Generic Trajectory Planning Algorithm for Urban Autonomous Driving

Abstract

In this paper, a new local planning algorithm for urban autonomous driving is presented. Our main contribution is to define a fully algorithmic method, based on a geometrical representation of the environment, to compute predictive speed profiles on multiple paths, to ensure safety and comfort with respect to the scene and its predicted evolution. Simulation results are provided to evaluate the behaviour of the proposed algorithm on various scenarios. Those results show a good, comfortable and safe reaction of the vehicle to its static and dynamic environment with processing times compatible with real-time control.

Efficient Speed Planning in the Path-Time Space for Urban Autonomous Driving

“…In this section, we give some simulation results of the integration of this speed planning method inside our local planning method. We also propose a comparison with our previous speed planning method presented in [16], later referred as the "stop-point method". In this method, each position of the candidate trajectory for the EV is compared with all predicted positions of the dynamic obstacles at the same time.…”

Virtual Obstacle for a Safe and Comfortable Approach to Limited Visibility Situations in Urban Autonomous Driving

“…The virtual obstacle principle is designed to be integrated in the motion planning algorithm proposed by [9]. In the following sections, relevant details of the planning algorithm are provided and the virtual obstacle concept is presented.…”