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

TL;DR

This paper presents D-Reflex, a neural network-based method enabling a humanoid robot to quickly find and use a wall contact point to prevent falls, improving safety in hazardous environments.

Contribution

Introduction of D-Reflex, a neural network that enables humanoid robots to exploit walls for fall prevention in real-time.

Findings

D-Reflex prevents over 75% of avoidable falls in simulation.

The method is effective on both simulated and real TALOS robots.

Neural network computes contact points within milliseconds.

Abstract

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.