Abstract
The era of mobile robotics for use in service and field applications is gaining momentum. The need for adaptability becomes self evident in allowing robots to evolve better behaviors to meet overall task criteria. We report the use of neuro-fuzzy learning for teaching mobile robot behaviors, selecting exemplar cases from a potential continuum of behaviors. Proximate active sensing was successfully achieved with infrared in contrast to the usual ultrasonics and viewed the front area of robot movement. The well-known ANFIS architecture has been modified compressing layers to a necessary minimum with weight normalization achieved by using a sigmoidal function. Trapezoidal basis functions (B splines of order 2) with a partition of 1 were used to speed up computation. Reference to previous reinforcement learning results was made in terms of speed of learning and quality of behavior. Even with the limited input information, appropriate learning invariably took place in a reliable manner.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zurada, J., Marks II, R., Robinson, C. eds: Computational Intelligence. IEEE Press No. PC04580 New York 1994.
Jang, J.S.R., Sun, C.T., Mitzutani, E.: Neuro-fuzzy and Soft Computing, Prentice Hall, 1997.
Sutton, R., Barto, A.: Reinforcement Learning. MIT Press Bradford Books USA 1998.
Brown, M., Harris, C: Neuro-fuzzy Adaptive Modelling and Control. Pren. Hall UK 1994.
Harris, C.J., Brown, M., Bossley, K.M., Mills, D.J., Feng, M.: Advances in neuro-fuzzy algorithms for real-time modeling and control. J. Eng. Appl. of AI, Vol. 9(1) (1996) 1–16.
Evans, J.M.: Helpmate: an autonomous mobile robot courier for hospitals. Proceedings IEEE/RSJ Int. Conf. on Intelligent Robots & Systems, Munich Germany, (1994) 1695–1700.
Wallace, A.: Flow control of mobile robots using agents. 29th International Symposium on Robotics 97 BRA, Birmingham UK April 27–May 1 (1998).
Mataric, M.: Behavior based robotics as a tool for synthesis of artificial behavior and analysis of natural behavior. J. Experimental & Theoretical AI Vol. 9, (1997) 323–336.
Mataric, M.: Reinforcement learning in a multi-robot domain. Autonomous Robots, Vol. 4 No 1 (1997) 73–83.
Mataric, M.: Studying the role of embodiment in cognition. Cybernetics & Systems, Vol. 28 No 6 (1997) 457–470.
Mataric, M.: Learning social behaviors. Robot. & Auton. Systems, Vol 20 (1997) 191–204.
Michaud, F., Mataric, M.: Learning from history for behavior-based mobile robots in non-stationary conditions. Autonomous Robots/Machine Learning (Joint Issue Feb 1998) 1–29.
Kelly, I.D., Keating, D.: Increased learning rates through the sharing of experiences of multiple autonomous mobile robot agents. IEEE World Congress on Computational Intelligence Alaska USA (1998).
Habib, M.K., Asama, H., Ishida, Y., Matsumoto A., Endo I.: Simulation environment for an autonomous and decentralized multi-agent robotic system. Proceedings IEEE/RSJ International Conf. on Intelligent Robots & Systems Rayleigh NC USA 1992) 1550–1557.
Willgoss, R. The simulation of multiple mobile robot task assignments. 29th International Symposium on Robotics 97, BRA, Birmingham UK April 27–May 1 (1998) 127–130.
Song, K.T., Sheen, L.H.: Fuzzy-neuro control design for obstacle avoidance of a mobile robot. Joint Conf. 4th IEEE Int. Conf. on Fuzzy Systems and 2nd Int. Fuzzy Engineering Symp. Vol. 1 (1995) 71–76.
Tsoukalas, L.H., Houstis, E.H., Jones, G.V.: Neurofuzzy motion planners for intelligent robots. Journal of Intelligent and Robotic Systems Vol. 19 (1997) 339–356.
Tschishold-Gurman, N.: The neural network model RuleNet and its application to mobile robot navigation. Fuzzy Sets and Systems Vol. 85 (1997) 287–303.
Aycard, O., Charpillet, F., Haton, J-P.: A new approach to design fuzzy controllers for mobile robots navigation. Proc. IEEE Int. Symp. Computational Intelligence in Robotics and Automation (1997) 68–73.
Gaussier, P., Moga, S., Quoy, M., Banquet, J.P.: From perception-action loops to imitation processes: a bottom-up approach of learning by imitation. Applied Artificial Intelligence, Vol. 12 (1998) 701–727.
Rylatt, M., Czarnecki, C. & Routen, T.: Connectionist Learning in Behavior-Based Mobile Robots. Artificial Intelligence Review Vol. 12 (1998) 445–468.
Ng, K.C., Trivedi, M.M.: A Neuro-Fuzzy Controller fro Mobile Robot Navigation and Multirobot Convoying. IEEE Trans. SMC Part B: Cybernetics, Vol. 28(6) (1998) 829–840.
Willgoss, R.A., Iqbal, J.: Reinforcement Learning of Behaviors in Mobile Robots Using Noisy Infrared Sensors. Proc. Australian Conference on Robotics and Automation. Brisbane ARAA (1999) 119–125.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Willgoss, R., Iqbal, J. (1999). Neurofuzzy Learning of Mobile Robot Behaviours. In: Foo, N. (eds) Advanced Topics in Artificial Intelligence. AI 1999. Lecture Notes in Computer Science(), vol 1747. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46695-9_24
Download citation
DOI: https://doi.org/10.1007/3-540-46695-9_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66822-0
Online ISBN: 978-3-540-46695-6
eBook Packages: Springer Book Archive