A study on automatic parking for automobiles using Rational Policy Making Method

The reinforcement learning is applied to automatic parking problem for four-wheeled automobile. The automobile controlled by reinforcement learning learns the appropriate steering angle against the outer environment using distance measuring sensors. The Rational Policy Making (PRM) Method is introduced in order to cope with random start positions. The present method has the advantage of easy implementation and be able to learn the rule of control in the environment with the confusion of state. The simulation results show the automobile can obtain the human-like behavior such as switchback. Moreover, the RPM method leads the high success ratio of parking from random starting positions.