A reinforcement learning algorithm for optimal motion of car-like vehicles

In this paper, we propose a new reinforcement learning algorithm to obtain the optimal motion of a vehicle considering kinematic and obstacle constraints. The algorithm is an extension of the CACM technique for learning the dynamic behaviour of the vehicle instead of using its analytical state equations. The method overcomes some limitations of reinforcement learning techniques when they are employed in applications with continuous non-linear systems, such as car-like vehicles. In particular, a good approximation to the optimal behaviour is obtained by a lookup table without of using function approximation. Simulation results of learning optimal motion in the presence of obstacles are reported to show the satisfactory performance of the method compared with the popular Q-learning algorithm.