Abstract
This paper presents an algorithm for autonomous vehicle trajectory generation and tracking that achieves a high speed navigation. The response of an autonomous vehicle in tracking a path, depends partly on the nature of the path. To generate amenable candidate paths, a path planning algorithm uses clothoid curves that have continuities of curvature. And the curves are achieved by using fast numerical optimization techniques and effective initial guesses for the curve parameters. Lastly, the path planning algorithm compares the cost of each candidate and selects the best candidate. To track the path, a path tracking algorithm consists of two controllers which are a steering controller and a speed controller. The steering controller uses a LQR controller. And the speed controller uses a PID controller which is based on the inverse dynamics of the vehicle power train model. Simulation results show that the algorithm is efficient enough to use in real time.
Keywords: Continuous Curvature Trajectory, Path Tracking, Obstacle Avoidance, High Speed Navigation, Autonomous Vehicle