Navigation of an Autonomous Car Using Vector Fields and the Dynamic Window Approach

This work presents a safe navigation approach for a car-like robot. The approach relies on a global motion planning based on velocity vector fields along with a dynamic window approach for avoiding unmodeled obstacles. Basically, the vector field is associated with a kinematic, feedback linearization controller whose outputs are validated, and eventually modified, by the dynamic window approach. Experiments with a full-size autonomous car equipped with a stereo camera show that the vehicle was able to track the vector field and avoid obstacles in its way.