TU Darmstadt / ULB / TUbiblio

Bio-inspired motion control of the musculoskeletal BioBiped1 robot based on a learned inverse dynamics model

Scholz, Dorian and Kurowski, Stefan and Radkhah, Kathayon and Stryk, Oskar von and Stryk, Oskar von (2011):
Bio-inspired motion control of the musculoskeletal BioBiped1 robot based on a learned inverse dynamics model.
In: Proc. 11th IEEE-RAS Int. Conf. on Humanoid Robots (HUMANOIDS), [Conference or Workshop Item]

Abstract

Based on the central hypothesis that a humanoid robot with human-like walking and running performance requires a bio-inspired embodiment of the musculoskeletal functions of the human leg as well as of its control structure, a bio-inspired approach for joint position control of the BioBiped1 robot is presented in this paper. This approach combines feedforward and feedback control running at 1 kHz and 40 Hz, respectively. The feed-forward control is based on an inverse dynamics model which is learned using Gaussian process regression to account for the robot’s body dynamics and external influences. For evaluation the learned model is used to control the robot purely feed-forward as well as in combination with a slow feedback controller. Both approaches are compared to a basic feedback PD-controller with respect to their tracking ability in experiments. It is shown, that the combined approach yields good results and outperforms the basic feedback controller when applied to the same set-point trajectories for the leg joints.

Item Type: Conference or Workshop Item
Erschienen: 2011
Creators: Scholz, Dorian and Kurowski, Stefan and Radkhah, Kathayon and Stryk, Oskar von and Stryk, Oskar von
Title: Bio-inspired motion control of the musculoskeletal BioBiped1 robot based on a learned inverse dynamics model
Language: English
Abstract:

Based on the central hypothesis that a humanoid robot with human-like walking and running performance requires a bio-inspired embodiment of the musculoskeletal functions of the human leg as well as of its control structure, a bio-inspired approach for joint position control of the BioBiped1 robot is presented in this paper. This approach combines feedforward and feedback control running at 1 kHz and 40 Hz, respectively. The feed-forward control is based on an inverse dynamics model which is learned using Gaussian process regression to account for the robot’s body dynamics and external influences. For evaluation the learned model is used to control the robot purely feed-forward as well as in combination with a slow feedback controller. Both approaches are compared to a basic feedback PD-controller with respect to their tracking ability in experiments. It is shown, that the combined approach yields good results and outperforms the basic feedback controller when applied to the same set-point trajectories for the leg joints.

Title of Book: Proc. 11th IEEE-RAS Int. Conf. on Humanoid Robots (HUMANOIDS)
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Simulation, Systems Optimization and Robotics Group
Date Deposited: 20 Jun 2016 23:26
Identification Number: 2011:Humanoids-BioBiped1
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item