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 .
Status of Claims
This is in response to applicant’s filing date of September 19, 2025, and Preliminary Amendment filed on September 28, 2026, cancelling claims 2-3, 5-6, and 8. Claims 1, 4, 7, and 9-10 are currently pending.
Priority
Acknowledgment is made of applicant’s claim for foreign priority to Application CN2024113164018, filed on September 20, 2024. The certified copy of the application as required by 37 CFR 1.55 has been received.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on September 8, 2026, is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections -- 35 U.S.C. § 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claims 1, 4, 7, and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Yamane et al (US-20210078178-A1)(“Yamane”), Campbell et al (NPL:” "Learning Whole-Body Human-Robot Haptic Interaction in Social Contexts")(“Campbell”), and Randy Gomez (US-20240282145-A1)(“Gomez”).
As per claim 1, Yamane discloses a method for planning and controlling a humanoid behavior of a robot for close physical interactions (Figures 3-6), comprising:
step S1, acquiring demonstration data of close interactions between the robot and human beings through motion capture (Yamane at Figure 5 and Para. [0031] discloses receiving physical human robot interaction data:” during the training phase, a learning-from demonstration (LfD) framework for teaching pHRI social interactions that involve whole-body haptic interaction, (i.e., direct human-robot contacts potentially taking place anywhere on the robot body) may be implemented when the sensors 102, 104, 174, 176 receive sensor data or sensor measurements, respectively.”) ;
step S2, obtaining a plurality of human behavior pattern categories based on the demonstration data by using prior knowledge and clustering analysis (Yamane at Para. [0031] discloses creating models for the interaction with the robot:” whole-body haptic information, including both kinesthetic and tactile information, which may be utilized to build a model enabling intimate haptic interactions as the arms may be often occluded from view of cameras or image capture devices and touch may be one of the only valid source of information on the timing and intensity of contacts. In hugging, for example, each person or hug participant feels the other's hugging force at the chest and back, and may adjust the arm joint torques to match the force applied to the other participant through the whole arms. Because the robot may utilize LfD, the robot may be capable of acting safely and comfortably for the human partner or ‘partner’ during pHRI.”);
step S3, segmenting and calibrating the demonstration data based on the plurality of human behavior pattern categories to obtain a plurality of groups of movement primitive sequences comprising human behavior pattern labels, constructing a hierarchical directed graph, and obtaining a robot behavior planner through training (Yamane at Par. [0036] discloses that response of the person and robot can be categorized according to certain models and a response pattern can be correlated from the measured values:” processor 182 may receive an action associated with a human involved in pHRI with the robot based on the updated sensor measurement dataset. The processor 182 may generate a response for the robot based on the updated sensor measurement dataset and the received action. This response for the robot may be generated based on a Bayesian Interaction Primitives (BIP) model, which may be approximated using a Monte Carlo Ensemble. The BIP model may be indicative of or be used to model the spatiotemporal relationship between the tactile and kinesthetic information during whole-body haptic interactions from the training phase, thereby enabling the robot to learn whole-body human-robot haptic interaction in association with social contexts. The BIP model may be capable of predicting both an appropriate robotic response (e.g., joint trajectories) as well as the contact forces that should be exerted by the robot, given observations of the partner's pose and the force currently being exerted on the robot by the partner.”); and
step S4, constructing a dynamically consistent mapping model between a target trajectory and an action space, and realizing the planning and control of the humanoid behavior of the robot based on the dynamically consistent mapping model and the robot behavior planner (Yamane at Para. [0053] discloses mapping a trajectory between a robot and a person that is consistent with size differentials and a desired effect:” the robot or system for pHRI may perform motion retargeting. The predicted joint trajectories and contact forces may be then sent to a motion retargeting controller because the contact forces also depend on the partner's body size and shape. For example, the operator may have an object in front of him or her and the robot may have a corresponding object located similarly. In other words, there may be an object on the operator side environment that the operator may touch.”),
wherein obtaining the plurality of human behavior pattern categories by using the prior knowledge and the clustering analysis in step S2 comprises (Yamane at Para. [0051] discloses that the response is based on prior knowledge of the interactions:” the robot may be presented with observations of a human partner and, utilizing both the prior knowledge (e.g., the BIP model) and the current observations or inputs from sensors on the robot, infers the next partner actions, and the corresponding appropriate robot response. The spatiotemporal relationship model of the BIP model allows inference of both the robot's poses and forces from those of the partner, allowing responsive behavior to be generated not only to discernable movements but also indiscernible ones, such as the strength of the hug.”):
Yamane does not explicitly disclose segmenting the demonstration data into categories.
Yamane does not disclose, but Campbell discloses a process step S201, obtaining a clustering result based on the demonstration data through density-based clustering analysis (Campbell at Page 10181 discloses categorizing the various interactions (hugs) into groups or clusters:” During online testing, the participants were instructed to initiate and conclude the hug, as in training, except now with no teleoperation and no instruction to match the force of the robot. Each participant performed six long hugs, six short hugs, and two hugs each for the following edge cases: doing nothing, delaying before hugging, delaying after raising arms, hugging the air without moving, and hugging the robot without making contact.”) ; and
Yamane does not disclose, but Campbell discloses a process step S202, obtaining key attributes in human close physical interaction behaviors based on the clustering result and the prior knowledge obtained in advance, and constructing the plurality of human behavior pattern categories (Campbell at Figure 5-9 at Page 10181 discloses that interaction such as a hug can be categorized into different category based on duration, based on time before beginning the hug, and based on forces as measured by the robot.) ,
Yamane does not disclose, but Campbell discloses a process wherein step S202 comprises step S2021, obtaining the prior knowledge based on pre-acquired interdisciplinary literature (Campbell at Page 10178 disclose using interdisciplinary literature to formulate a model for robot interaction as it pertains to a robot human hug:” Intimate, social pHRI such as hugging has been found to have positive effects on the human emotional state [6], [7],[8]. However, the robot platforms used in these studies all had limited physical capabilities, making it impossible for the robots to provide the human with reciprocal forces.);
Yamane does not disclose, but Campbell discloses a process step S2022, obtaining the key attributes in the human close physical interaction behaviors based on the prior knowledge and the clustering result, wherein the key attributes comprise tightness, hugging style, and bimanual cooperation style (Campbell discloses various attribute of a physical interaction such as tightness and duration (Page 10178:”hug duration and strength are important factors to realize comfortable robotic hugs.”), style and cooperation between the participants (Page 10179:” we employ mutual information estimation based on binning and incrementally select features until there is no significant improvement in mutual information, based on a desired threshold (> 0:07). We opt to use mutual information rather than other standard measures as some of the force sensors experience false positives due to deformation caused by the robot's own movements.”); and
Yamane does not disclose, but Campbell discloses a process step S2023, dividing hugging actions into the plurality of human behavior pattern categories based on the key attributes according to whether a chest is in contact, an extension direction of an upper arm, and directions of forces applied to two arms (Campbell at Page 10179 discloses that a plurality of pattern can be defined when modelling a human robot interaction as to a hug:” hugging motion where both of the partner's arms wrap under the robot's arms will register different contact forces than if the arms wrap over. Furthermore, this can vary between person to person as physical characteristics such as height influence contact location and strength.”),
Yamane does not disclose, but Campbell discloses a process wherein, in step S3, the hierarchical directed graph is constructed as: G = (S, V, R, P, σ), wherein S represents a target hugging action, V is an AND node or an OR node in the hierarchical directed graph, R represents a top-down production rule from a parent node α to a child node β of the parent node α, P represents a probability associated with each production rule, and σ is a behavior planning sequence defined by grammar (Campbell at Figure 1 and Page 10178 discloses various planning sequences that are vectorized and assigned a probability of action:” At run-time, the robot is presented with observations of a human partner and, utilizing both the prior knowledge and the current observations, infers (a) the next partner actions, and (b) the appropriate robot response. This is shown in the Testing block of Fig. 1. The spatiotemporal relationship we model allows us to infer both the robot's poses and forces from those of the partner, allowing responsive behavior to not only discernable movements but also indiscernable ones, such as the strength of the hug.”),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to implement the human robot interaction in context method taught in Campbell in the robot interaction controller in Yamane with a reasonable expectation of success. because this results in a robot response to appear more natural and therefore easier to interact with by including phase look-ahead when engaging in robot human interaction (see Campbell at Page 10182).
Yamane and Campbell do not disclose but Gomez disclose a process wherein obtaining the robot behavior planner through training in step S3 comprises: learning an association between a movement primitive space and a state space using a Q-learning rule in a temporal-difference manner, by using a joint space of two arms as the state space and using probability P between respective nodes as a learning object, and recovering a grammatical structure by automatic structural distillation according to posterior probability, thereby obtaining the robot behavior planner (Gomez at Para. [0058] discloses that q-learning rules are well known in the human robot interaction space:” Q-learning is used as the reinforcement learning algorithm. The robot 1 acquires a user's current emotional state (facial emotion or gesture) and selects an action with the largest Q value using the greedy strategy. Next, the action selected by the robot 1 is executed, and then the user gives feedback R in accordance with his/her preference. When the action selected by the robot 1 is desirable, the user will show a positive reaction with his/her facial expression, and the Q value of the selected action will increase.”),
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the robot hugging control as taught by Yamane and Campbell with the q-learning rules in human robot interaction as taught by Gomez with a reasonable expectation of success in order for the one or more method steps to follow q-learning rules to augment the knowledge of the robot and prepare it for future interactions. The teaching suggestion/motivation to combine is that by using q-rules learning methods, speed of learning can be improved as taught by Gomez in Paras. [0057] -[0058].
wherein the demonstration data comprises motion-capture data of hugging actions of participants in a plurality of age groups acting in a plurality of roles in a plurality of preset scenarios, wherein the plurality of preset scenarios comprises social occasions, intimate relationships, emotional expression, and motor functions, and the plurality of roles comprises an initiator and a receiver (Yamane at Figure 2, cameras and sensors to capture hugging action, and Para. [0110] discloses capturing and correlating observations (camera) and sensor data to a hugging scenario between a robot and person:” first camera 292 may receive a video feed of the robot 100 engaged in pHRI with a partner and the processor 182 may process the feed using an OpenPose (e.g., a real time system for multi-person pose detection) to generate a pose of the partner. A second camera 294 may receive a second video feed of the robot 100 engaged in pHRI with a partner and the processor 182 may process the feed to supplement generation of the pose of the partner. A display 296 may display one or more of the results associated with the pose and the robot for pHRI. Using the data or measurements from any of the sensors 102, 104, 174, 176, during the training phase, feature selection may be performed as described above, and the BIP model may be built accordingly.”); and
wherein real-time observation data of an angle and a velocity of each joint are calculated and obtained by combining inertial sensing data and optical sensing data (Yamane at Paras [0105]-[0107] discloses the fusing of observation data and sensor data relating to the velocity and angle of joints:” Motion reference offset is aimed at tweaking the reference joint orientations obtained from IMU measurements such that the robot is more likely to realize the same contact state as the operator in the future. One transformation matrix may be stored for each IMU (e.g., sensor) and update all matrices of the IMUs in the same limb as the force sensor pair that transitioned from contact state 2) to contact state 4). .sup.0{circumflex over (R)}.sub.j2 may denote the reference orientation of joint j when a force sensor on the operator side made a contact. In contact state 2), the corresponding force sensor on the robot has not touched the human at this point. Due to the controller prioritizing force over motion, the robot will gradually move toward the human.”).
As per claim 4, Yamane, Campbell, and Gomez disclose a method for planning and controlling the humanoid behavior of the robot for close physical interactions according to claim 1, wherein the segmenting and calibrating the demonstration data based on the plurality of human behavior pattern categories in the step S3 comprises:
constructing a respective movement primitive for each of the plurality of human behavior pattern categories and segmenting and calibrating the demonstration data to obtain the plurality of groups of movement primitive sequences including human behavior pattern labels (Campbell at Page 10177 discloses creating a model of movement primitives inclusive of human behavior patterns:” We model the interaction as a Bayesian Interaction Primitive(BIP) [2], [3], [4], a spatiotemporal LfD framework. This model is capable of predicting both an appropriate robotic response (consisting of joint trajectories) as well as contact forces that should be exerted by the robot, given observations of the partner's pose and the force currently exerted by the partner onto the robot. The predicted joint trajectories and contact forces are then sent to a motion retargeting controller[5], which is capable of accounting for variances in the partner’s body shape and size. While previous applications of this framework include haptic interaction [3], the tactile information has thus far been dense, low-dimensional, and only used as an input observation.”).
As per claim 7, Yamane, Campbell, and Gomez disclose a method for planning and controlling the humanoid behavior of the robot for close physical interactions according to claim 1, wherein the realizing the planning and control of the humanoid behavior of the robot based on the dynamically consistent mapping model and the robot behavior planner in the step S4 comprises:
generating a next movement primitive needed to complete the target hugging action by using the robot behavior planner for different joint states, and performing the target hugging action by using a respective mapping model (Yamane at Para. [0036] discloses generating movement primitives based on the target hugging action between a human and a robot:” processor 182 may generate a response for the robot based on the updated sensor measurement dataset and the received action. This response for the robot may be generated based on a Bayesian Interaction Primitives (BIP) model, which may be approximated using a Monte Carlo Ensemble. The BIP model may be indicative of or be used to model the spatiotemporal relationship between the tactile and kinesthetic information during whole-body haptic interactions from the training phase, thereby enabling the robot to learn whole-body human-robot haptic interaction in association with social contexts. The BIP model may be capable of predicting both an appropriate robotic response (e.g., joint trajectories) as well as the contact forces that should be exerted by the robot, given observations of the partner's pose and the force currently being exerted on the robot by the partner.”).
As per claim 9, Yamane, Campbell, and Gomez disclose and electronic device, comprising one or more processors and a memory with one or more programs stored therein, the one or more programs comprising instructions for executing the method for planning and controlling the humanoid behavior of the robot for close physical interactions according to claim 1 ( See above rejection of claim 1 and Figures 1-5 of Yamane showing processor and actions performed by the programmed processor).
As per claim 10, Yamane, Campbell, and Gomez disclose a computer-readable storage medium (Yamane at Paras. [0120]-[0121].), comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs comprising instructions for executing the method for planning and controlling the humanoid behavior of the robot for close physical interactions according to claim 1 ( See above rejection of claim 1 and Figures 1-5 of Yamane showing processor and actions performed by the programmed processor).
CONCLUSION
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ELLIS B. RAMIREZ whose telephone number is (571)272-8920. The examiner can normally be reached 7:30 am to 5:00pm.
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, Ramon Mercado can be reached at 571-270-5744. 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.
/ELLIS B. RAMIREZ/Primary Examiner, Art Unit 3658
Prosecution Insights