ABSTRACT
This paper presents a novel GIM-based learning approach for biomimetic robot motion learning. A general internal model is developed for describing discrete and rhythmic animal movements. Based on analysis, the paper shows that the learning approach is able to generate similar movement patterns for the robots directly, through the minimum changes in GIM parameters, thus avoid the usual time-consuming learning or training process. The GIM also exhibits the phase-shift property, which is necessary when the coordination among multiple GIMs is required to perform a complex task. Finally, the GIM-based learning approach is applied to learn two basic fish-like swimming patterns for a biomimatic robotic fish under locomotion control. The results verify the effectiveness of the learning approach.
- A. J. Ijspeert. 2001. A connectionist central pattern generator for the aquatic and terrestrial gaits of a simulated salamander. Biological Cybernetics 84, 1, 331--348.Google ScholarCross Ref
- A. J. Ijspeert. 2008. Central pattern generators for locomotion control in animals and robots: a review. Neural Networks 21, 4, 642--653. Google ScholarDigital Library
- Eve Marder, D. B. 2001. Central pattern generators and the control of rhythmic movements. Current Biology 11, 986--996.Google ScholarCross Ref
- J., L. M. 1960. Note on the swimming of slender fish. Journal of fluid mechanics 9, 1, 305--317.Google ScholarCross Ref
- Jian-Xin Xu, W. W. 2008. A general internal model approach for motion learning. IEEE Transaction on system, man, and cybernetics 38, 477--487. Google ScholarDigital Library
- Liu. J, Dukes. L, Knight. R, and Hu. H. 2004. Development of fish-like swimming behavious for an autonomous robtic fish. In Proceeding of the Control, University of Bath, vol. 1, 217.Google Scholar
- Michael S., G. S. 1995. An efficient swimming machine. Scientific American 272, 3, 64--70.Google ScholarCross Ref
- M. Sfakiotakis, D. M. Lane, and Davies, J. 1999. Reviw of fish swimming modes for aquatic locomotion. IEEE Journal of Oceanic Engineering 24, 2, 237--252.Google ScholarCross Ref
- Shigeo Hirose, peter Cave, C. G. 1993. Biologically inspired robots: snake-like locomotors and manipulators. Oxford: Oxford University Press. Google ScholarDigital Library
- Shiya Aoi, Soichiro Fujiki, e. 2011. Generation of adaptive splitbelt treadmill walking by a biped robot using nonlinear oscillators with phase resetting. In IEEE International conference on intelligent robots and systems, vol. 1, 2274--2279.Google Scholar
- Xu Jian-Xin, Qinyuan Ren, X. N. 2012. Mimicry of fish swimming patterns in a robotic fish. In IEEE International Symposium on Industrial Electronics, vol. 1, 1274--1279.Google ScholarCross Ref
- Y. Hu, and W. Tian, J. Liang, T. 2011. Learning fish-like swimming with a cpg-based locomotion controller. In IEEE International conference on intelligent robots and systems, vol. 1, 1863--1868.Google Scholar
Index Terms
- A GIM-based approach for biomimetic robot motion learning
Recommendations
Robot motion adaptation through user intervention and reinforcement learning
Three versions of an interactive framework for robot motion learning are proposed.Each version requires a different level of user involvement in the learning process.The experimental results show that user involvement speeds up the learning ...
A General Internal Model Approach for Motion Learning
In this paper, we present a general internal model (GIM) approach for motion skill learning at elementary and coordination levels. A unified internal model (IM) is developed for describing discrete and rhythmic movements. Through analysis, we show that ...
Learning algorithm for a brachiating robot
This paper introduces a new concept of multi-locomotion robot inspired by an animal. The robot, 'Gorilla Robot II', can select the appropriate locomotion from biped locomotion, quadruped locomotion and brachiation according to an environment or task. We ...
Comments