S.G. Tzafestas

Microprocessors play a dominant role in computer technology and have contributed uniquely in the development of many new concepts and design techniques for modem industrial systems. This contribution is excessively high in the area of robotic and manufacturing systems. However, it is the editor's feeling that a reference book describing this contribution in a cohesive way and covering the major hardware and software issues is lacking. The purpose of this book is exactly to fill in this gap through the collection and presentation of the experience of a number of experts and professionals working in different academic and industrial environments. The book is divided in three parts. Part 1 involves the first four chapters and deals with the utilization of microprocessors and digital signal processors ( DSPs ) for the computation of robot dynamics. The emphasis here is on parallel computation with particular problems attacked being task granularity, task allocation/scheduling and communication issues. Chapter I, by Zheng and Hemami, is concerned with the real-time multiprocessor computation of torques in robot control systems via the Newton-Euler equations. This reduces substantially the height of the evaluation tree which leads to more effective parallel processing. Chapter 2, by D'Hollander, examines thoroughly the automatic scheduling of the Newton-Euler inverse dynamic equations. The automatic program decomposition and scheduling techniques developed are embedded in a tool used to generate multiprocessor schedules from a high-level language program.

Microprocessors in Robotic and Manufacturing Systems

This book contains thirty timely contributions in the emerging field of Computational Intelligence (CI) with reference to system control design and applications. The three basic constituents ofCI are neural networks (NNs). fuzzy logic (FL) I fuzzy reasoning (FR). and genetic algorithms (GAs). NNs mimic the distributed functioning of the human brain and consist of many. rather simple. building elements (called artificial neurons) which are controlled by adaptive parameters and are able to incorporate via learning the knowledge provided by the environment, and thus respond intelligently to new stimuli. Fuzzy logic (FL) provides the means to build systems that can reason linguistically under uncertainty like the human experts (common sense reasoning). Both NNs and FL I FR are among the most widely used tools for modeling unknown systems with nonlinear behavior. FL suits better when there is some kind of knowledge about the system. such as, for example, the linguistic information of a human expert. On the other hand. NNs possess unique learning and generalization capabilities that allow the user to construct very accurate models of nonlinear systems simply using input-output data. GAs offer an interesting set of generic tools for systematic random search optimization following the mechanisms of natural genetics. In hybrid Computational Intelligence - based systems these three tools (NNs, FL, GAs) are combined in several synergetic ways producing integrated tools with enhanced learning, generalization. universal approximation. reasoning and optimization abilities.

Computational Intelligence in Systems and Control Design and Applications

Anastasios N. Venetsanopoulos

Great progresses have been made in the application of fuzzy set theory and fuzzy logic. Most remarkable area of application is 'fuzzy control', where fuzzy logic was first applied to plant control systems and its use is expanding to consumer products. Most of fuzzy control systems uses fuzzy inference with max-min or max-product composition, similar to the algorithm that first used by Mamdani in 1970s. Some algorithms are developed to refine fuzzy controls systems but the main part of algorithm stays the same. Triggered by the success of fuzzy control systems, other ways of applying fuzzy set theory are also investigated. They are usually referred to as 'fuzzy expert sys tems', and their purpose are to combine the idea of fuzzy theory with AI based approach toward knowledge processing. These approaches can be more generally viewed as 'fuzzy information processing', that is to bring fuzzy idea into informa tion processing systems.

Fuzzy Reasoning in Information, Decision and Control Systems

Günther Schmidt

Madan Singh

Volume 1 Fault Diagnostics and Reliability Proceedings of the First European Workshop on Fault Diagnostics, Reliability and Related Knowledge-Based Approaches, Island of Rhodes, Greece, August 31–September 3, 1986

System Fault Diagnostics, Reliability and Related Knowledge-Based Approaches

Intelligent Systems involve a large class of systems which posses human-like capabilities such as learning, observation, perception, interpretation, reasoning under uncertainty, planning in known and unknown environments, decision making, and control action. The field of intelligent systems is actually a new interdisciplinary field which is the outcome of the interaction, cooperation and synergetic merging of classical fields such as system theory, control theory, artificial intelligence, information theory, operational research, soft computing, communications, linguistic theory, and others. Integrated intelligent decision and control systems involve three primary hierarchical levels, namely organization, coordination and execution levels. As we proceed from the be performed organization to the execution level, the precision about the jobs to increases and accordingly the intelligence required for these jobs decreases. This is in compliance with the principle of increasing precision with decreasing intelligence (IPOI) known from the management field and theoretically established by Saridis using information theory concepts. This book is concerned with intelligent systems and techniques and gives emphasis on the computational and processing issues. Control issues are not included here. The contributions of the book are presented in four parts as follows.

Concepts, Tools and Applications

Advances in Intelligent Systems

H. B. Verbruggen

This book is concerned with Artificial Intelligence (AI) concepts and techniques as applied to industrial decision making, control and automation problems. The field of AI has been expanded enormously during the last years due to that solid theoretical and application results have accumulated. During the first stage of AI development most workers in the field were content with illustrations showing ideas at work on simple problems. Later, as the field matured, emphasis was turned to demonstrations that showed the capability of AI techniques to handle problems of practical value. Now, we arrived at the stage where researchers and practitioners are actually building AI systems that face real-world and industrial problems. This volume provides a set of twenty four well-selected contributions that deal with the application of AI to such real-life and industrial problems. These contributions are grouped and presented in five parts as follows: Part 1: General Issues Part 2: Intelligent Systems Part 3: Neural Networks in Modelling, Control and Scheduling Part 4: System Diagnostics Part 5: Industrial Robotic, Manufacturing and Organizational Systems Part 1 involves four chapters providing background material and dealing with general issues such as the conceptual integration of qualitative and quantitative models, the treatment of timing problems at system integration, and the investigation of correct reasoning in interactive man-robot systems.

Artificial Intelligence in Industrial Decision Making, Control and Automation

This book is concerned with Intelligent Control methods and applications. The field of intelligent control has been expanded very much during the recent years and a solid body of theoretical and practical results are now available. These results have been obtained through the synergetic fusion of concepts and techniques from a variety of fields such as automatic control, systems science, computer science, neurophysiology and operational research. Intelligent control systems have to perform anthropomorphic tasks fully autonomously or interactively with the human under known or unknown and uncertain environmental conditions. Therefore the basic components of any intelligent control system include cognition, perception, learning, sensing, planning, numeric and symbolic processing, fault detection/repair, reaction, and control action. These components must be linked in a systematic, synergetic and efficient way. Predecessors of intelligent control are adaptive control, self-organizing control, and learning control which are well documented in the literature. Typical application examples of intelligent controls are intelligent robotic systems, intelligent manufacturing systems, intelligent medical systems, and intelligent space teleoperators. Intelligent controllers must employ both quantitative and qualitative information and must be able to cope with severe temporal and spatial variations, in addition to the fundamental task of achieving the desired transient and steady-state performance. Of course the level of intelligence required in each particular application is a matter of discussion between the designers and users. The current literature on intelligent control is increasing, but the information is still available in a sparse and disorganized way.

Methods and Applications of Intelligent Control

Robotics is a modern interdisciplinary field that has emerged from the marriage of computerized numerical control and remote manipulation. Today's robotic systems have intelligence features, and are able to perform dexterous and intelligent human-like actions through appropriate combination of learning, perception, planning, decision making and control. This book presents advanced concepts, techniques and applications reflecting the experience of a wide group of specialists in the field. Topics include: kinematics, dynamics, path planning and tracking, control, mobile robotics, navigation, robot programming, and sophisticated applications in the manufacturing, medical, and other areas.

S.G. Tzafestas

About

Books

Join the club