DETAILED ACTION
Remarks
This non-final office action is in response to the application filled on 06/11/2025. Claims 1-20 are pending and examined below.
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 .
Priority
Acknowledgment is made of applicant’s claim for domestic benefit under 35 U.S.C. 119 (e). The provisional application No. 63/702,084, was filed on 10/02/2024.
Information Disclosure Statement
As of date of this action, IDS filled has been annotated and considered.
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) 1-3, 11, 17, 18 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL title “Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking”, by (“Xu”), and further in view of US 2023/0202043 (“Xie”).
Regarding claim 1 (and similarly claim 11 and 20), Xu discloses a computer-implemented method for controlling a robot (see at least section III, C task and motion planning), the method comprising:
receiving a task and motion planning (TAMP)-domain language input, a goal,
(see at least fig 4, where data input to model, see also section III, A task planning, where “start state to the desired goal
condition”);
generating a plan skeleton based on the TAMP-domain language input, the goal,
(see at least section I, where “skeletons of discrete
symbolic actions (e.g., which objects to pick and place)”);
generating, based on the plan skeleton, one or more feasible particles (see at least fig 2); and
generating, based on the plan skeleton and at least one of the one or more
feasible particles, a robot plan (see at least fig 2, motion planning).
Xu does not disclose the following limitations:
receiving…sensor data;
generating a plan skeleton based on…the sensor data; and
sensor data causing the robot to perform at least part of the robot plan.
However, Xie discloses a method wherein receiving…sensor data (see at least [0067], where “receiving of control data and sensor data”);
generating a plan skeleton based on…the sensor data (see at least [0068], where “the planner performs path planning according to the target point and the sensor data collected by the sensor module received by the monitor, after finding the optimal path”); and
sensor data causing the robot to perform at least part of the robot plan (see at least [0006], where “control the robotic arm to complete an automation operation process by the control system module, and receiving joint data fed back in real-time of the sensor module”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Xu to incorporate the teachings of Xie by including the above feature for providing control instruction based on real-time feedback.
Regarding claim 2, Xie further discloses a method wherein determining the plan skeleton comprises:
generating, based on the sensor data, a state (see at least [0023] and [0025]); and
generating the plan skeleton further based on the state (see at least [0064], [0068] and [0073]).
Regarding claim 3, Xie further discloses a method wherein determining the plan skeleton comprises:
selecting, based on the state, one or more first actions included in the plan
skeleton (see at least [0050] and [0052]);
selecting, based on the goal, one or more second actions included in the first
actions (see at least [0068], where “target point”); and
generating, based on the one or more second actions, the plan skeleton (see at least [0068], where “optimal path”).
Regarding claim 17, Xu further discloses a system wherein generating the one or more particles comprises sampling a uniform distribution (see at least section IV, A collecting data, where “The position of the table and size of both bodies are uniformly randomly sampled.”).
Regarding claim 18, Xu further discloses a system wherein generating the one or more optimized particles comprises using at least one of a stochastic first-order optimizer, an augmented Lagrangian, coordinate descent, or a second-order optimizer (see at least section IV, B, where “the optimizer for model fitting”).
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL title “Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking”, by (“Xu”), and in view of US 2023/0202043 (“Xie”), as applied to claim 1 above, and further in view of US 2021/0000445 (“Tan”).
Regarding claim 4, Xu in view of Xie and Yao does not disclose claim 4. However, Tan a method wherein determining the plan skeleton comprises performing a best-first search of candidate plan skeletons (see at least [0042], where “Method 400 further includes generating 406 a planned trajectory using trajectory generation module 202 that satisfies the selected task by identifying a best fit trajectory from the reference anatomy scan trajectories from database 208”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Xu in view of Xie to incorporate the teachings of Tan by including the above feature for providing rapid directional focus, minimized memory overhead in open spaces, and drastically reduced node exploration.
Claim(s) 5-7 and 12-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL title “Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking”, by (“Xu”), and in view of US 2023/0202043 (“Xie”), as applied to claim 1 above, and further in view of US 2021/0316749 (“Yao”).
Regarding claim 5 (and similarly claim 12), Xu further discloses a method wherein determining the one or more feasible particles comprises:
generating, based on a candidate plan skeleton, one or more particles (see at least section II, A, where “candidate task plans”);
generating one or more optimized particles based on one or more constraints included in the candidate plan skeleton, (see at least fig 2); and
determining, based on the one or more optimized particles, the one or more
feasible particles (see at least section II, A, where “validate the feasibility of candidate
task plans”).
Xu in view of Xie does not disclose the following limitation:
generating one or more optimized particles based on…one or more cost functions included in the candidate plan skeleton.
However, Yao discloses a method wherein generating one or more optimized particles based on…one or more cost functions included in the candidate plan skeleton (see at least [0062], where “Referring to FIG. 7, a planned path of QP segment 721 may be generated by QP optimization based on the above cost function, according to the left constraints 710 and right lateral constraints 711 of the QP segment 721.”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Xu in view of Xie to incorporate the teachings of Yao by including the above feature for providing multi-objective balance, obstacle safety buffers, and computational adaptability.
Regarding claim 13 (and similarly claim 6), Xu further discloses a system wherein generating the one or more particles comprises caching one or more particle outputs from one or more samplers keyed at least by one of a constraint context or a parameter binding (see at least abstract, where “generating robot trajectories if several constraints are satisfied”).
Regarding claim 7 (and similarly claim 14), The computer-implemented method of claim 5, wherein generating the one or more optimized particles comprises solving a constraint satisfaction problem (see at least abstract, where “generating robot trajectories if several constraints are satisfied”).
Claim(s) 8 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL title “Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking”, by (“Xu”), and in view of US 2023/0202043 (“Xie”), as applied to claim 1 above, and in view of US 2021/0316749 (“Yao”), as applied to claim 5 above, and further in view of US 2023/0278582 (“Zhang”).
Regarding claim 8 (and similarly claim 15), Xu in view of Xie and Yao does not disclose claim 8. However, Zhang discloses a method wherein generating the one or more optimized particles comprises:
generating, based on the one or more cost functions included in the candidate
plan skeleton, one or more vectorized versions of the cost functions (see at least [0037], where “the score neural network model (122) may learn the costs associated with following a particular trajectory from the input vector and learn how to combine the costs into the trajectory score that is a predicted score for following the trajectory.”);
performing, based on the one or more vectorized versions of the cost functions,
at least one of a batch cost computation or a gradient evaluation in parallel (see at least [0083], where “a set of trajectories may be sampled and then processed as a batch computation.”); and
generating, based on at least one of the batch cost computation or the gradient
evaluation, the one or more optimized particles (see at least [0084] and [0098]).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Xu in view of Xie and Yao to incorporate the teachings of Zhang by including the above feature for gaining speed advantage during computation.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL title “Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking”, by (“Xu”), and in view of US 2023/0202043 (“Xie”), as applied to claim 1 above, and in view of US 2021/0316749 (“Yao”), as applied to claim 5 above, and further in view of US 2024/0221386 (“Appaya Dhanabalan”).
Regarding claim 9, Xu in view of Xie and Yao does not disclose claim 9. However, Appaya Dhanabalan discloses a method wherein generating the one or more optimized particles comprises at least one of a batch cost computation or a gradient evaluation performed on a graphics processing unit (GPU) (see at least [0116], where “The output engine 208 can optimize the cost function to determine an optimal motion plan for a tracking object”; see also [0136], where “graphics processing units (GPUs)”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Xu in view of Xie and Yao to incorporate the teachings of Appaya Dhanabalan by including the above feature for gaining speed advantage during computation.
Claim(s) 10 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL title “Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking”, by (“Xu”), and in view of US 2023/0202043 (“Xie”), as applied to claim 1 above, and further in view of US 2023/0179512 (“Drusinsky”).
Regarding claim 10 (and similarly claim 19), Xu further discloses a method wherein generating the robot plan comprises:
computing, based on the one or more feasible particles and the plan skeleton,
(see citation above); and
generating, based on the first feasible particle
skeleton, the robot plan (see citation above).
Xu in view of Xie does not disclose the following limitations:
computing…one or more ranks;
determining, based on the one or more ranks, a first feasible particle with a
highest rank; and
generating, based on the first feasible particle with the highest rank…, the robot plan.
However, Drusinky discloses a method wherein computing…one or more ranks (see at least [0013], where “ranking the potential paths by the generated score values”);
determining, based on the one or more ranks, a first feasible particle with a
highest rank (see at least [0014]); and
generating, based on the first feasible particle with the highest rank…, the robot plan (see at least [0013], where “navigate a vehicle or any other object associated with each agent along the highest ranked paths.”).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Xu in view of Xie to incorporate the teachings of Drusinky by including the above feature for comprehensive cost balancing.
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over NPL title “Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking”, by (“Xu”), and in view of US 2023/0202043 (“Xie”), as applied to claim 1 above, and in view of US 2021/0316749 (“Yao”), as applied to claim 12 above, and further in view of US 2023/0278593 (“Wang”).
Regarding claim 16, Xu further discloses a system wherein generating the one or more optimized particles comprises skeleton in the entry (see at least section II, B Heuristic for motion planning and C, learning to guide TAMP).
Xu in view of Xie does not disclose the following limitation:
selecting the candidate plan skeleton from a priority queue, wherein each entry in the priority queue is associated with a heuristic value.
However, Wang discloses a system wherein generating the one or more optimized particles comprises selecting the candidate plan skeleton from a priority queue, wherein each entry in the priority queue is associated with a heuristic value (see at least [0099], [0101] and [0103]).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to have modified Xu in view of Xie and Yao to incorporate the teachings of Wang by including the above feature for navigating path efficiently by combining actual path cost and estimated goal distance.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SOHANA TANJU KHAYER whose telephone number is (408)918-7597. The examiner can normally be reached on Monday - Thursday, 7 am-5.30 pm, PT.
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, Abby Lin can be reached on 571-270-3976. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SOHANA TANJU KHAYER/Primary Examiner, Art Unit 3657
Prosecution Insights