Journal
IEEE ROBOTICS AND AUTOMATION LETTERS
Volume 7, Issue 4, Pages 9028-9035Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2022.3188884
Keywords
Machine learning for robot control; humanoid robot systems
Categories
Funding
- CPER CyberEntreprise
- Direction General de l'Armement (convention Inria-DGA humanoide resilient)
- Creativ'Lab platform of Inria/LORIA
- CPER SCIARAT
- Scientific Interest Group
Ask authors/readers for more resources
This letter introduces a method called D-Reflex, which uses a neural network to choose the contact position of a humanoid robot when leaning on a wall, in order to achieve a stable posture. The experimental results show that D-Reflex can effectively prevent falls and can be applied to real robots.
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 he 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 letter 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 (1.75 m, 100 kg, 30 degrees of freedom) to avoid more than 75% of the avoidable falls and can work on the real robot.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available