Multiobjective Dynamic Constrained Evolutionary Algorithm for Control of a Multi-segment Articulated Manipulator
In this paper a multiobjective dynamic constrained evolutionary algorithm is proposed for control of a multi-segment articulated manipulator. The algorithm is tested in simulated dynamic environments with moving obstacles. The algorithm does not require previous training - a feasible sequence of movements is found and maintained based on a population of candidate movements. The population is evolved using typical evolutionary operators as well as several new ones that are dedicated for the manipulator control task. The algorithm is shown to handle manipulators with up to 100 segments. The increased maneuverability of the manipulator with 100 segments is well utilized by the algorithm. The results obtained for such manipulator are better than for the 10-segment one which is computationally easier to handle.
Keywordsinverse kinematics multiobjective evolutionary optimization constrained problems
Unable to display preview. Download preview PDF.
- 1.Aristidou, A., Lasenby, J.: Motion capture with constrained inverse kinematics for real-time hand tracking. In: Proceedings of the IEEE International Symposium on Communications, Control and Signal Processing (ISCCSP 2010), pp. 1–5 (2010)Google Scholar
- 4.Deb, K., Goyal, M.: A combined genetic adaptive search (GeneAS) for engineering design. Computer Science and Informatics 26, 30–45 (1996)Google Scholar
- 7.Grefenstette, J.: Genetic algorithms for changing environments. In: Parallel Problem Solving from Nature 2, pp. 137–144. Elsevier (1992)Google Scholar
- 9.Pieper, D.L.: The kinematics of robots under computer control. Phd thesis, Stanford University (1968)Google Scholar
- 10.Singh, H.K., Isaacs, A., Ray, T., Smith, W.: Infeasibility driven evolutionary algorithm (IDEA) for engineering design optimization. In: Wobcke, W., Zhang, M. (eds.) AI 2008. LNCS (LNAI), vol. 5360, pp. 104–115. Springer, Heidelberg (2008)Google Scholar