Practical motion planning for car-parking control in narrow environment

The automatic parking assist system is one of the key components in future automobiles. Path planning of a car-like robot is difficult because of non-holonomic constraints. In this study, the authors propose a practical path planning algorithm for the car-parking control problem. Reachable regions from a goal can be easily computed using the proposed scheme. A variety of candidate paths can be generated by using conventional back-propagation scheme. Finally, we can obtain optimal solutions with respect to performance measures such as collision safety, moving distance, control efforts and so forth. The presented simulation results clearly show that the proposed scheme provides useful solutions.