Optimal motion planning based on CACM-RL using SLAM
Tomás Arribas, M. Gómez, Sebastián Sánchez · 2012
This work aims to integrate SLAM into the path planning based on Control Adjoining Cell Mapping and Reinforcement Learning (CACM-RL) algorithm to give a total autonomy and auto-location to mobile vehicles. This way, the implementation does not depend on any external device (e.g. camera) to perform optimal control and motion planning. SLAM is performed using Particle Filtering based on the information provided by inexpensive ultrasonic sensors and odometry. A real scenario, in where some obstacles have been introduced, is used to demonstrate the efficiency and viability of the proposed technique.