DETAILED ACTION
This non-final action is in response to the request for continued examination (RCE), filed 11 December 2025, and amendment, filed 19 November 2025, both of which were in response to the final action dated 19 September 2025.
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 11 December 2025 has been entered.
Reply to RCE and Amendment
Claims 1-20 are pending. Claims 1, 4, 8, 11 and 15 have been amended.
The examiner acknowledges and accepts the filing of amended paragraph [0108] of specification.
With regard to the 35 U.S.C. 103 rejection of claims 1-20 (pgs. 3-30, Action) applicant’s amendments necessitated additional searching and consideration of new grounds of rejection. Accordingly, the new grounds of rejection under 35 U.S.C. 103 are: claims 1, 4, 5, 8, 11, 12, 15, 17 and 18 in view of Zhao, Shahriar and Bacchus; claims 2, 6, 9, 13 and 16 in view of Zhao, Shahriar, Bacchus and Ide; claims 3, 7, 10 and 14 in view of Zhao Shahriar, Bacchus and Azagirre; and claims 19 and 20 in view of Zhao Shahriar, Bacchus, Ide and Azagirre.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
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 non-obviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 4, 5, 8, 11, 12, 15, 17 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Publication Number 2019/0367021 to Zhao et al. (hereafter Zhao) in view of U.S. Patent Publication Number 2020/0167934 to Bacchus and U.S. Patent Publication Number 2023/0150514 to Shahriar et al. (hereafter Shahriar).
As per claim 1, Zhao discloses [a] method (see at least Zhao, Abstract) comprising:
associating the road user within a vehicle transportation network with mapped lanes of the vehicle transportation network (see at least Zhao, [0117] disclosing that the HD map data 510 is data from a high-definition (i.e., high-precision) map, which can be used by an autonomous vehicle. The HD map data 510 can include accurate information regarding a vehicle transportation network to within a few centimeters. For example, the HD map data 510 can include details regarding road lanes, road dividers, traffic signals, traffic signs, speed limit; [0223] disclosing that A vehicle 1404 is predicted to be moving from the right shoulder of the road (or from the lane to the right of the lane that includes the AV 1402) into the path of the AV along a path 1420; [0272] disclosing with regard to Fig. 19 that The AV 1952 detects a vehicle 1954. That is, the AV 1952 detects an object that is classified as “vehicle.” The AV 1952 can determine (for example, based on map data) that the road includes two lanes (i.e., a lane 1953A and a lane 1953B) <interpreted as within a vehicle transportation network>. As such, the AV 1932 can associate a first hypothesis (e.g., “go straight” corresponding to a path 1958 such that the vehicle 1954 stays in the lane 1953B) and a second hypothesis (e.g., “change to left lane” corresponding to a path 1956 such that the vehicle 1954 moves to the lane 1953A));
determining at least two possible paths of the road user using the mapped lanes (see at least Zhao, [0095] disclosing that AV 302 can include a world modeling module, which can track at least some detected external objects. The world modeling module can predict one or more potential hypotheses (i.e., trajectories, paths, or the like) for each tracked object of at least some of the tracked objects. The AV 302 can include a trajectory planning system (or, simply, a trajectory planner) that can be executed by a processor to generate (considering an initial state, desired actions, and at least some tracked objects with predicted trajectories) a collision-avoiding, law-abiding, comfortable response (e.g., trajectory, path, etc.); [0113] disclosing that Fig. 5 is an example of layers of a trajectory planner 500 for an autonomous vehicle according to implementations of this disclosure. The trajectory planner 500 can be, or can be a part of, the trajectory planner 408 of Fig. 4. The trajectory planner 500 can receive drive goals 501. The trajectory planner 500 can receive a sequence of drive goals 501 that can represent, for example, a series of lane selections and speed limits that connect a first location to a second location. For example, a drive goal of the drive goals 501 can be “starting at location x, travel on a lane having a certain identifier (e.g., lane with an identifier that is equal to A123) while respecting speed limit y”. The trajectory planner 500 can be used to generate a trajectory that accomplishes the sequence of the drive goals 501); ... (1) ... ; ... (2) ... ;
generating, for each possible path of the at least two possible paths, a respective first probability using the kinematic trajectory of the road user (see at least Zhao, [0106] disclosing that the world model module 402 fuses sensor information, tracks objects, maintains lists of hypotheses for at least some of the dynamic objects (e.g., an object A might be going straight, turning right, or turning left), creates and maintains predicted trajectories for each hypothesis, and maintains likelihood estimates of each hypothesis (e.g., object A is going straight with probability 90% considering the object pose/velocity and the trajectory poses/velocities) <interpreted as a first probability using the kinematic trajectory>), ... (3) ... , ... (4) ... ; ... (5) ... ; ... (6) ... , ... (6) ... ; ... (7) ... ; ... (8) ... , ... (9) ... ;
determining, by a control system of a vehicle, a control action for the vehicle using the kinematic path and the second probability (see at least Zhao, [0109] disclosing that The road-level plan determined by the route planning module 404 and the objects (and corresponding state information) maintained by the world model module 402 can be used by the decision-making module 406 to determine discrete-level decisions along the road-level plan. An example of decisions included in the discrete-level decisions is illustrated with respect to discrete decisions 414. An example of discrete-level decisions may include: stop at the interaction between road A and road B, move forward slowly, accelerate to a certain speed limit, merge onto the rightmost lane, etc.; [0100]); and
autonomously performing by the control system of the vehicle, the control action (see at least Zhao, [0060]; [0074] disclosing that the trajectory controller outputs signals operable to control the vehicle 100 such that the vehicle 100 follows the trajectory that is determined by the trajectory controller. For example, the output of the trajectory controller can be an optimized trajectory that may be supplied to the powertrain 104, the wheels 132/134/136/138, or both. The optimized trajectory can be a control input, such as a set of steering angles, with each steering angle corresponding to a point in time or a position. The optimized trajectory can be one or more paths, lines, curves, or a combination thereof.; [0075]). The difference between the claimed invention and Zhao, is that Zhao does not explicitly teach the following limitation taught in Bacchus, a comparable method where it is known to:
(1) determining a kinematic trajectory of the road user (see at least Bacchus, abstract, [0060] disclosing that the target path enumeration module 840 associates the target object with a tracked object. The lane representation module 850 determines the lane assignment and dynamic properties of the tracked object. The tracked objects have several splines represented by nearby target trajectories. The multiple model (MM) filter 860 applies Markov chain representing model transition probabilities and Model probabilities tracking applications to the tracked object);
(5) determining an updated kinematic trajectory of the road user (see at least Bacchus, [0088] disclosing with regard to Fig. 15, that at step 1510, a determination is made if the hypotheses already exists for the object ID? (i.e. identified object); if not, the flow continues to step 1520 to find candidate paths about or around the object position. For example, the object can have multiple trajectories of directions and corresponding paths. The perception system utilizes different models for each possible lane constrained target path: such as a straight path, U-turn, left turn, etc. At step 1530, the perception system fits splines for each path. The track objects can have several splines representing nearby potential candidate trajectories. The tracks objects have a vector of Kalman filters for each lane constrained hypothesis (equal to the number of splines) as wells as for the stationary hypotheses (i.e. based on data from the stationary model). The trajectories are vectors of potential lane level trajectories within a current horizon (e.g. 100 m) that a target object may follow (in ground coordinates). At step 1540, the perception system creates hypotheses and initializes hypothesis probabilities. The hypothesis probability is determined at least based on results from filtering models and from results from classifying features related to the object track for the target object. At step 1550, the perception system updates the Kalman filter with object data. The lane constrained models track the object by object vectors using Kalman filters based on each lane constrained hypothesis (equal to the number of splines) as wells as stationary hypotheses, and the unconstrained models track object properties such as acceleration and velocity. An output is generated based on a list of hypothesis with certain checks performed to determine which hypotheses are feasible based on the sensor fusion and maplets (i.e. mapping data). splines which have no corresponding hypothesis are used to create new hypotheses. Stationary hypotheses are updated directly since the stationary hypotheses do not have splines. At 1560, in the alternative, if the hypotheses at step 510 already exists for the object ID, the perception system simply updates paths using the associated hypotheses. At step 1570, after the hypotheses are determined, the features associated with the objects are calculated. The feature computation generates features for classification by the classification models; [0089] disclosing that at step 1575, the perception system evaluates the likelihood of features using classification models. For example, the path constrained model, the unconstrained model (i.e. constant velocity, acceleration etc. models), and the stationary model (i.e. where zero speed is assumed for the tracked object) send path and object data to the Kalman filters. The track states communicate with the Kalman filters and send track state data to the hypothesis probability update at step 1580. Also, the hypothesis probability update at step 1580 receives data from the classification models because each hypothesis has a corresponding Naïve Bayes model (i.e. classification model) with a likelihood L.sub.i(x). Next at step 1585, delete hypotheses with small probabilities);
(8) generating a second probability for the kinematic path (see at least Bacchus, [0088]; [0089] disclosing that at step 1575, the perception system evaluates the likelihood of features using classification models. For example, the path constrained model, the unconstrained model (i.e. constant velocity, acceleration etc. models), and the stationary model (i.e. where zero speed is assumed for the tracked object) send path and object data to the Kalman filters. The track states communicate with the Kalman filters and send track state data to the hypothesis probability update at step 1580. Also, the hypothesis probability update at step 1580 receives data from the classification models because each hypothesis has a corresponding Naïve Bayes model (i.e. classification model) with a likelihood L.sub.i(x). Next at step 1585, delete hypotheses with small probabilities; [0089]).
The difference between the claimed invention and Zhao, as modified by Bacchus, is that neither Zhao nor Bacchus explicitly teaches the following limitation taught in Shahriar, a comparable method where it is known to:
(2) wherein the kinematic trajectory is determined based on a velocity, a heading, and a yaw rate of the road user (see at least Shahriar, [0054] disclosing that with regard to eq. 12, where δ is a vehicle from road wheel angle, v.sub.y is vehicle lateral velocity, v.sub.x is longitudinal velocity, ω.sub.z, is yaw rate, l.sub.r is distance of CG to rear axle of the vehicle, l.sub.fds the distance of CG to front axle of the vehicle, C.sub.1 is relative heading of host vehicle to the lane marking, C.sub.0 is lateral offset of host vehicle to the desired trajectory, ρ.sub.v is estimated vehicle curvature, θ.sub.v, road estimated bank angle, ϕ.sub.v is estimated road grade angle, α.sub.y,k is lateral acceleration, ψ.sub.k is estimated vehicle heading, C.sub.f is front tire cornering stiffness, C.sub.r is rear tire cornering stiffness, m is vehicle's mass, I.sub.z is vehicle's moment of inertia, α.sub.1, α.sub.2>0 are design parameter for weighted average (α.sub.1+α.sub.2=1));
(3) generating, for each possible path of the at least two possible paths, a respective first probability, based on the mapped lanes (see at least Shahriar, [0059] disclosing that the computing device 205 can quantify an error between the map data, the sensor data, and/or the camera data over a predefined period of time, i.e., steady state, by using suitable models of the rationalization value R and its rate of change R; [0060] disclosing that the rationalization value R can be used to modify one or more vehicle 20 operations. In some instances, the computing device 205 may de-weight camera data received from the cameras 140 when the rationalization value R exceeds a predetermined rationalization threshold. .... The computing device 205 can also evaluate a localized lane likelihood based on the rationalization value with respect to identified lane line and correct for lane level localization. The computing device 205 can also adapt an autonomous or a semiautonomous feature availability or control based on an assessment of the rationalization error over the prediction horizon),
(4) wherein the respective first probability represents how likely the road user is to follow the each possible path given the kinematic trajectory of the road user (see at least Shahriar, [0060]);
(6) generating, in response to determining, based on the updated kinematic trajectory that the road user deviated from the mapped lanes (see at least Shahriar, [0060]),
(7) a kinematic path is not associated with the mapped lanes (see at least Shahriar, [0060]);
(9) wherein the second probability represents how likely the road the road user is to follow each possible path (see at least Shahriar, [0059]; [0060]).
Zhao, Bacchus and Shahriar are analogous art to claim 1 because they are in the same field of controlling a vehicle using map and kinematic prediction. Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]).
Therefore, it would have been prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as disclosed in Zhao, to provide the benefit of (1) determining a kinematic trajectory of the road user, (5) determining an updated kinematic trajectory of the road user, and (8) generating, for each possible path of the at least two possible paths, a second probability using the updated kinematic trajectory of the road user, as disclosed in Bacchus, and (3) generating, for each possible path of the at least two possible paths, a respective first probability based on the mapped lanes, using the kinematic trajectory of the road user, (4) having the respective first probability represent how likely the road user is to follow the each possible path given the kinematic trajectory of the road user, (6) generating, based on the updated kinematic trajectory that the road user deviated from the mapped lanes, (7) a kinematic path is not associated with the mapped lanes, and (9) having the second probability represent how likely the road user is to follow each possible path, as disclosed in Shahriar, with a reasonable expectation of success. The results would have been predicable to one of ordinary skill.
As per claim 4, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 1, as shown above. Zhao further discloses the following limitation:
wherein the kinematic trajectory of the road user is determined using a first heading and a first angle of the road user measured at a first time in relation to a second heading and a second angle of the road user measured at a second time (see at least Zhao, [0289] disclosing that the prediction of the future object states can be provided for a specified end time. For example, the process 2000 can, for each hypothesis, predict a respective trajectory for the object associated with the hypothesis and predict states of the object at discrete time points along the trajectory up to the specified end time. A predicted state includes predicted locations, predicted velocities, predicted headings, etc. However, for ease of explanation, predicted locations are described. For example, the specified end time may be 6 seconds and the process 2000 can predict locations of the object at 0.5 seconds increments up to 6 seconds. As such, twelve locations of the object are predicted. In an example, a location can be defined by the (x, y) coordinates of the object. The location can be relative to the current location of the AV).
As per claim 5, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 1, as shown above. Zhao further discloses the following limitation:
wherein the at least two possible paths are determined based on defined traffic rules and lane priority rules for the mapped lanes (see at least Zhao, [0044] disclosing that The response(s) can be predicted because traversing a vehicle transportation network is governed by rules of the road (e.g., a vehicle turning left must yield to oncoming traffic, a vehicle must drive between a lane's markings), by social conventions (e.g., at a stop sign, the driver on the right is yielded to), and physical limitations (e.g., a stationary object does not instantaneously move laterally into a vehicle's right of way). See also Fig. 3; [0398]).
As per claim 8, similar to claim 1, Zhao discloses [a]n apparatus (see at least Zhao, abstract), comprising:
a memory (see at least Zhao, [0064] disclosing that the user interface 124 and the processor 120 may be integrated in a first physical unit, and the memory 122 may be integrated in a second physical unit. Although not shown in FIG. 1, the controller 114 may include a power source, such as a battery. Although shown as separate elements, the location unit 116, the electronic communication unit 118, the processor 120, the memory 122, the user interface 124, the sensor 126, the electronic communication interface 128, or any combination thereof can be integrated in one or more electronic units, circuits, or chips); and
a processor configured to execute instructions stored in the memory (see at least Zhao, [0067] disclosing that the memory 122 may include any tangible non-transitory computer-usable or computer-readable medium capable of, for example, containing, storing, communicating, or transporting machine-readable instructions or any information associated therewith, for use by or in connection with the processor 120) to:
associate a road user within a vehicle transportation network with mapped lanes of the vehicle transportation network (see at least Zhao, [0117]; [0223]);
determine at least two possible paths of the road user using the mapped lanes (see at least Zhao, [0113]); ... (1) ... ; ... (2) ... ;
generating, for each possible path of the at least two possible paths, a first probability using the kinematic trajectory of the road user (see at least Zhao, [0106]), ... (3) ... , ... (4) ... ; ... (5) ... ; ... (6) ... , ... (6) ... ; ... (7) ... ; ... (8) ... , ... (9) ... ;
determine, by a control system of a vehicle, a control action for the vehicle using the kinematic path and the second probability (see at least Zhao, [0109]; [0100]); and
autonomously perform by the control system of the vehicle, the control action (see at least Zhao, [0060]; [0074]; [0075]). The difference between the claimed invention and Zhao, is that Zhao does not explicitly teach the following limitation taught in Bacchus, a comparable method where it is known to:
(1) determine a kinematic trajectory of the road user (see at least Bacchus, abstract, [0060]);
(5) determine an updated kinematic trajectory of the road user (see at least Bacchus, [0088]; [0089]);
(8) generate, a second probability for the kinematic path (see at least Bacchus, [0088]; [0089]).
The difference between the claimed invention and Zhao, as modified by Bacchus, is that neither Zhao nor Bacchus explicitly teaches the following limitation taught in Shahriar, a comparable method where it is known to:
(2) wherein the kinematic trajectory is determined based on a velocity, a heading, and a yaw rate of the road user (see at least Shahriar, [0054]);
(3) generate, for each possible path of the at least two possible paths, a respective first probability, based on the mapped lanes, (see at least Shahriar, [0059]; [0060]),
(4) wherein the respective first probability represents how likely the road user is to follow the each possible path given the kinematic trajectory of the road user (see at least Shahriar, [0060]);
(6) generate, in response to determining, based on the updated kinematic trajectory that the road user deviated from the mapped lanes (see at least Shahriar, [0060]),
(7) a kinematic path is not associated with the mapped lanes (see at least Shahriar, [0060]);
(9) wherein the second probability represents how likely the road the road user is to follow each possible path (see at least Shahriar, [0059]; [0060]).
Zhao, Bacchus and Shahriar are analogous art to claim 8 because they are in the same field of controlling a vehicle using map and kinematic prediction. Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]).
Therefore, it would have been prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as disclosed in Zhao, to provide the benefit of (1) determining a kinematic trajectory of the road user, (5) determining an updated kinematic trajectory of the road user, and (8) generating, for each possible path of the at least two possible paths, a second probability using the updated kinematic trajectory of the road user, as disclosed in Bacchus, and (3) generating, for each possible path of the at least two possible paths, a respective first probability based on the mapped lanes, using the kinematic trajectory of the road user, (4) having the respective first probability represent how likely the road user is to follow the each possible path given the kinematic trajectory of the road user, (6) generating, based on the updated kinematic trajectory that the road user deviated from the mapped lanes, (7) a kinematic path is not associated with the mapped lanes, and (9) having the second probability represent how likely the road user is to follow each possible path, as disclosed in Shahriar, with a reasonable expectation of success. The results would have been predicable to one of ordinary skill.
As per claim 11, similar to claim 4, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 8, as shown above. Zhao further discloses the following limitation:
wherein the kinematic trajectory of the road user is determined using a first heading and a first angle of the road user measured at a first time with respect to a second heading and a second angle of the road user measured at a second time (see at least Zhao, [0289]).
As per claim 12, similar to claim 5, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 1, as shown above. Zhao further discloses the following limitation:
wherein the at least one two possible paths are determined based on defined traffic rules and lane priority rules for the mapped lanes (see at least Zhao, [0044]; See also Fig. 3; [0398]).
As per claim 15, similar to claims 1 and 8, Zhao discloses [a] non-transitory computer-readable medium storing instructions operable to cause one or more processors to perform operations (see at least Zhao, [0067]) comprising:
associating a road user within a vehicle transportation network with mapped lanes of the vehicle transportation network (see at least Zhao, [0117]; [0223]; [0272]);
determining at least two possible paths of the road user predicted using the mapped lanes (see at least Zhao, [0095]; [0113]); ... (1) ... ; ... (2) ... ;
generating, for each possible path of the at least two possible paths, a respective first probability using the kinematic trajectory of the road user (see at least Zhao, [0106]), ... (3) ... , ... (4) ... ; ... (5) ... ; ... (6) ... , ... (6) ... ; ... (7) ... ; ... (8) ... , ... (9) ... ;
determining, by a control system of a vehicle, a control action for the vehicle using the kinematic path and the second probability (see at least Zhao, [0109]; [0100]); and
autonomously performing by the control system of the vehicle, the control action (see at least Zhao, [0060]; [0074]). The difference between the claimed invention and Zhao, is that Zhao does not explicitly teach the following limitation taught in Bacchus, a comparable method where it is known to:
(1) determining a kinematic trajectory of the road user (see at least Bacchus, abstract, [0060]);
(5) determining an updated kinematic trajectory of the road user (see at least Bacchus, [0088]; [0089]);
(8) generating a second probability for the kinematic path (see at least Bacchus, [0088]; [0089]).
The difference between the claimed invention and Zhao, as modified by Bacchus, is that neither Zhao nor Bacchus explicitly teaches the following limitation taught in Shahriar, a comparable method where it is known to:
(2) wherein the kinematic trajectory is determined based on a velocity, a heading, and a yaw rate of the road user (see at least Shahriar, [0054]);
(3) generating, for each possible path of the at least two possible paths, a respective first probability, based on the mapped lanes (see at least Shahriar, [0059]; [0060]),
(4) wherein the respective first probability represents how likely the road user is to follow the each possible path given the kinematic trajectory of the road user (see at least Shahriar, [0060]);
(6) generating, in response to determining, based on the updated kinematic trajectory that the road user deviated from the mapped lanes (see at least Shahriar, [0060]),
(7) a kinematic path is not associated with the mapped lanes (see at least Shahriar, [0060]);
(9) wherein the second probability represents how likely the road the road user is to follow each possible path (see at least Shahriar, [0059]; [0060]).
Zhao, Bacchus and Shahriar are analogous art to claim 15 because they are in the same field of controlling a vehicle using map and kinematic prediction. Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]).
Therefore, it would have been prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as disclosed in Zhao, to provide the benefit of (1) determining a kinematic trajectory of the road user, (5) determining an updated kinematic trajectory of the road user, and (8) generating, for each possible path of the at least two possible paths, a second probability using the updated kinematic trajectory of the road user, as disclosed in Bacchus, and (3) generating, for each possible path of the at least two possible paths, a respective first probability based on the mapped lanes, using the kinematic trajectory of the road user, (4) having the respective first probability represent how likely the road user is to follow the each possible path given the kinematic trajectory of the road user, (6) generating, based on the updated kinematic trajectory that the road user deviated from the mapped lanes, (7) a kinematic path is not associated with the mapped lanes, and (9) having the second probability represent how likely the road user is to follow each possible path, as disclosed in Shahriar, with a reasonable expectation of success. The results would have been predicable to one of ordinary skill.
As per claim 17, similar to claims 4 and 11, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 15, as shown above. Zhao further discloses the following limitation:
wherein the kinematic trajectory of the road user is determined using a first heading and a first angle of the road user measured at a first time in relation to a second heading and a second angle of the road user measured at a second time (see at least Zhao, [0289]).
As per claim 18, similar to claims 5 and 12, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 15, as shown above. Zhao further discloses the following limitation:
wherein the at least two possible paths are determined based on defined traffic rules and lane priority rules for the mapped lanes (see at least Zhao, [0044] ; See also Fig. 3; [0398]).
Claims 2, 6, 9, 13 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Zhao, Bacchus and Shahriar as applied to claims 1, 8 and 15 above, and further in view of 2013/0197890 to Ide et al. (hereafter Ide).
As per claim 2, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 1, as shown above. Zhao discloses the following limitation:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is 0 (see at least Zhao, [0268] disclosing that with respect to Fig. 19, that the AV 1912 can associate a likelihood with each of the paths 1918, 1920. In an example, a likelihood of 0.2 can be assigned to the path 1918 and a likelihood of 0.8 can be assigned to the path 1920. As such, there is a 20% chance that the oncoming dynamic object 1914 <interpreted as the road user> will continue straight forward and stop and/or slow down before reaching the parked vehicle 1916; and an 80% chance that the oncoming dynamic object 1914 will go around the parked vehicle 1916 <it would be obvious to one of skill in the art that when the path and the updated paths do not match the probability would be 0>) ... . But, neither Zhao, Bacchus nor Shahriar explicitly disclose the following limitation what one of ordinary skill in the art would apply to the calculation of the kinematic prediction:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is 0 when the second probability corresponding to another path of the at least two possible paths is greater than a threshold (see at least Ide, [0359] disclosing that the known/unknown determining unit 226 subtracts a predetermined offset (threshold) from the logarithmic likelihood log L(t)', divides this result by a predetermined value <interpreted as the threshold value>, and inputs this result to a tan h function, thereby saturating the logarithmic likelihood log L(t)'. According to the processing in steps S41 and S42, the observation likelihood L(t)' is converted into a parameter that takes a range of -1 to 1).
Zhao, Bacchus, Shahriar and Ide are analogous art to claim 2 because they relate to the field of controlling a vehicle using map and kinematic prediction. Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]). Ide relates to a data processing method which enable prediction to be performed even when there is a gap in the data of the current location obtained in real time (see at least Ide, [0001]).
Therefore it would be prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as discloses in Zhao as modified by Bacchus, and further modified by, to provide the benefit having the second probability corresponding to the path based on the updated kinematic trajectory is 0 when the second probability corresponding to another path of the at least two possible paths is greater than a threshold, as disclosed in Ide, with a reasonable expectation of success. Doing so would provide the benefit of improving the real time navigation to a destination (see at least Ide, [0009]; [0010]).
As per claim 6, the combination of Zhao, Bacchus, Shahriar and Ide disclose all of the limitations of claim 2, as shown above. Ide further discloses the following limitation:
wherein the threshold value is a number between 0 and 1 (see at least Ide, [0310] disclosing that The transition probability table is configured of, as illustrated in FIG. 24, a table with (M+1) row by (M+1) columns. With the transition probability table, the state transition probability a.sub.ij between the states of the existing model of the first row and first column to the M-th row and M-th column is multiplied by (1-eps). Also, the eps is set to each element of the (M+1)-th column of the transition probability table excluding the lowest (M+1)-th row, and the eps is set to each element of the (M+1)-th row excluding the lowest (M+1)-th row. The eps mentioned here is, for example, around 1.0E-8, a sufficiently smaller predetermined value than 1 <interpreted as the threshold value>, and is lower than any of the transition probabilities between state nodes of the existing model;[0359]; [0362]).
As per claim 9, similar to claim 2, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 8, as shown above. Zhao discloses the following limitation:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is 0 (see at least Zhao, [0268]) ... . But, neither Zhao, Bacchus nor Shahriar explicitly disclose the following limitation what one of ordinary skill in the art would apply to the calculation of the kinematic prediction:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is 0 when the second probability corresponding to another path of the at least two possible paths is greater than a threshold (see at least Ide, [0359]).
Zhao, Bacchus, Shahriar and Ide are analogous art to claim 9 because they relate to the field of controlling a vehicle using map and kinematic prediction. Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]). Ide relates to a data processing method which enable prediction to be performed even when there is a gap in the data of the current location obtained in real time (see at least Ide, [0001]).
Therefore it would be prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as discloses in Zhao as modified by Bacchus, and further modified by Shahriar, to provide the benefit having the second probability corresponding to the path based on the updated kinematic trajectory is 0 when the second probability corresponding to another path of the at least two possible paths is greater than a threshold, as disclosed in Ide, with a reasonable expectation of success. Doing so would provide the benefit of improving the real time navigation to a destination (see at least Ide, [0009]; [0010]).
As per claim 13, similar to claim 6, the combination of Zhao, Bacchus, Shahriar and Ide disclose all of the limitations of claim 9, as shown above. Ide further discloses the following limitation:
wherein the threshold value is a number between 0 and 1 (see at least Ide, [0310]; [0359]; [0362]).
As per claim 16, similar to claims 2 and 9, the combination of Zhao, Bacchus and Shahriar discloses all of the limitations of claim 8, as shown above. Zhao discloses the following limitation:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is 0 (see at least Zhao, [0268]) ... . But, neither Zhao, Bacchus nor Shahriar explicitly disclose the following limitation what one of ordinary skill in the art would apply to the calculation of the kinematic prediction:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is 0 when the second probability corresponding to another path of the at least two possible paths is greater than a threshold (see at least Ide, [0359]).
Zhao, Bacchus, Shahriar and Ide are analogous art to claim 16 because they relate to the field of controlling a vehicle using map and kinematic prediction. Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]). Ide relates to a data processing method which enable prediction to be performed even when there is a gap in the data of the current location obtained in real time (see at least Ide, [0001]).
Therefore it would be prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as discloses in Zhao as modified by Bacchus and further modified by Shahriar, to provide the benefit having the second probability corresponding to the path based on the updated kinematic trajectory is 0 when the second probability corresponding to another path of the at least two possible paths is greater than a threshold, as disclosed in Ide, with a reasonable expectation of success. Doing so would provide the benefit of improving the real time navigation to a destination (see at least Ide, [0009]; [0010]).
Claims 3, 7, 10 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Zhao, Bacchus and Shahriar as applied to claims 1, 8 and 15 above, and further in view of U.S. Patent Publication Number 2022/0044570 to Azagirre Lekuona et al. (hereafter Azagirre).
As per claim 3, the combination of Zhao, Bacchus and Shahriar disclose all of the limitations of claim 1, as shown above. But, neither Zhao, Bacchus nor Shahriar explicitly teach the following limitation taught in Azagirre:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is multiplied by a smoothing factor (see at least Azagirre, [0112] the provider dispatch control system 106 can penalize the squared difference between a multi-outcome transportation-value metric at a time and a multi-outcome transportation-value metric at an incremental time from the time (e.g., the next hour) by applying the time smoothing value (e.g., multiplying by a fractional value). For example, the provider dispatch control system 106 can penalize the squared difference between a multi-outcome transportation-value metric at a time and a multi-outcome transportation-value metric at an incremental time from the time (e.g., the next hour) by applying a time smoothing value (e.g., λ.sub.T=0.1) in the following equation <shown after this paragraph, not reproduced>).
Zhao, Bacchus, Shahriar and Azagirre are analogous art to claim 3 because they are in the same filed of same field of controlling a vehicle using map and kinematic prediction. Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]). Azagirre relates to modeling multi-outcome transportation-value metrics that account for spatio-temporal trajectories across locations, times and other contextual features, and then utilize computer networks to dispatch provider devices to locations based on the multi-outcome transportation-value metrics (see at least Azagirre, Abstract).
Therefore it would be prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as discloses in Zhao as modified by Bacchus, and further modified by Shahriar, to provide the benefit having the probability corresponding to the path be multiplied by a smoothing factor, as disclosed in Azagirre, with a reasonable expectation of success. Doing so would provide the benefit of increasing the accuracy of the path determination (see at least Azagirre, [0004]).
As per claim 7, the combination of Zhao, Bacchus, Shahriar and Azagirre disclose all of the limitations of claim 3, as shown above. Azagirre further disclose the following limitation:
wherein the smoothing factor is a number between 0 and 1 (see at least Azagirre, [0112] <fractional value is interpreted as a factor between 0 and 1>).
As per claim 10, similar to claim 3, the combination of Zhao, Bacchus and Shahriar disclose all of the limitations of claim 8, as shown above. But, neither Zhao, Bacchus nor Shahriar explicitly teach the following limitation taught in Azagirre:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is multiplied by a smoothing factor (see at least Azagirre, [0112]).
Zhao, Bacchus, Shahriar and Azagirre are analogous art to claim 10 because they are in the same filed of same field of controlling a vehicle using map and kinematic prediction. Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]). Azagirre relates to modeling multi-outcome transportation-value metrics that account for spatio-temporal trajectories across locations, times and other contextual features, and then utilize computer networks to dispatch provider devices to locations based on the multi-outcome transportation-value metrics (see at least Azagirre, Abstract).
Therefore it would be prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as discloses in Zhao as modified by Bacchus and further modified by Shahriar, to provide the benefit having the probability corresponding to the path be multiplied by a smoothing factor, as disclosed in Azagirre, with a reasonable expectation of success. Doing so would provide the benefit of increasing the accuracy of the path determination (see at least Azagirre, [0004]).
As per claim 14, similar to claim 7, the combination of Zhao, Bacchus, Shahriar and Azagirre disclose all of the limitations of claim 10, as shown above. Azagirre further disclose the following limitation:
wherein the smoothing factor is a number between 0 and 1 (see at least Azagirre, [0112] <fractional value is interpreted as a factor between 0 and 1>).
Claims 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhao, Bacchus, Shahriar and Azagirre as applied to claim 16 above, and further in view of Ide.
As per claim 19, similar to claims 3 and 10, the combination of Zhao, Bacchus, Shahriar and Ide discloses all of the limitations of claim 16, as shown above. But, neither Zhao, Bacchus, Shahriar nor Ide explicitly teach the following limitation taught in Azagirre:
wherein the second probability corresponding to the path based on the updated kinematic trajectory is multiplied by a smoothing factor (similar to claim 3, see at least Azagirre, [0112]).
Zhao, Bacchus, Shahriar, Ide and Azagirre are analogous art to claim 19 because they are in the same filed of same field of controlling a vehicle using map and kinematic prediction. Bacchus relates to systems and methods for object tracking, lane-assignment and classification to improve a perception model to track objects (see at least Bacchus, [0001]). Zhao relates to methods for object tracking for autonomous vehicles including providing a lane following trajectory (see at least Zhao, Abstract, [0002]). Shahriar relates to systems and methods for determining a rationalization value that represents a deviation in sensor data and corresponding map data (see at least Shahriar, [0001]). Ide relates to a data processing method which enable prediction to be performed even when there is a gap in the data of the current location obtained in real time (see at least Ide, [0001]). Azagirre relates to modeling multi-outcome transportation-value metrics that account for spatio-temporal trajectories across locations, times and other contextual features, and then utilize computer networks to dispatch provider devices to locations based on the multi-outcome transportation-value metrics (see at least Azagirre, Abstract).
Therefore it would be prima facie obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method, as discloses in Zhao as modified by Shahriar, Bacchus, and as further modified by Ide, to provide the benefit having the probability corresponding to the path be multiplied by a smoothing factor, as disclosed in Azagirre, with a reasonable expectation of success. Doing so would provide the benefit of increasing the accuracy of the path determination (see at least Azagirre, [0004]).
As per claim 20, similar to claims 6, 7 and 11, the combination of Zhao, Bacchus, Shahriar, Ide and Azagirre discloses all of the limitations of claim 19, as shown above. Ide further discloses the following limitation:
wherein the threshold value is a first number between 0 and 1 (similar to claim 6, see at least Ide, [0310];[0359]; [0362]) ... . And, Azagirre further disclose the following limitation:
.. the smoothing factor is a second number between 0 and 1 (similar to claim 7, see at least Azagirre, [0112] ).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: U.S. Patent Publication Number 2022/0101155 to Beaudoin et al. (hereafter Beaudoin) at [0012] disclosing that the estimated probability for a particular trajectory template represents the probability that an agent will follow the particular trajectory template; and U.S. Patent Publication Number 2024/0132112 to Afshar et al. (hereafter Afshar) at [0114] disclosing respective probabilities; [0138] disclosing a loss function is defined as a smooth l1 losses of the longitudinal and lateral components.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PATRICK M. BRADY III whose telephone number is (571)272-7458. The examiner can normally be reached Monday - Friday 7:00 am - 4;30 pm.
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, Erin Bishop can be reached at 571-270-3713. 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.
PATRICK M. BRADY III
Examiner
Art Unit 3665
/PATRICK M BRADY/Examiner, Art Unit 3665
/Erin D Bishop/Supervisory Patent Examiner, Art Unit 3665