迷走を止める:メタ認知推論による効率的な視覚言語ナビゲーション
Stop Wandering: Efficient Vision-Language Navigation via Metacognitive Reasoning
基礎モデルを用いた訓練不要の視覚言語ナビゲーションエージェントに、空間記憶・履歴認識計画・反射的修正を統合したメタ認知機構を導入し、探索の停滞や冗長な再訪問を減らして効率と性能を向上させた。
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: Xueying Li, Feng Lyu, Hao Wu, Mingliu Liu, Jia-Nan Liu, Guozi Liu
分類: cs.RO, cs.CV
原文アブストラクト
Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy frontier selection and passive spatial memory, leading to inefficient behaviors such as local oscillation and redundant revisiting. We argue that this stems from a lack of metacognitive capabilities: the agent cannot monitor its exploration progress, diagnose strategy failures, or adapt accordingly. To address this, we propose MetaNav, a metacognitive navigation agent integrating spatial memory, history-aware planning, and reflective correction. Spatial memory builds a persistent 3D semantic map. History-aware planning penalizes revisiting to improve efficiency. Reflective correction detects stagnation and uses an LLM to generate corrective rules that guide future frontier selection. Experiments on GOAT-Bench, HM3D-OVON, and A-EQA show that MetaNav achieves state-of-the-art performance while reducing VLM queries by 20.7%, demonstrating that metacognitive reasoning significantly improves robustness and efficiency.
