Header logo is

Unsupervised {Contact} {Learning} for {Humanoid} {Estimation} and {Control}


Conference Paper



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(s): Rotella, Nicholas and Schaal, Stefan and Righetti, Ludovic
Book Title: 2018 IEEE International Conference on Robotics and Automation (ICRA)
Pages: 411--417
Year: 2018
Publisher: IEEE

Department(s): Autonomous Motion, Movement Generation and Control
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1109/ICRA.2018.8462864

Address: Brisbane, Australia
URL: https://arxiv.org/abs/1709.07472


  title = {Unsupervised {Contact} {Learning} for {Humanoid} {Estimation} and {Control}},
  author = {Rotella, Nicholas and Schaal, Stefan and Righetti, Ludovic},
  booktitle = {2018 {IEEE} {International} {Conference} on {Robotics} and {Automation} ({ICRA})},
  pages = {411--417},
  publisher = {IEEE},
  address = {Brisbane, Australia},
  year = {2018},
  url = {https://arxiv.org/abs/1709.07472}