction module 303 and store the predicted trajectories in persistent storage device 352 as part of predicted trajectories 314. Actual trajectories 313 and predicted trajectories 314 can be utilized to train a DNN model”)
In reference to claim 14.
“14. The method of claim 13,” (preamble)
Intel and Li teach:
“wherein the one or more neural network models comprise a multi-layer perceptron (MLP) model (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning, such as through one or more convolutional neural networks”, CNNs are a variant of MLP), and the MLP model is generated using data comprising (i) a plurality of predicted states of objects (Li [0064], “FIG. 7 is a flow diagram illustrating a process of training a deep neural network for evaluating predicted trajectories according to one embodiment.”, The predicted state(s) is/are the predicted trajectories used for training the DNN.), and (ii) a plurality of sensor data each corresponding to a respective one of the plurality of predicted states and obtained from a respective plurality of sensors (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning”).”
Claim Rejections - 35 USC § 103 - 12
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Intel in view of Xerox in further view of UATC in further view of UATC in further view of Toyota in further view of 7D in further view of Google in further view of ARM.
In reference to claim 12.
“12. The one or more processors of claim 1,” (preamble)
Intel teaches:
“wherein the one or more processors are comprised in at least one of: a control system for an autonomous or semi-autonomous machine;” (Intel [170], “autonomous vehicles”)
“a perception system for an autonomous or semi-autonomous machine;” (Intel [0177], “A perception engine 238 may be provided in some examples, which may take as inputs various sensor data (e.g., 258) including data, in some instances, from extraneous sources and/or sensor fusion module 236 to perform object recognition and/or tracking of detected objects, among other example functions corresponding to autonomous perception of the environment encountered (or to be encountered) by the vehicle 105.”)
“a system for performing simulation operations;” (Intel [0788], “The sensor data 12104 may be captured from sensors of one or more autonomous vehicles or may be simulated data (e.g., using any of the simulation techniques described herein or other suitable simulation techniques).”)
“a system for performing deep learning operations;” (Intel [0177], “Perception engine 238 may perform object recognition from sensor data inputs using deep learning, such as through one or more convolutional neural networks and other machine learning models 256.”)
“a system implemented using an edge device;” (Intel [170], “edge device”)
“a system implemented using a robot;” (Intel [170], “autonomous vehicles”)
“a system for performing conversational Al operations;” (Intel [0570], “In addition, the autonomous vehicle may prompt the driver for input (e.g., enable a conversation with the driver using a voice recognition software)”)
“a system for generating synthetic data;” (Intel [0439], “In various embodiments of the present disclosure, a system may create synthetic data in order to bolster data sets lacking real data for one or more contexts.”)
“a system incorporating one or more virtual machines (VMs);” (Intel [170], “virtual machines”)
“a system implemented at least partially in a data center;” (Intel [0223], “Accordingly, such systems may generate huge amounts of data for collection and inter-device communication, making scaling and offloading of such amounts of data (e.g., to data centers, cloud- or fog-based services, and other devices an expensive operation.”)
“or a system implemented at least partially using cloud computing resources.” (Intel [170], “cloud-based system”)
Toyota teaches:
“a system for performing digital twin operations;” (Toyota [0012], “multiple instances of the digital data are received over time as part of a feedback loop and the digital twin is recursively updated based on the digital data received in the feedback loop.”)
Motivation to combine Intel, Xerox, UATC, Toyota.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox, UATC and Toyota. Intel, Xerox, UATC discloses a system of object tracking in a multi-sensor autonomous vehicle system. Toyota discloses an application of digital twin in autonomous vehicles. One would be motivated to combine these references because the disclosure of Toyota provides a processing model for the system of Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (F) Known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art.
7D teaches:
“a system for performing light transport simulation;” (7D [0064], “Block S300 can be performed using Monte Carlo-based light transport simulation coupled with simulation of virtual optics and sensors”)
Motivation to combine Intel, Xerox, UATC, Toyota, 7D.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox, UATC, Toyota and 7D. Intel, Xerox, UATC, Toyota discloses a system of object tracking in a multi-sensor autonomous vehicle system. 7D discloses a system of Monte Carlo-based light transport simulation. One would be motivated to combine these references because the disclosure of 7D provides a mechanism to visualize the data collected by the system of Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (F) Known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art.
Google teaches:
“a system for performing collaborative content creation for 3D assets;” (Google [0014], “FIG. 4 is a messaging diagram that illustrates an example technique for collaborative 3D modeling at a pair of client devices communicatively coupled to a collaboration server”)
Motivation to combine Intel, Xerox, UATC, Toyota, 7D, Google.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox, UATC, Toyota, 7D and Google. Intel, Xerox, UATC, Toyota, 7D discloses a system of object tracking in a multi-sensor autonomous vehicle system. Google discloses a system of sharing 3D model data collaboratively. One would be motivated to combine these references because the disclosure of Google provides a mechanism to aggregate and visualize the data collected by the system of Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (F) Known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art.
ARM teaches:
“a system for generating or presenting at least one of virtual reality, augmented reality, or mixed reality content;” (ARM [0010], “FIG. 1, provided for context, shows schematically a system 100 for implementing an image processing pipeline. The system 100 may form part of virtual reality (VR), augmented reality (AR), mixed reality (MR) and/or computer vision (CV) equipment.”)
Motivation to combine Intel, Xerox, UATC, Toyota, 7D, Google, ARM.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine Intel, Xerox, UATC, Toyota, 7D, Google and ARM. Intel, Xerox, UATC, Toyota, 7D, Google discloses a system of object tracking in a multi-sensor autonomous vehicle system. ARM discloses a system for presenting data in augmented, mixed, and virtual reality. One would be motivated to combine these references because the disclosure of 7D provides a mechanism to visualize the data collected by the system of Intel. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (F) Known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art.
Claim Rejections - 35 USC § 102 – 19
Claim 19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by UATC.
In reference to claim 19.
“19. One or more processor comprising: one more circuits“ (preamble)
UATC teaches:
provide one or more control signals to a physical component of a machine to cause the machine to perform one or more operations(UATC, [0082], “…the mobility controller can send one or more control signals to the responsible vehicle control component (e.g., braking control system, steering control system and/or acceleration control system) to execute the instructions and implement the motion plan data”), the one or more control signals generated based at least on an object track corresponding to an object at a time (UATC, [0058], “For example, by more accurately and efficiently associating detected objects with object tracks the disclosed technology can allow for more accurate and efficient operation of an autonomous vehicle's motion planning system which can be used to more create motion paths for the autonomous vehicle and avoid unintentional contact with objects outside the vehicle.”) as determined using one or more association scores computed using one or more neural network model (UATC, [0093], “ The decoder 214 can access the output of the machine-learned association model 212 and perform one or more operations to decode the output of the machine-learned association model and generate the association data 222 which can include the association score 216”)
the one or more association scores computed(UATC, [0129]-[0130], “In some embodiments, the one or more association scores can be based at least in part of the one or more features of the detected object…” where UATC basing their association scores off the features of an a detected object corresponds computing an association score) based at least on: obtaining one or more inputs generated based at least on: sensor data comprising measurements corresponding to the object from a plurality of sensors(UATC, [0096]-[0098], “The tracked objects 302 can include a set of tracked objects that are being tracked over a plurality of time intervals…The detections 304 can be a set of sensor outputs that is associated with the detection of one or more objects in an environment that are detected by one or more sensors…the object descriptor 310 can include input data and/or sensor data that indicate the location, position, velocity, acceleration, and/or physical dimensions of the tracked object 308… the detection descriptor 314 can include input data and/or sensor data, based at least in part on one or more sensor outputs that include information associated with the location, position, velocity, acceleration, and/or physical dimensions associated with the detection 312” where UATC basing their association scores off the features of a detected features with sensor measured inputs of the tracked object features such as location, position, velocity, acceleration, and/or physical dimension over a time interval corresponds to computing an association score based on obtaining one or more inputs generated based on sensor data comprising measurements to the object.), and data representative of one or more values of one or more parameters corresponding to a predicted state of the object at the time(with UATC, [0103] “The object state and uncertainty 324 can include a prediction of the state of an object associated with the detected object 312 (e.g., a location, velocity, physical dimensions, and/or acceleration of a detected object)” where UATC basing their association scores off the features of a detected features with the prediction of the state of an objected associated with the detected object corresponds to computing an association score based on data representative of one or more values of one or more parameters corresponding to a predicted state of the object at the time)
causing processing, using the one or more neural network models, of the one or more inputs(UATC, [0028], “The association computing system can be configured to perform joint association across multiple classifications of objects. In some embodiments, the association computing system can generate association data that indicates whether the detected object is associated with at least one of the one or more object tracks, based at least in part on the input data and/or one or more machine-learned models. For example, the input data can be provided as an input to the one or more machine-learned models that have been configured and/or trained to receive the input and generate an output including the association data”)
Claim Rejections - 35 USC § 103 – 20
Claim 20 are rejected under 35 U.S.C. 103 as being unpatentable over UATC over Xerox
In reference to claim 20.
“20. The one or more processors of claim 19,” (preamble)
Xerox teaches:
“wherein, at each iteration of the one or more neural network models, the one or more neural network models output an association score between each detected object in the sensor data and the object (Xerox [0037], “In other words, the neural network 56 takes the candidate objects—which can be associated with a target object being tracked in a given previous frame and a new or existing object in a current frame—and creates a data association matrix—a number of targets by a number of detections. The neural network 56 generates a probability (“association score”)”, The association score is indicative of an association between the predicted state (i.e., the tracked object state) and each candidate object. Each frame is an iteration.).”
Motivation to combine UATC and Xerox
It would have been obvious to one of ordinary skill in the art before the effective filing date of the present application to combine UATC and Xerox as UATC and Xerox are in a similar field of endeavor of using association scores to track/detect with neural networks across successive time intervals. UATC discloses a system of object tracking in a multi-sensor autonomous vehicle system. Xerox discloses a utilization of the previously computed association score for filtering predicted object tracks. One would be motivated to combine these references because the disclosure of Xerox would provide as both Xerox and UATC are addressing the same problem and Xerox’s method allows UATC’s time-based tracking to be explicitly repetitive. Further, MPEP 2143 sets forth the Supreme Court rationales for obviousness including: (E) Obvious to try – choosing from a finite number of identified, predictable solutions, with a reasonable expectation of success.
Response to Arguments
Applicant's arguments filed 01/02/2026 have been fully considered but they are not persuasive. A breakdown of the arguments can be found below:
101
Applicant appears to argue on pages 8-9 that the measurements from sensors, neural network model processing, updating environment data and generating and providing a control signal to a physical component that cause a machine to change operation should be viewed as a whole and whether the claim integrates any judicial exception into a practical application rather than merely “apply it”. Further, Applicant argues that the specific measuring and processing when combines with a control signal provide to a physical component of the machine integrates into any abstract concept into a practical application.
Examiner respectfully disagrees as current recited the measurements from sensors(“obtain one or more inputs using: one or more values for one or more input parameters corresponding to the predicted state of the object, and sensor data corresponding to the object and including measurements from a plurality of sensors”) are received at a high level of generality and categorized as extra solution activity of obtaining and/or gathering data over a network, see MPEP §2106.05(g).
Similarly, the use of neural networks, updating of data and generation of the control signal(“generate, based at least on one or more neural network model processing the one or more inputs, a score indicative of an association”, “update data corresponding to the environment according to whether the score exceeds an association threshold;” and “generate a control signal based at least on the updated data”) are recited at a high level of generality with little to no details on how the limitations are performed and do not integrate the invention into a practical application.
102/103
Applicant appears to argue on pages 11 appears to argue that the amended language concerning obtaining one or more inputs is not taught by Intel and Xerox.
Examiner has cited to UATC for the amended language concerning obtaining one or more inputs.
Applicant appears to argue on pages 11 appears to argue that UATC is missing the disclosure of the neural network processing of the claimed inputs to generate the claimed score and the combination presupposes an association score.
Examiner respectfully disagrees as UATC does processing with neural networks inputs to generate an association score as described in [0089]-[0102] and Figure 3 using LSTM’s which is considered neural network as well as disclosures throughout the application, such as [0064] citing the operations computing can include neural network and [0092] stating “In some embodiments, the machine-learned association model 212 can include an LSTM model”. It is further noted that one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
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 CHARLES JEFFREY JONES JR whose telephone number is (703)756-1414. The examiner can normally be reached Monday - Friday 8:00 - 5:00 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, Kakali Chaki can be reached at 571-272-3719. 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.
/C.J.J./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
Prosecution Insights