Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving
Shuyao Shi, Neiwen Ling, Zhehao Jiang, Xuan Huang, Yuze He, Xiaoguang Zhao, Bufang Yang, Chen Bian, Jingfei Xia, Zhenyu Yan, Raymond Yeung, Guoliang Xing
TL;DR
This work presents Soar, a real-world end-to-end smart roadside infrastructure system designed to scale across existing lampposts for autonomous driving. It integrates a bi-directional multi-hop I2I network with an injector-sniffer I2V broadcast, a publisher-subscriber data model, and a hierarchical DL task management framework to enable concurrent, data-intensive DL tasks at the edge. Real-world deployment of 18 nodes over two campus clusters demonstrates high reliability and significant performance gains: application delivery success of 96.1%, about twofold improvements in general throughput, and substantial gains in I2V broadcast bandwidth compared with baselines, all while maintaining low power (~70 W per node) and cost. The results provide practical insights into scalable, cost-effective SRI deployment and outline avenues for incorporating emerging V2X technologies and enhanced security in future work.
Abstract
Recently,smart roadside infrastructure (SRI) has demonstrated the potential of achieving fully autonomous driving systems. To explore the potential of infrastructure-assisted autonomous driving, this paper presents the design and deployment of Soar, the first end-to-end SRI system specifically designed to support autonomous driving systems. Soar consists of both software and hardware components carefully designed to overcome various system and physical challenges. Soar can leverage the existing operational infrastructure like street lampposts for a lower barrier of adoption. Soar adopts a new communication architecture that comprises a bi-directional multi-hop I2I network and a downlink I2V broadcast service, which are designed based on off-the-shelf 802.11ac interfaces in an integrated manner. Soar also features a hierarchical DL task management framework to achieve desirable load balancing among nodes and enable them to collaborate efficiently to run multiple data-intensive autonomous driving applications. We deployed a total of 18 Soar nodes on existing lampposts on campus, which have been operational for over two years. Our real-world evaluation shows that Soar can support a diverse set of autonomous driving applications and achieve desirable real-time performance and high communication reliability. Our findings and experiences in this work offer key insights into the development and deployment of next-generation smart roadside infrastructure and autonomous driving systems.