Abstract
Collaborative perception empowers each agent to improve its perceptual ability through the exchange of perceptual messages with other agents. It inherently results in a fundamental trade-off between perception ability and communication cost. To address this bottleneck issue, our core idea is to optimize the collaborative messages from two key aspects: representation and selection. The proposed codebook-based message representation enables the transmission of integer codes, rather than high-dimensional feature maps. The proposed information-filling-driven message selection optimizes local messages to collectively fill each agent's information demand, preventing information overflow among multiple agents. By integrating these two designs, we propose CodeFilling, a novel communication-efficient collaborative perception system, which significantly advances the perception-communication trade-off and is inclusive to both homogeneous and heterogeneous collaboration settings. We evaluate CodeFilling in both a real-world dataset, DAIR-V2X, and a new simulation dataset, OPV2VH+. Results show that CodeFilling outperforms previous SOTA Where2comm on DAIR-V2X/OPV2VH+ with 1,333/1,206 times lower communication volume. Our code is available at this https URL.
Abstract (translated)
合作感知使每个智能体通过与其他智能体交换感知信息来提高其感知能力。这固有地导致感知能力和通信成本之间的基本权衡。为解决这个瓶颈问题,我们核心的想法是优化两个关键方面:表示和选择。基于代码的报文表示允许传输整数编码,而不是高维特征图。所提出的信息填充驱动的消息选择优化了局部消息,使其 collective fill each agent's information demand,防止了多个智能体之间的信息溢出。通过整合这两个设计,我们提出了CodeFilling,一种新颖的通信高效的协作感知系统,显著提高了感知-通信权衡,并适用于各种协作设置。我们在DAIR-V2X和OPV2VH+这两个真实世界数据集上评估了CodeFilling。结果表明,CodeFilling在DAIR-V2X/OPV2VH+上优于之前的最佳SOTAWhere2comm,通信量降低了1,333/1,206倍。我们的代码可在此处访问的链接中获取。
URL
https://arxiv.org/abs/2405.04966