Applications

Abstract

This chapter focuses on applications of model-based reinforcement learning to closed-loop control of autonomous vehicles. The first part of the chapter is devoted to online approximation of the optimal station keeping strategy for a fully actuated six degrees-of-freedom marine craft. The developed strategy is experimentally validated using an autonomous underwater vehicle, where the three degrees-of-freedom in the horizontal plane are regulated. The second part of the chapter is devoted to online approximation of an infinite horizon optimal path-following strategy for a unicycle-type mobile robot. An approximate optimal guidance law is obtained by using an adaptive dynamic programming technique that uses concurrent-learning-based adaptive update laws to estimate the unknown optimal policy. Simulation results demonstrate that the developed method learns an optimal controller which is approximately the same as an offline numerical solver, and experimental results demonstrate the ability of the controller to learn the approximate solution in real-time.