Feasible and Optimal Trajectories Generation for Autonomous driving Vehicles, 11-24.

Real-time feasible and optimal trajectory generation subject to the vehicle physical constraints, the surrounding obstacles, and the environmental conditions is one of the most important parts of autonomous driving vehicles. This study presents three smooth and fast trajectories generations for autonomous driving vehicles subject to the vehicle physical constraints on speed, acceleration, and steering angle as well as the hard physical limitations of the vehicle speed and the vehicle steering angle. In vehicle safety dynamics, the vehicle steering angle and the vehicle speed are always related in a strict function depending on the surrounding obstacles and the environmental conditions. Three different methods for vehicle feasible trajectory planning generation are introduced and compared. The optimal feasible trajectory is selected based on the smoother curve, the shorter distance, and the smaller tracking errors. Results from this study can be used for online autonomous driving vehicle and for autonomous parking systems. This study provides fundamental mathematical algorithms to online map out optimal feasible paths for ground autonomous vehicles.