用强化学习训练机器人空中抓物，成功率超80%。
Catch It! Learning to Catch in Flight with Mobile Dexterous Hands
- 分两阶段训练全身控制策略，提升抓取适应性。
- 仿真中对多种形状物体随机抛掷，成功率约80%。
- 策略可直接部署于真实机器人，无需额外调参。
空中抓取（如投掷物体）是人类日常技能，但对机器人而言极具挑战。本文构建了一个由移动底盘、6自由度机械臂和12自由度灵巧手组成的移动操作臂系统，以应对这一高维复杂任务。提出一种两阶段强化学习框架，在仿真中高效训练全身控制的抓取策略。训练过程中随机化物体的投掷姿态、形状与尺寸，以增强策略对不同飞行轨迹和物体特性的适应能力。结果表明，所训练策略在仿真中对多样物体以随机轨迹投掷的场景，成功率可达约80%，显著优于基线方法。该策略可直接在真实世界部署，仅依赖机载感知与计算，成功抓取人类随机投掷的各类沙袋。项目主页见：https://mobile-dex-catch.github.io/。
原文摘要 · Abstract (English)
Catching objects in flight (i.e., thrown objects) is a common daily skill for humans, yet it presents a significant challenge for robots. This task requires a robot with agile and accurate motion, a large spatial workspace, and the ability to interact with diverse objects. In this paper, we build a mobile manipulator composed of a mobile base, a 6-DoF arm, and a 12-DoF dexterous hand to tackle such a challenging task. We propose a two-stage reinforcement learning framework to efficiently train a whole-body-control catching policy for this high-DoF system in simulation. The objects' throwing configurations, shapes, and sizes are randomized during training to enhance policy adaptivity to various trajectories and object characteristics in flight. The results show that our trained policy catches diverse objects with randomly thrown trajectories, at a high success rate of about 80\% in simulation, with a significant improvement over the baselines. The policy trained in simulation can be directly deployed in the real world with onboard sensing and computation, which achieves catching sandbags in various shapes, randomly thrown by humans. Our project page is available at https://mobile-dex-catch.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。