V2X-Lead: LiDAR-based End-to-End Autonomous Driving with Vehicle-to-Everything Communication Integration
It addresses the challenge of imperfect perception for autonomous vehicles in complex urban environments, though it appears incremental by combining existing technologies like LiDAR and V2X with deep reinforcement learning.
This paper tackled the problem of navigating unregulated urban scenarios in mixed-autonomy traffic by integrating LiDAR and V2X communication data into an end-to-end autonomous driving method, resulting in improved safety and efficiency for tasks like unsignalized intersections and generalizability to unseen scenarios like roundabouts.
This paper presents a LiDAR-based end-to-end autonomous driving method with Vehicle-to-Everything (V2X) communication integration, termed V2X-Lead, to address the challenges of navigating unregulated urban scenarios under mixed-autonomy traffic conditions. The proposed method aims to handle imperfect partial observations by fusing the onboard LiDAR sensor and V2X communication data. A model-free and off-policy deep reinforcement learning (DRL) algorithm is employed to train the driving agent, which incorporates a carefully designed reward function and multi-task learning technique to enhance generalization across diverse driving tasks and scenarios. Experimental results demonstrate the effectiveness of the proposed approach in improving safety and efficiency in the task of traversing unsignalized intersections in mixed-autonomy traffic, and its generalizability to previously unseen scenarios, such as roundabouts. The integration of V2X communication offers a significant data source for autonomous vehicles (AVs) to perceive their surroundings beyond onboard sensors, resulting in a more accurate and comprehensive perception of the driving environment and more safe and robust driving behavior.