A redundant manipulator with unknown models produces a large control error during a task execution,and the position and orientation of its end-effector need to be corrected for different tasks.To solve this problem,a position and orientation control scheme for the end-effector of a redundant manipulator is proposed based on a data-driven technology.The proposed scheme utilizes an online learning technology,which is able to be applied to con-trol a redundant manipulator with unknown models.By introducing the quaternion representation,the rotation matrix controlling the orientation of the end-effector of a redundant manipulator is transformed into a quaternion representation control method.In addition,a neural dynamics solver is designed to solve the proposed scheme.The-oretical analysis,simulations,and comparisons demonstrate the feasibility,validity,and novelty of the proposed scheme.
关键词
冗余机器人/数据驱动/位姿控制/轨迹跟踪
Key words
Redundant manipulators/data-driven technology/position and orientation control/trajectory tracking
维普
万方数据