Abstract:
In certain cases analytical derivation of physics-based models of robots is difficult or even impossible. A potential workaround is the approximation of robot models from...Show MoreMetadata
Abstract:
In certain cases analytical derivation of physics-based models of robots is difficult or even impossible. A potential workaround is the approximation of robot models from sensor data-streams employing machine learning approaches. In this paper, the inverse dynamics models are learned by employing a novel real-time deep learning algorithm. The algorithm exploits the methods of self-organized learning, reservoir computing and Bayesian inference. It is evaluated and compared to other state of the art algorithms in terms of generalization ability, convergence and adaptability using five datasets gathered from four robots. Results show that the proposed algorithm can adapt to real-time changes of the inverse dynamics model significantly better than the other state of the art algorithms.
Date of Conference: 28 September 2015 - 02 October 2015
Date Added to IEEE Xplore: 17 December 2015
ISBN Information:
Department of Mechanical and Manufacturing Engineering, Aalborg University Copenhagen, Denmark
Department of Mechanical and Manufacturing Engineering, Aalborg University Copenhagen, Denmark
Department of Mechanical and Manufacturing Engineering, Aalborg University Copenhagen, Denmark
Department of Mechanical and Manufacturing Engineering, Aalborg University Copenhagen, Denmark
Department of Mechanical and Manufacturing Engineering, Aalborg University Copenhagen, Denmark
Department of Mechanical and Manufacturing Engineering, Aalborg University Copenhagen, Denmark