Vehicle cooperation improves autonomous driving with future action prediction
V2X-WAM: A Cooperative World Action Model for End-to-End Autonomous Driving
RoboticsComputer Vision and Pattern Recognition
Summary
Self-driving cars usually make decisions based on what they see nearby, but they often don't think ahead about what will happen next. The authors created a method called V2X-WAM that helps vehicles and road infrastructure share information to better predict how traffic will change in the future. This method uses these predictions to plan safer, more accurate driving paths. Tests showed it works better than other current methods and uses less data to communicate.
What this means in practice
- •For autonomous vehicle engineers: Design cooperative driving systems that anticipate future traffic changes for safer and more accurate autonomous navigation.
- •For road infrastructure planners: Develop communication protocols to efficiently share compressed traffic data from infrastructure to vehicles for enhanced cooperative driving.
Authors
Junwei You, Weizhe Tang, Can Wang, Yan Zhao, Jun Hua, Haotian Shi, Wei Zhang, Lin Wang, Bin Ran
Abstract
Vehicle-infrastructure cooperation can complement onboard sensing with broader and more informative observations of the traffic environment, providing valuable support for end-to-end autonomous driving. However, existing cooperative driving methods mainly exploit roadside information to enhance the representation of the current scene, while the future consequences of prospective driving actions are rarely modeled explicitly. This limits the ability of the planner to anticipate how its decisions may interact with the evolving traffic environment. To address this issue, we propose V2X-WAM, a cooperative world action model that tightly couples cooperative scene understanding, action generation, and future-world reasoning. V2X-WAM constructs a reliability-aware spatiotemporal representation from vehicle- and infrastructure-side observations, while compressing infrastructure information into a compact quantized message for efficient communication. Based on the resulting cooperative representation, a multimodal planner generates prospective trajectories, which explicitly condition future occupancy and dynamic-flow prediction. The predicted world consequences are then fed back to refine the planned trajectory, forming a closed interaction between action and future-world evolution. Experiments on a large-scale real-world cooperative driving dataset demonstrate that V2X-WAM consistently improves planning accuracy and safety over representative end-to-end cooperative driving methods, while achieving stronger future-world prediction and substantially lower communication overhead. Ablation studies further validate the effectiveness of the proposed design.