Abstract
This research explores a new hybrid evolutionary learning methodology for multi-behaviour robot control. The new approach is an extension of the Fuzzy Genetic Network Programming algorithm with Reinforcement learning presented in [1]. The new learning system allows for the utilisation of any pre-trained intelligent systems as processing nodes comprising the phenotypes. We envisage that compounding the GNP with more powerful processing nodes would extend its computing prowess. As proof of concept, we demonstrate that the extended evolutionary system can learn multi-behaviours for robots by testing it on the simulated Mirosot robot soccer domain to learn both target pursuit and wall avoidance behaviours simultaneously. A discussion of the development of the new evolutionary system is presented following an incremental order of complexity. The experiments show that the proposed algorithm converges to the desired multi-behaviour, and that the obtained system accuracy is better than a system that does not utilise pre-trained intelligent processing nodes.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Sendari, S., Mabu, S., Hirasawa, K.: Fuzzy genetic network programming with reinforcement learning for mobile robot navigation. In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Anchorage, Alaska, USA, pp. 2243–2248. IEEE (2011)
Reyes, N.H., Barczak, A.L., Susnjak, T., Sincák, P., Vašcák, J.: Real-Time Fuzzy Logic-based Hybrid Robot Path-Planning Strategies for a Dynamic Environment. In: Efficiency and Scalability Methods for Computational Intellect, pp. 115–141. IGI Global (2013)
Vascák, J., Reyes, N.H.: Use and perspectives of fuzzy cognitive maps in robotics. In: Papageorgiou, E.I. (ed.) Fuzzy Cognitive Maps for Applied Sciences and Engineering. ISRL, vol. 54, pp. 253–266. Springer, Heidelberg (2014)
Reyes, N.H., Dadios, E.P.: Dynamic color object recognition using fuzzy logic. JACIII 8(1), 29–38 (2004)
Gerdelan, A., Reyes, N.: Synthesizing adaptive navigational robot behaviours using a hybrid fuzzy a* approach. In: Reusch, B. (ed.) Computational Intelligence, Theory and Applications, vol. 38, pp. 699–710. Springer, Heidelberg (2006)
Reyes, N.H., Barczak, A.L.C., Susnjak, T.: Tuning fuzzy-based hybrid navigation systems using calibration maps. In: Kim, J.-H., Matson, E., Myung, H., Xu, P. (eds.) Robot Intelligence Technology and Applications. AISC, vol. 208, pp. 713–722. Springer, Heidelberg (2013)
Hirasawa, K., Okubo, M., Katagiri, H., Hu, J., Murata, J.: Comparison between genetic network programming (gnp) and genetic programming (gp). In: Proceedings of the 2001 Congress on Evolutionary Computation, vol. 2, pp. 1276–1282 (2001)
Katagiri, H., Hirasama, K., Hu, J.: Genetic network programming - application to intelligent agents. In: IEEE International Conference on Systems, Man and Cybernetics, vol. 5, pp. 3829–3834 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Wang, W., Reyes, N.H., Barczak, A.L.C., Susnjak, T., Sincak, P. (2015). Multi-Behaviour Robot Control using Genetic Network Programming with Fuzzy Reinforcement Learning. In: Kim, JH., Yang, W., Jo, J., Sincak, P., Myung, H. (eds) Robot Intelligence Technology and Applications 3. Advances in Intelligent Systems and Computing, vol 345. Springer, Cham. https://doi.org/10.1007/978-3-319-16841-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-16841-8_15
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16840-1
Online ISBN: 978-3-319-16841-8
eBook Packages: EngineeringEngineering (R0)