arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.14830cs.ROcs.AIcs.LG
收藏

RL-100:基于现实强化学习的高效机器人操作

RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning

Kun Lei, Huanyu Li, Dongjie Yu, Zhenyu Wei, Lingxiao Guo, Zhennan Jiang, Ziyu Wang, Shiyu Liang, Huazhe Xu

AI总结:

RL-100通过结合扩散视觉-运动策略和截断PPO目标,实现了高效且鲁棒的现实机器人操作,展示了在多种任务中高达100%的成功率和良好的适应性。

摘要:

现实中的家庭和工厂机器人操作需要可靠性、效率和鲁棒性,这些性能应不低于甚至超过熟练的人类操作员。我们提出了RL-100,一种基于扩散视觉-运动策略的现实强化学习框架。RL-100在去噪过程中统一了模仿学习和强化学习,采用单一的截断PPO替代目标,从而在离线和在线阶段均获得保守且稳定的改进。为满足部署延迟要求,一种轻量级的一致性蒸馏方法将多步扩散压缩成一步控制器,以实现高频控制。该框架任务、具象和表示无关,支持单动作和动作分块控制。我们在八个多样化的现实机器人任务上评估了RL-100,从动态推拉、敏捷滚球到倾倒、布料折叠、卸螺钉、多阶段榨汁和长时框折叠。RL-100在所有评估试验中均达到100%的成功率,总计1000次试验中1000次成功,其中在一项任务中连续250次成功。它在完成时间上与专家远程操作员相当或更优。无需重新训练,单一策略在环境和动态变化下可实现约90%的零样本成功率,能在少量样本下适应显著的任务变化(86.7%),并保持对激进的人类干扰的鲁棒性(约96%)。值得注意的是,我们的榨汁机器人在购物商场零样本部署时连续服务了约七小时而无故障。这些结果表明,通过从人类先验知识出发,对训练目标与人类基础指标对齐,并可靠地将性能延伸到人类示范之外,可以找到一种实用的机器人学习部署路径。

英文摘要:

Real-world robotic manipulation in homes and factories demands reliability, efficiency, and robustness that approach or surpass those of skilled human operators. We present RL-100, a real-world reinforcement learning framework built on diffusion visuomotor policies. RL-100 unifies imitation and reinforcement learning under a single clipped PPO surrogate objective applied within the denoising process, yielding conservative and stable improvements across offline and online stages. To meet deployment latency requirements, a lightweight consistency distillation method compresses multi-step diffusion into a one-step controller for high-frequency control. The framework is task-, embodiment-, and representation-agnostic, and supports both single-action and action-chunking control. We evaluate RL-100 on eight diverse real-robot tasks, from dynamic pushing and agile bowling to pouring, cloth folding, unscrewing, multi-stage juicing, and long-horizon box folding. RL-100 attains 100 percent success across evaluated trials, for a total of 1000 out of 1000 episodes, including up to 250 out of 250 consecutive trials on one task. It matches or surpasses expert teleoperators in time to completion. Without retraining, a single policy attains approximately 90 percent zero-shot success under environmental and dynamics shifts, adapts in a few-shot regime to significant task variations (86.7 percent), and remains robust to aggressive human perturbations (about 96 percent). Notably, our juicing robot served random customers continuously for about seven hours without failure when deployed zero-shot in a shopping mall. These results suggest a practical path to deployment-ready robot learning by starting from human priors, aligning training objectives with human-grounded metrics, and reliably extending performance beyond human demonstrations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑