LaViRA: 連続環境におけるゼロショット視覚言語ナビゲーションのための言語・視覚・ロボット行動翻訳
LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments
自然言語指示に基づき未学習の連続環境をナビゲートするゼロショット手法。行動を言語・視覚・ロボットの3階層に分解し、各段階で異なる規模のマルチモーダル大規模言語モデルを活用することで、汎化性能と実機制御の効率を両立した。
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: Hongyu Ding, Ziming Xu, Yudong Fang, You Wu, Zixuan Chen, Jieqi Shi, Jing Huo, Yifan Zhang, Yang Gao
分類: cs.RO
原文アブストラクト
LaViRA: Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to navigate unseen environments based on natural language instructions without any prior training. Current methods face a critical trade-off: either rely on environment-specific waypoint predictors that limit scene generalization, or underutilize the reasoning capabilities of large models during navigation. We introduce LaViRA, a simple yet effective zero-shot framework that addresses this dilemma by decomposing action into a coarse-to-fine hierarchy: Language Action for high-level planning, Vision Action for middle-level perceptual grounding, and Robot Action for low-level control. This modular decomposition allows us to leverage the distinct strengths of different scales of Multimodal Large Language Models (MLLMs) at each stage, creating a system that is powerful in its reasoning, grounding and practical control. LaViRA significantly outperforms existing state-of-the-art methods on the VLN-CE benchmark, demonstrating superior generalization capabilities in unseen environments, while maintaining transparency and efficiency for real-world deployment. Project page: https://robo-lavira.github.io/lavira-zs-vln/
