测试协作式机器人在通信故障下的表现，发现性能可暴跌96%。
AgentComm-Bench: Stress-Testing Cooperative Embodied AI Under Latency, Packet Loss, and Bandwidth Collapse
- 构建六维通信压力测试基准，模拟延迟、丢包等真实网络问题。
- 导航任务在带宽崩溃下性能下降超96%，感知任务F1值下降超85%。
- 提出轻量冗余编码策略，在80%丢包下导航性能提升一倍以上。
协作式具身智能的多智能体方法几乎总在理想通信条件下评估：零延迟、无丢包、无限带宽。然而，实际部署于无线机器人、拥堵网络中的自动驾驶汽车或对抗频谱中的无人机群时，这些条件无法保证。本文提出AgentComm-Bench，一套系统化的基准测试套件与评估协议，涵盖六类通信退化场景：延迟、丢包、带宽崩溃、异步更新、过时记忆和冲突传感器数据。该基准覆盖三类任务：协作感知、多智能体路径导航与协同区域搜索，并评估五种通信策略，包括一种基于冗余消息编码与过时感知融合的轻量级新方法。实验表明，依赖通信的任务会严重恶化：过时记忆与带宽崩溃使导航性能下降超过96%，内容损坏（过时或冲突数据）使感知F1值下降超85%。脆弱性取决于退化类型与任务设计的交互作用；感知融合对丢包鲁棒，但会放大损坏数据影响。冗余消息编码在80%丢包下使导航性能提升超过一倍。我们公开发布AgentComm-Bench作为实用评估协议，建议协作式具身智能研究在多种退化条件下报告性能。
原文摘要 · Abstract (English)
Cooperative multi-agent methods for embodied AI are almost universally evaluated under idealized communication: zero latency, no packet loss, and unlimited bandwidth. Real-world deployment on robots with wireless links, autonomous vehicles on congested networks, or drone swarms in contested spectrum offers no such guarantees. We introduce AgentComm-Bench, a benchmark suite and evaluation protocol that systematically stress-tests cooperative embodied AI under six communication impairment dimensions: latency, packet loss, bandwidth collapse, asynchronous updates, stale memory, and conflicting sensor evidence. AgentComm-Bench spans three task families: cooperative perception, multi-agent waypoint navigation, and cooperative zone search, and evaluates five communication strategies, including a lightweight method we propose based on redundant message coding with staleness-aware fusion. Our experiments reveal that communication-dependent tasks degrade catastrophically: stale memory and bandwidth collapse cause over 96% performance drops in navigation, while content corruption (stale or conflicting data) reduces perception F1 by over 85%. Vulnerability depends on the interaction between impairment type and task design; perception fusion is robust to packet loss but amplifies corrupted data. Redundant message coding more than doubles navigation performance under 80% packet loss. We release AgentComm-Bench as a practical evaluation protocol and recommend that cooperative embodied AI work report performance under multiple impairment conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。