Use and Perspectives of Fuzzy Cognitive Maps in Robotics
Fuzzy Cognitive Maps (FCM) started in the last decade to penetrate to areas as decision-making and control systems including robotics, which is characterized by its distributiveness, need for parallelism and heterogeneity of used means. This chapter deals
- PDF / 590,858 Bytes
- 14 Pages / 439.37 x 666.142 pts Page_size
- 55 Downloads / 206 Views
Use and Perspectives of Fuzzy Cognitive Maps in Robotics Ján Vašˇcák and Napoleon H. Reyes
Abstract Fuzzy Cognitive Maps (FCM) started in the last decade to penetrate to areas as decision-making and control systems including robotics, which is characterized by its distributiveness, need for parallelism and heterogeneity of used means. This chapter deals with specification of needs for a robot control system and divides defined tasks into three basic decision levels dependent on their specification of use as well as applied means. Concretely, examples of several FCMs applications from the low and middle decision levels are described, mainly in the area of navigation, movement stabilization, action selection and path cost evaluation. Finally, some outlooks for future development of FCMs are outlined.
1 Introduction Although FCMs were originally designed for modelling purposes in nontechnical areas only [5, 13] but their flexibility and ability to represent mainly causal relations between objects and notions enabled them to penetrate also to technical areas [20], first of all to the field of decision-making and its support. There are several reasons and motivations for use of FCMs in these systems. Firstly, technical systems have to process various kinds of imprecision and uncertainty. Secondly, many solved tasks require finding not only a solution but also regarding various constraints and
Electronic supplementary material The online version of this article (doi: 10.1007/978-3642-39739-4_15) contains supplementary material, which is available to authorized users. J. Vašˇcák (B) Center for Intelligent Technologies, Technical University of Košice, Košice, Slovakia e-mail: [email protected] N. H. Reyes Institute of Natural and Mathematical Sciences, Massey University, Auckland, New Zealand e-mail: [email protected] E. I. Papageorgiou (ed.), Fuzzy Cognitive Maps for Applied Sciences and Engineering, Intelligent Systems Reference Library 54, DOI: 10.1007/978-3-642-39739-4_15, © Springer-Verlag Berlin Heidelberg 2014
253
254
J. Vašˇcák and N. H. Reyes
Fig. 1 Basic information structure of a mobile robot configured by decision levels DL-0–DL-2
limitations. Finally, knowledge representation and its human-friendliness play a very important role in selection of computational means from many practical reasons like safety and maintenance or compatibility with the reasoning of human operators. A broad description about the research in the area of FCMs can be found in [17]. Although robots are devices of diverse constructions but they all should be able to more or less reproduce human-like approaches in task solving, not only movements but also the way of thinking how to perform a kinematic task. From the informatics viewpoint they are characterized as multi-level hierarchical systems, as depicted in Fig. 1 [23], where basic information modules and their relations are divided into several decision levels (DL), which are mutually subordinated from DL-0 as the low, DL-1 as the middle and DL-2 as the high one, too. Usu
Data Loading...
