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

arXiv: https://arxiv.org/abs/2109.04424 · HTML: https://mlsanity.com/paper/2109.04424/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2021.

## Built on by (most cited first, 3 of 3)

- [Advanced Skills by Learning Locomotion and Local Navigation End-to-End](https://mlsanity.com/paper/2209.12827/) (2022)
- [Olympus: A Jumping Quadruped for Planetary Exploration Utilizing Reinforcement Learning for In-Flight Attitude Control](https://mlsanity.com/paper/2503.03574/) (2025)
- [First do not fall: learning to exploit a wall with a damaged humanoid robot](https://mlsanity.com/paper/2203.00316/) (2022)

## Abstract (arXiv)

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.