An A* based path planning approach for autonomous vehicles
Karthikeyan Mayilvaganam, Anmol Shrivastava, Prabhu Rajagopal · 2021
This paper presents a path planning algorithm for an autonomous vehicle. The proposed method uses a tree to generate an obstacle-free path (branches of the tree) in the presence of static obstacles. The tree's growth is constrained by the vehicle's kinematic constraints, such as maximum turning angle and linear velocity. The tree generation method proposed in this work generates branches only in the direction of viable vehicle movement, making the proposed tree generation method efficient. The algorithm uses a heuristics-based A* algorithm which evaluates the tree to find an obstacle-free path. The A* algorithm uses the cost value defined at the tree branches to estimate the obstacle-free path. The developed algorithm is versatile and can be applied to autonomous vehicles, such as Autonomous Underwater Vehicle (AUV) and Autonomous Ground Vehicle (AGV).