engleski

Time Optimal Robot Control with Obstacle Avoidance Constraints

This paper presents a new numerical algorithm for time optimal control of nonlinear multivariable systems with control and state vectors constraints. The algorithm is based on the backpropagation-through-time algorithm(BPTT), which is used as a learning algorithm for recurrent neural networks. The proposed algorithm provides better convergence properties then numerical algorithm based on conversion of optimal control problem into a nonlinear programming one. The algorithm is applied to the problem of time optimal robot control with obstacle avoidance constraints.

Time Optimal Control; Nonlinear Systems; Robot Control; Gradient Algorithm

nije evidentirano