Learning Feasibility Constraints for Multi-contact Locomotion of Legged Robots

Justin Carpentier 1 Rohan Budhiraja 1 Nicolas Mansard 1
1 LAAS-GEPETTO - Équipe Mouvement des Systèmes Anthropomorphes
LAAS - Laboratoire d'analyse et d'architecture des systèmes [Toulouse]
Abstract : Relying on reduced models is nowadays a standard cunning to tackle the computational complexity of multi-contact locomotion. To be really effective, reduced models must respect some feasibility constraints in regards to the full model. However, such kind of constraints are either partially considered or just neglected inside the existing reduced problem formulation. This work presents a systematic approach to incorporate feasibility constraints inside trajectory optimization problems. In particular, we show how to learn the kinematic feasibility of the centre of mass to be achievable by the whole-body model. We validate the proposed method in the context of multi-contact locomotion: we perform two stairs climbing experiments on two humanoid robots, namely the HRP-2 robot and the new TALOS platform.
Document type :
Conference papers
Robotics: Science and Systems, Jul 2017, Cambridge, MA, United States. Porceedings of Robotics Science and Systems, 9p., 〈http://www.roboticsconference.org/〉
Liste complète des métadonnées

Cited literature [36 references]  Display  Hide  Download

https://hal.laas.fr/hal-01526200
Contributor : Justin Carpentier <>
Submitted on : Monday, May 22, 2017 - 5:07:44 PM
Last modification on : Thursday, January 11, 2018 - 6:26:26 AM
Document(s) archivé(s) le : Wednesday, August 23, 2017 - 5:06:07 PM

File

17-rss-learning.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - ShareAlike 4.0 International License

Identifiers

  • HAL Id : hal-01526200, version 1

Citation

Justin Carpentier, Rohan Budhiraja, Nicolas Mansard. Learning Feasibility Constraints for Multi-contact Locomotion of Legged Robots. Robotics: Science and Systems, Jul 2017, Cambridge, MA, United States. Porceedings of Robotics Science and Systems, 9p., 〈http://www.roboticsconference.org/〉. 〈hal-01526200〉

Share

Metrics

Record views

181

Files downloads

237