A mobile robot to navigate purposefully from a start location to a target location, needs three basic requirements: sensing, learning, and reasoning. In the existing system, the mobile robot navigates in a known environment on a predefined path. However, the pervasive presence of uncertainty in sensing and learning, makes the choice of a suitable tool of reasoning and decision-making that can deal with incomplete information, vital to ensure a robust control system. This problem can be overcome by the proposed navigation method using fuzzy support vector machine (FSVM). It proposes a fuzzy logic-based support vector machine (SVM) approach to secure a collision-free path avoiding multiple dynamic obstacles. The navigator consists of an FSVM-based collision avoidance. The decisions are taken at each step for the mobile robot to attain the goal position without collision. Fuzzy-SVM rule bases are built, which require simple evaluation data rather than thousands of input-output training data. The effectiveness of the proposed method is verified by a series of simulations and implemented with a microcontroller for navigation.Defence Science Journal, 2010, 60(4), pp.387-391, DOI:http://dx.doi.org/10.14429/dsj.60.496
Fuzzy Support Vector Machine-based Multi-agent Optimal Path
2010-07-09
doi:10.14429/dsj.60.496
Defence Science Journal; Vol 60 No 4: Machine Learning and Pattern Recognition; 387-391 ; 0976-464X ; 0011-748X
Article (Journal)
Electronic Resource
English
DDC: | 629 |
Support vector machine based multi-view face detection and recognition
British Library Online Contents | 2004
|NARROW PASSAGE PATH PLANNING USING FAST MARCHING METHOD AND SUPPORT VECTOR MACHINE
British Library Conference Proceedings | 2014
|