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 .
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.
Joint Inventors
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 01/05/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Amendment
Claims 1, 15, and 20 have been amended. No claims have been added and claim 2 has been cancelled. No rejections have been withdrawn as a result of amendment, but the mapping of the 35 U.S.C. 102(a)(1) rejection has been updated in view of amendment.
Response to Arguments
Applicant's arguments filed 11/5/2025 have been fully considered but they are not persuasive.
Applicant contends that Handa does not disclose a third and fourth policy determination as claimed in the instant application. Examiner respectfully disagrees.
Examiner finds that the iterative optimization of the neural network described in Handa discloses the broadest reasonable interpretation of the multiple policies updated in the instant application, as the iterative nature of the process in Handa means that the process can happen any number of times, and any number of policies can be updated over any number of iterations.
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 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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Handa et al. (DE102020127508B4, referred to as Handa).
Regarding claim 1: Handa discloses: A method for dexterous manipulation by a robot, the method comprising: performing a virtual simulation wherein a robot model adopts a virtual target position from a virtual initial position, and ([0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world.) deriving a first policy for maneuvering a robot based on the virtual simulation; performing a first set of real simulations wherein a first robot adopts a real target position from a real initial position based on the first policy, and deriving a second policy for maneuvering a robot based on sensor data generated in the first set of real simulations; combining the first policy and the second policy to derive a third policy for maneuvering a robot, wherein action recommendations provided by the first policy and the second policy are added together; causing at least one of the first robot and a second robot to adopt a real target position from a real initial position based on at least one of the third policy and a subsequently derived policy for maneuvering a robot and performing a second set of real simulations wherein the first robot adopts a real target position from a real initial position based on the third policy, and deriving a fourth policy for maneuvering a robot based on sensor data generated in the second set of real simulations. ([0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world.)
Regarding claim 2: Handa discloses: The method of claim 1,
Handa further discloses: further comprising performing a second set of real simulations wherein the first robot adopts a real target position from a real initial position based on the third policy, and deriving a fourth policy for maneuvering a robot based on sensor data generated in the second set of real simulations. ([0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 3: Handa discloses: The method of claim 1,
Handa further discloses: wherein the virtual target position in the virtual simulation disposes the robot model in a same orientation and configuration as the real target position of the first robot in the first set of real simulations.
Regarding claim 4: Handa discloses: The method of claim 1,
Handa further discloses: further comprising repeatedly performing the virtual simulation for a plurality of iterations, wherein deriving the first policy includes processing virtual data generated from the plurality of iterations with a machine learning algorithm. ([0100] errors are then backpropagated by the untrained neural network 1506. In at least one embodiment, the training framework 1504 adjusts weights that control the untrained neural network 1506. In at least one embodiment, the training framework 1504 includes tools for monitoring how well the untrained neural network 1506 converges to a model, such as the trained neural network 1508, that is capable of building a network based on known input data, such as a user interface. B. new data 1512 to generate correct answers as in result 1514. In at least one embodiment, the training framework 1504 repeatedly trains the untrained neural network 1506 while adjusting the weights to produce an output of the untrained neural network 1506 using a loss function and an adjustment algorithm, such as a loss function.)
Regarding claim 5: Handa discloses: The method of claim 4,
Handa further discloses: wherein the machine learning algorithm employs a smoothness reward corresponding to an acceleration value of a portion of the robot model. ([0026] this system is a gloveless solution for controlling a multi-fingered, high-motion robot system to solve a variety of grasping and manipulation tasks. In some examples, depth cameras and various graphics processing units (“GPUs”) can be used together with deep learning and optimization to create a sophisticated teleoperation system with minimal footprint. In some examples, a variety of physical tasks can be performed using visual feedback alone. Therefore, this system can utilize the human ability to plan, move, and predict the consequences of physical actions through vision alone, which may be a sufficient prerequisite for solving a wide variety of tasks. [0039] Riemannian motion policies (“RMPs”) are real-time motion generation methods that compute acceleration fields from potential function gradients and corresponding Riemannian metrics. RMPs can combine the generation of multi-priority Cartesian trajectories and collision avoidance behavior in a coherent reference system.)
Regarding claim 6: Handa discloses: The method of claim 4,
Handa further discloses: wherein the virtual initial position of the robot model is randomized over the plurality of iterations. ([0035] the uniform subsampling used in the input may indicate that the points on the fingers are not densely sampled, and therefore refinement may be required in a second stage in which the points on the hand are resampled from the original raw point cloud, taking into account the pose and segmentation of the first stage. In at least one embodiment, the second stage may be trained on the same loss functions, but may instead use only the points sampled on the hand to accurately predict the 23 keypoints. In at least one embodiment, random perturbations may be added to the second-stage hand pose to ensure robustness against any inaccuracies in the first-stage hand pose. Fig. 4 illustrates the refinement of the second stage within the system, according to at least one embodiment. In at least one embodiment, both stages of PointNet can be trained on 100K point clouds collected over a batch of 30-45 minutes each for a total of 7-8 hours by running DART to provide annotations for keypoints, joint angles, and segmentation.)
Regarding claim 7: Handa discloses: The method of claim 1,
Handa further discloses: further comprising recording pose data of a virtual object in the virtual simulation, and deriving the first policy based on the pose data, wherein at least one of a pose of the virtual object, a contact force between the virtual object and the robot model, a mass of the virtual object, a center of mass of the object, and an amount of friction between the virtual object and the robot model is randomized at multiple time steps in the virtual simulation. ([0052] For the first term in the cost function, a comparison of q<sub>t</sub>s between the simulated and real robots may be useful, even if they have the same u<sub>t</sub>, since q<sub>t</sub>may be different depending on the collision constraints imposed by the current object pose in contact with the robot hand, which may make it physically impossible for a joint to reach a commanded target angle. [0053] In at least one embodiment, a touch sensor is considered to be in contact when its force magnitude is greater than a certain threshold. In at least one embodiment, α<sub>(i,l)</sub> is equal to 1 if the binary contact state of the l-th touch sensor of the i-th simulation matches that of the real touch sensor, and equal to 0 otherwise. In at least one embodiment, β<sub>(i,l)</sub>is equal to 1 if the l-th touch sensor of the i-th simulation matches the real touch sensor in whether the sensor experiences translational slip or not, and 0 otherwise; γ<sub>(i,l)</sub>is the same for rotational slip.)
Regarding claim 8: Handa discloses: The method of claim 1,
Handa further discloses: wherein at least one of the virtual initial position and the virtual target position include the robot model grabbing a virtual object, and the method further comprises deriving the first policy based on at least one of pose data and position data of the virtual object as the robot model moves from the virtual initial position toward the virtual target position in the virtual simulation. ([0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0072] To obtain feedback through real-world contacts, SynTouch BioTac sensors or a variation thereof can be attached to each of the fingertips. One or more processes performed in conjunction with various sensors and the raw electrode readings from the sensors can be used to predict the contact force, slip direction, and grip stability. A trained model can be used to estimate force vectors c<sub>t</sub>. In various examples, the cost functions may not contain slack terms. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 9: Handa discloses: The method of claim 1,
Handa further discloses: wherein at least one of the real initial position and the real target position include the first robot grabbing a real object, and the method further comprises deriving the second policy based on sensor data indicating at least one of a pose and a position of the real object as the first robot moves from the real initial position toward the real target position in the first set of real simulations. ([0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0072] To obtain feedback through real-world contacts, SynTouch BioTac sensors or a variation thereof can be attached to each of the fingertips. One or more processes performed in conjunction with various sensors and the raw electrode readings from the sensors can be used to predict the contact force, slip direction, and grip stability. A trained model can be used to estimate force vectors c<sub>t</sub>. In various examples, the cost functions may not contain slack terms. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 10: Handa discloses: The method of claim 9,
Handa further discloses: further comprising deriving the first policy based on at least one of the pose data and the position data of the virtual object relative to at least one of pose data and position data of the robot model in the virtual simulation; and deriving the second policy based on sensor data indicating at least one of the pose and the position of the real object relative to at least one of a pose and a position of the first robot in the first set of real simulations. ([0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0072] To obtain feedback through real-world contacts, SynTouch BioTac sensors or a variation thereof can be attached to each of the fingertips. One or more processes performed in conjunction with various sensors and the raw electrode readings from the sensors can be used to predict the contact force, slip direction, and grip stability. A trained model can be used to estimate force vectors c<sub>t</sub>. In various examples, the cost functions may not contain slack terms. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 11: Handa discloses: The method of claim 9,
Handa further discloses: wherein the first robot includes a robotic arm connected with a robotic hand, and the real object includes a handle, wherein the at least one of the real initial position and the real target position of the first set of real simulations includes the robotic hand grabbing the real object by the handle. ([0027] Fig. 1 shows an example of a teleoperation for various tasks, according to at least one embodiment. In one example, a robot gripper 104 grasps a cylinder using a grasp pose based on a pose of a human hand 102.)
Regarding claim 12: Handa discloses: The method of claim 11,
Handa further discloses: wherein the real initial position includes the robotic hand grabbing the handle in a first position, and the real target position includes the robotic hand grabbing the handle in a second position, wherein at least one of the pose and the position of the real object changes relative to the pose and the position of the robotic hand as the real object moves from the first position toward the second position. ([0027] Fig. 1 shows an example of a teleoperation for various tasks, according to at least one embodiment. In one example, a robot gripper 104 grasps a cylinder using a grasp pose based on a pose of a human hand 102. [0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0072] To obtain feedback through real-world contacts, SynTouch BioTac sensors or a variation thereof can be attached to each of the fingertips. One or more processes performed in conjunction with various sensors and the raw electrode readings from the sensors can be used to predict the contact force, slip direction, and grip stability. A trained model can be used to estimate force vectors c<sub>t</sub>. In various examples, the cost functions may not contain slack terms. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 13: Handa discloses: The method of claim 9,
Handa further discloses: further comprising adding noise to the at least one of pose data and position data of the virtual object, wherein the first policy is derived based on the at least one of pose data and position data of the virtual object with the added noise. ([0021] experiments using dynamics models and particle filtering techniques show that adding noise to the applied forces rather than the underlying dynamics provides more accurate tracking results. In at least one embodiment, tactile feedback is combined with a vision-based object tracker to track trajectories of objects during planar sliding tasks, and in another embodiment, incremental smoothing and mapping (SMM) is used. Incremental Smoothing and Mapping (iSAM) is used to combine global visual pose estimates with local contact pose measurements.)
Regarding claim 14: Handa discloses: The method of claim 1,
Handa further discloses: further comprising recording pose data of a virtual object in the virtual simulation, adding noise to the pose data, and deriving the first policy based on the pose data with the added noise. ([0021] experiments using dynamics models and particle filtering techniques show that adding noise to the applied forces rather than the underlying dynamics provides more accurate tracking results. In at least one embodiment, tactile feedback is combined with a vision-based object tracker to track trajectories of objects during planar sliding tasks, and in another embodiment, incremental smoothing and mapping (SMM) is used. Incremental Smoothing and Mapping (iSAM) is used to combine global visual pose estimates with local contact pose measurements.)
Regarding claim 15: Rejected using the same rationale as claim 1, however further directed to “at least one computer configured to…”, which is further disclosed by Handa: at least one computer configured to… ([0072] The simulations can be performed on a computer with one or more graphical processing units, one or more central processing units and one or more memory units.)
Regarding claim 16: Handa discloses: The system of claim 15,
Handa further discloses: wherein at least one of the virtual initial position and the virtual target position in the virtual simulation includes the robot model grabbing a virtual object, and at least one of the real initial position and the real target position in the real simulation includes the first robot grabbing a real object, wherein the at least one computer is configured to: derive the first policy based on at least one of pose data and position data of the virtual object as the robot model moves from the virtual initial position toward the virtual target position in the virtual simulation; and derive the second policy based on sensor data indicating at least one of a pose and a position of the real object as the first robot moves from the real initial position toward the real target position in the first set of real simulations. ([0028] a robot gripper 108 grasps a cube with a grasping pose based on a human hand 106. [0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0072] To obtain feedback through real-world contacts, SynTouch BioTac sensors or a variation thereof can be attached to each of the fingertips. One or more processes performed in conjunction with various sensors and the raw electrode readings from the sensors can be used to predict the contact force, slip direction, and grip stability. A trained model can be used to estimate force vectors c<sub>t</sub>. In various examples, the cost functions may not contain slack terms. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 17: Handa discloses: The system of claim 16,
Handa further discloses: wherein the robot model includes a robotic arm connected with a robotic hand, the virtual object includes a handle, and the at least one of the virtual initial position and the virtual target position in the virtual simulation includes the robotic hand grabbing the virtual object by the handle, wherein the first robot includes a robotic arm connected with a robotic hand, the real object includes a handle, and the at least one of the real initial position and the real target position in the real simulation includes the robotic hand grabbing the real object by the handle. ([0027] Fig. 1 shows an example of a teleoperation for various tasks, according to at least one embodiment. In one example, a robot gripper 104 grasps a cylinder using a grasp pose based on a pose of a human hand 102. [0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0072] To obtain feedback through real-world contacts, SynTouch BioTac sensors or a variation thereof can be attached to each of the fingertips. One or more processes performed in conjunction with various sensors and the raw electrode readings from the sensors can be used to predict the contact force, slip direction, and grip stability. A trained model can be used to estimate force vectors c<sub>t</sub>. In various examples, the cost functions may not contain slack terms. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 18: Handa discloses: The system of claim 17,
Handa further discloses: wherein the handle of the virtual object is elongated and each of the virtual initial position and the virtual target position in the virtual simulation includes the robotic hand grabbing the handle, wherein the robotic hand moves along a length of the handle, and rotates a grip on the handle when the robot model moves from the virtual initial position to the virtual target position, and wherein the handle of the real object is elongated and each of the real initial position and the real target position in the real simulation includes the robotic hand grabbing the handle, wherein the robotic hand moves along a length of the handle, and rotates a grip on the handle when the first robot moves from the real initial position to the real target position. ([0027] Fig. 1 shows an example of a teleoperation for various tasks, according to at least one embodiment. In one example, a robot gripper 104 grasps a cylinder using a grasp pose based on a pose of a human hand 102. [0016] a physics simulation is used as a forward model for robot-object interactions, and the algorithm jointly optimizes the state and parameters of the simulations so that they better match those of the real world. [0072] To obtain feedback through real-world contacts, SynTouch BioTac sensors or a variation thereof can be attached to each of the fingertips. One or more processes performed in conjunction with various sensors and the raw electrode readings from the sensors can be used to predict the contact force, slip direction, and grip stability. A trained model can be used to estimate force vectors c<sub>t</sub>. In various examples, the cost functions may not contain slack terms. [0074] for each object, both in simulation and in real experiments, two demonstrations of two types of trajectories for manipulation can be used: 1) picking and placing (pick-and-place) using a finger grasp and rotating the object in the hand, and 2) the same but with fingertips breaking and re-establishing contact during the grasp (finger movements). This can result in a total of 24 trajectories that can be analyzed for both simulations and real-world experiments. In both trajectories, the object can be moved translationally and rotationally by inertial forces as well as by pressure contacts with the table. [0379] the neurons 3202 may be organized in one or more layers…The neuromorphic processor 3200 may include, without limitation, any suitable combination of recurrent layers and feed-forward layers, including, without limitation, both sparsely connected feed-forward layers and fully connected feed-forward layers.)
Regarding claim 19: Handa discloses: The system of claim 16,
Handa further discloses: wherein the sensor is a camera configured to generate image data indicating the at least one of the pose and the position of the first robot, and indicating at least one of a pose and a position of the real object during the first set of real simulations. ([0074] This can result in a total of 24 trajectories that can be analyzed for both simulations and real-world experiments. In both trajectories, the object can be moved translationally and rotationally by inertial forces as well as by pressure contacts with the table. Each trajectory can last about a minute. In various embodiments, the pose estimation algorithm can be used with approx. 30 Hz, which can result in a total of approximately 2k individual images per trajectory.)
Regarding claim 20: Rejected using the same rationale as claims 1 and 15, however further directed to “A non-transitory computer readable storage medium…”, which is further disclosed by Handa: A non-transitory computer readable storage medium… ([0499] a non-transitory computer-readable storage medium stores instructions and a central processing unit (“CPU”) executes some of the instructions, while a graphics processing unit (“GPU”) executes other instructions.)
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 extension fee 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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ATTICUS A CAMERON whose telephone number is 703-756-4535. The examiner can normally be reached M-F 8:30 am - 4:30 pm. 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, Thomas Worden can be reached on 571-272-4876. 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.
/ATTICUS A CAMERON/ /JASON HOLLOWAY/ Primary Examiner, Art Unit 3658
Examiner, Art Unit 3658A
Prosecution Insights