Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning-猫眼课题宝

DOI：

10.15607/rss.2021.xvii.061

发表时间：

2021-05

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

J. Siekmann;Kevin R. Green;John Warila;Alan Fern;J. Hurst

准确和精确的地形估计是机器人在实际环境中运动的一个难题。因此，拥有不依赖于准确估计到脆弱性程度的系统是有用的。在本文中，我们通过研究两足机器人在没有任何外部感知或地形模型的情况下穿越阶梯状地形的问题，探索了这种方法的局限性。对于这种盲目的两足动物平台来说，由于出人意料的海拔变化，这个问题似乎很困难(即使对人类来说也是如此)。我们的主要贡献是证明了拟真实强化学习(RL)可以在两足机器人CASSIE上实现仅使用本体感知反馈的在阶梯状地形上的鲁棒移动。重要的是，这只需要修改现有的平坦地形训练RL框架以包括阶梯状地形随机化，而不需要对奖励函数进行任何改变。据我们所知，这是人类规模的两足机器人的第一个控制器，能够仅使用本体感知可靠地穿越各种真实世界的楼梯和其他类似楼梯的干扰。

Accurate and precise terrain estimation is a difficult problem for robot locomotion in real-world environments. Thus, it is useful to have systems that do not depend on accurate estimation to the point of fragility. In this paper, we explore the limits of such an approach by investigating the problem of traversing stair-like terrain without any external perception or terrain models on a bipedal robot. For such blind bipedal platforms, the problem appears difficult (even for humans) due to the surprise elevation changes. Our main contribution is to show that sim-to-real reinforcement learning (RL) can achieve robust locomotion over stair-like terrain on the bipedal robot Cassie using only proprioceptive feedback. Importantly, this only requires modifying an existing flat-terrain training RL framework to include stair-like terrain randomization, without any changes in reward function. To our knowledge, this is the first controller for a bipedal, human-scale robot capable of reliably traversing a variety of real-world stairs and other stair-like disturbances using only proprioception.

Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning

文献摘要

相似文献