US 12,454,054 B2
Method for controlling robot, robot and computer-readable storage medium
Jiajun Wang, Shenzhen (CN); Mingguo Zhao, Shenzhen (CN); and Youjun Xiong, Shenzhen (CN)
Assigned to UBTECH ROBOTICS CORP LTD, Shenzhen (CN)
Filed by UBTECH ROBOTICS CORP LTD, Shenzhen (CN)
Filed on Aug. 5, 2023, as Appl. No. 18/230,620.
Application 18/230,620 is a continuation of application No. PCT/CN2021/132997, filed on Nov. 25, 2021.
Claims priority of application No. 202110164574.2 (CN), filed on Feb. 5, 2021.
Prior Publication US 2023/0373089 A1, Nov. 23, 2023
Int. Cl. B25J 9/16 (2006.01)
CPC B25J 9/1661 (2013.01) 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for controlling a robot, the method comprising:
providing the robot comprising: a processor, one or more joint end effectors, and a communication unit, wherein the one or more joint end effectors and the communication unit are electrically coupled to the processor, and the communication unit is to establish a communication connection between the robot and a trajectory planning device through a network, and wherein a state estimator is installed on the robot;
obtaining, by the processor, current motion state information of the robot fed back by the state estimator, and obtaining, by the communication unit, desired motion trajectory information corresponding to a target task from the trajectory planning device through the network, wherein the target task comprises at least one to-be-performed task of the robot;
determining, by the processor, task execution coefficient matrices corresponding to the robot performing the target task according to the desired motion trajectory information and the current motion state information;
constructing, by the processor, matching dynamic constraints for task-driven parameters of the robot according to the desired motion trajectory information and the current motion state information;
constructing, by the processor, matching parameter distribution constraints for the task-driven parameters according to the current motion state information and body action safety constraints corresponding to the target task;
solving, by the processor, a pre-stored task execution loss function by using the task execution coefficient matrices to obtain target-driven parameters satisfying the dynamic constraints and the parameter distribution constraints; and
driving, by the processor, the robot to perform the target task through controlling operation state of each joint end effector of the robot according to the target-driven parameters.