发表机构
Beijing University of Posts and Telecommunications（北京邮电大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出CoAnchor框架，以目标级时空锚点为接口，联合处理协同感知中的时空错位问题，在模拟和真实数据集上验证了其鲁棒性与精度-效率权衡优势。
AI 中文摘要
协同感知通过融合附近智能体的观测结果，扩展了单辆车的感知范围，提升了自动驾驶的鲁棒性。但在实际部署中，接收到的协作智能体消息常受通信延迟和相对位姿噪声的共同影响，导致观测过时、空间错位及特征融合不稳定。现有方法通常仅从空间或时间维度解决这些问题，而以统一高效的方式联合处理这些问题仍具挑战性。本文提出CoAnchor，一种以锚点为核心的异步协同感知时空对齐框架。CoAnchor不直接在密集鸟瞰图（BEV）特征上推理，而是构建稀疏的目标级时空锚点作为位姿校正的共享接口，在统一循环中紧密结合空间细化、时间传播和当前时刻验证，同时保持整体校正过程轻量。在模拟和真实世界数据集上的大量实验表明，CoAnchor在干净设置下仍保持竞争力，且在延迟与位姿扰动共同作用下，以良好的精度-效率权衡提升了鲁棒性。
英文摘要
Collaborative perception extends the sensing range of a single vehicle by fusing observations from nearby agents, which improves the robustness of autonomous driving. In realistic deployments, however, the received collaborator messages are often affected by both communication delay and relative-pose noise, which jointly cause stale observations, spatial misalignment, and unstable feature fusion. Existing methods usually address these issues from either the spatial or temporal side, but handling them jointly in a unified and efficient manner remains challenging. In this paper, we propose CoAnchor, an anchor-centric spatio-temporal alignment framework for asynchronous collaborative perception. Instead of directly reasoning on dense BEV features, CoAnchor builds sparse object-level spatio-temporal anchors as a shared interface for pose correction and tightly connects spatial refinement, temporal propagation, and current-time verification within one unified loop, while keeping the overall correction process lightweight. Extensive experiments on both simulated and real-world datasets illustrate that CoAnchor remains competitive under clean settings and improves the robustness under joint delay and pose perturbations with a favorable practical accuracy-efficiency trade-off.
CommentsMM2026
