Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 05/18/2026 has been entered.
Response to Arguments
Applicant's arguments, filed 05/18/2026, regarding the rejection of claims 1-22 under 35 U.S.C. 103 have been fully considered but they are not persuasive. Applicant argues on pages 8-11 that the prior art, particularly Jaekel, Wu, and Yang, do not teach the amended claim language of independent claims 1, 11, and 19, particularly regarding the pull-back operation involving propagation of a “motion policy” of a child node from the child node to a parent node of the child node in the directed tree, where the child node comprises both a state and a motion policy, as recited in amended Claim 1. However, Wu expressly describes the pullback operation as “the operation of reversely transmitting the state and acceleration of the child node to the father node and obtaining the acceleration of the father node”, as described previously and in further detail below. Additionally, the remaining elements of the amended claims are disclosed by Yang, as detailed below. Likewise, the dependent claims previously rejected that have not been amended are also rejected in view of Jaekel, Wu, and Yang.
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(s) 1-4, 6-21, and 23-24 are rejected under 35 U.S.C. 103 as being unpatentable over Jaekel et al. US 20170190052 A1 (“Jaekel”) in combination with Wu et al. CN 115972196 A (“Wu”) and Yang et al. US 20230294277 A1 (“Yang”).
Regarding Claim 1. Jaekel teaches a system for generating a motion policy for a robotic device, the system comprising:
memory that stores computer-executable instructions; and
a processor in communication with the memory, wherein the computer- executable instructions, when executed by the processor (Claim 35 describes a robot processor for carrying out the program. A robot controller can also be utilized to perform the methods described [paragraph 11]. Claim 35 also describes a non-transitory computer-readable storage medium), cause the processor to:
process a request to move a subcomponent of the robotic device to a target position (A motion planning system for steering the tool center point (TCP), so that a tool, such as a welding gun, moves on the firmly programmed motion path [paragraph 12]. This tool, or manipulator, or end effector is a subcomponent of the robot);
obtain sensor data from the robotic device (Sensors are commonly used in continuous path and analogous playback, such as a force-torque sensor [paragraph 7], but in Jaekel’s method, additional sensors are used, for, example, the projection of a laser line onto a component, the capturing of this line with a camera system and the conversion of the detected line into a motion path for the robot [paragraph 8]);
determine one or more subtasks for moving the subcomponent of the robotic device to the target position using the sensor data (Waypoints, representing a goal or intermediate point of a movement command, such as a point-to-point movement, can be entered by the operator [paragraph 6], which can be saved via the teach-in program [paragraph 7]. These points represent subtasks in the task of moving to an end goal. This motion path to the end goal is the task, and the midpoints represent the subtasks);
generate a directed tree using the determined one or more subtasks (a motion path can be calculated for each execution module of the motion template, preferably using path planning algorithms, for example, the rapidly exploring random tree algorithm [paragraph 56]. Paragraph 98 explains the motion path generation in more detail);
determine that the global configuration space policy, when implemented, results in the subcomponent of the robotic device reaching an equilibrium state at a second position that is at least the threshold distance from the target position (Paragraphs 117-124 describe a process for determining that the path planning algorithm results in the subcomponent of the robotic device reaching an equilibrium state at the target position. This process further involves computing the sum of target vectors and moving the robot relative to the computed sum [paragraphs 372-373], which reads on a threshold distance);
generate a randomized motion policy in response to the determination that the global configuration space policy results in the subcomponent of the robotic device reaching the equilibrium state at the second position (paragraphs 86-94); and
cause the robotic device to move the subcomponent of the robotic device to the target position according to the randomized motion policy (FIG. 10, [paragraphs 245-246]).
Jaekel does not explicitly teach:
traverse the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree.
However, Wu teaches:
traverse the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree (The method described in steps 1-3 on page 5 of the original document, particularly step 3, which reads “generating strategy: composed of forward push and pull back two operation operations; the forward push is the operation operation of transmitting the state from the parent node of the task mapping tree to the sub-node of the task mapping tree; the back-pull is to reversely transmit the state and acceleration of the sub-node of the task mapping tree to the father node of the task mapping tree and obtain the operation operation of the acceleration of the father node; namely in each control period, firstly using the forward push operation recursively propagating the position and speed information in each sub-task space, according to the geometric dynamic system in step (2) to obtain the acceleration of the sub-task space, and then recursively obtaining the acceleration of each task space to obtain the acceleration of the global task recursively using the backpull operation”. Further, in the paragraph beginning with “Return:” which explains what is meant by the pullback operation, it expressly states that “[t]he pullback is the operation of reversely transmitting the state and acceleration of the child node to the father node and obtaining the acceleration of the father node”).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with traverse the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree as taught by Wu so as to streamline the motion planning of the robot, as described in the background of Wu.
Jaekel also does not teach:
wherein each node of the directed tree comprises a state and a Riemannian motion policy;
wherein the motion policy is a Riemannian motion policy.
However, Yang teaches:
wherein each node of the directed tree comprises a state and a Riemannian motion policy;
wherein the motion policy is a Riemannian motion policy (Given a selected grasp, a robot in an existing system is typically driven towards the grasp end-effector pose by local (or non-global) policies, such as may include Riemannian Motion Policies or visual servoing [paragraph 31]).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with wherein each node of the directed tree comprises a state and a Riemannian motion policy; wherein the motion policy is a Riemannian motion policy as taught by Yang so as to smoothen the motion from one position to another in the robot movement, as described in paragraph 31 of Yang.
Regarding Claim 2. Jaekel in combination with Wu and Yang teaches the system of Claim 1.
Jaekel also teaches:
wherein the computer-executable instructions, when executed, further cause the processor to:
decompose an overall task of moving the subcomponent to the target position into the one or more subtasks (Waypoints, representing a goal or intermediate point of a movement command, such as a point-to-point movement, can be entered by the operator [paragraph 6], which can be saved via the teach-in program [paragraph 7]. These points represent subtasks in the task of moving to an end goal. This motion path to the end goal is the task, and the midpoints represent the subtasks).
Jaekel does not teach:
generate a Riemannian motion policy for each subtask in the one or more subtasks.
However, Yang teaches:
generate a Riemannian motion policy for each subtask in the one or more subtasks (Given a selected grasp, a robot in an existing system is typically driven towards the grasp end-effector pose by local (or non-global) policies, such as may include Riemannian Motion Policies or visual servoing [paragraph 31]).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with generate a Riemannian motion policy for each subtask in the one or more subtasks as taught by Yang so as to smoothen the motion from one position to another in the robot movement, as described in paragraph 31 of Yang.
Regarding Claim 3. Jaekel in combination with Wu and Yang teaches the system of claim 1.
Jaekel also teaches:
wherein the computer-executable instructions, when executed, further cause the processor to generate the root node, one or more child nodes, and the leaf nodes to form the directed tree (this is inherent to how rapidly exploring random tree algorithms work), wherein the leaf node represents one of the one or more subtasks (a motion path can be calculated for each execution module of the motion template, preferably using path planning algorithms, for example, the rapidly exploring random tree algorithm [paragraph 56]. Paragraph 98 explains the motion path generation in more detail).
Regarding Claim 4. Jaekel in combination with Wu and Yang teaches the system of claim 1.
Jaekel also teaches:
wherein the computer-executable instructions, when executed, further cause the processor to:
apply a resolve operation to results of the pushforward operation and the pullback operation to generate the global configuration space policy (FIGS. 6-10 show visual configurations of the configurations T1-T6 that are generated by an operator and that are intended for programming the robot 7 for screwing in accordance with field of application shown in FIG. 5 [paragraph 230]. These involve moving forward to the screw at 12, and in FIG. 10, moving back from the screw. The execution modules with parameters generated thusly can then be mapped to a target system, which serves as a resolve operation [paragraphs 290-291]. These motion plans are generated using the rapidly exploring random tree algorithm [paragraph 291]).
Regarding Claim 6. Jaekel in combination with Wu and Yang teaches the system of claim 1.
Jaekel also teaches:
wherein the request to move the subcomponent comprises an indication of a location of the target position and an indication of a behavior for the subcomponent to perform when reaching the target position (The movement of an end effector (subcomponent) along with its velocity and/or acceleration, position and/or orientation of the tool center point of the robot relative to a coordinate system, can all be constraints for the robot control [paragraphs 30-36]).
Regarding Claim 7. Jaekel in combination with Wu and Yang teaches the system of claim 6.
Jaekel also teaches:
wherein the behavior comprises one of follow, move to pose, move towards pose, grasp, release, scan, catch, throw, push, pull, handoff, drill, or weld (FIGS. 6-10 shows the robot moving towards and moving away from a screw. These actions can include a screwing operation [paragraph 188]).
Regarding Claim 8. Jaekel in combination with Wu and Yang teaches the system of claim 6.
Jaekel also teaches:
wherein the computer-executable instructions, when executed, further cause the processor to cause the subcomponent of the robotic device to perform the behavior when the subcomponent of the robotic devices reaches the target position (According to FIG. 9, the operator activates the screwdriver 10, screws in the screw 12 and stops the screwdriver 10. The operator repeats the process and saves two redundant configurations T4 and T5, each at the end of the movement [paragraph 240]. Note that the operator does not have to be a person, it can be a basic operator, multiple execution modules, a path planner relying on one or more controllers [paragraph 145]).
Regarding Claim 9. Jaekel in combination with Wu and Yang teaches the system of claim 1.
Jaekel also teaches:
wherein the subcomponent of the robotic device comprises an end effector of the robotic device (A motion planning system for steering the tool center point (TCP), so that a tool, such as a welding gun, moves on the firmly programmed motion path [paragraph 12]. This tool, or manipulator, or end effector is a subcomponent of the robot).
Regarding Claim 10. Jaekel in combination with Wu and Yang teaches the system of Claim 1.
Jaekel does not teach:
wherein the directed tree comprises a Riemannian motion policy tree.
However, Yang teaches:
wherein the directed tree comprises a Riemannian motion policy.
Yang is not explicit that this is a Riemannian motion policy tree. However, Yang teaches both a logic tree and a Riemannian motion policy, and applying the two well-known mathematical frameworks to form a Riemannian motion policy and modifying Jaekel to include this modification would have been obvious to one of ordinary skill in the art at the time the invention was filed so as to smoothen the motion of the robot.
Regarding Claim 11. Jaekel teaches a computer-implemented method for generating a motion policy for a robotic device (A motion planning system for steering the tool center point (TCP), so that a tool, such as a welding gun, moves on the firmly programmed motion path [paragraph 12]. This tool, or manipulator, or end effector is a subcomponent of the robot), the computer-implemented method comprising:
receiving a request to move a subcomponent of the robotic device to a target position (A motion planning system for steering the tool center point (TCP), so that a tool, such as a welding gun, moves on the firmly programmed motion path [paragraph 12]. This tool, or manipulator, or end effector is a subcomponent of the robot);
determining one or more subtasks for moving the subcomponent of the robotic device to the target position (Waypoints, representing a goal or intermediate point of a movement command, such as a point-to-point movement, can be entered by the operator [paragraph 6], which can be saved via the teach-in program [paragraph 7]. These points represent subtasks in the task of moving to an end goal. This motion path to the end goal is the task, and the midpoints represent the subtasks);
generating a directed tree using the determined one or more subtasks (a motion path can be calculated for each execution module of the motion template, preferably using path planning algorithms, for example, the rapidly exploring random tree algorithm [paragraph 56]. Paragraph 98 explains the motion path generation in more detail);
determining that the global configuration space policy, when implemented, results in the subcomponent of the robotic device reaching an equilibrium state at a second position that is at least a threshold distance from the target position (Paragraphs 117-124 describe a process for determining that the path planning algorithm results in the subcomponent of the robotic device reaching an equilibrium state at the target position. This process further involves computing the sum of target vectors and moving the robot relative to the computed sum [paragraphs 372-373], which reads on a threshold distance);
generating a randomized motion policy in response to the determination that the global configuration space policy results in the subcomponent of the robotic device reaching the equilibrium state at the second position (paragraphs 86-94); and
causing the robotic device to move the subcomponent of the robotic device to the target position according to the randomized motion policy (FIG. 10, [paragraphs 245-246]).
Jaekel does not explicitly teach:
traversing the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree.
However, Wu teaches:
traversing the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree (The method described in steps 1-3 on page 5 of the original document, particularly step 3, which reads “generating strategy: composed of forward push and pull back two operation operations; the forward push is the operation operation of transmitting the state from the parent node of the task mapping tree to the sub-node of the task mapping tree; the back-pull is to reversely transmit the state and acceleration of the sub-node of the task mapping tree to the father node of the task mapping tree and obtain the operation operation of the acceleration of the father node; namely in each control period, firstly using the forward push operation recursively propagating the position and speed information in each sub-task space, according to the geometric dynamic system in step (2) to obtain the acceleration of the sub-task space, and then recursively obtaining the acceleration of each task space to obtain the acceleration of the global task recursively using the backpull operation”. Further, in the paragraph beginning with “Return:” which explains what is meant by the pullback operation, it expressly states that “[t]he pullback is the operation of reversely transmitting the state and acceleration of the child node to the father node and obtaining the acceleration of the father node”).
Jaekel also does not teach:
wherein each node of the directed tree comprises a state and a Riemannian motion policy;
wherein the motion policy is a Riemannian motion policy.
However, Yang teaches:
wherein each node of the directed tree comprises a state and a Riemannian motion policy;
wherein the motion policy is a Riemannian motion policy (Given a selected grasp, a robot in an existing system is typically driven towards the grasp end-effector pose by local (or non-global) policies, such as may include Riemannian Motion Policies or visual servoing [paragraph 31]).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with wherein each node of the directed tree comprises a state and a Riemannian motion policy; wherein the motion policy is a Riemannian motion policy as taught by Yang so as to smoothen the motion from one position to another in the robot movement, as described in paragraph 31 of Yang.
Regarding Claim 12. Jaekel in combination with Wu and Yang teaches the computer-implemented method of Claim 11.
Jaekel also teaches:
wherein determining one or more subtasks further comprises:
decomposing an overall task of moving the subcomponent to the target position into the one or more subtasks (Waypoints, representing a goal or intermediate point of a movement command, such as a point-to-point movement, can be entered by the operator [paragraph 6], which can be saved via the teach-in program [paragraph 7]. These points represent subtasks in the task of moving to an end goal. This motion path to the end goal is the task, and the midpoints represent the subtasks).
Jaekel does not teach:
generate a Riemannian motion policy for each subtask in the one or more subtasks.
However, Yang teaches:
generate a Riemannian motion policy for each subtask in the one or more subtasks (Given a selected grasp, a robot in an existing system is typically driven towards the grasp end-effector pose by local (or non-global) policies, such as may include Riemannian Motion Policies or visual servoing [paragraph 31]).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with generate a Riemannian motion policy for each subtask in the one or more subtasks as taught by Yang so as to smoothen the motion from one position to another in the robot movement, as described in paragraph 31 of Yang.
Regarding Claim 13. Jaekel in combination with Wu and Yang teaches the computer-implemented method of Claim 11.
Jaekel also teaches:
wherein generating a directed tree further comprises generating the root node, one or more child nodes, and the leaf nodes to form the directed tree (this is inherent to how rapidly exploring random tree algorithms work), wherein the leaf node represents one of the one or more subtasks (a motion path can be calculated for each execution module of the motion template, preferably using path planning algorithms, for example, the rapidly exploring random tree algorithm [paragraph 56]. Paragraph 98 explains the motion path generation in more detail).
Regarding Claim 14. Jaekel in combination with Wu and Yang teaches the computer-implemented method of Claim 11.
Jaekel also teaches:
wherein traversing the directed tree further comprises:
applying a resolve operation to results of the pushforward operation and the pullback operation to generate the global configuration space policy (FIGS. 6-10 show visual configurations of the configurations T1-T6 that are generated by an operator and that are intended for programming the robot 7 for screwing in accordance with field of application shown in FIG. 5 [paragraph 230]. These involve moving forward to the screw at 12, and in FIG. 10, moving back from the screw. The execution modules with parameters generated thusly can then be mapped to a target system, which serves as a resolve operation [paragraphs 290-291]. These motion plans are generated using the rapidly exploring random tree algorithm [paragraph 291]).
Regarding Claim 16. Jaekel in combination with Wu and Yang teaches the computer-implemented method of Claim 11.
Jaekel also teaches:
wherein the request to move the subcomponent comprises an indication of a location of the target position and an indication of a behavior for the subcomponent to perform when reaching the target position (The movement of an end effector (subcomponent) along with its velocity and/or acceleration, position and/or orientation of the tool center point of the robot relative to a coordinate system, can all be constraints for the robot control [paragraphs 30-36]).
Regarding Claim 17. Jaekel in combination with Wu and Yang teaches the computer-implemented method of Claim 11.
Jaekel also teaches:
wherein the behavior comprises one of follow, move to pose, move towards pose, grasp, release, scan, catch, throw, push, pull, handoff, drill, or weld (FIGS. 6-10 shows the robot moving towards and moving away from a screw. These actions can include a screwing operation [paragraph 188]).
Regarding Claim 18. Jaekel in combination with Wu and Yang teaches the computer-implemented method of Claim 16.
Jaekel also teaches:
further comprising causing the subcomponent of the robotic device to perform the behavior when the subcomponent of the robotic devices reaches the target position (According to FIG. 9, the operator activates the screwdriver 10, screws in the screw 12 and stops the screwdriver 10. The operator repeats the process and saves two redundant configurations T4 and T5, each at the end of the movement [paragraph 240]. Note that the operator does not have to be a person, it can be a basic operator, multiple execution modules, a path planner relying on one or more controllers [paragraph 145]).
Regarding Claim 19. Jaekel teaches a non-transitory, computer-readable medium comprising computer-executable instructions for generating a motion policy for a robotic device (A motion planning system for steering the tool center point (TCP), so that a tool, such as a welding gun, moves on the firmly programmed motion path [paragraph 12]. This tool, or manipulator, or end effector is a subcomponent of the robot. Claim 36 adds that this system can include a non-transitory storage medium having computer coding to perform the described functions of the system), wherein the computer- executable instructions, when executed by a computer system, cause the computer system to:
process a request to move a subcomponent of the robotic device to a target position (A motion planning system for steering the tool center point (TCP), so that a tool, such as a welding gun, moves on the firmly programmed motion path [paragraph 12]. This tool, or manipulator, or end effector is a subcomponent of the robot);
generate a directed tree based on the request (a motion path can be calculated for each execution module of the motion template, preferably using path planning algorithms, for example, the rapidly exploring random tree algorithm [paragraph 56]. Paragraph 98 explains the motion path generation in more detail);
determine that the global configuration space policy, when implemented, results in the subcomponent of the robotic device reaching an equilibrium state at a second position that is at least a threshold distance from the target position (Paragraphs 117-124 describe a process for determining that the path planning algorithm results in the subcomponent of the robotic device reaching an equilibrium state at the target position. This process further involves computing the sum of target vectors and moving the robot relative to the computed sum [paragraphs 372-373], which reads on a threshold distance);
generate a randomized motion policy in response to the determination that the global configuration space policy results in the subcomponent of the robotic device reaching the equilibrium state at the second position (paragraphs 86-94); and
cause the robotic device to move the subcomponent of the robotic device to the target position according to the randomized motion policy (FIG. 10, [paragraphs 245-246]).
Jaekel does not explicitly teach:
traverse the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree.
However, Wu teaches:
traverse the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree (The method described in steps 1-3 on page 5 of the original document, particularly step 3, which reads “generating strategy: composed of forward push and pull back two operation operations; the forward push is the operation operation of transmitting the state from the parent node of the task mapping tree to the sub-node of the task mapping tree; the back-pull is to reversely transmit the state and acceleration of the sub-node of the task mapping tree to the father node of the task mapping tree and obtain the operation operation of the acceleration of the father node; namely in each control period, firstly using the forward push operation recursively propagating the position and speed information in each sub-task space, according to the geometric dynamic system in step (2) to obtain the acceleration of the sub-task space, and then recursively obtaining the acceleration of each task space to obtain the acceleration of the global task recursively using the backpull operation”. Further, in the paragraph beginning with “Return:” which explains what is meant by the pullback operation, it expressly states that “[t]he pullback is the operation of reversely transmitting the state and acceleration of the child node to the father node and obtaining the acceleration of the father node”).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with traverse the directed tree recursively by application of a pushforward operation in a first pass from a root node of the directed tree to a leaf node of the directed tree and application of a pullback operation in a second pass from the leaf node to the root node to propagate a value to the root node and generate a global configuration space policy that defines one of a position or a movement of the subcomponent of the robotic device that results in the subcomponent of the robotic device reaching within a threshold distance of the target position, wherein the pullback operation comprises propagation of a natural form of a motion policy of a child note in the directed tree from the child node to a parent node of the child node in the directed tree as taught by Wu so as to streamline the motion planning of the robot, as described in the background of Wu.
Jaekel also does not teach:
wherein each node of the directed tree comprises a state and a Riemannian motion policy;
wherein the motion policy is a Riemannian motion policy.
However, Yang teaches:
wherein each node of the directed tree comprises a state and a Riemannian motion policy;
wherein the motion policy is a Riemannian motion policy (Given a selected grasp, a robot in an existing system is typically driven towards the grasp end-effector pose by local (or non-global) policies, such as may include Riemannian Motion Policies or visual servoing [paragraph 31]).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with wherein each node of the directed tree comprises a state and a Riemannian motion policy; wherein the motion policy is a Riemannian motion policy as taught by Yang so as to smoothen the motion from one position to another in the robot movement, as described in paragraph 31 of Yang.
Regarding Claim 20. Jaekel in combination with Wu and Yang teaches the non-transitory, computer-readable medium of Claim 19.
Jaekel also teaches:
wherein the request to move the subcomponent comprises an indication of a location of the target position and an indication of a behavior for the subcomponent to perform when reaching the target position (The movement of an end effector (subcomponent) along with its velocity and/or acceleration, position and/or orientation of the tool center point of the robot relative to a coordinate system, can all be constraints for the robot control [paragraphs 30-36]), and wherein the computer-executable instructions, when executed, further cause the computer system to cause the subcomponent of the robotic device to perform the behavior when the subcomponent of the robotic devices reaches the target position (According to FIG. 9, the operator activates the screwdriver 10, screws in the screw 12 and stops the screwdriver 10. The operator repeats the process and saves two redundant configurations T4 and T5, each at the end of the movement [paragraph 240]. Note that the operator does not have to be a person, it can be a basic operator, multiple execution modules, a path planner relying on one or more controllers [paragraph 145]).
Regarding Claim 21. Jaekel in combination with Wu teaches the system of claim 1.
Jaekel does not teach:
wherein the pushforward operation comprises propagation of a state of a first node in the directed tree to update a state of one or more second child nodes of the first node in the directed tree, from the root node to the leaf node.
However, Wu teaches:
wherein the pushforward operation comprises propagation of a state of a first node in the directed tree to update a state of one or more second child nodes of the first node in the directed tree, from the root node to the leaf node (Step 3 of the method on page 5, beginning with “(3) generating strategy: composed of forward push…”).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with wherein the pushforward operation comprises propagation of a state of a first node in the directed tree to update a state of one or more second child nodes of the first node in the directed tree, from the root node to the leaf node as taught by Wu so as to further optimize the process of motion planning for the robot.
Regarding Claim 23. Jaekel in combination with Wu and Yang teaches the system of claim 1.
Jaekel does not teach:
wherein the value comprises a weighted combination of leaf node Riemannian motion policies.
However, Yang teaches:
wherein the value comprises a weighted combination of leaf node Riemannian motion policies (Paragraph 54, and especially the formula contained therein shows how a weighted combination is applied to the Riemannian motion policy of paragraph 31).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with wherein the value comprises a weighted combination of leaf node Riemannian motion policies as taught by Yang so as to further manipulate the results of the motion planning policy as needed for the task at hand, as discussed by Yang in paragraph 52.
Regarding Claim 24. Jaekel in combination with Wu teaches the system of claim 1.
Jaekel does not teach:
wherein the motion policy comprises a mapping of a pose and velocity of an object corresponding to the child node to an acceleration of the object on a manifold and a matrix that defines a geometric structure of the manifold (Jaekel does teach that the motion policy can include velocity and pose (orientation) information of an object in paragraphs 67 and 73, but does not teach that they are mapped to the child node).
However, Wu teaches:
wherein the motion policy comprises a mapping of a pose and velocity of an object corresponding to the child node to an acceleration of the object on a manifold and a matrix that defines a geometric structure of the manifold (FIG. 2, as well as the paragraph beginning with “As shown in FIG. 2”. Additionally, a metric matrix detailing speed and direction (velocity) is used to define a structure in the manifold shown in FIG. 3 in the paragraph beginning with “in the formula,” therein defining the metric matrix. Further, the pullback in the step (3), specifically, the state and acceleration of the sub-node is reversely propagated to the parent node and obtaining the operation operation of the parent node acceleration, the calculation of the optimal father node acceleration can be according to a least squares formula shown on page 3 of Wu).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with wherein the motion policy comprises a mapping of a pose and velocity of an object corresponding to the child node to an acceleration of the object on a manifold and a matrix that defines a geometric structure of the manifold as taught by Wu so as to allow the system to map the pose and velocity information of the object as already taught by Jaekel.
Claim(s) 5 is rejected under 35 U.S.C. 103 as being unpatentable over Jaekel et al. US 20170190052 A1 (“Jaekel”) in view of Wu et al. CN 115972196 A (“Wu”) and Yang et al. US 20230294277 A1 (“Yang”) as applied to claim 1 above, and further in view of Riley Knox, "Pathfinding with Randomly-Explored Random Tree," 2021, Galada (“Knox”).
Regarding Claim 5. Jaekel in combination with Wu and Yang teaches the system of Claim 1.
Jaekel also teaches:
wherein the computer-executable instructions, when executed, further cause the processor to:
select a random position (paragraphs 320-327 how a random point is selected for calculating a random vector);
identify a first point that is a closest point to the selected random position (paragraphs 320-327);
determine that motion from the first node to the selected random position is collision-free (paragraph 310);
add a second point that corresponds to the selected random position and a link between the first point and the second point (paragraphs 320-327); and
identify a shortest path between a third point that represents an initial position of the subcomponent and the one of the additional points that is within the threshold distance of the target position, wherein the shortest path represents the randomized motion policy (a distance magnitude constraint function calculates the shortest distance between two points of the first and second model [paragraph 311]).
Jaekel does not explicitly teach:
the random position is between nodes of a search tree and the target position;
the points are nodes in the search tree; and
add one or more additional nodes to the search tree until one of the additional nodes is within the target distance of the target position.
However, Riley teaches:
the random position is between nodes of a search tree and the target position;
the points are nodes in the search tree; and
add one or more additional nodes to the search tree until one of the additional nodes is within the target distance of the target position (The entire document, but particularly pages 2 and 3).
It would have been obvious to one of ordinary skill in the art at the time the invention was filed to modify the invention of Jaekel with the random position is between nodes of a search tree and the target position; the points are nodes in the search tree; and add one or more additional nodes to the search tree until one of the additional nodes is within the target distance of the target position as taught by Riley, in part because this appears to be how Random Tree path exploration works, and because it is a known method for selecting random points and generating a motion path with a high probability of success.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AARON G CAIN whose telephone number is (571)272-7009. The examiner can normally be reached Monday: 7:30am - 4:30pm EST to Friday 7:30pm - 4:30am.
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, Wade Miles can be reached at (571) 270-7777. 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.
/AARON G CAIN/Examiner, Art Unit 3656
Prosecution Insights