CoDS：基于专家驱动检测与BEV分割的鲁棒协同感知
CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation
- Peking University（北京大学）
- Macau University of Science and Technology（澳门科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对多源噪声导致协同感知性能下降的问题，提出CoDS框架，通过CoRM、S-MoE和BTCI模块提升鲁棒性，在公开数据集上优于基线且抗噪稳定。
AI中文摘要：
协同感知通过多智能体信息交换突破了单视角感知的局限性，但位姿误差、通信延迟等多源噪声会降低融合特征质量，限制感知性能。检测与鸟瞰图（BEV）分割的联合训练是天然的解决方案：分割得到的道路区域可约束目标分布，检测得到的边界框可恢复模糊的分割边界。为此，我们提出了专家驱动检测与BEV分割的鲁棒协同感知框架CoDS。为解决融合质量的空间不一致问题，我们首先引入协同可靠性图（CoRM）以显式量化特征质量分布；基于CoRM，设计语义混合专家（S-MoE）模块，为不一致的特征需求提取差异化特征；最后，为进一步缓解特征噪声退化，双向任务互补交互（BTCI）通过双向注入优化任务感知特征。在OPV2V和V2V4Real数据集上的大量实验表明，CoDS在两项任务上均优于现有基线，且在多源噪声下保持稳定鲁棒性。代码见：this https URL 和 this https URL。
英文摘要：
Collaborative perception breaks through single-view limitations via multi-agent information exchange. However, multi-source noise such as pose errors and communication delays degrades fusion feature quality, constraining perception performance. Joint training of detection and BEV segmentation provides a natural remedy, where segmented road regions help constrain target distributions and detection bounding boxes help recover ambiguous segmentation boundaries. To this end, we propose a robust Collaborative perception framework with expert-driven Detection and bev Segmentation (CoDS). To address spatial inconsistency in fusion quality, we first introduce the Collaborative Reliability Map (CoRM) to explicitly quantify feature quality distribution. Based on CoRM, we design the Semantic Mixture-of-Experts (S-MoE) module to extract differentiated features for inconsistent feature demands. Finally, to further mitigate feature noise degradation, the Bidirectional Task Complementary Interaction (BTCI) refines task-aware features through bidirectional injection. Extensive experiments on OPV2V and V2V4Real datasets show that our CoDS surpasses existing baselines on both tasks and maintains stable robustness under multi-source noise. Code: https://github.com/JinlongW128/CoDS and https://openi.pcl.ac.cn/OpenAIDriving/CoDS.
