Intelligent Low Cost Mobile Robot and Environmental Classification

Abstract

In this paper low cost mobile robot is designed and developed. A tree diagram of material selection is used to help designer to determine the requirements of mobile robot process design. 5 pieces of low price infrared sensors and 8 bits low cost microcontroller-based system are utilized to process sensors signal and driving actuators to guide mobile robot movement. Fuzzy-Kohonen Network (FKN) method is embedded into the mobile robot as pattern recognition approach of 21 environmental classifications. We have fully implemented the system with a real mobile robot and made experiments for evaluating the mobile robot ability. As a result, we found out that the environment recognition is done well, that mobile robot successfully identified several environmental situations. Furthermore, our method is adaptive to noisy environments and produce satisfactory performance.

References

• Bulusu, N.; Heidemann, J.; Estrin, D. 2002. GPS-less low-cost outdoor localization for very small devices. Personal Communication 5:28-34.
• Agrawal, M., Konolige, K., and Iocchi, L. 2005. Real-time detection of independent motion using stereo. Proceeding IEEE workshop on Motion (WACV/MOTION).
• Yamada, S., and Murota, M. 1998. Unsupervised Learning to Recognize : Environments from Behavior Sequences in a Mobile Robot. Proceedings on the IEEE International Conference on Robotics & Automation Leuven, Belgium. 1871-1876.
• Cui, X., Hardin, T., Ragade, R.K., and Elmaghraby, A.S. 2004. A Swarm-based Fuzzy Logic Control Mobile Sensor Network for Hazardous Contaminants Localization. IEEE, 194-203.
• Lazarus, S.B., Tsourdos, A., Zbikowski, R., and White, B.A. 2008. Unstructured environmental mapping using low cost sensors. Proceeding on IEEE International Conference on Networking, Sensing and Control, 1080-1085.
• Yunfeng, W. and Gregory, S.C. 2000. A new potential field method for robot path planning. Proceedings of the IEEE International Conference on Robotics & Automation, San Francisco, CA, 977–982.
• Liu, C., Marcelo, H.A.J., Krishnan, H., and Ser-Yong, L. 2000. Virtual obstacle concept for local-minimum-recovery in potential field based navigation. Proceedings of the 2000 IEEE International Conference on Robotics & Automation, San Francisco, CA, 2:983 –988.
• Maravall, D., de Lope, J., and Serradilla, F. 2000. Combination of model-based and reactive methods in autonomous navigation. Proceedings of the IEEE Intern. Conf. Robotics & Automation, San Francisco, CA, 977–982.
• Ryu, B.S., and Yang, H.S. 1999. Integration of reactive behaviors and enhanced topological map for robust mobile robot navigation. IEEE Transaction on System, Man, and Cybernetics—part A, 29(5):474–485.
• Eduardo Kac, 2001a. The origin and development of robotic art. The Journal of research into New Media Technologies, 7(1):76-86.
• Eduardo Kac, 2001b. Towards a chronology of robotic art. The Journal of research into New Media Technologies, 791:87-111.
• Smith, C.W. 2002. Material design for a robotic arts studio. Master of science-Thesis-Massachusetts Institute of Technology.
• Song, K.T., and Huang, S.Y. 2004. Mobile Robot Navigation Using Sonar Direction Weights. Proc. IEEE International Conference on Control Applications, Taiwan
• Nwe, A.A., Aung, W.P., and Myint, Y.M. 2008. Software implementation of obstacle detection and avoidance system for wheeled mobile robot. World Academy of Science, Engineering and technology 42: 572-577.
• Govers, E. 2007. Thesis – Fast local Mapping for mobile robots. Utrecht University and Philips Applied Technologies.
• Song, K.T., and Sheen, L.W. 2000. Heuristic fuzzy-neuro network and its application to reactive navigation of a mobile robot. Fuzzy Sets and Systems, 110:331-340.
• Kumar, M., and Garg. D.P. 2005. "Neuro-fuzzy control applied to multiple cooperating robots", Industrial Robot: An International Journal, 32(3):234 – 239.
• Wang, H., Chen, C., dan Huang, Z. 2007. Ultrasonic Sensor Based Fuzzy-Neural Control Algorithm of Obstacle Avoidance for Mobile Robot. Springer-Verlag Berlin Heidelberg, 1:824-833.
• Al Mutib, K. and Mattar, E. 2011. Neuro-fuzzy Controlled Autonomous Mobile Robotics System. Proceeding International conferences on computer modeling and simulation. Cambridge, March 30 - April 1.2011, 1-7.
• Hoffmann, F. 2000. Soft computing techniques for the design of mobile robot behaviors. Information Science, 122: 241-258.
• Tsai, C.C., Chen, C.C., Chan, C.K., and Li, Y.Y 2010. Behavior-Based Navigation Using Heuristic Fuzzy Kohonen Clustering Network for Mobile Service Robots. International Journal of Fuzzy Systems. 12(1): 25-32.

Index Terms

Keywords