Collaborative Perception for Connected and Autonomous Driving: Challenges, Possible Solutions and Opportunities
Senkang Hu, Zhengru Fang, Yiqin Deng, Xianhao Chen, Yuguang Fang
TL;DR
The paper investigates safety and reliability gaps in single-agent autonomous driving and proposes collaborative perception through V2X communications. It identifies challenges such as data volume, asynchronous sharing, pose errors, and security, and introduces a channel-aware framework to adapt the communication graph and reduce latency. An exemplar system architecture with transmission-delay minimization, adaptive reconstruction, and domain alignment is proposed and evaluated on the OPV2V dataset, showing improved BEV fusion and IoU. The work highlights opportunities in multi-modal collaboration, real-world generalization, secure collaboration, and incentive mechanisms for practical deployment.
Abstract
Autonomous driving has attracted significant attention from both academia and industries, which is expected to offer a safer and more efficient driving system. However, current autonomous driving systems are mostly based on a single vehicle, which has significant limitations which still poses threats to driving safety. Collaborative perception with connected and autonomous vehicles (CAVs) shows a promising solution to overcoming these limitations. In this article, we first identify the challenges of collaborative perception, such as data sharing asynchrony, data volume, and pose errors. Then, we discuss the possible solutions to address these challenges with various technologies, where the research opportunities are also elaborated. Furthermore, we propose a scheme to deal with communication efficiency and latency problems, which is a channel-aware collaborative perception framework to dynamically adjust the communication graph and minimize latency, thereby improving perception performance while increasing communication efficiency. Finally, we conduct experiments to demonstrate the effectiveness of our proposed scheme.