Unsupervised Contact Learning for Humanoid Estimation and Control

Nicholas Rotella, Stefan Schaal, Ludovic Righetti

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

Abstract

This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Robotics and Automation, ICRA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages411-417
Number of pages7
ISBN (Electronic)9781538630815
DOIs
StatePublished - Sep 10 2018
Event2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia
Duration: May 21 2018May 25 2018

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Conference2018 IEEE International Conference on Robotics and Automation, ICRA 2018
CountryAustralia
CityBrisbane
Period5/21/185/25/18

Fingerprint

Kinematics
Contact sensors
Hand tools
Units of measurement
Fuzzy clustering
Sensors
State estimation
Robots
Friction

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Rotella, N., Schaal, S., & Righetti, L. (2018). Unsupervised Contact Learning for Humanoid Estimation and Control. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018 (pp. 411-417). [8462864] (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2018.8462864

Unsupervised Contact Learning for Humanoid Estimation and Control. / Rotella, Nicholas; Schaal, Stefan; Righetti, Ludovic.

2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 411-417 8462864 (Proceedings - IEEE International Conference on Robotics and Automation).

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

Rotella, N, Schaal, S & Righetti, L 2018, Unsupervised Contact Learning for Humanoid Estimation and Control. in 2018 IEEE International Conference on Robotics and Automation, ICRA 2018., 8462864, Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 411-417, 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 5/21/18. https://doi.org/10.1109/ICRA.2018.8462864
Rotella N, Schaal S, Righetti L. Unsupervised Contact Learning for Humanoid Estimation and Control. In 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 411-417. 8462864. (Proceedings - IEEE International Conference on Robotics and Automation). https://doi.org/10.1109/ICRA.2018.8462864
Rotella, Nicholas ; Schaal, Stefan ; Righetti, Ludovic. / Unsupervised Contact Learning for Humanoid Estimation and Control. 2018 IEEE International Conference on Robotics and Automation, ICRA 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 411-417 (Proceedings - IEEE International Conference on Robotics and Automation).
@inproceedings{9ed59757ddc7471e956acd17c5e43013,
title = "Unsupervised Contact Learning for Humanoid Estimation and Control",
abstract = "This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force.",
author = "Nicholas Rotella and Stefan Schaal and Ludovic Righetti",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/ICRA.2018.8462864",
language = "English (US)",
series = "Proceedings - IEEE International Conference on Robotics and Automation",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "411--417",
booktitle = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018",

}

TY - GEN

T1 - Unsupervised Contact Learning for Humanoid Estimation and Control

AU - Rotella, Nicholas

AU - Schaal, Stefan

AU - Righetti, Ludovic

PY - 2018/9/10

Y1 - 2018/9/10

N2 - This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force.

AB - This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force.

UR - http://www.scopus.com/inward/record.url?scp=85063153229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063153229&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2018.8462864

DO - 10.1109/ICRA.2018.8462864

M3 - Conference contribution

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 411

EP - 417

BT - 2018 IEEE International Conference on Robotics and Automation, ICRA 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -