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

TL;DR

This paper presents a novel controller combining trajectory optimization and machine learning to enable a quadruped robot to land on its feet after falls, inspired by the falling cat phenomenon.

Contribution

It introduces a reflex neural network approach for trajectory learning that outperforms traditional policy methods in robot landing tasks.

Findings

Reflex neural network approach outperforms policy approach.

Successful robot landings from -90 to 90 degrees pitch.

Validated in both simulation and hardware.

Abstract

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.