SpatialNav: 空間シーングラフを活用したゼロショット視覚言語ナビゲーション
SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation
環境を事前探索して空間シーングラフを構築し、エージェント中心の地図と方位合わせした視覚表現、遠隔物体位置推定を組み合わせることで、ゼロショット視覚言語ナビゲーションの性能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: Jiwen Zhang, Zejun Li, Siyuan Wang, Xiangyu Shi, Zhongyu Wei, Qi Wu
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, relying primarily on local observations for navigation, which leads to inefficient exploration and a significant performance gap. To deal with the problem, we consider a zero-shot VLN setting that agents are allowed to fully explore the environment before task execution. Then, we construct the Spatial Scene Graph (SSG) to explicitly capture global spatial structure and semantics in the explored environment. Based on the SSG, we introduce SpatialNav, a zero-shot VLN agent that integrates an agent-centric spatial map, a compass-aligned visual representation, and a remote object localization strategy for efficient navigation. Comprehensive experiments in both discrete and continuous environments demonstrate that SpatialNav significantly outperforms existing zero-shot agents and clearly narrows the gap with state-of-the-art learning-based methods. Such results highlight the importance of global spatial representations for generalizable navigation.
