HAM-VLN: 階層的エージェント記憶を活用したゼロショット視覚言語ナビゲーション
HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation
ロボットが未知環境で指示に従って移動する際、画像や地図の代わりにエージェント自身が書き込む永続的な世界グラフを記憶として使い、次の行動選択と同じLLM呼び出しで記憶も更新することで、長期的なナビゲーションの記憶・推論ボトルネックを解消した。追加のLLM呼び出しなしで文脈長を65%以上削減しつつ、複数のナビゲーションベンチマークで最高性能を達成した。
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: An Liu, Bingxi Liu, Hongyu Ding, Yixuan Jiang, Yaran Chen, Fulin Tang, Cong Leng, Hong Zhang, Jian Cheng
分類: cs.RO
原文アブストラクト
Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a multimodal LLM to understand its observations and plan the next action. However, long-horizon navigation based on either image streams or dense map inevitably introduces a growing memory and reasoning bottleneck. We present HAM-VLN, a decision-coupled, agent-authored memory that equips the robot with a persistent, depth-grounded world graph. In the same model call used to select the next action, HAM-VLN also records semantic and reflective information---including room type, objects, navigation progress, and failure notes. Recent waypoints remain verbatim within a bounded window, while older history re-enters the context only through retrieval scored by relevance, recency, and salience, together with one-hop topological expansion. This design requires no additional LLM calls beyond the per-waypoint decision. Compared to previous methods, HAM-VLN not only improves various navigation metrics but also reduces the context length by more than 65%. Specifically, HAM-VLN achieves 61.0% Success Rate (SR) on VLN-CE R2R, 52.7% SR on VLN-CE RxR, and 79.7% SR on HM3D-v2 ObjectNav without any training.
