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 .
Claims 1-20 have been examined.
P = paragraph e.g. P[0001] = paragraph[0001]
Claim Rejections - 35 USC § 112
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 1-20 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.
As per Claim 1, the claim recites “determine an independent trajectory for the EV independent from motion of the at least one OA based on the state of the EV, and an independent trajectory for the at least one OA independent from motion of the EV based on the state of the at least one OA; determine jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA by optimizing a cost function of a difference between the joint trajectories and the independent trajectories”.
The limitation “determine jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA by optimizing a cost function of a difference between the joint trajectories and the independent trajectories” is unclear. Specifically, it is unclear if “determine jointly and interdependently trajectories” is referring to determining two different steps of generated two different types of trajectories or “jointly” trajectories in addition to “interdependently” trajectories, or if “jointly and interdependently” refers to a single step.
Furthermore, the limitation “to produce joint trajectories of the EV and the at least one OA” is written as an intended use as seen by the word “to”, making the scope of this limitation unclear.
Furthermore, the limitation “by optimizing a cost function of a difference between the joint trajectories and the independent trajectories” appears to be further limiting “determine jointly and interdependently trajectories for the motion of the EV and the at least one OA”, however, the step of “determine jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA” implies the “joint trajectories” do not exist until the “determine” step is completed as indicated by “to produce joint trajectories of the EV and the at least one OA” which appears to be an intended result of the “determine” step, yet the claim further limits the “determine” step by relying on “the joint trajectories and the independent trajectories” that do not yet exist, as seen in the limitation “by optimizing a cost function of a difference between the joint trajectories and the independent trajectories”. Therefore, it is unclear how the step of “determine jointly and interdependently trajectories for the motion of the EV and the at least one OA” can be performed by “optimizing a cost function of a difference between the joint trajectories and the independent trajectories” when the “joint trajectories” and the “independent trajectories” have not yet been generated.
Therefore, the claim is unclear.
As per Claim 13, the claim recites “determining an independent trajectory for the EV independent from motion of the at least one OA based on the state of the EV, and an independent trajectory for the at least one OA independent from motion of the EV based on the state of the at least one OA; determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA by optimizing a cost function of a difference between the joint trajectories and the independent trajectories”.
The limitation “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA by optimizing a cost function of a difference between the joint trajectories and the independent trajectories” is unclear. Specifically, it is unclear if “determining jointly and interdependently trajectories” is referring to determining two different steps of generated two different types of trajectories or “jointly” trajectories in addition to “interdependently” trajectories, or if “jointly and interdependently” refers to a single step.
Furthermore, the limitation “to produce joint trajectories of the EV and the at least one OA” is written as an intended use as seen by the word “to”, making the scope of this limitation unclear.
Furthermore, the limitation “by optimizing a cost function of a difference between the joint trajectories and the independent trajectories” appears to be further limiting “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA”, however, the step of “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA” implies the “joint trajectories” do not exist until the “determining” step is completed as indicated by “to produce joint trajectories of the EV and the at least one OA” which appears to be an intended result of the “determine” step, yet the claim further limits the “determining” step by relying on “the joint trajectories and the independent trajectories” that do not yet exist, as seen in the limitation “by optimizing a cost function of a difference between the joint trajectories and the independent trajectories”. Therefore, it is unclear how the step of “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA” can be performed by “optimizing a cost function of a difference between the joint trajectories and the independent trajectories” when the “joint trajectories” and the “independent trajectories” have not yet been generated.
Therefore, the claim is unclear.
As per Claim 20, the claim recites “determining an independent trajectory for the EV independent from motion of the at least one OA based on the state of the EV, and an independent trajectory for the at least one OA independent from motion of the EV based on the state of the at least one OA; determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA by optimizing a cost function of a difference between the joint trajectories and the independent trajectories”.
The limitation “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA by optimizing a cost function of a difference between the joint trajectories and the independent trajectories” is unclear. Specifically, it is unclear if “determining jointly and interdependently trajectories” is referring to determining two different steps of generated two different types of trajectories or “jointly” trajectories in addition to “interdependently” trajectories, or if “jointly and interdependently” refers to a single step.
Furthermore, the limitation “to produce joint trajectories of the EV and the at least one OA” is written as an intended use as seen by the word “to”, making the scope of this limitation unclear.
Furthermore, the limitation “by optimizing a cost function of a difference between the joint trajectories and the independent trajectories” appears to be further limiting “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA”, however, the step of “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA” implies the “joint trajectories” do not exist until the “determining” step is completed as indicated by “to produce joint trajectories of the EV and the at least one OA” which appears to be an intended result of the “determine” step, yet the claim further limits the “determining” step by relying on “the joint trajectories and the independent trajectories” that do not yet exist, as seen in the limitation “by optimizing a cost function of a difference between the joint trajectories and the independent trajectories”. Therefore, it is unclear how the step of “determining jointly and interdependently trajectories for the motion of the EV and the at least one OA” can be performed by “optimizing a cost function of a difference between the joint trajectories and the independent trajectories” when the “joint trajectories” and the “independent trajectories” have not yet been generated.
Therefore, the claim is unclear.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-7, 13-15 and 17-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Chen et al. (2025/0058802).
Regarding Claim 1, Chen et al. teaches the claimed controller (“Controller(s) 936…”, see P[0125]) for controlling an ego vehicle (EV) in an environment surrounding the EV and including at least one other agent (OA) representing a moving object, the controller comprising:
a processor coupled with instructions stored in a memory, wherein the stored instructions, when executed by the processor (“…a processor executing instructions stored in memory”, see P[0099]), cause the controller to:
collect a state of the EV and a state of the at least one OA (“An observation may correspond to one or more states of the environment where a state of the environment may correspond to one or more particular times or time steps. For example, the observation determiner 104 may determine one or more aspects of states of the environment, such as states of actors (e.g., the vehicle 900 and other objects, static or dynamic) in the environment, scene context, and/or lane information”, see [0037]);
determine an independent trajectory for the EV independent from motion of the at least one OA based on the state of the EV (“The motion planner 108 may use the route information to configure the problem space, the solution space, goal states or locations, and/or an initial trajectory or path for the ego machine”, see P[0048]), and an independent trajectory for the at least one OA independent from motion of the EV based on the state of the at least one OA (“…the route information may represent one or more of: at least a portion of one or more predicted trajectories for one or more of the obstacles; one or more predicted locations for one or more of the obstacles; one or more predicted states for one or more of the obstacles; and/or one or more goal locations and/or trajectories for one or more of the obstacles…an initial trajectory or path for one or more of the obstacles”, see P[0051]);
determine jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA (“…jointly evaluating and updating both the ego and obstacle routes 120…”, see P[0067] and “…jointly optimized trajectories for the agent 220 and the vehicle 900…”, see P[0068]) by optimizing a cost function of a difference between the joint trajectories and the independent trajectories (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023] and “…the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles…”, see P[0023] and “…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059] and “By jointly evaluating and updating both the ego and obstacle routes 120, the updater 118 may determine the ego route while accounting for the impact of the ego route on routes of the obstacles”, see P[0067] and “…the routes 230B and 240 may correspond to a solution to a joint optimization of the problem space performed using the motion planner 108”, see P[0068] and “…the evaluator 116 and updater 118 of the motion planner 108 allowed for the vehicle 900 to change lanes by accounting for the agent 220 swerving to avoid a collision with the vehicle 900 (e.g., while penalizing the deviation of the agent 220 from the route 230A)”, see P[0069] and “…the evaluator 116 may evaluate the ego and obstacle routes to compute one or more cost values of the one or more cost functions…the updater 118 may use the one or more cost values to compute one or more gradients of the one or more cost functions with respect to control inputs for the ego machine”, see P[0070]); and
control the motion of the EV based on the joint trajectory of the EV (“…the updater 118 may use the one or more cost values to compute one or more gradients of the one or more cost functions with respect to control inputs for the ego machine. A gradient may indicate how the one or more cost functions will change with variations in the control inputs (e.g., steering and/or acceleration controls)”, see P[0070] and “One or more portions of the updated ego and obstacle routes 120 (e.g., an ego trajectory) may be provided to the control component 112 to define the trajectory for the ego machine (e.g., iteratively as the routes are updated). The motion planner 108 may pass information indicating the updated ego and obstacle routes 120 (e.g., an ego trajectory) to the control component”, see P[0098] and “At block B610, the method 600 includes performing one or more control operations based at least on the trajectory. For example, the control component 112 may one or more control operations for the vehicle 900 using the trajectory”, see P[0104] and “The processor also includes one or more circuits to perform one or more control operations for a machine using a trajectory, the trajectory determined based at least on evaluating one or more cost functions corresponding to at least one first route corresponding to the machine and at least one second route corresponding to at least one agent to jointly adjust the at least one first route corresponding to the machine and the at least one second route corresponding to the at least one agent”, see P[0119]).
Regarding Claim 2, Chen et al. teaches the claimed controller of claim 1, wherein the cost function produces a higher cost if one or both of the EV and the at least one OA deviate from the independent trajectories (“…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059]), and wherein a cost of deviation of the EV is different than a cost of deviation of the at least one OA (“A relatively large η.sub.e may cause more selfish and intrusive behavior by the ego machine with respect to the agents and a relatively small ne may cause more altruistic ego behavior with respect to the agents”, see P[0066]).
Regarding Claim 3, Chen et al. teaches the claimed controller of claim 1, wherein the environment includes a first OA and a second OA, such that the cost function penalizes a difference of a first joint trajectory of the first OA from a first independent trajectory of the first OA with a first cost of deviation and penalizes a difference of a second joint trajectory of the second OA from a second independent trajectory of the second OA with a second cost of deviation (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023] and “…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059]), wherein the first cost of deviation is different from the second cost of deviation (“A relatively large η.sub.e may cause more selfish and intrusive behavior by the ego machine with respect to the agents and a relatively small ne may cause more altruistic ego behavior with respect to the agents”, see P[0066]).
Regarding Claim 4, Chen et al. teaches the claimed controller of claim 3, wherein the processor is further configured to determine the first cost of deviation and the second cost of deviation based on a type and behavior of the first OA and the second OA (“…the one or more cost functions may include one or more terms that penalize one or more of acceleration, jerk, and/or other motion or route characteristics for the ego machine”, see P[0059] and “An observation may correspond to one or more states of the environment where a state of the environment may correspond to one or more particular times or time steps. For example, the observation determiner 104 may determine one or more aspects of states of the environment, such as states of actors (e.g., the vehicle 900 and other objects, static or dynamic) in the environment, scene context, and/or lane information”, see [0037]).
Regarding Claim 5, Chen et al. teaches the claimed controller of claim 3, wherein the cost function is optimized subject to a first constraint on a mutual position between the EV and the first OA and a second constraint on a mutual position between the EV and the second OA, and wherein the first constraint is different from the second constraint (“…one or more safety constraints may be defined for the problem space, such as one or more collision avoidance constraints and one or more lane boundary constraints. In at least one embodiment, machines (e.g., vehicles) may be modeled using rectangles and/or other shapes and pedestrians may be modeled using circles and/or other shapes (e.g., circles having a varying radius). The collision avoidance constraints may be encoded, for example, for pedestrians (e.g., circles) and machines (e.g., rectangles) based at least on checking cases where a maximum margin is achieved on the X axis, Y axis, and corners of the machines”, see P[0062]).
Regarding Claim 6, Chen et al. teaches the claimed controller of claim 2, wherein the processor is further configured to update the cost of deviation of the at least one OA based on a difference between the joint trajectory of the at least one OA and an observed trajectory of the at least one OA (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023] and “…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059]).
Regarding Claim 7, Chen et al. teaches the claimed controller of claim 6, wherein the cost function is optimized subject to a safety constraint on a mutual position between the EV and the at least one OA, and wherein the processor is further configured to update the safety constraint based on the difference between the joint trajectory of the at least one OA and the observed trajectory of the at least one OA (“…one or more safety constraints may be defined for the problem space, such as one or more collision avoidance constraints and one or more lane boundary constraints. In at least one embodiment, machines (e.g., vehicles) may be modeled using rectangles and/or other shapes and pedestrians may be modeled using circles and/or other shapes (e.g., circles having a varying radius). The collision avoidance constraints may be encoded, for example, for pedestrians (e.g., circles) and machines (e.g., rectangles) based at least on checking cases where a maximum margin is achieved on the X axis, Y axis, and corners of the machines”, see P[0062]).
Regarding Claim 13, Chen et al. teaches the claimed method for controlling an ego vehicle (EV) in an environment surrounding the EV and including at least one other agent (OA) representing a moving object, the method comprising:
collecting a state of the EV and a state of the at least one OA (“An observation may correspond to one or more states of the environment where a state of the environment may correspond to one or more particular times or time steps. For example, the observation determiner 104 may determine one or more aspects of states of the environment, such as states of actors (e.g., the vehicle 900 and other objects, static or dynamic) in the environment, scene context, and/or lane information”, see [0037]);
determining an independent trajectory for the EV independent from motion of the at least one OA based on the state of the EV (“The motion planner 108 may use the route information to configure the problem space, the solution space, goal states or locations, and/or an initial trajectory or path for the ego machine”, see P[0048]), and an independent trajectory for the at least one OA independent from motion of the EV based on the state of the at least one OA (“…the route information may represent one or more of: at least a portion of one or more predicted trajectories for one or more of the obstacles; one or more predicted locations for one or more of the obstacles; one or more predicted states for one or more of the obstacles; and/or one or more goal locations and/or trajectories for one or more of the obstacles…an initial trajectory or path for one or more of the obstacles”, see P[0051]);
determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA (“…jointly evaluating and updating both the ego and obstacle routes 120…”, see P[0067] and “…jointly optimized trajectories for the agent 220 and the vehicle 900…”, see P[0068]) by optimizing a cost function of a difference between the joint trajectories and the independent trajectories (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023] and “…the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles…”, see P[0023] and “…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059] and “By jointly evaluating and updating both the ego and obstacle routes 120, the updater 118 may determine the ego route while accounting for the impact of the ego route on routes of the obstacles”, see P[0067] and “…the routes 230B and 240 may correspond to a solution to a joint optimization of the problem space performed using the motion planner 108”, see P[0068] and “…the evaluator 116 and updater 118 of the motion planner 108 allowed for the vehicle 900 to change lanes by accounting for the agent 220 swerving to avoid a collision with the vehicle 900 (e.g., while penalizing the deviation of the agent 220 from the route 230A)”, see P[0069] and “…the evaluator 116 may evaluate the ego and obstacle routes to compute one or more cost values of the one or more cost functions…the updater 118 may use the one or more cost values to compute one or more gradients of the one or more cost functions with respect to control inputs for the ego machine”, see P[0070]); and
controlling the motion of the EV based on the joint trajectory of the EV (“…the updater 118 may use the one or more cost values to compute one or more gradients of the one or more cost functions with respect to control inputs for the ego machine. A gradient may indicate how the one or more cost functions will change with variations in the control inputs (e.g., steering and/or acceleration controls)”, see P[0070] and “One or more portions of the updated ego and obstacle routes 120 (e.g., an ego trajectory) may be provided to the control component 112 to define the trajectory for the ego machine (e.g., iteratively as the routes are updated). The motion planner 108 may pass information indicating the updated ego and obstacle routes 120 (e.g., an ego trajectory) to the control component”, see P[0098] and “At block B610, the method 600 includes performing one or more control operations based at least on the trajectory. For example, the control component 112 may one or more control operations for the vehicle 900 using the trajectory”, see P[0104] and “The processor also includes one or more circuits to perform one or more control operations for a machine using a trajectory, the trajectory determined based at least on evaluating one or more cost functions corresponding to at least one first route corresponding to the machine and at least one second route corresponding to at least one agent to jointly adjust the at least one first route corresponding to the machine and the at least one second route corresponding to the at least one agent”, see P[0119]).
Regarding Claim 14, Chen et al. teaches the claimed method of claim 13, wherein the cost function produces a higher cost if one or both of the EV and the at least one OA deviate from the independent trajectories (“…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059]), and wherein a cost of deviation of the EV is different than a cost of deviation of the at least one OA (“A relatively large η.sub.e may cause more selfish and intrusive behavior by the ego machine with respect to the agents and a relatively small ne may cause more altruistic ego behavior with respect to the agents”, see P[0066]).
Regarding Claim 15, Chen et al. teaches the claimed method of claim 13, wherein the environment includes a first OA and a second OA, such that the cost function penalizes a difference of a first joint trajectory of the first OA from a first independent trajectory of the first OA with a first cost of deviation and penalizes a difference of a second joint trajectory of the second OA from a second independent trajectory of the second OA with a second cost of deviation (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023] and “…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059]), wherein the first cost of deviation is different from the second cost of deviation (“A relatively large η.sub.e may cause more selfish and intrusive behavior by the ego machine with respect to the agents and a relatively small ne may cause more altruistic ego behavior with respect to the agents”, see P[0066]).
Regarding Claim 17, Chen et al. teaches the claimed method of claim 15, wherein the method further comprises determining the first cost of deviation and the second cost of deviation based on a type and behavior of the first OA and the second OA (“…the one or more cost functions may include one or more terms that penalize one or more of acceleration, jerk, and/or other motion or route characteristics for the ego machine”, see P[0059] and “An observation may correspond to one or more states of the environment where a state of the environment may correspond to one or more particular times or time steps. For example, the observation determiner 104 may determine one or more aspects of states of the environment, such as states of actors (e.g., the vehicle 900 and other objects, static or dynamic) in the environment, scene context, and/or lane information”, see [0037])).
Regarding Claim 18, Chen et al. teaches the claimed method of claim 15, wherein the cost function is optimized subject to a first constraint on a mutual position between the EV and the first OA and a second constraint on a mutual position between the EV and the second OA, and wherein the first constraint is different from the second constraint (“…one or more safety constraints may be defined for the problem space, such as one or more collision avoidance constraints and one or more lane boundary constraints. In at least one embodiment, machines (e.g., vehicles) may be modeled using rectangles and/or other shapes and pedestrians may be modeled using circles and/or other shapes (e.g., circles having a varying radius). The collision avoidance constraints may be encoded, for example, for pedestrians (e.g., circles) and machines (e.g., rectangles) based at least on checking cases where a maximum margin is achieved on the X axis, Y axis, and corners of the machines”, see P[0062]).
Regarding Claim 19, Chen et al. teaches the claimed method of claim 14, wherein the method further comprises updating the cost of deviation of the at least one OA based on a difference between the joint trajectory of the at least one OA and an observed trajectory of the at least one OA (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023] and “…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059]).
Regarding Claim 20, Chen et al. teaches the claimed non-transitory computer-readable storage medium embodied thereon a program executable by a processor (“…a processor executing instructions stored in memory”, see P[0099]) for performing a method for controlling an ego vehicle (EV) in an environment surrounding the EV and including at least one other agent (OA) representing a moving object, the method comprising:
collecting a state of the EV and a state of the at least one OA (“An observation may correspond to one or more states of the environment where a state of the environment may correspond to one or more particular times or time steps. For example, the observation determiner 104 may determine one or more aspects of states of the environment, such as states of actors (e.g., the vehicle 900 and other objects, static or dynamic) in the environment, scene context, and/or lane information”, see [0037]);
determining an independent trajectory for the EV independent from motion of the at least one OA based on the state of the EV (“The motion planner 108 may use the route information to configure the problem space, the solution space, goal states or locations, and/or an initial trajectory or path for the ego machine”, see P[0048]), and an independent trajectory for the at least one OA independent from motion of the EV based on the state of the at least one OA (“…the route information may represent one or more of: at least a portion of one or more predicted trajectories for one or more of the obstacles; one or more predicted locations for one or more of the obstacles; one or more predicted states for one or more of the obstacles; and/or one or more goal locations and/or trajectories for one or more of the obstacles…an initial trajectory or path for one or more of the obstacles”, see P[0051]);
determining jointly and interdependently trajectories for the motion of the EV and the at least one OA to produce joint trajectories of the EV and the at least one OA (“…jointly evaluating and updating both the ego and obstacle routes 120…”, see P[0067] and “…jointly optimized trajectories for the agent 220 and the vehicle 900…”, see P[0068]) by optimizing a cost function of a difference between the joint trajectories and the independent trajectories (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023] and “…the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles…”, see P[0023] and “…the one or more cost functions include one or more terms that penalize the ego machine's tracking error with respect to the route information provided to the motion planner 108 by the ego route determiner 106A. For example, the one or more terms may penalize deviation from the planned and/or nominal trajectory provided to the motion planner 108 for the ego machine”, see P[0059] and “By jointly evaluating and updating both the ego and obstacle routes 120, the updater 118 may determine the ego route while accounting for the impact of the ego route on routes of the obstacles”, see P[0067] and “…the routes 230B and 240 may correspond to a solution to a joint optimization of the problem space performed using the motion planner 108”, see P[0068] and “…the evaluator 116 and updater 118 of the motion planner 108 allowed for the vehicle 900 to change lanes by accounting for the agent 220 swerving to avoid a collision with the vehicle 900 (e.g., while penalizing the deviation of the agent 220 from the route 230A)”, see P[0069] and “…the evaluator 116 may evaluate the ego and obstacle routes to compute one or more cost values of the one or more cost functions…the updater 118 may use the one or more cost values to compute one or more gradients of the one or more cost functions with respect to control inputs for the ego machine”, see P[0070]); and
controlling the motion of the EV based on the joint trajectory of the EV (“…the updater 118 may use the one or more cost values to compute one or more gradients of the one or more cost functions with respect to control inputs for the ego machine. A gradient may indicate how the one or more cost functions will change with variations in the control inputs (e.g., steering and/or acceleration controls)”, see P[0070] and “One or more portions of the updated ego and obstacle routes 120 (e.g., an ego trajectory) may be provided to the control component 112 to define the trajectory for the ego machine (e.g., iteratively as the routes are updated). The motion planner 108 may pass information indicating the updated ego and obstacle routes 120 (e.g., an ego trajectory) to the control component”, see P[0098] and “At block B610, the method 600 includes performing one or more control operations based at least on the trajectory. For example, the control component 112 may one or more control operations for the vehicle 900 using the trajectory”, see P[0104] and “The processor also includes one or more circuits to perform one or more control operations for a machine using a trajectory, the trajectory determined based at least on evaluating one or more cost functions corresponding to at least one first route corresponding to the machine and at least one second route corresponding to at least one agent to jointly adjust the at least one first route corresponding to the machine and the at least one second route corresponding to the at least one agent”, see P[0119]).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (2025/0058802) in view of Sumer et al. (2023/0399002).
Regarding Claim 8, Chen et al. does not expressly recite the claimed controller of claim 7, wherein the safety constraint is obtained by a control barrier function constraint that includes values of states and values of first-order derivatives of the state of the EV and the state of the at least one OA.
However, Sumer et al. (2023/0399002) teaches wherein a safety constraint is obtained by a control barrier function constraint that includes values of states and values of first-order derivatives of a state of an EV and a state of at least one OA (Sumer et al.; “The computer 110 may be programmed to operate based on a control barrier function (as discussed below with respect to Expressions (2)-(4)) that determines a barrier distance h along a virtual line 220 extending from the vehicle 100, e.g., a reference point 150, to a target 200. The relative distance h is defined as a distance (or length) along the line 220 from a point 230 on the virtual boundary 170 at respective orientations of a virtual line 220 to the target 200. The point 230 is at an intersection of the virtual line 220 with the virtual boundary 170. A distance h is defined as a distance from the virtual boundary 170 of the vehicle 100 to a target 200”, see P[0055] and “…the computer 110 may be programmed to determine the derivative of the distance function based on a derivative of a distance of a virtual line 220 extending from the virtual boundary 170 to the one or more targets 200 and a derivative of the orientation of the virtual line 220 relative to a virtual reference line x.sub.H. Expression (3) further depends on a control input u(t), e.g., actuation of steering and acceleration of the vehicle 100. Thus, control function u(t) or a range for the control function u(t) may be identified which satisfies the Expression (3). A function {dot over (h)}((x(t), u(t)) is a temporal derivative of function h based on a state vector x(t) of the vehicle 100 and the control or input vector u(t)”, see P[0060]).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Chen et al. with the teachings of Sumer et al., and wherein the safety constraint is obtained by a control barrier function constraint that includes values of states and values of first-order derivatives of the state of the EV and the state of the at least one OA, as rendered obvious by Sumer et al., in order to “determine a virtual barrier around a vehicle” (Sumer et al.; see Abstract).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (2025/0058802) in view of Puchkarev et al. (2023/0030104).
Examiner’s Note:
Regarding Claim 9, the limitation “such that” indicates an intended use, therefore, the limitation “such that when the cost function is subject to the modified safety constraint, a percentage fraction of realizations of the joint trajectories that satisfy the safety constraint with uncertainty in the safety constraint is larger than a pre-assigned percentage fraction” is directed to an intended use that does not further limit the claim.
Regarding Claim 9, Chen et al. does not expressly recite the claimed controller of claim 7, wherein the processor is further configured to modify the safety constraint based on a confidence on the safety constraint, such that when the cost function is subject to the modified safety constraint, a percentage fraction of realizations of the joint trajectories that satisfy the safety constraint with uncertainty in the safety constraint is larger than a pre-assigned percentage fraction.
However, Puchkarev et al. (2023/0030104) teaches modify the safety constraint based on a confidence on the safety constraint, such that when the cost function is subject to the modified safety constraint, a percentage fraction of realizations of the joint trajectories that satisfy the safety constraint with uncertainty in the safety constraint is larger than a pre-assigned percentage fraction (Puchkarev et al.; “…a confidence value may represent a percentage of interactions with a particular type of object during which the autonomous vehicle may not meet the lateral gap threshold”, see P[0064] and “…the autonomous vehicle is controlled in an autonomous driving mode based on the lateral gap threshold for the object. The planning system 168 may then attempt to solve for a trajectory that maintains the confidence value as well as other typical constraints (e.g. following lanes, following traffic controls, following speed limits, meeting acceptable acceleration and deceleration thresholds, following a route, etc.). For instance, the planning system 168 may attempt to ensure that it is at least as confident as the confidence value that the autonomous vehicle will not violate the lateral gap threshold for the object given the current uncertainties”, see P[0065] and “…the confidence value can be adjusted by reducing the lateral gap threshold (e.g. by adjusting the baseline lateral gap threshold) component of the confidence value”, see P[0066]).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Chen et al. with the teachings of Puchkarev et al., and wherein the processor is further configured to modify the safety constraint based on a confidence on the safety constraint, such that when the cost function is subject to the modified safety constraint, a percentage fraction of realizations of the joint trajectories that satisfy the safety constraint with uncertainty in the safety constraint is larger than a pre-assigned percentage fraction, as rendered obvious by Puchkarev et al., in order to “provide for controlling an autonomous vehicle” and so that an “autonomous vehicle may be controlled in an autonomous driving mode based on the lateral gap threshold for the object” (Puchkarev et al.; see Abstract).
Claims 10-12 are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (2025/0058802) in view of Dede et al. (2022/0097690).
Regarding Claim 10, Chen et al. teaches the claimed controller of claim 1, wherein the cost function includes a motion objective of the EV and a…motion objective of the at least one OA (“…the motion planner can jointly optimize the trajectories of the machine and one or more obstacles with respect to the cost function. In at least one embodiment, the cost function includes one or more terms to penalize deviation, for one or more obstacle trajectories, from one or more initial routes predicted for the obstacles, and one or more of acceleration or jerk for at least one obstacle. The terms may be used to limit the ego machine's ability to force nearby agents to deviate from their nominal and/or likely paths”, see P[0023]).
Chen et al. does not expressly recite the bolded portions of the claimed
wherein the cost function includes a motion objective of the EV and a weighted motion objective of the at least one OA.
However, Dede et al. (2022/0097690) teaches a weighted motion objective of the at least one OA (Dede et al.; “A second population of neurons in the ONN can be dedicated to predicting if the trajectory of the other vehicle within the conflict zone will be violated by the mobile vehicle. Weights controlling the first population of can be configured by a first weight matrix. The first weight matrix can be adjusted based on responses to changes in acceleration and/or heading of the mobile vehicle. A first bias vector can control the bias of the first population of neurons. The first bias vector can correspond to the relative position between the mobile vehicle and the other vehicle. Weights controlling the second population of neurons can be configured by a second weight matrix”, see P[0027] and Claim 19).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Chen et al. with the teachings of Dede et al., and wherein the cost function includes a motion objective of the EV and a weighted motion objective of the at least one OA, as rendered obvious by Dede et al., in order to provide for “navigation in conflict zone environments” (Dede et al.; see Abstract).
Regarding Claim 11, Chen et al. does not expressly recite the claimed controller of claim 10, wherein a weight of the weighted motion objective of the at least one OA depends on a weight matrix that is based on a latent parameter of the at least one OA.
However, Dede et al. (2022/0097690) teaches wherein a weight of the weighted motion objective of the at least one OA depends on a weight matrix that is based on a latent parameter of the at least one OA (Dede et al.; “A second population of neurons in the ONN can be dedicated to predicting if the trajectory of the other vehicle within the conflict zone will be violated by the mobile vehicle. Weights controlling the first population of can be configured by a first weight matrix. The first weight matrix can be adjusted based on responses to changes in acceleration and/or heading of the mobile vehicle. A first bias vector can control the bias of the first population of neurons. The first bias vector can correspond to the relative position between the mobile vehicle and the other vehicle. Weights controlling the second population of neurons can be configured by a second weight matrix”, see P[0027] and Claim 19).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Chen et al. with the teachings of Dede et al., and wherein a weight of the weighted motion objective of the at least one OA depends on a weight matrix that is based on a latent parameter of the at least one OA, as rendered obvious by Dede et al., in order to provide for “navigation in conflict zone environments” (Dede et al.; see Abstract).
Regarding Claim 12, Chen et al. teaches the claimed controller of claim 11, wherein the processor is further configured to compute the latent parameter of the at least one OA based on an observed trajectory of the at least one OA and the joint trajectory of the at least one OA (“An observation may correspond to one or more states of the environment where a state of the environment may correspond to one or more particular times or time steps. For example, the observation determiner 104 may determine one or more aspects of states of the environment, such as states of actors (e.g., the vehicle 900 and other objects, static or dynamic) in the environment, scene context, and/or lane information”, see [0037] and “…the route information may represent one or more of: at least a portion of one or more predicted trajectories for one or more of the obstacles; one or more predicted locations for one or more of the obstacles; one or more predicted states for one or more of the obstacles; and/or one or more goal locations and/or trajectories for one or more of the obstacles…an initial trajectory or path for one or more of the obstacles”, see P[0051]).
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (2025/0058802) in view of Fuchs et al. (11,377,118).
Regarding Claim 16, Chen et al. does not expressly recite the claimed method of claim 15, wherein one or a combination of the first cost of deviation and the second cost of deviation is collected over a wireless communication channel.
However, Fuchs et al. (11,377,118) teaches a vehicle receiving a cost using an interface which may be a wireless interface (Fuchs et al.; see col.10, particularly lines 63-67 and col.11, particularly lines 1-25, and col.6, particularly lines 60-67 and col.7, particularly lines 1-11).
Therefore, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Chen et al. with the teachings of Fuchs et al., and wherein one or a combination of the first cost of deviation and the second cost of deviation is collected over a wireless communication channel, as rendered obvious by Fuchs et al., in order to provide for “cooperatively coordinating future driving maneuvers of a vehicle with fellow maneuvers of at least one fellow vehicle” (Fuchs et al.; see Abstract).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ISAAC G SMITH whose telephone number is (571)272-9593. The examiner can normally be reached Monday-Thursday, 8AM-5PM.
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, ANISS CHAD can be reached at 571-270-3832. 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.
/ISAAC G SMITH/ Primary Examiner, Art Unit 3662