arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.04424cs.RO
收藏

Mini Cheetah,the Falling Cat:A Case Study in机器学习and轨迹优化for Robot Acrobatics

Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics

University of Notre Dame(圣母大学)

Vince Kurtz, He Li, Patrick M. Wensing, Hai Lin

摘要:

猫在摔倒后总是用脚着地,这似乎与基本的物理学原理背道而驰。在本文中,我们设计了一个控制器,土地的迷你猎豹四足机器人的脚以及。具体来说,我们将探索轨迹优化和机器学习如何协同工作,以实现高度动态的生物启发行为。我们发现,反射的方法,其中一个神经网络学习整个状态轨迹,优于政策的方法,其中一个神经网络学习从状态到控制输入的映射。我们在仿真和硬件实验中验证了我们提出的控制器,并且能够使机器人在跌倒时以-90至90度之间的初始俯仰角站立着陆。

英文摘要:

Seemingly in defiance of basic physics, cats consistently land on their feet after falling. In this paper, we design a controller that lands the Mini Cheetah quadruped robot on its feet as well. Specifically, we explore how trajectory optimization and machine learning can work together to enable highly dynamic bioinspired behaviors. We find that a reflex approach, in which a neural network learns entire state trajectories, outperforms a policy approach, in which a neural network learns a mapping from states to control inputs. We validate our proposed controller in both simulation and hardware experiments, and are able to land the robot on its feet from falls with initial pitch angles between -90 and 90 degrees.

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。

↑