Collaborative perception has recently shown great potential to improve perception capabilities over single-agent perception. Existing collaborative perception methods usually consider an ideal communication environment. However, in practice, the communication system inevitably suffers from latency issues, causing potential performance degradation and high risks in safety-critical applications, such as autonomous driving. To mitigate the effect caused by the inevitable communication latency, from a machine learning perspective, we present the first latency-aware collaborative perception system, which actively adopts asynchronous perceptual features from multiple agents to the same timestamp, promoting the robustness and effectiveness of collaboration. To achieve such a feature-level synchronization, we propose a novel latency compensation module, calledSyncNet, which leverages feature-attention symbiotic estimation and time modulation techniques. Experimental results show that our method outperforms the state-of-the-art collaborative perception method by 15.6% on the latest collaborative perception dataset V2X-SIM.
翻译:现有的协作性认知方法通常考虑理想的通信环境,但在实践中,通信系统不可避免地会遇到潜伏问题,造成潜在的性能退化和安全关键应用(如自主驱动)的高风险。为了减轻不可避免的通信潜伏所造成的影响,我们从机器学习的角度介绍了第一个潜伏性认知系统,该系统积极采用从多个代理器到同一时间戳的无同步感知特征,促进协作的稳健性和有效性。为了实现这种特征级同步,我们提议了一个称为SyncNet的新型延缓性补偿模块,它利用了特殊注意共生估计和时间调节技术。实验结果表明,我们的方法在最新的协作性认知数据集V2X-SIM上比目前最先进的协作性认知方法高出15.6%。