NaVILA: 脚式ロボットのための視覚-言語-行動モデルによるナビゲーション
NaVILA: Legged Robot Vision-Language-Action Model for Navigation
脚式ロボットの視覚言語ナビゲーションにおいて、VLAモデルで「75cm前進」のような中間行動を生成し、それを強化学習による歩行ポリシーで実行する2階層フレームワークを提案した論文。
著者: An-Chieh Cheng, Yandong Ji, Zhaojing Yang, Zaitian Gongye, Xueyan Zou, Jan Kautz, Erdem Bıyık, Hongxu Yin, Sifei Liu, Xiaolong Wang
分類: cs.RO, cs.CV
原文アブストラクト
This paper proposes to solve the problem of Vision-and-Language Navigation with legged robots, which not only provides a flexible way for humans to command but also allows the robot to navigate through more challenging and cluttered scenes. However, it is non-trivial to translate human language instructions all the way to low-level leg joint actions. We propose NaVILA, a 2-level framework that unifies a Vision-Language-Action model (VLA) with locomotion skills. Instead of directly predicting low-level actions from VLA, NaVILA first generates mid-level actions with spatial information in the form of language, (e.g., "moving forward 75cm"), which serves as an input for a visual locomotion RL policy for execution. NaVILA substantially improves previous approaches on existing benchmarks. The same advantages are demonstrated in our newly developed benchmarks with IsaacLab, featuring more realistic scenes, low-level controls, and real-world robot experiments. We show more results at https://navila-bot.github.io/
