arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.03381cs.ROcs.LG
收藏

基于强化学习的现实世界人形机器人运动控制

Real-World Humanoid Locomotion with Reinforcement Learning

University of California, Berkeley（加州大学伯克利分校）

Ilija Radosavovic, Tete Xiao, Bike Zhang, Trevor Darrell, Jitendra Malik, Koushil Sreenath

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对人形机器人经典控制器泛化适配能力不足的问题，提出基于因果Transformer的全学习运动控制方法，通过仿真大规模无模型强化学习训练，零样本部署到现实世界，实现多地形行走、抗干扰及上下文自适应。

摘要：

能够在多样化环境中自主作业的人形机器人有望助力解决工厂劳动力短缺、居家老人照护以及新行星开拓等问题。尽管人形机器人的经典控制器已在诸多场景中取得出色成果，但它们难以泛化并适配新环境。本文提出一种完全基于学习的现实世界人形机器人运动控制方法。我们的控制器是一个因果Transformer，以本体感知观测值与动作的历史序列为输入，预测下一时刻的动作。我们假设观测-动作历史包含关于环境的有用信息，强大的Transformer模型可利用这些信息在不更新权重的情况下实现上下文内行为适配。我们在仿真中的一组随机环境集合上，通过大规模无模型强化学习训练模型，并以零样本方式部署到现实世界。该控制器能够在多种户外地形行走，对外部干扰具备鲁棒性，且可实现上下文内自适应。

英文摘要：

Humanoid robots that can autonomously operate in diverse environments have the potential to help address labour shortages in factories, assist elderly at homes, and colonize new planets. While classical controllers for humanoid robots have shown impressive results in a number of settings, they are challenging to generalize and adapt to new environments. Here, we present a fully learning-based approach for real-world humanoid locomotion. Our controller is a causal transformer that takes the history of proprioceptive observations and actions as input and predicts the next action. We hypothesize that the observation-action history contains useful information about the world that a powerful transformer model can use to adapt its behavior in-context, without updating its weights. We train our model with large-scale model-free reinforcement learning on an ensemble of randomized environments in simulation and deploy it to the real world zero-shot. Our controller can walk over various outdoor terrains, is robust to external disturbances, and can adapt in context.

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。

↑