Hybrid Mechanical and Data-driven Modeling Improves Inverse Kinematic Control of a Soft Robot. (2016)

• Record Type: Journal Article
• Authors: Reinhart, René Felix; Steil, Jochen Jakob
• Is Part Of: Procedia technology. Volume 26(2016)
• Page Start: 12
• Page End: 19
• Publication Date: 2016
• Subjects: Machine Learning -- Learning Feed-forward Control -- Soft Robot -- Inverse Kinematics; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.08.003
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: Feed-forward control relies on accurate knowledge about the controlled plant, e.g. models of manipulator kinematics or dynamics. However, for many plants, mechanical models do not capture all aspects of a plant or the plant's intrinsic properties, e.g. soft materials, do hardly allow for exact and efficient mechanical modeling. In this context, machine learning is a suitable technique to extract non-linear plant models from data. The paper shows that feed-forward control based on inversion of a hybrid forward model comprising a mechanical model and a learned error model can significantly improve accuracy. The proposed approach is demonstrated for inverse kinematic control of a redundant soft robot with a hybrid model that is constructed from continuum kinematics together with an efficient neural network error model.