Optimal path tracking seeks the optimal motion along a given geometric path according to a desired objective while taking system dynamics and constraints into account. In the case of time-optimal path tracking, the system inputs to track a given path while achieving minimal execution time are computed. In practice however, due to an imperfect plant model, the computed inputs might be suboptimal, result in poor tracking or even be infeasible in that they exceed given limits. This paper presents a novel two-step iterative learning approach for industrial robots to improve the performance of path tracking tasks by repeatedly updating the nonlinear robot model and solving a time-optimal path tracking problem. The proposed learning algorithm is experimentally validated on a serial robotic manipulator, which shows that the developed approach results in reduced execution time and increased accuracy.
展开▼
