MobileVLA-R1: 四足歩行ロボットのための視覚-言語-行動モデルを強化学習で強化
MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots
自然言語指示を四足歩行ロボットの連続制御に接地させるため、多粒度Chain-of-Thoughtデータセットと教師あり学習+GRPO強化学習の二段階学習を組み合わせた統合VLAフレームワークを提案し、実機で有効性を示した。
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: Ting Huang, Dongjian Li, Rui Yang, Zeyu Zhang, Zida Yang, Hao Tang
分類: cs.RO, cs.CV
原文アブストラクト
Grounding natural-language instructions into continuous control for quadruped robots remains a fundamental challenge in vision language action. Existing methods struggle to bridge high-level semantic reasoning and low-level actuation, leading to unstable grounding and weak generalization in the real world. To address these issues, we present MobileVLA-R1, a unified vision-language-action framework that enables explicit reasoning and continuous control for quadruped robots. We construct MobileVLA-CoT, a large-scale dataset of multi-granularity chain-of-thought (CoT) for embodied trajectories, providing structured reasoning supervision for alignment. Built upon this foundation, we introduce a two-stage training paradigm that combines supervised CoT alignment with GRPO reinforcement learning to enhance reasoning consistency, control stability, and long-horizon execution. Extensive evaluations on VLN and VLA tasks demonstrate superior performance over strong baselines, with approximately a 5% improvement. Real-world deployment on a quadruped robot validates robust performance in complex environments. Code: https://github.com/AIGeeksGroup/MobileVLA-R1. Website: https://aigeeksgroup.github.io/MobileVLA-R1.
