# First do not fall: learning to exploit a wall with a damaged humanoid robot

arXiv: https://arxiv.org/abs/2203.00316 · HTML: https://mlsanity.com/paper/2203.00316/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 30 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 7 of 7)

- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control](https://mlsanity.com/paper/1909.04947/) (2019)
- [Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors](https://mlsanity.com/paper/2003.04663/) (2020)
- [Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics](https://mlsanity.com/paper/1709.06917/) (2017)
- [Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics](https://mlsanity.com/paper/2109.04424/) (2021)
- [Agile Actions with a Centaur-Type Humanoid: A Decoupled Approach](https://mlsanity.com/paper/2103.07183/) (2021)

## Abstract (arXiv)

Humanoid robots could replace humans in hazardous situations but most of such situations are equally dangerous for them, which means that they have a high chance of being damaged and falling. We hypothesize that humanoid robots would be mostly used in buildings, which makes them likely to be close to a wall. To avoid a fall, they can therefore lean on the closest wall, as a human would do, provided that they find in a few milliseconds where to put the hand(s). This article introduces a method, called D-Reflex, that learns a neural network that chooses this contact position given the wall orientation, the wall distance, and the posture of the robot. This contact position is then used by a whole-body controller to reach a stable posture. We show that D-Reflex allows a simulated TALOS robot (1.75m, 100kg, 30 degrees of freedom) to avoid more than 75% of the avoidable falls and can work on the real robot.