面向往返视觉语言导航的可靠性感知稀疏路径记忆
Reliability-Aware Sparse Route Memory for Round-Trip Vision-Language Navigation
浏览论文内容
中文总结 AI 辅助
针对往返视觉语言导航，提出可靠性感知稀疏路径记忆，通过反向查询几何锚点与动作仲裁，将在线返回成功率从22.0%提升至55.1%，揭示信息质量、行为一致性与在线可靠性是独立瓶颈。
中文摘要 AI 辅助
视觉语言导航（VLN）通常被评估为单向任务，尽管部署的机器人在到达目标后可能需要返回。我们研究了连续往返VLN，并诊断了方向可观测性、偏差恢复和终止稳定性方面的失败。我们提出了一种可靠性感知的稀疏路径记忆，它将已执行的出站轨迹记录为有序的几何锚点，并通过结构化提示、动作级仲裁和终端验证以相反顺序查询这些锚点。在使用NaVILA和模拟Unitree Go2的50个反向配对片段中，仅语言返回在22.0%的片段中成功，而我们的在线系统达到55.1%。在具有精确路径信息的情况下，相同的接口实现了86.0%，这表明有效的返回既需要准确的信息，也需要对该信息的一致行动。剩余的在线差距主要源于过于不可靠而无法授权干预的几何证据。这些结果将信息质量、行为一致性和在线可靠性区分为长视野导航中的独立限制。
英文摘要
Vision-language navigation (VLN) is typically evaluated as a one-way task, although deployed robots may need to return after reaching a goal. We study continuous round-trip VLN and diagnose failures in directional observability, deviation recovery, and termination stability. We propose a reliability-aware sparse route memory that records the executed Outbound trajectory as ordered geometric anchors and queries them in reverse through a structured hint, action-level arbitration, and terminal verification. On 50 reverse-paired episodes using NaVILA and a simulated Unitree Go2, language-only Return succeeds in 22.0% of episodes, while our online system reaches 55.1%. With exact route information, the same interfaces achieve 86.0%, showing that effective Return requires both accurate information and consistent action on that information. The remaining online gap arises mainly from geometric evidence that is too unreliable to authorise intervention. These results distinguish information quality, behavioural consistency, and online reliability as separate limits in long-horizon navigation.
发表机构
- University College London（伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。
