NavDreamer: 動画生成モデルをゼロショット3Dナビゲータとして活用
NavDreamer: Video Models as Zero-Shot 3D Navigators
動画生成モデルを言語指示とナビゲーション軌道のインターフェースとして用い、ゼロショットで3Dナビゲーションを実現するフレームワークを提案。
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: Xijie Huang, Weiqi Gai, Tianyue Wu, Congyu Wang, Zhiyang Liu, Xin Zhou, Yuze Wu, Fei Gao
分類: cs.RO
原文アブストラクト
Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to capture temporal dynamics and physical laws. We propose NavDreamer, a video-based framework for 3D navigation that leverages generative video models as a universal interface between language instructions and navigation trajectories. Our main hypothesis is that video's ability to encode spatiotemporal information and physical dynamics, combined with internet-scale availability, enables strong zero-shot generalization in navigation. To mitigate the stochasticity of generative predictions, we introduce a sampling-based optimization method that utilizes a VLM for trajectory scoring and selection. An inverse dynamics model is employed to decode executable waypoints from generated video plans for navigation. To systematically evaluate this paradigm in several video model backbones, we introduce a comprehensive benchmark covering object navigation, precise navigation, spatial grounding, language control, and scene reasoning. Extensive experiments demonstrate robust generalization across novel objects and unseen environments, with ablation studies revealing that navigation's high-level decision-making nature makes it particularly suited for video-based planning.
