Early to Share, Late to Save: Synchronisation-Driven Communication Gating in Bandwidth-Constrained Cooperative VLN

arXiv:2607.08504v1 Announce Type: cross Abstract: 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 extbf{bandwidth-constrained cooperative VLN} and propose extbf{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 extbf{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

Source: arXiv cs.RO | 2026-07-10