Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics
This addresses the challenge of dynamic robot acrobatics for robotics researchers, though it is incremental as it builds on existing bioinspired and control methods.
The paper tackled the problem of enabling a quadruped robot to land on its feet after falls by designing a controller that combines trajectory optimization and machine learning, achieving successful landings from initial pitch angles between -90 and 90 degrees in simulation and hardware.
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.