Obstacle-Avoidance Path Planning of Unmanned Vehicles based on Polynomial Optimization

In order to solve the obstacle avoidance path planning problem of automatic driving vehicles on unstructured roads, an A* algorithm is used to search for the collision-free path. The path waypoints are compressed by the RDP (Ramer-Douglas-Peucker) algorithm [5]. A polynomial is used to fit the path between two adjacent waypoints to ensure the continuity of vehicle speed, acceleration, jerk (derivative of acceleration), and snap (derivative of jerk), so that the unmanned vehicle drives smoothly. Finally, five S-curves are used to complete the speed-time planning of the path, and the colliding parts on the path are filled by interpolation. Simulation results show that this method can effectively and quickly complete global path planning. It can also be applied to real-time planning scenarios.