DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Introduction
This is a response to applicant’s submissions filed on December 19, 2025. Claims 1-2, 4-15, 17-18, 20-22, and 24 are pending.
Examiner' s Note
Examiner has cited particular paragraphs / columns and line numbers or figures in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, in preparing the responses, to fully consider the references in their entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. Applicant is reminded that the Examiner is entitled to give the broadest reasonable interpretation to the language of the claims. Furthermore, the Examiner is not limited to Applicants' definition which is not specifically set forth in the disclosure.
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 December 19, 2025 has been entered.
Response to Arguments
All of applicants arguments have been considered.
Applicant’s argument that paragraph 0050 of the specification details using sensor data from a current and previous instance (Applicant’s Response, pgs. 13-14) is persuasive. The rejection under 35 U.S.C. 112(a) of claim 8 is withdrawn.
It is noted that the rejection under 35 U.S.C. 112(b) of claim 8 is withdrawn as paragraph 0050 of the specification details performing path smoothing using the previous path with a current path to create a new smoothed path for navigation.
Regarding applicant’s argument that Jafari Tafti and Towal do not teach or suggest the amendments made to claim 1, 9 and 18 (Applicant’s Response, pgs. 16-17), the examiner respectfully disagrees. Towal teaches inputting training images into the DNN to produce a predicted path ([0116]). This predicted path is then comparted to the annotated paths, which is part of the ground truth data ([0113]), using a loss function to create parameters that can then be used to update the DNN ([0116]).
Specification
Amendments to the specification were received on December 19, 2025.
The disclosure is objected to because of the following informalities:
In paragraph 0030, it is unclear how one would use an iterative least square fitting algorithm to convert geometries to locations of points associated with paths as a least square fitting algorithm is used to plot a line based on points.
Appropriate correction is required.
Claim Objections
Claim 24 is objected to because of the following informalities:
In claim 24, lines 2-3, “the one or more fitting algorithms” should read “one or more fitting algorithms”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 24 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention.
In claim 24, lines 2-5, the limitation “converting, using the one or more fitting algorithms, the one or more polylines as represented by the ground truth data to the ground truth Bezier points associated with the one or more second paths" is not detailed within the specification. Paragraph 0030 states that the second ground truth data may be generated by converting the geometries represented by the first ground truth data using iterative least square fitting. One of ordinary skill would not be able to use a fitting algorithm to convert the polylines to Bezier points using a fitting algorithm as a fitting algorithm is used to plot a line based on points.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-2, 4-8, and 21-22 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In claim 1, line 16 the limitation "the one or more Bezier curves" renders the claim indefinite because it lacks antecedent basis and it is unclear if it is referring to the one or more second Bezier curves previously recited (claim 1, lines 13-14) or new Bezier curves.
Claims 2, 4-8, and 21-22 are also rejected as being dependent upon a rejected base claim as they do not clear the deficiencies of the claims from which they depend.
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.
Claims 1, 4, 7, 9, 11, 14-15, 17-18, and 20-22 are rejected under 35 U.S.C. 103 as being unpatentable over Jafari Tafti (US 2018/0348767) in view of Towal (US 2019/0384304).
Regarding claim 1, Jafari Tafti discloses a method comprising:
generating, based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least one of Bezier points associated with a first path or a first Bezier curve associated with the first path (Jafari Tafti, [0071] regarding the trajectory planning system generating a plurality of waypoints, [0071] regarding the trajectory refining system interpolating between the waypoints to generate a spatial path using piecewise Bezier curves, & [0063] regarding the trajectory planner receiving sensor fusion data); and
causing, based at least on the first output, the machine to navigate along at least a portion of the first path within the environment (Jafari Tafti, [0073] regarding the revised trajectory which is composed of the spatial path being provided to the longitudinal and lateral controller to use in driving the host vehicle).
Jafari Tafti does not disclose generating, by one or more machine learning and based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least one of Bezier points associated with a first path or a first Bezier curve associated with the first path,
wherein the one or more machine learning models are trained, at least, by:
determining, using the one or more machine learning models and based at least on training sensor data, one or more second outputs indicating one or more second Bezier curves associated with one or more second paths;
determining one or more losses based at least on one or more predicted polylines associated with the one or more Bezier curves and one or more ground truth polylines associated with the one or more second paths; and
updating the one or more machine learning models based at least on the one or more losses.
Towal teaches using a machine learning model to generate path geometries ([0034]),
wherein the one or more machine learning models are trained, at least by:
inputting training images into the DNN ([0116]);
determining one or more losses based at least on one or more predicted polylines associated with the one or more Bezier curves and one or more ground truth polylines associated with the one or more second paths (Towal, [0116] regarding using one or more loss functions to compute the accuracy of the DNN's predicted paths with the annotated paths); and
updating the one or more machine learning models based at least on the one or more losses (Towal, [0116] regarding updating the parameters of the DNN until the accuracy reaches an optimal or acceptable level).
Jafari Tafti and Towal are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti to incorporate using a machine learning model to generate a vehicle trajectory, as disclosed by Towal, with a reasonable expectation of success because doing so would yield the predictable result of creating more accurate trajectories efficiently.
Jafari Tafti, as modified, teaches generating, by one or more machine learning models and based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least one of Bezier points associated with a first path or a first Bezier curve associated with the first path,
wherein the one or more machine learning models are trained, at least, by:
determining, using the one or more machine learning models and based at least on training sensor data, one or more second outputs indicating one or more second Bezier curves associated with one or more second paths (Jafari Tafti, [0071] regarding the trajectory planning system generating a plurality of waypoints & [0071] regarding the trajectory refining system interpolating between the waypoints to generate a spatial path using piecewise Bezier curve).
Regarding claim 4, Jafari Tafti in view of Towal teaches the method as claimed in claim 1, further comprising:
generating, by the one or more machine learning models and based at least on the sensor data, a third output indicating a classification associated with the first path (Jafari Tafti, [0081] regarding determining whether the update trajectory satisfies dynamic constraints),
wherein the causing the machine to navigate along the at least the portion of the first path is further based at least on the classification (Jafari Tafti, [0081] regarding using the updated trajectory for driving the vehicle if the dynamic constraints are satisfied).
Regarding claim 7, Jafari Tafti in view of Towal teaches the method as claimed in claim 1, wherein:
the sensor data represents at least a sensor representation (Jafari Tafti, [0048] regarding the sensor system including sensing devices that sensor observable conditions of the exterior environment of the autonomous vehicle); and
the first output indicates at least one of:
two-dimensional locations associated with the sensor representation at which the Bezier points are located (Jafari Tafti, Fig. 5A regarding waypoints being locations on the road around the vehicle); or
the first Bezier curve associated with the first path as represented by the sensor representation (Jafari Tafti, [0081] regarding using the updated trajectory for driving the vehicle if the dynamic constraints are satisfied).
Regarding claim 9, Jafari Tafti discloses a system comprising:
one or more processors to:
determine, based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least one of first Bezier points associated with a first path or a Bezier curve associated with the first path (Jafari Tafti, [0071] regarding the trajectory planning system generating a plurality of waypoints, [0071] regarding the trajectory refining system interpolating between the waypoints to generate a spatial path using piecewise Bezier curves, & [0063] regarding the trajectory planner receiving sensor fusion data); and
cause, based at least on the first output, the machine to navigate within the environment (Jafari Tafti, [0073] regarding the revised trajectory which is composed of the spatial path being provided to the longitudinal and lateral controller to use in driving the host vehicle).
Jafari Tafti does not disclose one or more processors to:
determine, using one or more machine learning models and based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least one of first Bezier points associated with a first path or a Bezier curve associated with the first path,
wherein the one or more machine learning models are trained, at least, by:
determining, using the one or more machine learning models and based at least on training sensor data, one or more second outputs indicating at least second Bezier points associated with one or more second paths;
determining, based at least on ground truth data representing one or more polylines associated with the one or more second paths, ground truth Bezier points associated with the one or more second paths; and
determining, based at least on the second Bezier points and the ground truth Bezier points, one or more losses for updating the one or more machine learning model.
Towal teaches using a machine learning model to generate path geometries ([0034]),
wherein the one or more machine learning models are trained, at least by:
inputting training images into the DNN ([0116]);
ground truth data including annotated paths ([0113]); and
determining one or more losses for updating the one or more machine learning model (Towal, [0116] regarding using one or more loss functions to compute the accuracy of the DNN's predicted paths with the annotated paths and updating the parameters of the DNN until the accuracy reaches an optimal or acceptable level)
Jafari Tafti and Towal are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti to incorporate using a machine learning model to generate a vehicle trajectory, as disclosed by Towal, with a reasonable expectation of success because doing so would yield the predictable result of creating more accurate trajectories efficiently.
Jafari Tafti, as modified, teaches one or more processors to:
determine, using one or more machine learning models and based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least one of first Bezier points associated with a first path or a Bezier curve associated with the first path
wherein the one or more machine learning models are trained, at least, by:
determining, using the one or more machine learning models and based at least on training sensor data, one or more second outputs indicating at least second Bezier points associated with one or more second paths (Towal, [0116] regarding the training set of images being input into the DNN) (Jafari Tafti, [0071] regarding the trajectory planning system generating a plurality of waypoints & [0071] regarding the trajectory refining system interpolating between the waypoints to generate a spatial path using piecewise Bezier curve);
determining, based at least on ground truth data representing one or more polylines associated with the one or more second paths, ground truth Bezier points associated with the one or more second paths (Towal, [0113] regarding ground truth data including annotated paths. As Jafari Tafti determines points first and then creates a Bezier curve through the points the annotated path would be composed of Bezier points for comparing to.); and
determining, based at least on the second Bezier points and the ground truth Bezier points, one or more losses for updating the one or more machine learning model (Towal, [0116] regarding using one or more loss functions to compute the accuracy of the DNN's predicted paths with the annotated paths and updating the parameters of the DNN until the accuracy reaches an optimal or acceptable level).
Regarding claim 11, Jafari Tafti in view of Towal teaches the system as claimed in claim 9,
wherein the one or more processors are further to:
determine, using the one or more machine learning models and based at least on the sensor data, a third output indicating a classification associated with the first path (Jafari Tafti, [0081] regarding determining whether the update trajectory satisfies dynamic constraints),
wherein the machine is further caused to navigate within the environment based at least on the classification (Jafari Tafti, [0081] regarding using the updated trajectory for driving the vehicle if the dynamic constraints are satisfied).
Regarding claim 14, Jafari Tafti in view of Towal teaches the system as claimed in claim 9, wherein an individual point, from the first Bezier points, is associated with at least one:
a two-dimensional location associated with a sensor representation represented by the sensor data located (Jafari Tafti, Fig. 5A regarding waypoints being locations on the road around the vehicle); or
a three-dimensional location associated with the environment in which the machine is navigating (Jafari Tafti, [0081] regarding using the updated trajectory for driving the vehicle if the dynamic constraints are satisfied).
Regarding claim 15, Jafari Tafti in view of Towal teaches the system as claimed in claim 9. Towal further teaches wherein the one or more processors are further to:
generate, based at least on a second Bezier curve associated with a third path, an updated curve associated with the first path by smoothing at least a portion of the Bezier curve associated with the first path (Towal, [0043] regarding preforming temporal smoothing of the path geometry),
wherein the machine is caused to navigate within the environment based at least on the update curve associated with the first path (Towal, [0052] regarding using the path geometry to control the vehicle).
Jafari Tafti and Towal are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate smoothing the geometry, as disclosed by Towal, with a reasonable expectation of success because doing so would yield the predictable result of improving the geometry of the curve to increase comfort of the passengers.
Regarding claim 17, Jafari Tafti in view of Towal teaches the system as claimed in claim 9, wherein the system is comprised in at least one of:
a control system for an autonomous or semi-autonomous machine located (Jafari Tafti, [0051] regarding a controller for automatically controlling the autonomous vehicle);
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 implemented using a robot;
a system for performing conversational Al operations;
a system implementing one or more large language models (LLMs);
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.
Regarding claim 18, Jafari Tafti discloses one or more processors comprising processing circuitry to:
generate, based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least first points associated with a curve (Jafari Tafti, [0071] regarding the trajectory planning system generating a plurality of waypoints, [0071] regarding the trajectory refining system interpolating between the waypoints to generate a spatial path using piecewise Bezier curves, & [0063] regarding the trajectory planner receiving sensor fusion data); and
cause the machine to navigate along at least a portion of the first curve (Jafari Tafti, [0073] regarding the revised trajectory which is composed of the spatial path being provided to the longitudinal and lateral controller to use in driving the host vehicle).
Jafari Tafti does not disclose one or more processors comprising processing circuitry to:
generate, using one or more machine learning models and based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least first points associated with a curve; and
cause the machine to navigate along at least a portion of the first curve,
wherein the one or more machine learning models are trained, at least, by:
generating, using the one or more machine learning models and based at least on training sensor data, one or more second outputs associated with one or more predicted lines corresponding to one or more paths within an environment;
determining one or more losses based at least on the one or more predicted line and one or more ground truth lines associated with the one or more paths; and
updating the one or more machine learning models based at least on the one or more losses.
Towal teaches using a machine learning model to generate path geometries ([0034]),
wherein the one or more machine learning models are trained, at least by:
inputting training images into the DNN ([0116]);
determining one or more losses based at least on the one or more predicted line and one or more ground truth lines associated with the one or more paths (Towal, [0116] regarding using one or more loss functions to compute the accuracy of the DNN's predicted paths with the annotated paths); and
updating the one or more machine learning models based at least on the one or more losses (Towal, [0116] regarding updating the parameters of the DNN until the accuracy reaches an optimal or acceptable level).
Jafari Tafti and Towal are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti to incorporate using a machine learning model to generate a vehicle trajectory, as disclosed by Towal, with a reasonable expectation of success because doing so would yield the predictable result of creating more accurate trajectories efficiently.
Jafari Tafti, as modified, teaches one or more processors comprising processing circuitry to:
generate, using one or more machine learning models and based at least on sensor data obtained using one or more sensors of a machine within an environment, a first output indicating at least first points associated with a curve,
wherein the one or more machine learning models are trained, at least, by:
generating, using the one or more machine learning models and based at least on training sensor data, one or more second outputs associated with one or more predicted lines corresponding to one or more paths within an environment.
Regarding claim 20, Jafari Tafti in view of Towal teaches the one or more processors as claimed in claim 18, herein the one or more processors are comprised in at least one of:
a control system for an autonomous or semi-autonomous machine (Jafari Tafti, [0051] regarding a controller for automatically controlling the autonomous vehicle);
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 implemented using a robot;
a system for performing conversational Al operations;
a system implementing one or more large language models (LLMs);
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.
Regarding claim 21, Jafari Tafti in view of Towal teaches the method as claimed in claim 1. Towal further teaches wherein the one or more machine learning models are further trained by determining the one or more predicted polylines based at least on the one or more second Bezier curves (Towal, [0113] regarding training the DNN using ground truth data which includes annotated paths & [0114] regarding the annotated paths being the ego-lane (i.e., the path the vehicle is to follow)).
Jafari Tafti and Towal are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate training the machine learning model using Bezier curves, as disclosed by Towal, with a reasonable expectation of success because doing so would yield the predictable result of training the machine learning model using the data it is being used to output.
Regarding claim 22, Jafari Tafti in view of Towal teaches the method as claimed in claim 1. Towal further teaches using layers to compute different steps of the path geometry (Fig. 1C).
Jafari Tafti and Towal are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate using different machine learning layers to compute the first path and the classification of the path, as disclosed by Towal, with a reasonable expectation of success because doing so would yield the predictable result of limiting the computing power required during each step.
Claims 2 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Jafari Tafti in view of Towal, and further in view of Reichardt (US 2023/0234580).
Regarding claim 2, Jafari Tafti in view of Towal teaches the method as claimed in claim 1, but fails to explicitly teach wherein:
a first point, of the Bezier points, is located at a first location on the first Bezier curve that is associated with a start of the first path;
a second point, of the Bezier points, is located at a second location on the first Bezier curve that is associated with an end of the first path; and
a third point, of the Bezier points, is located at a third location that is outside of the first Bezier curve.
Reichardt teaches wherein:
a first point, of the Bezier points, is located at a first location on the first Bezier curve that is associated with a start of the first path (Reichardt, Fig. 3B regarding p0);
a second point, of the Bezier points, is located at a second location on the first Bezier curve that is associated with an end of the first path (Reichardt, Fig. 3B regarding p3); and
a third point, of the Bezier points, is located at a third location that is outside of the first Bezier curve (Reichardt, Fig. 3B regarding p2).
Jafari Tafti and Reichardt are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate determining Bezier point locations, as disclosed by Reichardt, with a reasonable expectation of success because doing so would yield the predictable result of determining a Bezier curve.
Regarding claim 10, Jafari Tafti in view of Towal teaches the system as claimed in claim 9, but fails to teach wherein:
a first point, of the first Bezier points, is located at a first location on the Bezier curve that is associated with a start of the first path;
a second point, of the first Bezier points, is located at a second location on the Bezier curve that is associated with an end of the first path; and
a third point, of the first Bezier points, is located at a third location that is outside of the Bezier curve.
Reichardt teaches wherein:
a first point, of the first Bezier points, is located at a first location on the Bezier curve that is associated with a start of the first path (Reichardt, Fig. 3B regarding p0);
a second point, of the first Bezier points, is located at a second location on the Bezier curve that is associated with an end of the first path (Reichardt, Fig. 3B regarding p3); and
a third point, of the first Bezier points, is located at a third location that is outside of the Bezier curve (Reichardt, Fig. 3B regarding p2).
Jafari Tafti and Reichardt are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate determining Bezier point locations, as disclosed by Reichardt, with a reasonable expectation of success because doing so would yield the predictable result of determining a Bezier curve.
Claims 5-6, 8, and 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Jafari Tafti in view of Towal, and further in view of Feng (CN 115393810).
Regarding claim 5, Jafari Tafti in view of Towal teaches the method as claimed in claim 1, but fails to teach determining, using the one or more machine learning models and based at least on the sensor data, a third output indicating second Bezier points associated with a third path; and
determining, based at least on the second Bezier points, a third Bezier curve associated with the third path,
wherein the causing the machine to navigate along the at least the first portion of the path is further based at least the third Bezier curve associated with the third path.
Feng teaches determining, using the one or more machine learning models and based at least on the sensor data, a third output indicating second Bezier points associated with a third path (Feng, [0020] regarding using a convolution layer to predict and regress the coordinates of the four third-order Bezier curve control points & [0013] regarding using an RGB image from a camera to obtain a basic feature map); and
determining, based at least on the second Bezier points, a third Bezier curve associated with the third path (Feng, [0020] regarding the Bezier curve control points representing a third-order Bezier curve),
wherein the causing the machine to navigate along the at least the first portion of the path is further based at least the third Bezier curve associated with the third path (Feng, [0003] regarding using the lane lines to autonomously maintain the current lane and autonomous cruising).
Jafari Tafti and Feng are considered to be analogous to the claimed invention because they are in the same field of path determination. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate determining a Bezier curve for each candidate lane line, as disclosed by Feng, with a reasonable expectation of success because doing so would yield the predictable result of improving lane detection, thereby improving driving accuracy and safety.
Regarding claim 6, Jafari Tafti in view of Towal, and further in view of Feng teaches the method as claimed in claim 5, wherein:
the first path is associated with a current path that the machine is to navigate (Jafari Tafti, [0081] regarding using the updated trajectory for driving the vehicle if the dynamic constraints are satisfied).
Feng further teaches wherein:
the third path is associated with at least one of a right edge associated with the current path or a left edge associated with the current path (Feng, [0006] regarding using Bezier curves to model lane lines (i.e., edges of the current path)).
Jafari Tafti and Feng are considered to be analogous to the claimed invention because they are in the same field of path determination. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate determining a Bezier curve for each candidate lane line, as disclosed by Feng, with a reasonable expectation of success because doing so would yield the predictable result of improving lane detection, thereby improving driving accuracy and safety.
Regarding claim 8, Jafari Tafti in view of Towal teaches the method as claimed in claim 1, but fails to explicitly teach wherein the sensor data is obtained using the one or more sensors at a first time, and wherein the method further comprises:
determining, using the one or more machine learning models and based at least on second sensor data obtained using the one or more sensors at a second time that is after the first time, a third output indicating second Bezier points associated with a third path;
determining, based at least on the second Bezier points, a third Bezier curve associated with the third path; and
determine, based at least on the first Bezier curve associated with the first path and the third Bezier curve associated with the third path, a fourth Bezier curve associated with the first path,
wherein the causing the machine to navigate along the at least the portion of the first path is based at least on the fourth Bezier curve associated with the first path.
Feng teaches wherein the sensor data is obtained using the one or more sensors at a first time, and wherein the method further comprises:
determining, using the one or more machine learning models and based at least on second sensor data obtained using the one or more sensors at a second time that is after the first time, a third output indicating second Bezier points associated with a third path (Feng, [0020] regarding using a convolution layer to predict and regress the coordinates of the four third-order Bezier curve control points & [0013] regarding using an RGB image from a camera to obtain a basic feature map); and
determining, based at least on the second Bezier points, a third Bezier curve associated with the third path (Feng, [0020] regarding the Bezier curve control points representing a third-order Bezier curve).
Jafari Tafti and Feng are considered to be analogous to the claimed invention because they are in the same field of path determination. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate determining a Bezier curve for each candidate lane line, as disclosed by Feng, with a reasonable expectation of success because doing so would yield the predictable result of improving lane detection, thereby improving driving accuracy and safety.
Towal further teaches wherein the sensor data is obtained using the one or more sensors at a first time, and wherein the method further comprises:
determine, based at least on the first Bezier curve associated with the first path and the third Bezier curve associated with the third path, a fourth Bezier curve associated with the first path (Towal, [0043] regarding preforming temporal smoothing of the path geometry (i.e., creating a new path geometry that is smoothed)),
wherein the causing the machine to navigate along the at least the portion of the first path is based at least on the fourth Bezier curve associated with the first path (Towal, [0052] regarding using the path geometry to control the vehicle).
Jafari Tafti and Towal are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectories. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate smoothing the geometry, as disclosed by Towal, with a reasonable expectation of success because doing so would yield the predictable result of improving the geometry of the curve to increase comfort of the passengers.
Regarding claim 12, Jafari Tafti in view of Towal teaches the system as claimed in claim 9, but fails to teach wherein the one or more processors are further to:
determine, using the one or more machine learning models and based at least on the sensor data, a third output indicating third Bezier points associated with a third path; and
determine, based at least on the third Bezier points, a second Bezier curve associated with the third path,
wherein the machine is further caused to navigate within the environment based at least the second Bezier curve associated with the third path.
Feng teaches wherein the one or more processors are further to:
determine, using the one or more machine learning models and based at least on the sensor data, a third output indicating third Bezier points associated with a third path (Feng, [0020] regarding using a convolution layer to predict and regress the coordinates of the four third-order Bezier curve control points & [0013] regarding using an RGB image from a camera to obtain a basic feature map); and
determine, based at least on the third Bezier points, a second Bezier curve associated with the third path (Feng, [0020] regarding the Bezier curve control points representing a third-order Bezier curve),
wherein the machine is further caused to navigate within the environment based at least the second Bezier curve associated with the third path (Feng, [0003] regarding using the lane lines to autonomously maintain the current lane and autonomous cruising).
Jafari Tafti and Feng are considered to be analogous to the claimed invention because they are in the same field of path determination. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate determining a Bezier curve for each candidate lane line, as disclosed by Feng, with a reasonable expectation of success because doing so would yield the predictable result of improving lane detection, thereby improving driving accuracy and safety.
Regarding claim 13, Jafari Tafti in view of Towal, and further in view of Feng teaches the system as claimed in claim 12, wherein:
the first path is associated with a current path that the machine is to navigate (Jafari Tafti, [0081] regarding using the updated trajectory for driving the vehicle if the dynamic constraints are satisfied).
Feng further teaches wherein:
the third path is associated with at least one of a right edge associated with the current path or a left edge associated with the current path (Feng, [0006] regarding using Bezier curves to model lane lines (i.e., edges of the current path)).
Jafari Tafti and Feng are considered to be analogous to the claimed invention because they are in the same field of path determination. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to have modified Jafari Tafti, as modified, to incorporate determining a Bezier curve for each candidate lane line, as disclosed by Feng, with a reasonable expectation of success because doing so would yield the predictable result of improving lane detection, thereby improving driving accuracy and safety.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEX GRIFFIN whose telephone number is (703)756-1516. The examiner can normally be reached Monday - Thursday 7:30am - 5:30pm.
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.
/ALEX B GRIFFIN/Examiner, Art Unit 3665
/Erin D Bishop/Supervisory Patent Examiner, Art Unit 3665