Empirical Inference

Control of Musculoskeletal Systems using Learned Dynamics Models

2018

Article

ei


Controlling musculoskeletal systems, especially robots actuated by pneumatic artificial muscles, is a challenging task due to nonlinearities, hysteresis effects, massive actuator de- lay and unobservable dependencies such as temperature. Despite such difficulties, muscular systems offer many beneficial prop- erties to achieve human-comparable performance in uncertain and fast-changing tasks. For example, muscles are backdrivable and provide variable stiffness while offering high forces to reach high accelerations. In addition, the embodied intelligence deriving from the compliance might reduce the control demands for specific tasks. In this paper, we address the problem of how to accurately control musculoskeletal robots. To address this issue, we propose to learn probabilistic forward dynamics models using Gaussian processes and, subsequently, to employ these models for control. However, Gaussian processes dynamics models cannot be set-up for our musculoskeletal robot as for traditional motor- driven robots because of unclear state composition etc. We hence empirically study and discuss in detail how to tune these approaches to complex musculoskeletal robots and their specific challenges. Moreover, we show that our model can be used to accurately control an antagonistic pair of pneumatic artificial muscles for a trajectory tracking task while considering only one- step-ahead predictions of the forward model and incorporating model uncertainty.

Author(s): Büchler, D. and Calandra, R. and Schölkopf, B. and Peters, J.
Journal: IEEE Robotics and Automation Letters
Volume: 3
Number (issue): 4
Pages: 3161--3168
Year: 2018
Publisher: IEEE

Department(s): Empirical Inference
Research Project(s):
Bibtex Type: Article (article)
Paper Type: Journal

DOI: 10.1109/LRA.2018.2849601
State: Published
URL: https://ieeexplore.ieee.org/document/8391763/
Attachments: RAL18final

BibTex

@article{BucCalSchPet18,
  title = {Control of Musculoskeletal Systems using Learned Dynamics Models},
  author = {B{\"u}chler, D. and Calandra, R. and Sch{\"o}lkopf, B. and Peters, J.},
  journal = {IEEE Robotics and Automation Letters},
  volume = {3},
  number = {4},
  pages = {3161--3168},
  publisher = {IEEE},
  year = {2018},
  doi = {10.1109/LRA.2018.2849601},
  url = {https://ieeexplore.ieee.org/document/8391763/}
}