Title :
Calibration of a physics-based model of an anthropomimetic robot using Evolution Strategies
Author :
Wittmeier, Steffen ; Gaschler, Andre ; Jäntsch, Michael ; Dalamagkidis, Konstantinos ; Knoll, Alois
Author_Institution :
Fac. of Inf., Tech. Univ. Munchen, Munich, Germany
Abstract :
The control of tendon-driven and, in particular, of anthropomimetic robots using techniques from traditional robotics remains a very challenging task [1, 2]. Hence, we previously proposed to employ physics-based simulation engines to simulate the complex dynamics of this emerging class of robots [3] and to use the simulation model as an internal model for robot control [4]. This approach, however, relies on an accurate model to be successful. In this paper, we present the automated, steady-state pose calibration of a physics-based, anthropomimetic robot model using a (μ, λ)-Evolution Strategy. For the acquisition of the poses of the physical robot, a stereo-vision, infrared-marker based motion capture system with real-time capabilities was developed. The employed (μ, λ)-Evolution Strategy uses a Gaussian-based, non-isotropic, self-adapting mutation operator to explore the search space and reduce the simulation-reality gap. The obtained results are impressive, resulting in a reduction of joint angle errors in the range of one to two orders of magnitude and an absolute joint angle error of 0.5°-4.5° per pose evaluated.
Keywords :
Gaussian processes; anthropometry; calibration; control system synthesis; infrared detectors; path planning; robot dynamics; robot vision; search problems; stereo image processing; (μ,λ)-evolution strategy; Gaussian-based operator; absolute joint angle error; anthropomimetic robot; automated steady-state pose calibration; evolution strategies; infrared-marker based motion capture system; internal model; nonisotropic operator; physics-based model calibration; physics-based simulation engines; pose acquisition; real-time capabilities; robot control; self-adapting mutation operator; simulation model; simulation-reality gap; stereo-vision; tendon-driven control; Potentiometers; Robots;
Conference_Titel :
Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on
Conference_Location :
Vilamoura
Print_ISBN :
978-1-4673-1737-5
DOI :
10.1109/IROS.2012.6385591