Spatial Iterative Learning Control for Robots in Contact with Unknown Environments

A spatial iterative control method is developed for robots to interact with an unknown environment at a desired level. Motivated by the human adaptive behaviour, the developed robot controller can adapt its reference trajectory to maintain a desired interaction force by designing a learning law. Considering the uncertain dynamics of the robot, an adaptive control algorithm integrating neural networks is employed to enable the robot to track the reference trajectory, so that the interaction performance is achieved. Through Lyapunov theory, signals of the closed-loop system are analyzed and proven to be convergent. Simulation results exhibit that the learning controller for the robot has adaptive properties in contacting tasks.