Towards Collaborative Autonomous Driving: Simulation Platform and End-to-End System

2024-04-15

arXiv.org

AI Summary

To address inefficient information sharing, lack of closed-loop evaluation, and absence of end-to-end cooperative systems in vehicle-to-everything–assisted autonomous driving (V2X-AD), this paper proposes a driving-oriented V2X communication optimization strategy. We introduce V2Xverse—the first full-stack cooperative autonomous driving simulation and learning platform supporting closed-loop evaluation—and implement CoDriving, an end-to-end system integrating multi-agent simulation, V2X communication modeling, shared perception fusion, and deep reinforcement learning for inter-vehicle perceptual collaboration and joint decision-making. Experiments under dynamic communication constraints demonstrate a 62.49% improvement in driving score and a 53.50% reduction in pedestrian collision rate over state-of-the-art end-to-end methods. Key contributions include: (1) the first driving-task-driven communication scheduling mechanism; and (2) the first V2X-AD full-stack system unifying high-fidelity simulation, closed-loop training, and reproducible evaluation.

Technology Category

• Multiagent Systems: Agent Communication
• Computer Vision: Vision for Robotics & Autonomous Driving
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Vehicle-to-everything-aided autonomous driving (V2X-AD) has a huge potential to provide a safer driving solution. Despite extensive researches in transportation and communication to support V2X-AD, the actual utilization of these infrastructures and communication resources in enhancing driving performances remains largely unexplored. This highlights the necessity of collaborative autonomous driving: a machine learning approach that optimizes the information sharing strategy to improve the driving performance of each vehicle. This effort necessitates two key foundations: a platform capable of generating data to facilitate the training and testing of V2X-AD, and a comprehensive system that integrates full driving-related functionalities with mechanisms for information sharing. From the platform perspective, we present V2Xverse, a comprehensive simulation platform for collaborative autonomous driving. This platform provides a complete pipeline for collaborative driving. From the system perspective, we introduce CoDriving, a novel end-to-end collaborative driving system that properly integrates V2X communication over the entire autonomous pipeline, promoting driving with shared perceptual information. The core idea is a novel driving-oriented communication strategy. Leveraging this strategy, CoDriving improves driving performance while optimizing communication efficiency. We make comprehensive benchmarks with V2Xverse, analyzing both modular performance and closed-loop driving performance. Experimental results show that CoDriving: i) significantly improves the driving score by 62.49% and drastically reduces the pedestrian collision rate by 53.50% compared to the SOTA end-to-end driving method, and ii) achieves sustaining driving performance superiority over dynamic constraint communication conditions.

Problem

• Optimizes V2X communication for safer autonomous driving
• Develops simulation platform for collaborative driving training
• Integrates shared perception to enhance vehicle performance

Innovation

• V2Xverse: simulation platform for collaborative driving
• CoDriving: end-to-end system with V2X communication
• Driving-oriented strategy optimizes communication efficiency