考え、記憶し、ナビゲートする:VLM推論によるゼロショット物体目標ナビゲーション
Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning
VLMをナビゲーションの能動的な戦略立案者として活用し、構造化された思考連鎖プロンプトと行動履歴・障害物マップの解釈により、ゼロショット物体目標ナビゲーションの効率を大幅に向上させた。
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: Mobin Habibpour, Fatemeh Afghah
分類: cs.RO, cs.AI
原文アブストラクト
While Vision-Language Models (VLMs) are set to transform robotic navigation, existing methods often underutilize their reasoning capabilities. To unlock the full potential of VLMs in robotics, we shift their role from passive observers to active strategists in the navigation process. Our framework outsources high-level planning to a VLM, which leverages its contextual understanding to guide a frontier-based exploration agent. This intelligent guidance is achieved through a trio of techniques: structured chain-of-thought prompting that elicits logical, step-by-step reasoning; dynamic inclusion of the agent's recent action history to prevent getting stuck in loops; and a novel capability that enables the VLM to interpret top-down obstacle maps alongside first-person views, thereby enhancing spatial awareness. When tested on challenging benchmarks like HM3D, Gibson, and MP3D, this method produces exceptionally direct and logical trajectories, marking a substantial improvement in navigation efficiency over existing approaches and charting a path toward more capable embodied agents.
