Optimal Trajectory Generation for Discretized Terminal Conditions based on Reference Lines

In the paper, optimal trajectory generation method is proposed, which produces trajectories approaching the target location with smooth accelerations and continuous curvatures, fulfilling the vehicle kinematic restrictions. Firstly, a fixed number of alternative trajectories are generated in the Frenet-Serret Frame via initial and terminal states of motion based on a global path which is acquired by global path planning in a topological map. These meet the requirement of comfortability and feasibility for autonomous driving. And then the best trajectory is chosen from alternatives as optimal trajectory with a small cost in association with non-holonomic vehicle constraints and obstacle avoidance. The proposed method satisfies distance-keeping, velocity-keeping, collision-avoiding, etc. The performance of the approach is verified by practical experiments at last.