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 .
Response to Amendment
The amendment filed 12/08/2025 has been entered. Claims 1, 4-6, 8-10, 13-15, and 17-20 remain pending in the application. Applicant’s amendments to the claims, specification, and drawings have overcome each and every objection and rejection under 35 U.S.C. 112(b) previously set forth in the Non-Final Office Action mailed 9/12/2025.
Response to Arguments
Applicant argues that Chu does not disclose the following features of amended claims 1 and 10:
determining a plurality of intermediate states associated with the object, the intermediate states defining respective motion sequences for the object to reach the goal state from the initial state,
wherein determining the plurality of intermediate states is based on the initial state, a pose associated with the goal state of the object which is determined by performing the pose estimation, and the task;
selecting one of the motion sequences, so as to define a selected motion sequence;
Specifically, Applicant asserts that Chu only describes atomic actions to take in order to meet the goal specification. This argument asserts that the PDDL planning solver generates a single sequence of executable atomic actions whose execution achieves the desired goal state. In contrast, Applicant defines a plurality of intermediate states, which includes a plurality of sequences of actions, and asserts that Chu only teaches the generation of only a single sequence of actions.
Applicant’s remarks regarding the “Planning with PDDL” section of Chu are exceedingly narrow and neglect to address the fact that Chu discloses that “each action involve(s) an intermediate state change of the objects in the environment and/or manipulator”. Chu specifically addresses in this section “scenarios where an intermediate goal exists” through the implementation of a “state keeper” with the PDDL. Ultimately, Applicant’s arguments are not persuasive, and the reference of Chu will be applied again below.
Aside from the direct acknowledgment of intermediate states in the disclosure of Chu, the claim language is additionally very broad. In the realm of robotic motion planning, “intermediate states associated with the object” are very common, even outside of the specific affordance planning of the present application. The “respective motion sequences for the object to reach the goal state from the initial state” could refer to a variety of motion planning methods, such as calculating multiple routes for the purposes of obstacle avoidance. Even more broadly, the intermediate states are based on the initial state, the goal state pose, and the task, which once again can apply to a vast variety of pick-and-place robotic motion actions.
Claim Rejections - 35 USC § 102
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 1, 4-6, 9-10, 13-15, and 18 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Chu et al., hereinafter Chu (NPL Reference: Recognizing object affordances to support scene reasoning for manipulation tasks).
Regarding claims 1 and 10, Chu teaches a method for operating an autonomous machine in a physical environment, and an autonomous system, the method and system comprising:
detecting an object within the physical environment (see at least Page 10: “. In the experiment setting, the sensor input includes depth information. Image areas with target affordances are mapped to 3D space for manipulation planning and execution.” Additionally, the object is detected in the final paragraph on page 10 before analysis occurs. See also FIG. 2);
performing pose estimation on the object so as to determine an initial state of the object (see at least Page 10: “the grasp center is computed by averaging the grasp-able pixels, with grasping orientation determined by fitting a line to predicted pixels”. See also FIG. 2 for detecting an object and its initial state.);
identifying a task that requires that the autonomous machine interact with the object (see at least FIG.2 and the caption wherein the task is to place objects sequentially into a bowl);
based on the task, determining a goal state of the object (see at least FIG.2 and the caption wherein the plan is crucially linked to the known goal state of the object. See also Page 5: “The provision of a specified goal state”);
determining a plurality of intermediate states associated with the object, the intermediate states defining respective motion sequences for the object to reach the goal state from the initial state, wherein determining the plurality of intermediate states is based on the initial state, a pose associated with the goal state of the object which is determined by performing the pose estimation, and the task (see at least Page 7: “Goal-oriented manipulation may require an agent to achieve a goal state via a sequence of atomic actions, with each action involving an intermediate state change of the objects in the environment and/or the manipulator.” The actions are determined based on the “initial state and goal state descriptions” as well as a “domain definition” that includes the task and its corresponding effects. See also the generation of “a list of executable atomic actions for a robotic manipulator” for respective motion sequences. For a pose of the goal state see at least Page 10-11: “For experiments involving the grasp affordance, the grasp center is computed by averaging the grasp-able pixels, with grasping orientation determined by fitting a line to predicted pixels.” The pose of the object in the goal state is thus known to the system. Finally, see at least the section “Affordance with modified PDDL pipeline” on Page 11 which details methodology for using a “state keeper module” to work between states to work towards a goal);
selecting one of the motion sequences, so as to define a selected motion sequence (See at least Page 7: “the planned sequence is solved by Fast Downward”, wherein the planned sequence is a selected motion sequence. See also Page 14 which describes a grasp detector designed to choose a desired grasp from a candidate list when performing affordance evaluation); and
the autonomous machine performing the selected motion sequence, thereby fulfilling the task (see at least the Abstract: “execution completes the target task.”).
Regarding claim 10 specifically, Chu teaches
an autonomous machine configured to operate in a physical environment (robotic manipulator);
a processor (see at least FIG. 8 and Page 10 for description of a “7-DoF robotic manipulator” which processors sensor information as is known in the art); and
a memory storing instructions that, when executed by the processor, cause the autonomous system to perform the steps above (see at least FIG. 8 and Page 10 for description of a “7-DoF robotic manipulator” which processors sensor information and necessarily needs memory to execute the steps).
Regarding claims 4 and 13, Chu teaches the method as recited in claim 1, and the system as recited in claim 12, and Chu teaches determining the plurality of intermediate steps further comprises:
performing an affordance analysis on the object so as to determine a plurality of feasible actions for the autonomous machine in completing the task (see at least FIG. 2 and the caption: “Together with a pre-trained object detector, both objects and affordances in the robot’s view are identified” See also Page 3: “convert the recognized affordances (and objects) into executable action primitives based on simple specifications”).
Regarding claims 5 and 14, Chu teaches the method as recited in claim 1, and the system as recited in claim 10, and Chu teaches determining the plurality of intermediate states further comprises:
generating an affordance map associated with the object, based on the affordance map, determining that the goal state of the object is not reachable without reaching at least one of the plurality of intermediate states (see at least Page 11 wherein the section “Affordance for Task-Oriented Grasping” describes the generation of an affordance map and depth image for objects, and details the exemplary task types. See also Pages 12-13 which outline successes in each scenario as necessitating multiple steps reached with the intermediate states).
Regarding claims 6 and 15, Chu teaches the method as recited in claim 5, and the system as recited in claim 14, and Chu teaches the method and the system further comprising:
based on the affordance map and task, generating at least one intermediate state of the plurality of intermediate states, the at least one additional intermediate state enabling the goal state to be reachable (see at least the section “Affordance with modified PDDL pipeline” on Page 11 which details methodology for using a “state keeper module” to work between states to work towards a goal, as well as on Page 13: “A successful cut through string trial requires the manipulator to first grasp the target tool without dropping it, and then fully cut the string with the target”); and
augmenting the affordance map with the at least one additional intermediate state (see at least the section “Affordance as Auxiliary Task and Attribute” which defines a real time process for augmenting an affordance map while performing auxiliary, or intermediate, tasks.).
Regarding claims 9 and 18, Chu teaches the method as recited in claim 1, and the system as recited in claim 10, and Chu teaches performing the selected motion sequence further comprises:
executing a first state transition of the plurality of state transitions (see at least Page 7 for executing a first state transition using “a state keeper”); and
before executing a second state transition of the plurality of state transitions that directly follows the first state transition, determining whether a first intermediate state associated with the first state transition is reached (see at least Page 7 wherein the description of “state persistence” using the state keeper ensure that the robot determines an intermediate state is reached before continuing in the pursuit of a final goal state).
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 8 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chu in view of Mandlekar et al., hereinafter Mandlekar (Document ID: US 11958529 B2).
Regarding claims 8 and 17, Chu teaches the method as recited in claim 5, and the system as recited in claim 14, and Chu teaches known methods for decision making on Page 8 in the section “Baseline Methods”. But Chu does not explicitly teach selecting one of the motion sequences further comprises:
solving a Markov decision problem defined by the initial state, the goal state, and the plurality of the intermediate states.
Instead, Mandlekar teaches in Col 6, Line 3 the use of a Markov Decision Process for a robot manipulation task that considers the initial state, the next state(s) and the reward or goal state.
It would have been obvious to one of ordinary skill in the art before the filing date of the claimed invention to have modified the affordance analysis for task based robotic manipulation of Chu with the Markov Decision Process of Mandlekar in order to execute a design choice to use known methods of decision making for organizing robot motion.
Claim(s) 19 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chu in view of Buerger et al., hereinafter Buerger (Document ID: US 20190351542 A1) .
Regarding claims 19 and 20, Chu teaches the method as recited in claim 1, and the system as recited in claim 10, but Chu does not explicitly teach selecting one of the motion sequences comprises:
determining that the selected motion sequence defines a path that is shorter than the other motion sequences.
Instead, Buerger, whose invention pertains to considering a cost analysis for a robotic system, teaches a method for constraining robots to perform tasks according to shortest paths traversed in P [0081].
It would have been obvious to one of ordinary skill in the art before the filing date of the claimed invention to have modified the affordance analysis for task based robotic manipulation of Chu with the cost analysis for task allocation to a robot of Buerger in order to execute a design choice that selects robot motion paths based minimizing costs and promoting efficiency as in Buerger.
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.
Additional art made of record and not relied upon is considered pertinent to applicant's disclosure.
Document ID: US 20210308866 A1
Invention pertains to determining a plurality of stable intermediate poses for a workpiece.
Document ID: US 11325256 B2
Invention pertains to determining a full Cartesian path for a robot as it traverses to goal pose.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Dairon Estevez whose telephone number is (703)756-4552. The examiner can normally be reached M-F 8:00AM - 4:00PM.
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, Khoi Tran can be reached at (571) 272-6919. 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.
/D.E./Examiner, Art Unit 3656
/KHOI H TRAN/Supervisory Patent Examiner, Art Unit 3656
Prosecution Insights