MobileManiBench：モバイルマニピュレーションのためのモデル検証を簡素化するベンチマーク
MobileManiBench: Simplifying Model Verification for Mobile Manipulation
NVIDIA Isaac Simと強化学習を用いて、多様なモバイルマニピュレーション軌道を自動生成する大規模ベンチマークを構築し、代表的なVLAモデルの性能を評価した。
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: Wenbo Wang, Fangyun Wei, QiXiu Li, Xi Chen, Yaobo Liang, Chang Xu, Jiaolong Yang, Baining Guo
分類: cs.RO
原文アブストラクト
Vision-language-action models have advanced robotic manipulation but remain constrained by reliance on the large, teleoperation-collected datasets dominated by the static, tabletop scenes. We propose a simulation-first framework to verify VLA architectures before real-world deployment and introduce MobileManiBench, a large-scale benchmark for mobile-based robotic manipulation. Built on NVIDIA Isaac Sim and powered by reinforcement learning, our pipeline autonomously generates diverse manipulation trajectories with rich annotations (language instructions, multi-view RGB-depth-segmentation images, synchronized object/robot states and actions). MobileManiBench features 2 mobile platforms (parallel-gripper and dexterous-hand robots), 2 synchronized cameras (head and right wrist), 630 objects in 20 categories, 5 skills (open, close, pull, push, pick) with over 100 tasks performed in 100 realistic scenes, yielding 300K trajectories. This design enables controlled, scalable studies of robot embodiments, sensing modalities, and policy architectures, accelerating research on data efficiency and generalization. We benchmark representative VLA models and report insights into perception, reasoning, and control in complex simulated environments, with all code, datasets, and models publicly released.
