Occlusion-Aware Motion Planning for Autonomous Driving

Abstract

Motion planning for autonomous vehicles remains a challenge in urban road environments with occlusions. In this study, we present a motion planning framework that prioritizes safety, comfort, and efficiency to enable autonomous vehicles to navigate safely through urban roads with occlusions. Our solution consists of three main components: local path planning, trajectory planning, and speed planning. First, based on the improved Artificial Potential Field to generate the local path, then the optimal trajectory is solved in the S-L coordinate with the local path as the reference line. Subsequently, the potential risk probability of the occluded area is incorporated into the incomplete information static game framework and implement speed planning based on the game results and the proposed vehicle “safe driving” to complete the collision avoidance between the autonomous vehicle and visible or obscured dynamic traffic participants. In high pedestrian traffic scenarios, simulation verification shows that the proposed model enhances autonomous vehicle comfort levels by about 32% $\sim $ 48% compared to the baseline method utilizing automatic emergency brake system (AEB). We also conducted simulation verification of the proposed model in overtaking and left-turning traffic scenarios, comparing it with other models. The results demonstrate that our proposed model ensures safe autonomous driving in traffic scenario with occlusions while maintaining comfort and efficiency.

Keywords

• Autonomous vehicles
• collision avoidance
• motion planning
• path planning
• speed planning
• visual occlusion