Human inspired task-space setpoint control of robot manipulator: See only when necessary

Behaviors in human reaching movement suggest that certain visually guided tasks consist of an initial movement without visual feedback, and a fine movement with visual feedback when our hand is near the target. Inspired by this phenomenon, we propose a new setpoint controller that only requires vision feedback when the end effector is near a desired position. The proposed controller consists of a Cartesian-space region reaching controller that is activated at the initial stages and a vision based controller that is only activated when the end effector is near the desired position. We introduce a new potential energy function such that its geometrical center is not necessary the desired position. We shall show that the proposed task-space controller can transit smoothly from Cartesian-space feedback to vision-space feedback. Simulation results are presented to illustrate the performance of this setpoint controller.