Robust humanoid locomotion using trajectory optimization and sample-efficient learning

Mohammad Hasan Yeganegi, Majid Khadiv, S. Ali A. Moosavian, Jia Jie Zhu, Andrea Del Prete, Ludovic Righetti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Trajectory optimization (TO) is one of the most powerful tools for generating feasible motions for humanoid robots. However, including uncertainties and stochasticity in the TO problem to generate robust motions can easily lead to intractable problems. Furthermore, since the models used in TO have always some level of abstraction, it can be hard to find a realistic set of uncertainties in the model space. In this paper we leverage a sample-efficient learning technique (Bayesian optimization) to robustify TO for humanoid locomotion. The main idea is to use data from full-body simulations to make the TO stage robust by tuning the cost weights. To this end, we split the TO problem into two phases. The first phase solves a convex optimization problem for generating center of mass (CoM) trajectories based on simplified linear dynamics. The second stage employs iterative Linear-Quadratic Gaussian (iLQG) as a whole-body controller to generate full body control inputs. Then we use Bayesian optimization to find the cost weights to use in the first stage that yields robust performance in the simulation/experiment, in the presence of different disturbance/uncertainties. The results show that the proposed approach is able to generate robust motions for different sets of disturbances and uncertainties.

Original languageEnglish (US)
Title of host publication2019 IEEE-RAS 19th International Conference on Humanoid Robots, Humanoids 2019
PublisherIEEE Computer Society
Pages170-177
Number of pages8
ISBN (Electronic)9781538676301
DOIs
StatePublished - Oct 2019
Event19th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019 - Toronto, Canada
Duration: Oct 15 2019Oct 17 2019

Publication series

NameIEEE-RAS International Conference on Humanoid Robots
Volume2019-October
ISSN (Print)2164-0572
ISSN (Electronic)2164-0580

Conference

Conference19th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019
CountryCanada
CityToronto
Period10/15/1910/17/19

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Robust humanoid locomotion using trajectory optimization and sample-efficient learning'. Together they form a unique fingerprint.

  • Cite this

    Yeganegi, M. H., Khadiv, M., Moosavian, S. A. A., Zhu, J. J., Del Prete, A., & Righetti, L. (2019). Robust humanoid locomotion using trajectory optimization and sample-efficient learning. In 2019 IEEE-RAS 19th International Conference on Humanoid Robots, Humanoids 2019 (pp. 170-177). [9035003] (IEEE-RAS International Conference on Humanoid Robots; Vol. 2019-October). IEEE Computer Society. https://doi.org/10.1109/Humanoids43949.2019.9035003