内容简介：In this talk, two novel approaches termed Dynamic Self-Generated Fuzzy Q-Learning (DSGFQL) and Enhanced Dynamic Self-Generated Fuzzy Q-Learning (EDSGFQL) for automatically generating Fuzzy Inference Systems (FISs) will be presented. In the DSGFQL approach, the structure and preconditioning parts of an FIS are generated by Reinforcement Learning (RL) and the epsilon completeness criterion while the consequents are updated by Fuzzy Q-Learning, which is a widely used RL method. An extended Self Organizing Map (SOM) algorithm is used for adjusting the centers of Membership Functions (MFs) to enhance the proposed DSGFQL. The proposed DSGFQL and EDSGFQL methodologies can automatically create, delete and adjust fuzzy rules dynamically and they are superior to most of the existing RL methodologies in generating FISs. Simulation studies on wall-following and obstacle avoidance tasks by a mobile robot show that the proposed approaches are superior.

报告人简介：Dr Meng Joo Er received his B. Eng and M. Eng degrees in Electrical Engineering from the National University of Singapore in 1985 and 1988 respectively and a Ph.D degree in Systems Engineering from the Australian National University in 1992. From 1987 to 1989, he worked as a Research and Development Engineer in Chartered Electronics Industries Pte Ltd and a Software Engineer in Telerate Research and Development Pte Ltd respectively. He served as Director of the Intelligent Systems Centre, a University Research Centre co-funded by Nanyang Technological University (NTU) and Singapore Engineering Technologies from 2003 to 2006. Currently, he is an Associate Professor in the School of Electrical and Electronic Engineering (EEE), NTU.

His research interests include control theory and applications, fuzzy logic and neural networks, computational intelligence, cognitive systems, robotics and automation, sensor networks and biomedical engineering. He has authored two books entitled “Dynamic Fuzzy Neural Networks: Architectures, Algorithms and Applications” and “Engineering Mathematics with Real-World Applications” published by McGraw Hill in 2003 and 2005 respectively, eight book chapters and more than 300 refereed journal and conference papers in his research areas of interest.