Smooth Obstacle Avoidance Path Planning for Autonomous Vehicles

Abstract

Obstacle avoidance and overtaking are important manoeuvres for autonomous driving. The collision avoidance with a vehicle, a pedestrian or any obstacle and the generation of a feasible continuous curvature trajectory represent the major problems faced by researchers to provide a safe path planning solution. This paper presents an algorithm able to avoid vehicles or obstacles by proposing a smooth local modified trajectory of a global path. The proposed method is based on the combination of a parameterized sigmoid function and a rolling horizon. The major advantage of this method is the reactivity to the obstacle motion and the generation of a smooth trajectory in a low execution time. The lateral and the longitudinal safety distances are easily parameterized when generating the avoidance trajectory. Simulation results show that the algorithm performs collision avoidance manoeuvres for static and dynamic obstacles in an effective way. The method is validated by applying the avoidance approach on real measured trajectory.