Environment Recognition System Based on Multiple Classification Analyses for Mobile Robots
Various mechanisms have recently been developed that combine linkage mechanisms and wheels. In particular, the combination of passive linkage mechanisms and small wheels is a main research trend because standard wheeled mobile mechanisms find it difficult to move on rough terrain. In our previous research, a six-wheel mobile robot employing a passive linkage mechanism has been developed to enhance maneuverability and was able to climb over a 0.20 m bump and stairs. We designed a hybrid velocity and torque controller using a neural network since simple velocity controllers fail to climb up. In this paper, we propose an environment recognition system for a wheeled mobile robot that consists of multiple classification analyses to make the robot more adaptive to various environments by selecting a suitable system such as decision making, navigation and controller using the result of the environment recognition system. We evaluate the recognition performance in operation environments; slopes, bumps and stairs by comparing principle component, k-means and self-organizing map analyses.
Keywordswheeled mobile robot neural network self-organizing map environment recognition
Unable to display preview. Download preview PDF.
- Volpe R, Balaram J, Ohm T, Ivlev R. The Rocky 7 Mars rover prototype. Proceedings of the 1996 IEEE/RSJ International Conference on Intelligent Robots and Systems, 1996, 3, 1558–1564.Google Scholar
- Thueer T, Lamon P, Krebs A, Siegwart R. CRAB-exploration rover with advanced obstacle negotiation capabilities. Proceedings of the 9th ESA Workshop on Advanced Space Technologies for Robotics and Automation, Nordwijk, The Netherlands, 2006, 1–8.Google Scholar
- Sato M, Ishii K. A neural network based controller for a wheel type mobile robot. 2nd International Conference on Brain-Inspired Information Technology, 2006, 1291, 261–264.Google Scholar
- Jia S, Yasuda A, Chugo D, Takase K. LRF-based self-localization of mobile robot using extended kalman filter. SICE Annual Conference 2008, Chofu, Tokyo, Japan, 2008, 2295–2298.Google Scholar
- Richard O D, Pater E H, Davit G S. Pattern Classification, second edition, John Wiley and Sons, New York, 2007.Google Scholar
- Provost J, Kuipers B J, Miikkulainen R. Self-organizing perceptual and temporal abstraction for robot reinforcement learning. AAAI Workshop on Learning and Planning in Markov Processes, 2004.Google Scholar
- Fujii T, Hayashi A, Hida H. Using principle component analysis and non-hierarchical clustering to find landmarks. The 48th Annual Conference of the IPSJ, 1994, 53–54. (in Japanese)Google Scholar
- Takeshi Y, Shun Y, Kazunori K, Tesuya O, Hiroshi O. Speech recognition of using lip images from various directions. The 18th Annual Conference of the Japanese Society for Artificial Intelligence, 2004, 18, page no. 1E2-02. (in Japanese)Google Scholar
- Sato M, Kanda A, Ishii K. A neural network controller designed for a rough terrain mobile robot 2nd report: Effects on the controller property caused by the process of teaching data generation. Proceeding of the 2007 JSME Conference on Robotics and Mechatronics, Akita, Japan, 2007, page no. 2A1-D10. (in Japanese)Google Scholar