Scale-CDA：一款用于量产车的、可扩展的原型，旨在普及AI辅助的协同驾驶自动化（CDA）
Scale-CDA: A Scalable Aftermarket Platform to Democratize Cooperative Driving Automation in Production Cars
浏览论文内容
中文总结 AI 辅助
本研究提出Scale-CDA这一开源工具链，基于OpenDBC与Openpilot构建，成本低于1000美元，可实现AI辅助CDA的即插即用改装，通过多车辆测试验证了其低时延与数据隐私保护能力，为普及协同自动驾驶提供了实用方案。
中文摘要 AI 辅助
本研究提出了Scale-CDA，这是一种开源硬件/开源软件工具链，旨在普及具备功能的生成式AI辅助协同驾驶自动化（CDA）版本。Scale-CDA基于社区维护的OpenDBC接口（支持300余款车型）和Openpilot L2级高级驾驶辅助系统（ADAS）构建，可通过成本低于1000美元的现成部件（边缘计算机、网络摄像头、CAN适配器、可选的LTE/Wi-Fi无线电）实现即插即用式改装。采用Wi-Fi 6/LTE上的MQTT构建的轻量级车万物联网（V2X）栈提供双向连接。在7.5公里测试环路中的实地实验显示，平均往返时延为5.25毫秒，链路速率接近100兆比特每秒，验证了Wi-Fi 6作为非安全关键型CDA消息传输的可行低成本介质。在智能层，一款边缘部署的多模态大语言模型（MLLM）通过模型-上下文-协议（MCP）桥接收同步的视觉、CAN和V2X流，随后输出结构化JSON形式的建议和运动基元。元动作执行器库将这些高级命令转换为经过验证的Openpilot规划器钩子，实现车道变更、间隙管理和紧急停车，且不改动经安全认证的核心。在多车辆道路测试中，整套栈维持端到端决策时延低于60毫秒，同时通过在本地运行推理保障数据隐私。总体而言，Scale-CDA弥合了限制CDA研发的两个关键缺口：（i）用于大规模实地试验的可负担、可互操作的硬件；（ii）让生成式AI可在日常车辆上进行推理和动作控制的标准化接口。通过发布物料清单、连接API和生成式AI桥接作为开源资源，本研究为交通机构和研究人员提供了普及协同自动驾驶的实用蓝图，加速提升交通效率和安全性的部署。
英文摘要
Scaling cooperative driving automation (CDA) to production passenger vehicles requires an affordable retrofit platform that can accommodate heterogeneous OEM Controller Area Network (CAN) signals and advanced driver-assistance system (ADAS) commands. Scale-CDA addresses this challenge by building on OpenDBC and openpilot, which provide vehicle interfaces and Level-2 automation support for more than 300 car models. The proposed open-hardware and open-software prototype integrates commodity edge computing, camera sensing, Wi-Fi, cellular communication, and a CAN adapter for less than $1,000. It exchanges telemetry and cooperative messages through MQTT over Wi-Fi~6 or LTE, avoiding costly DSRC or C-V2X sidelink radios. In moving-vehicle experiments, Wi-Fi~6 achieved a mean round-trip time of 5.25~ms and mean negotiated physical-layer rates of 98.51~Mb/s for transmission and 109.17~Mb/s for reception, with approximately 2% of observations exceeding 50~ms. These results demonstrate feasibility for non-safety-critical CDA applications. Scale-CDA also introduces a Generative AI interface that combines camera observations, CAN data, and connectivity messages through the Model Context Protocol. The model generates semantic message intents and structured MetaActions, while deterministic adapters validate and encode cooperative messages and map admissible actions to existing Level-2 functions without allowing direct actuator control. An on-road construction-zone demonstration validates driver advisory, message generation, and speed-related MetaAction pathways. Scale-CDA provides a reproducible platform for connectivity and GenAI research on supported production vehicles.
