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 W. Yeung, Guoliang Xing
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- Peering Inside the Black-Box: Long-Range and Scalable Model Architecture Snooping via GPU Electromagnetic Side-ChannelRui Xiao, Sibo Feng, Soundarya Ramesh, Jun Han 等NDSS 2026 · 被引用 3 次
- UrgenGo: Urgency-Aware Transparent GPU Kernel Launching for Autonomous DrivingHanqi Zhu, Wuyang Zhang, Xinran Zhang, Ziyang Tao 等MobiCom 2025
- DarkDistill: Difficulty-Aligned Federated Early-Exit Network Training on Heterogeneous DevicesLehao Qu, Shuyuan Li, Zimu Zhou, Boyi Liu 等KDD 2025
- Towards Real-Time Defense against Object-Based LiDAR Attacks in Autonomous DrivingYan Zhang, Zihao Liu, Yi Zhu, Chenglin MiaoCCS 2025
它引用的顶会 Paper6
- EMP: edge-assisted multi-vehicle perceptionXumiao Zhang, Anlan Zhang, Jiachen Sun, Xiao Zhu 等MobiCom 2021 · 被引用 137 次
- VIPS: real-time perception fusion for infrastructure-assisted autonomous drivingShuyao Shi, Jiahe Cui, Zhehao Jiang, Zhenyu Yan 等MobiCom 2022 · 被引用 126 次
- VI-eye: semantic-based 3D point cloud registration for infrastructure-assisted autonomous drivingYuze He, Li Ma, Zhehao Jiang, Yi Tang 等MobiCom 2021 · 被引用 76 次
- Heimdall: mobile GPU coordination platform for augmented reality applicationsJuheon Yi, Youngki LeeMobiCom 2020 · 被引用 71 次
- LaLaRAND: Flexible Layer-by-Layer CPU/GPU Scheduling for Real-Time DNN TasksWoosung Kang, Kilho Lee, Jinkyu Lee, Insik Shin 等RTSS 2021 · 被引用 68 次
相关 Paper
- VILAM: Infrastructure-assisted 3D Visual Localization and Mapping for Autonomous DrivingJiahe Cui, Shuyao Shi, Yuze He, Jianwei Niu 等NSDI 2024 · 被引用 17 次
- VI-Map: Infrastructure-Assisted Real-Time HD Mapping for Autonomous DrivingYuze He, Chen Bian, Jingfei Xia, Shuyao Shi 等MobiCom 2023 · 被引用 35 次
- From FSD to FSC: Enabling Full Smart-Communication in Autonomous Vehicles Through Full Self-Driving ModelsZhicheng Wang, Shihan Zhao, Donghui Dai, Lei Yang 等INFOCOM 2026
- Autonomous Driving with Spiking Neural NetworksRuijie Zhu, Ziqing Wang, Leilani Gilpin, Jason EshraghianNeurIPS 2024 · 被引用 35 次
- A Networking Perspective on Starlink's Self-Driving LEO Mega-ConstellationYuanjie Li, Hewu Li, Wei Liu, Lixin Liu 等MobiCom 2023 · 被引用 58 次
