Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition

Ruiyang Hao, Haibao Yu, Jiaru Zhong, Chuanye Wang, Jiahao Wang, Yiming Kan, Wenxian Yang, Siqi Fan, Huilin Yin, Jianing Qiu, Yao Mu, Jiankai Sun, Li Chen, Walter Zimmer, Dandan Zhang, Shanghang Zhang, Mac Schwager, Ping Luo, Zaiqing Nie; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 1828-1839

With the rapid advancement of autonomous driving technology, vehicle-to-everything (V2X) communication has become a key enabler for enhancing perception range and driving safety by extending visibility beyond the line of sight. However, integrating multi-source sensor data from both ego-vehicles and infrastructure under real-world constraints--such as limited communication bandwidth and dynamic environments--poses significant technical challenges. To accelerate progress in this domain, we organized the End-to-End Autonomous Driving through V2X Cooperation Challenge, featuring two tracks: cooperative temporal perception and cooperative end-to-end planning. Built upon the UniV2X framework and the V2X-Seq-SPD dataset, the challenge attracted over 30 teams worldwide and provided a unified benchmark for evaluating cooperative driving systems. This paper presents the design and outcomes of the challenge, identifies key research challenges--such as bandwidth-aware fusion, robust multi-agent planning, and heterogeneous sensor integration--and analyzes emerging technical trends among top-performing solutions. By confronting realistic communication and fusion constraints, the challenge advances the development of scalable and reliable V2X-cooperative autonomous driving systems.