早めに共有し、後で節約する:帯域制約下の協調VLNにおける同期駆動通信ゲーティング
Early to Share, Late to Save: Synchronisation-Driven Communication Gating in Bandwidth-Constrained Cooperative VLN
帯域制約のある協調視覚言語ナビゲーション(VLN)において、通信の重要度を事後的にラベル付けする軽量な教師付きゲートを提案し、エピソード初期の自信がある状態での通信が効果的であることを示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Arav Gupta, Nivedan Yakolli, Avinash Gautam
分類: cs.MA, cs.RO
原文アブストラクト
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
