Patents by Inventor Xiaoyu Ren
Xiaoyu Ren has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240135160Abstract: A computer-implemented method for a machine-learning network that includes receiving an input dataset, sending the input dataset to a first machine-learning model to output predictions associated with the input data, identifying one or more slices associated with the input dataset and a first machine learning model in a first iteration, wherein each of the one or more slices include input data from the input dataset and common attributes associated with each slice; upon selecting one or more slices of the input dataset, training a shallow regressor model configured to predict residuals associated with the model, create a representation associated with a ground-truth label and a second representation associated with a model prediction associated with each sample associated with each of the one or more slices, determine residuals associated with every prediction of the first machine learning model, training the shallow regressor to compute one or more predicted residuals of the selected slices, generate an optiType: ApplicationFiled: October 15, 2022Publication date: April 25, 2024Inventors: Jorge Henrique Piazentin Ono, Xiaoyu Zhang, Liang Gou, Liu Ren
-
Publication number: 20240131702Abstract: A method for controlling a robotic arm that includes an end effector and a sensor that are mounted at an end of the robotic arm includes: obtaining, by the sensor, n gravity matrix data, wherein the n gravity matrix data are gravity matrix data of the end effector in an end coordinate system when the robotic arm is in a different poses, n?3; determining n rotation transformation matrices from a base coordinate system of the robotic arm to the end coordinate system when the robotic arm is in n different poses; calculating coordinates of a center of mass and mass of the end effector based on the n gravity matrix data and the a rotation transformation matrices; and controlling the robotic arm based on the coordinates of the center of mass and the mass.Type: ApplicationFiled: October 26, 2023Publication date: April 25, 2024Inventors: LIQUN HUANG, Xiaoyu Ren, Mingguo Zhao, Youjun Xiong
-
Publication number: 20240135159Abstract: A computer-implemented method for a machine-learning network includes receiving an input dataset, wherein the input dataset is indicative of image information, tabular information, radar information, sonar information, or sound information, sending the input dataset to the machine-learning model to output predictions associated with the input data, identifying one or more slices associated with the input dataset and the machine learning model in a first iteration, wherein each of the one or more slices include input data from the input dataset and common attributes associated with each slice, outputting an interface that includes information associated with the one or more slices and performance measurements of the one or more slices of the first iteration and subsequent iterations identifying subsequent slices, wherein the performance measurements relate to the predictions associated with the first iteration and subsequent iterations.Type: ApplicationFiled: October 15, 2022Publication date: April 25, 2024Inventors: Jorge Henrique Piazentin Ono, Xiaoyu Zhang, Huan Song, Liang Gou, Liu Ren
-
Patent number: 11858141Abstract: An impedance control method as well as a controller and a robot using the same are provided. The method includes: obtaining joint motion information and joint force information in the joint space of a robotic arm and an actual interaction force acting on an end-effector, and calculating actual motion information of the end-effector in the task space based on the joint motion information; calculating a corrected desired trajectory using environment information and a desired end-effector interaction force, and calculating the impedance control torque based on the joint force information, the actual interaction force, the actual motion information, and desired end-effector information including the corrected desired trajectory and determining a compensation torque based on a nonlinear term in a constructed dynamics equation so as to perform a joint torque control on the robotic arm based on the impedance control torque and the compensation torque.Type: GrantFiled: August 23, 2021Date of Patent: January 2, 2024Assignee: UBTECH ROBOTICS CORP LTDInventors: Liqun Huang, Xiaoyu Ren, Mingguo Zhao, Youjun Xiong
-
Patent number: 11845186Abstract: An inverse kinematics solving method for redundant robot as well as a redundant robot using the same are provided. The method includes: obtaining an expression of a Jacobian matrix null space of a current configuration of each robotic arm of the redundant robot corresponding to a preset end pose of the robotic arm according to the preset end pose, and obtaining a relation between an angular velocity of the joints of the redundant robot in the Jacobian matrix null space of the current configuration based on the obtained expression; traversing the Jacobian matrix null space using the relation, and building an energy cost function of the redundant robot based on the relation; obtaining a target joint angle of each joint of the redundant robot based on the optimal inverse kinematics solution to transmit to the servo of the joint so as to control the joint.Type: GrantFiled: December 31, 2020Date of Patent: December 19, 2023Assignee: UBTECH ROBOTICS CORP LTDInventors: Yuesong Wang, Liqun Huang, Xiaoyu Ren, Mingguo Zhao, Youjun Xiong
-
Patent number: 11724393Abstract: The present disclosure provides a robotic arm space position adjustment method, a robotic arm controller, and a computer readable storage medium. The method includes: calculating a potential energy function of moving a feature point of the robotic arm to a reference point based on an obtained preset acceleration of an artificial gravitational field, first vector of the artificial gravitational field in a preset reference coordinate system, second vector of the feature point of the robotic arm in the preset reference coordinate system, and a third vector of the reference point in the preset reference coordinate system; and calculating a null space virtual moment of moving the feature point of the robotic arm to the reference point based on a preset null space operator and the potential energy function, so as to adjust each joint of the robotic arm.Type: GrantFiled: December 30, 2020Date of Patent: August 15, 2023Assignee: UBTECH ROBOTICS CORP LTDInventors: Xiaoyu Ren, Liqun Huang, Yuesong Wang, Youjun Xiong
-
Publication number: 20230182328Abstract: A motion terrain determining method, a robot, and a computer-readable storage medium are provided. The method includes: determining each sine parameter and each cosine parameter corresponding to a target joint in a plurality of joints of the robot according to one or more constraint conditions; determining a motion trajectory of the robot according to the sine parameter and the cosine parameter corresponding to the target joint; and determining a motion terrain of the robot according to the motion trajectory. In this manner, the best motion terrain can be obtained, and the robot is controlled to move on the determined motion terrain when determining the dynamics parameters of the robot, where the obtained dynamics parameters are more accurate to effectively improve the efficiency of the identification of the dynamics parameters.Type: ApplicationFiled: December 14, 2022Publication date: June 15, 2023Inventors: Xiaoyu Ren, Liqun Huang, Huan Tan, Youjun Xiong
-
Patent number: 11654551Abstract: The present disclosure provides a redundant robotic arm control method, a redundant robotic arm, and a computer readable storage medium. The method includes: obtaining an external force acting on an end of the robotic arm and an external torque acting on each joint; calculating a first joint speed of each joint based on a degree of influence of the joint on the end in each motion dimension and the external force acting on the end; determining a zero space speed of each joint corresponding to a current position of the end based on a link torque of an external force acting on a link with respect to the joint; calculating a total joint speed based on the first joint speed and the zero space speed; and controlling the robotic arm to the move according to the total joint speed.Type: GrantFiled: December 28, 2020Date of Patent: May 23, 2023Assignee: UBTECH ROBOTICS CORP LTDInventors: Liqun Huang, Xiaoyu Ren, Yuesong Wang, Youjun Xiong
-
Patent number: 11659032Abstract: Techniques for accessing a file involve determining whether a client requests a permission for a target file, the permission allowing the client to cache data associated with the target file. The techniques further involve in response to determining that the client requests the permission, obtaining pattern information related to an access pattern in which the client accesses the target file. The techniques further involve determining availability of the permission to the client by applying the pattern information to a decision model, the decision model being trained based on training pattern information and training permission information. The techniques further involve providing, to the client, an indication on the availability. Accordingly, access conflicts can be reduced, so that the performance of the client and server can be improved.Type: GrantFiled: May 22, 2020Date of Patent: May 23, 2023Assignee: EMC IP Holding Company LLCInventors: Chaojun Zhao, Changxu Jiang, Jianfei Yang, Xiaoyu Ren
-
Patent number: 11654557Abstract: A direct force feedback control method as well as a controller and a robot using the same are provided. The method includes: obtaining an actual position and an actual speed of an end of the robotic arm and an actual external force acting on the end in a Cartesian space; calculating an impedance control component of the end in the Cartesian space based on the obtained actual position, the obtained actual speed, the obtained actual external force, an expected position, an expected speed, and an expected acceleration of the end; calculating a force control component of the end in the Cartesian space based on an expected interaction force acting on the end, the actual external force, and the actual speed; determining whether the actual external force is larger than a preset threshold, and obtaining a total force control quantity of the end of the robotic arm in the Cartesian space.Type: GrantFiled: March 10, 2021Date of Patent: May 23, 2023Assignee: UBTECH ROBOTICS CORP LTDInventors: Xiaoyu Ren, Liqun Huang, Youjun Xiong
-
Patent number: 11602844Abstract: A task hierarchical control method as well as a robot and a storage medium using the same are provided. The method includes: obtaining a task instruction for a robot, where the task instruction is for determining a target task card including an amount of selection matrices for dividing a target task into the amount of hierarchical subtasks and a controller name for executing each of the hierarchical subtasks; obtaining a null space projection matrix of each of the hierarchical subtasks based on the corresponding selection matrix; generating control finks of the amount according to the corresponding controller of each of the hierarchical subtasks and the corresponding null space projection matrix; calculating a control torque of each of the control links and obtaining a hierarchical control output quantity by adding ail the control torques; and controlling the robot to perform the target task using the hierarchical control output quantity.Type: GrantFiled: March 5, 2021Date of Patent: March 14, 2023Assignee: UBTECH ROBOTICS CORP LTDInventors: Xiaoyu Ren, Liqun Huang, Mingguo Zhao, Youjun Xiong
-
Patent number: 11442650Abstract: Storage management techniques involve: obtaining a historical usage of storage capacity for a storage device, and a historical feature characterizing the historical usage of storage capacity; generating a predicted usage of storage capacity for the storage device based on the historical feature and a predictor for predicting a usage of storage capacity; and updating the predictor by comparing the historical usage of storage capacity with the predicted usage of storage capacity. Therefore, such techniques can accurately predict the usage of storage capacity for the storage device.Type: GrantFiled: March 20, 2020Date of Patent: September 13, 2022Assignee: EMC IP Holding Company LLCInventors: Jie Huang, Xudong Wang, Ming Wang, Xiaoyu Ren
-
Patent number: 11379423Abstract: A method, computer program product, and computing system for receiving a request from a client device to access a file stored in a storage system configured to be communicatively coupled to a plurality of client devices. It may be determined whether to delegate the file to the requesting client device based upon, at least in part, a reinforcement learning model, thus defining a file delegation determination. An access pattern associated with the file may be monitored. The reinforcement learning model may be updated based upon, at least in part, the monitored access pattern associated with the file and the file delegation determination.Type: GrantFiled: May 3, 2019Date of Patent: July 5, 2022Inventors: Jianfei Yang, Chaojun Zhao, Xiaoyu Ren, Changxu Jiang, Srinivasa R. Chamarthy
-
Publication number: 20220009095Abstract: An impedance control method as well as a controller and a robot using the same are provided. The method includes: obtaining joint motion information and joint force information in the joint space of a robotic arm and an actual interaction force acting on an end-effector, and calculating actual motion information of the end-effector in the task space based on the joint motion information; calculating a corrected desired trajectory using environment information and a desired end-effector interaction force, and calculating the impedance control torque based on the joint force information, the actual interaction force, the actual motion information, and desired end-effector information including the corrected desired trajectory and determining a compensation torque based on a nonlinear term in a constructed dynamics equation so as to perform a joint torque control on the robotic arm based on the impedance control torque and the compensation torque.Type: ApplicationFiled: August 23, 2021Publication date: January 13, 2022Inventors: Liqun Huang, Xiaoyu Ren, Mingguo Zhao, Youjun Xiong
-
Publication number: 20220009093Abstract: A task hierarchical control method as well as a robot and a storage medium using the same are provided. The method includes: obtaining a task instruction for a robot, where the task instruction is for determining a target task card including an amount of selection matrices for dividing a target task into the amount of hierarchical subtasks and a controller name for executing each of the hierarchical subtasks; obtaining a null space projection matrix of each of the hierarchical subtasks based on the corresponding selection matrix; generating control finks of the amount according to the corresponding controller of each of the hierarchical subtasks and the corresponding null space projection matrix; calculating a control torque of each of the control links and obtaining a hierarchical control output quantity by adding ail the control torques; and controlling the robot to perform the target task using the hierarchical control output quantity.Type: ApplicationFiled: March 5, 2021Publication date: January 13, 2022Inventors: Xiaoyu Ren, Liqun Huang, Mingguo Zhao, Youjun Xiong
-
Publication number: 20210387334Abstract: A direct force feedback control method as well as a controller and a robot using the same are provided. The method includes: obtaining an actual position and an actual speed of an end of the robotic arm and an actual external force acting on the end in a Cartesian space; calculating an impedance control component of the end in the Cartesian space based on the obtained actual position, the obtained actual speed, the obtained actual external force, an expected position, an expected speed, and an expected acceleration of the end; calculating a force control component of the end in the Cartesian space based on an expected interaction force acting on the end, the actual external force, and the actual speed; determining whether the actual external force is larger than a preset threshold, and obtaining a total force control quantity of the end of the robotic arm in the Cartesian space.Type: ApplicationFiled: March 10, 2021Publication date: December 16, 2021Inventors: Xiaoyu Ren, Liqun Huang, Youjun Xiong
-
Publication number: 20210387340Abstract: The present disclosure provides a robotic arm space position adjustment method, a robotic arm controller, and a computer readable storage medium. The method includes: calculating a potential energy function of moving a feature point of the robotic arm to a reference point based on an obtained preset acceleration of an artificial gravitational field, first vector of the artificial gravitational field in a preset reference coordinate system, second vector of the feature point of the robotic arm in the preset reference coordinate system, and a third vector of the reference point in the preset reference coordinate system; and calculating a null space virtual moment of moving the feature point of the robotic arm to the reference point based on a preset null space operator and the potential energy function, so as to adjust each joint of the robotic arm.Type: ApplicationFiled: December 30, 2020Publication date: December 16, 2021Inventors: Xiaoyu Ren, Liqun Huang, Yuesong Wang, Youjun Xiong
-
Publication number: 20210197371Abstract: The present disclosure provides a redundant robotic arm control method, a redundant robotic arm, and a computer readable storage medium. The method includes: obtaining an external force acting on an end of the robotic arm and an external torque acting on each joint; calculating a first joint speed of each joint based on a degree of influence of the joint on the end in each motion dimension and the external force acting on the end; determining a zero space speed of each joint corresponding to a current position of the end based on a link torque of an external force acting on a link with respect to the joint; calculating a total joint speed based on the first joint speed and the zero space speed; and controlling the robotic arm to the move according to the total joint speed.Type: ApplicationFiled: December 28, 2020Publication date: July 1, 2021Inventors: Liqun Huang, Xiaoyu Ren, Yuesong Wang, Youjun Xiong
-
Publication number: 20210120004Abstract: Techniques for accessing a file involve determining whether a client requests a permission for a target file, the permission allowing the client to cache data associated with the target file. The techniques further involve in response to determining that the client requests the permission, obtaining pattern information related to an access pattern in which the client accesses the target file. The techniques further involve determining availability of the permission to the client by applying the pattern information to a decision model, the decision model being trained based on training pattern information and training permission information. The techniques further involve providing, to the client, an indication on the availability. Accordingly, access conflicts can be reduced, so that the performance of the client and server can be improved.Type: ApplicationFiled: May 22, 2020Publication date: April 22, 2021Inventors: Chaojun Zhao, Changxu Jiang, Jianfei Yang, Xiaoyu Ren
-
Publication number: 20200349119Abstract: A method, computer program product, and computing system for receiving a request from a client device to access a file stored in a storage system configured to be communicatively coupled to a plurality of client devices. It may be determined whether to delegate the file to the requesting client device based upon, at least in part, a reinforcement learning model, thus defining a file delegation determination. An access pattern associated with the file may be monitored. The reinforcement learning model may be updated based upon, at least in part, the monitored access pattern associated with the file and the file delegation determination.Type: ApplicationFiled: May 3, 2019Publication date: November 5, 2020Inventors: Jianfei Yang, Chaojun Zhao, Xiaoyu Ren, Changxu Jiang, Srinivasa R. Chamarthy