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 .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 6/29/2026 has been entered.
Claim Rejections related to 35 USC § 101 regarding to claims 1-20 is withdrawn.
Claim Objections
Claims 1, 8 and 15 are objected to because of the following informalities: typo.
Claims 1, 8 and 15 recite “controlling a robotic elements to perform the selected the exploratory action…” it seems “to perform the selected exploratory action”.
Appropriate correction is required.
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.
Claims 1, 4-8, 11-15, 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Goldberg et al. (Goldberg) US 2020/0198130 in view of von Drigalski et al. (von Frigalski) US 2023/0330854 and Mousavian et al. (Mousavian) US 20210138655
In regard to claim 1, Goldberg disclose A method for identifying a property of an object, ([0016][0021]-[0022][0026]-[0029][0033]-[0034] identify properties of an target object, see Fig. 2, for example)
Goldberg disclose the method comprising:
obtaining sensor data from at least one sensor; (Fig. 2,[0026][0038]-[0041] obtaining sensor image from sensor 220)
identifying, using the sensor data, a physical property of interest of an object, (Fig. 2, [0029]-[0033] [0038]-[0052] identify, using the sensor image, properties for the target the object) wherein the physical property is at least one of a mass, a center of mass, height, or friction; ([0016] [0029]-[0034] [0069] center of mass friction, mass, etc. properties)
predicting, using a model including one or more neural networks, a next uncertainty about the identified physical property of interest of the object and a state of the object based on a plurality of exploratory actions corresponding to respective types of physical properties; (Fig. 2, [0010]-[0020] [0026]-[0034] [0038]-[0052] [0053]-[0061] [0068]-[0069] using, NN, predicting a uncertainty about robust grasping, for example, for the object, and a state of the object, the uncertainty in variables related to initial state, contact, motion, combination, etc. based on actions (using robot motions to move grasped objects into specific configurations which are action sequences) and the actions corresponding to the type of properties, such as a given grasp action corresponding to the object mass, or geometry, etc.)
and
controlling a robotic element to perform the selected the exploratory action on the object sensor information indicative of the identified physical property of interest, (Fig. 2, [0013][0014][0020] [0028]-[0034] [0038]-[0044] [0053]-[0059][0062]-[0069] based on the selected action, to control a movement of a robotic grasping mechanism to grasp the object, poking the object, etc. and obtain the metric based on the property of interest of the object)
But Goldberg fail to explicitly disclose “selecting, among the plurality of actions, the action and having a minimum predicted the next uncertainty; wherein the model is trained to generate the exploratory actions based on a property of the object and evaluate the next uncertainty for the plurality of exploratory actions.”
Von Drigalski disclose selecting, among the plurality of actions, the action and having a minimum predicted the next uncertainty; ([0014]-[0018] [0061]-[0068] [0090]- [0091] [0120]-[0125] [0139]-[0148] selecting an highly executable action from the action sequences based on the failure probability and identify the action with the lowest cost and corresponding to the highest success rate and lowest failure rate (failure probability))
wherein the model is trained to generate the exploratory actions based on a property of the object and evaluate the next uncertainty for the plurality of exploratory actions. ([0010]-[0022] [0039]-[0042] [0061]-[0068] [0120]-[0125] [0139]-[0148] train the model to generate the action sequences based on the property of the object such as drive amount, movement time, cost, etc. to move the parts of a product and evaluate the failure (success) probability for the action sequences.)
It would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made to incorporate von Drigalski’s movement planning for a robot device into Goldberg’s invention as they are related to the same field endeavor of model training and learning of a robot. The motivation to combine these arts, as proposed above, at least because von Drigalski’s movement planning for a robot device based on failure rate would help to provide more training error control into Goldberg’s system. Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made that providing more training error control based on action sequence failure rate would help to improve accuracy of prediction precision and training efficiency.
But Goldberg and Von Drigalski fail to explicitly disclose “selecting, among the plurality of exploratory actions, an exploratory action associated with the identified physical property of interest;”
Mousavian disclose selecting, among the plurality of exploratory actions, an exploratory action associated with the identified physical property of interest; ([0003] [0070]-[0075] [0083]-[0094] select promising grasp points from the multiple graphs points around the object based on the identified property of the object)
It would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made to incorporate Mousavian’s movement determination for an object into von Drigalski and Goldberg’s invention as they are related to the same field endeavor of model training and learning of a robot. The motivation to combine these arts, as proposed above, at least because Mousavian’s movement determination based on the property of the object would help to provide movement control into von Drigalski and Goldberg’s system. Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made that providing more movement control based on the property of the object the would help to improve accuracy and success rate of the movement.
In regard to claim 4, Goldberg and Von Drigalski, Mousavian disclose The method of claim 1,
Goldberg disclose wherein the exploratory action comprises pressing the object with the robotic element and obtaining readings from the at least one sensor. (Fig. 2, [0010]- [0012] [0038]-0052] grasp the object with 240 and take sensor image then return data positions and forces, torques, etc.)
In regard to claim 5, Goldberg and Von Drigalski, Mousavian disclose The method of claim 1,
Goldberg disclose wherein the identifying the property of interest of the object comprises pressing the object with the robotic element at multiple points of the object and obtaining readings from the at least one sensor. (Fig. 2, [0010]- [0012] [0038]-[0053] grasp the object with 240 at target points of the object and then return data from the sensor about positions and forces, torques, etc.)
In regard to claim 6, Goldberg and Von Drigalski, Mousavian disclose The method of claim 1,
Goldberg disclose wherein the identifying the property of interest comprises lifting the object with the robotic element. (Fig. 2, [0012] [0053] [0068] lifting the object with 240)
In regard to claim 7, Goldberg and Von Drigalski, Mousavian disclose The method of claim 1,
Goldberg disclose wherein the model comprises a dynamics model and an observation model. ([0016]-[0023] [0052] object models and grasp quality CNN model, etc., note: please further define)
In regard to claims 8, 11-14, claims 8, 11-14 are system claims corresponding to the method claims 1, 4-7 above and, therefore, are rejected for the same reasons set forth in the rejections of claims 1, 4-7.
In regard to claims 15, 18-20, claims 15, 18-20 are medium claims corresponding to the method claims 1, 4-6 above and, therefore, are rejected for the same reasons set forth in the rejections of claims 1, 4-6.
Claims 2-3, 9-10, 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Goldberg et al. (Goldberg) US 2020/0198130, von Drigalski et al. (von Frigalski) US 2023/0330854 and and Mousavian et al. (Mousavian) US 20210138655
as applied to claim 1, further in view of Chen US 2019/0377949
In regard to claim 2, Goldberg and Von Drigalski, Mousavian disclose The method of claim 1,
But Goldberg and Von Drigalski, Mousavian fail to explicitly disclose “wherein the model is trained through repeated training iterations until a convergence is identified based on a reduced training error.”
Chen disclose wherein the model is trained through repeated training iterations until a convergence is identified based on a reduced training error. ([0041]-[0045] [0068]-[0070] training are iterated until converged based on a reduced error)
It would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made to incorporate Chen‘s ML training into Mousavian, Von Drigalski and Goldberg’s invention as they are related to the same field endeavor of model training and learning. The motivation to combine these arts, as proposed above, at least because Chen‘s ML training with training iteration would help to provide more training error control into Mousavian, Von Drigalski and Goldberg’s system. Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made that providing more training error control with iteration would help to improve accuracy of prediction precision and training efficiency.
In regard to claim 3, Goldberg and Von Drigalski, Mousavian disclose The method of claim 1,
But Goldberg and Von Drigalski, Mousavian fail to explicitly disclose “wherein the model is trained by minimizing a training loss by approximating a belief state.”
Chen disclose wherein the model is trained by minimizing a training loss by approximating a belief state. ([0041]-[0046] [0068]-[0070] minimizing the loss by a target loss function, such as true boundary box, etc.)
It would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made to incorporate Chen‘s ML training into Mousavian, Von Drigalski and Goldberg’s invention as they are related to the same field endeavor of model training and learning. The motivation to combine these arts, as proposed above, at least because Chen‘s ML training with training iteration would help to provide more training error control into and Mousavian, Von Drigalski and Goldberg’s system. Therefore it would have been obvious to one having ordinary skill in the art before the effective filing data of the claimed invention was made that providing more training error control with iteration would help to improve accuracy of prediction precision and training efficiency.
In regard to claims 9-10, claims 9-10 are system claims corresponding to the method claims 2-3 above and, therefore, are rejected for the same reasons set forth in the rejections of claims 2-3.
In regard to claims 16-17, claims 16-17 are medium claims corresponding to the method claims 2-3 above and, therefore, are rejected for the same reasons set forth in the rejections of claims 2-3.
Response to Arguments
Applicant’s arguments with respect to claim1-20 filed on 6/29/2026 have been considered but are moot because the arguments do not apply to the current rejection.
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure.
U.S. Patent Documents PATENT DATE INVENTOR(S) TITLE
US 20220314444 2022-10-06 Hajash et al.
Hybrid Robotic Motion Planning System Using Machine Learning And Parametric Trajectories
Hajash et al. disclose In one embodiment, a method includes accessing a trajectory plan for a task to be executed by a robotic system, determining actions to constrain the trajectory plan based on information associated with an environment associated with the robotic system, wherein pose-based waypoints and joint positions of the robotic system would be constrained by the actions, determining joint-based waypoints for the trajectory plan based on the pose-based waypoints, and executing the task based on the joint-based waypoints for the trajectory plan… see abstract.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XUYANG XIA whose telephone number is (571)270-3045. The examiner can normally be reached Monday-Friday 8am-4pm.
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, Jennifer Welch can be reached at 571-272-7212. 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.
XUYANG XIA
Primary Examiner
Art Unit 2143
/XUYANG XIA/Primary Examiner, Art Unit 2143
Prosecution Insights