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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Anne, Timothée, Dalin, Eloïse, Bergonzani, Ivan, Ivaldi, Serena, Mouret, Jean-Baptiste
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914741002174464
author Anne, Timothée
Dalin, Eloïse
Bergonzani, Ivan
Ivaldi, Serena
Mouret, Jean-Baptiste
author_facet Anne, Timothée
Dalin, Eloïse
Bergonzani, Ivan
Ivaldi, Serena
Mouret, Jean-Baptiste
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2203_00316
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle First do not fall: learning to exploit a wall with a damaged humanoid robot
Anne, Timothée
Dalin, Eloïse
Bergonzani, Ivan
Ivaldi, Serena
Mouret, Jean-Baptiste
Robotics
Artificial Intelligence
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.
title First do not fall: learning to exploit a wall with a damaged humanoid robot
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2203.00316