Real Time Localization, Path Planning and Motion Control for Autonomous Parking in Cluttered Environment with Narrow Passages

This paper propose a novel practical method for autonomous parking in cluttered environment with narrow passages. We present a modified FastSLAM algorithm for environment mapping to reduce the map entropy and increase the localization accuracy for autonomous parking. The proposed path planning method is based on predefined arc paths for real time generation of smooth paths to avoid obstacles. The corresponding control commands are generated to minimize the steering angle control error which executed by the vehicle actuators. The proposed parking method is implemented on an autonomous vehicle platform and evaluated in the different environments with narrow passages.