在带宽受限下，早期同步信息能显著提升协作导航效率。
Early to Share, Late to Save: Synchronisation-Driven Communication Gating in Bandwidth-Constrained Cooperative VLN
- 通过事后标注通信关键步，实现轻量级通信门控
- 早期高自信阶段通信效果最佳，比随机门控效率高260%
- 适合资源受限的智能体协作场景，如机器人导航
大多数协作视觉语言导航（VLN）方法假设通信无限制，忽视了实际应用中带宽受限、信息效率关键的问题。本文提出带宽受限的协作VLN，并引入后见之明门控（hindsight gating）：一种轻量级监督门控，基于导航失败事后标注通信关键步骤，避免REINFORCE方法的高方差问题。与直觉相反，我们发现训练后的门控在早期阶段频繁触发，且在高自信时更常开启，这一现象在所有预算水平（B ∈ {1,3,5}）下一致。原因在于循环隐藏状态对齐机制：早期通信注入具象化轨迹表示，经后续门控循环单元（GRU）更新持续累积，使累计对齐增益达+0.072（当传输次数B=3时），接近无约束通信的+0.078，对齐效率是随机门控（+0.020）的260%、熵基门控（+0.017）的320%。结果确立了带宽受限智能体的新通信范式：尽早同步表征，后期独立导航。代码已开源。
原文摘要 · Abstract (English)
Most cooperative Vision-Language Navigation (VLN) methods assume unlimited communication, not considering real-world applications where bandwidth is restricted and information efficiency is critical. We introduce \textbf{bandwidth-constrained cooperative VLN} and propose \textbf{hindsight gating}: a lightweight supervised gate that labels communication-critical steps post-hoc from navigation failures, avoiding the high variance of REINFORCE. Contrary to the intuition that agents should communicate when uncertain, we observe a consistent counter-intuitive pattern: trained gates fire predominantly in early episode steps and more often when agents are confident, across all budget levels ($B \in \{1,3,5\}$). We explain this through \textbf{recurrent hidden-state alignment}: early communication injects grounded trajectory representations that persist and compound through subsequent Gated Recurrent Unit (GRU) updates, achieving $+0.072$ cumulative alignment gain with $B{=}3$ transmissions, approaching unconstrained communication ($+0.078$) at 260\% greater alignment efficiency than random gating ($+0.020$) and 320\% greater efficiency than entropy-based gating ($+0.017$). Our results establish a new communication regime for bandwidth-limited embodied agents: synchronise representations early, navigate independently later. Our codebase is available at: https://github.com/AravG13/bandwidth-constrained-cooperative-vln
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。