Intelligent Systems: Overview file:///C|/WINDOWS/Desktop/Misc/Book/overview.

html

Overview
The ever increasing technological demands of today call for very complex systems, which
in turn require highly sophisticated controllers to ensure that high performance can be achieved
and maintained under adverse conditions. There are needs in the control of these complex
systems which cannot be met by conventional controllers and this is primarily due to the lack of
precise knowledge about the process to be controlled. Acquisition of adequate system knowledge
is often problematic or impractical due to system complexity and the fact that the structure and
parameters in many systems change in significant and unpredictable ways over time. Moreover,
to reduce design complexity control designers often utilize less detailed models for control than
what they have access to. To address the control demands of such highly complex and uncertain
systems one can enhance today's control methods using intelligent control systems and
techniques.

The area of Intelligent Control is a fusion of a number of research areas in Systems and
Control, Computer Science and Operations Research among others, coming together, merging
and expanding in new directions and opening new horizons to address the new problems of this
challenging and promising area. Perhaps in the not so distant future we will be able to witness
control systems which perform many intelligent functions so that they exhibit high degrees of
autonomy and hence release us from dangerous or mundane tasks. Intelligent control systems are
typically able to perform one or more of the following functions: planning actions at different
levels of detail, learning from past experience, identifying changes that threaten the system
behavior, such as failures, and reacting appropriately. This identifies the areas of Planning and
Expert Systems, Fuzzy Systems, Neural Networks, Machine Learning, and Failure Diagnosis, to
mention but a few, as existing research areas that are related and important to Intelligent Control.
In addition, there are novel problems raised in the context of machine intelligence and intelligent
control, the solution of which requires the development of completely new approaches and
methods- such is the case for example in the study of symbolic-numeric / discrete and
continuous state systems called "Hybrid Systems."

The Chapters in this book are written by the specialists in the area. They discuss a variety
of approaches, theories, solved and unsolved problems, fundamental and advanced methods, and
a number of applications. The contributions are grouped into three parts: Part I deals with the
theories, fundamentals, architectures and the different ways of looking at Intelligent Control.
Part 11 addresses specific classes of problems and suggests particular methods for Intelligent
Control such as expert, planning, fuzzy, neural, and learning systems. Part 111 explicitly deals
with applications. Applications are in fact diffused throughout the chapters of the book in the
form of examples for proof of concept or for illustration of ideas.

Overall, this book provides a solid introduction to the area. Studying the material one is
certainly impressed by the gains so far, by the amount of pioneering work which has been, and
currently is being performed but also by the enormity of the undertaking. It is quite clear that we
are at the very early stages of development in this important and extremely promising field. The
difficulties sometimes appear unsurpassed but the rewards are also without precedent, truly
fantastic.

1 of 5 8/16/01 3:00 PM
Intelligent Systems: Overview file:///C|/WINDOWS/Desktop/Misc/Book/overview.html

It is essential to have a view of the whole area, of the goals, theories, approaches, different
views, and architectures. This is presented in the six chapters of Part I. Such an overview of the
area, which is in fact a Systems' approach, is very helpful indeed as it provides the framework to
build upon. This framework has to be flexible to accommodate new ideas but it must also be
firm enough to provide good foundations. The theories presented in Part I are different enough,
but also similar enough for one to be able to identify the main concepts and ideas of intelligent
control that are common to all.

The first paper in Part I provides an introduction to the field and discusses the main
concepts and ideas. A general approach to design and control of intelligent systems is given in
chapters two and three. Distributed intelligent control is discussed next while distributed
intelligence systems, such as human organizations, are studied in chapter five. Chapter six
describes a rather distinct approach to design and control of intelligent systems. We provide a
brief overview of each of the chapters below:

Antsaklis and Passino provide an introduction to control systems that incorporate intelligent
methods to attain higher degrees of autonomy. An overview of the field of intelligent control is
provided, a hierarchical functional architecture is discussed, and the characteristics of such
systems are explained. It is emphasized that: (i) the area of intelligent control is interdisciplinary,
requiring research in and coordination among many research disciplines, and (ii) there is need
for analytical models and methods to study intelligent control systems and recent advances in the
area of discrete event and hybrid dynarnical systems do offer significant promise.

Albus describes an architecture for intelligent system design based on his RCSReal time Control
System-reference model architecture; in RCS the types of functions that are required in a real
time intelligent control system are defined together with how these functions relate to each other,
thus providing a structural approach to design. This systematic approach has been used in a
variety of applications such as in controlling machining workstations, space station telerobots,
autonomous underwater vehicles, and in postal service mail handling.

Zeigler and Chi present a model-based architecture for the design and simulation of high
autonomy systems. A model base is at the center of its planning, operation, diagnosis and fault
recovery strategies; timing effects are also being considered as they are so important for the
correct operation of the system. The general approach is characterized via a "hierarchical
encapsulation and abstraction principle". As a proof of concept, this approach is implemented to
automate a space-borne laboratory.

Acar and Ozguner, based on distributed control concepts, describe a structure-based hierarchy
for the intelligent control of systems; the mathematical foundations are stressed and analytical
results are presented. This approach is different in that its organization is based on the physical
structure of a system rather than on its functionality. The approach is illustrated on robotics
applications.

Levis discusses distributed intelligence systems such as human organizations. He describes an

2 of 5 8/16/01 3:00 PM
Intelligent Systems: Overview file:///C|/WINDOWS/Desktop/Misc/Book/overview.html

emerging mathematical theory for the analysis and design of such systems; an information
processing and decision making system approach is taken where both human and machine
intelligence coexist and interact. The theory is showing that such systems can exhibit a wide
variety of not well understood behavior.

Finally nested hierarchical control its foundations and history is presented by Meystel. It is
described as a development of theories of multiresolutional image and signal representation into
the domain of control theory that enables efficient practice of design and control using nested
search in state space.

Part II addresses particular questions and aspects of intelligent control. As it was mentioned
earlier one recognizes the research areas of expert and planning systems fuzzy systems neural
networks and learning systems as providing several methods for the intelligent control of
complex systems. All of these are addressed by the six chapters in Part II. Expert and planning
systems are considered in the first two chapters while fuzzy and neural control is the topic of the
next chapter. The remaining three chapters all discuss aspects of learning in control reflecting the
great importance of learning methods in intelligent control. In particular we provide a brief
overview of each of the chapters of Part II below:

Astrom and Arzen describe how to use expert systems to implement control functions. They
explain how such expert controllers can automate several tasks normally performed by operators
and process and control engineers by emulating their heuristic decision making activities. An
overview of the foundations of the area of expert control systems is provided and
implementation issues are discussed. It is explained how the expert control framework can be
composed of many conventional and intelligent control techniques.

Passino and Antsaklis develop a foundation of fundamental control theoretic concepts for the
modeling and analysis of AI planning systems. They introduce the ideas of feedforward and
feedback planning systems and highlight the importance of analyzing the dynamical behavior of
AI systems. Finally they show that discrete event system theoretic techniques can be used for the
modeling and analysis of simple AI planning problems.

Berenji provides an introduction to fuzzy and neural control. He explains the basic architecture
and operation of fuzzy controllers and how they implement interpolative reasoning. Hierarchical
fuzzy control and applications of fuzzy control are discussed. For neural approaches he explains
reinforcement leanzing in control and introduces hybrid fuzzy/neural control via the approximate
reasoningbased intelligent controller. A cart-pole balancing problem is discussed for proof of
concept.

Farrell and Baker provide an introduction to the area of learning control. They present an
extensive overview of the literature and a careful comparison between learning and adaptive
systems. They identify the advantages of augmenting conventional control approaches with
learning capabilities. In addition they illustrate the application of contemporary learning control
approaches to two examples. Finally the authors provide future research directions.

3 of 5 8/16/01 3:00 PM
Intelligent Systems: Overview file:///C|/WINDOWS/Desktop/Misc/Book/overview.html

Kokar shows how architectures for adaptive control systems have evolved into ones for learning
control. The author emphasizes that learning controllers should be able to learn goals models and
control laws. In addition he explains the COPER/IC architecture and overviews his contributions
within this framework. Finally he outlines future needs in the area of learning control.

Grant also describes techniques for learning control. In particular he discusses human control
passive learning and machine learning. He establishes the heuristics for control of the pole-cart
system and studies the acquisition of knowledge for learning controllers. He provides both
simulations and results from experiments in learning and neural control.

The emphasis in the last four chapters of the book is on particular applications of intelligent
control. It is important to clearly demonstrate that the approaches and ideas which were
discussed can successfully address real needs and this is done in Part III. The first two chapters
of Part III deal with robotic systems while the last two describe particular applications of
intelligent control methods to flight control and fault diagnosis in process control respectively. In
particular we provide a brief overview of each of the chapters of Part III below:

Nguyen and Stephanou discuss an intelligent integrated symbolic-numeric technique for

dexterous manipulation. In particular the authors use topological models and topological
reasoning for a multifingered robot hand. They show that with this approach both the hand
posture and functionality can be derived from the high level symbolic requirements and
translated into low level numeric joint space variables. The application nicely illustrates the use
of multilayer hierarchical intelligent control developed from both symbolic and numeric
models/algorithms.

Seetharaman and Valavanis study multi-sensory robotic systems with failure diagnostic
capabilities. In particular the authors investigate the problem of recovery from visual failures
which occur in multi-sensory robotic systems. In addition they examine problems with sensor
fusion in the multi-sensory system. The authors adhere to the classical three level hierarchical
approach to intelligent control focus on the function and complexity of the vision system and
explain the variety of problems that their approach applies to.

Belkin and Stengel describe an expert system that aids a pilot of an aircraft by automating
decision making tasks that are normally the responsibility of the crew. In particular the authors
introduce a cooperative rule-based expert systems approach to intelligent flight control. They
study the interactions between the expert systems which automate various functions and study
the performance of the entire AUTOCREW system in terms of its ability to assist the pilot.
Extension of the results to other applications is discussed. The approach provides an illustration
of several of the fundamental ideas in intelligent control including the division of responsibilities
and coordination of intelligent system activities.

Prasad and Davis study how to enhance the capabilities of process control computers to
automate the activity of failure diagnosis. The diagnostic activity is broken down into a set of
information-processing tasks and it is explained how such tasks are integrated to form a
framework to construct knowledge-based diagnostic systems. Moreover, it is shown how the

4 of 5 8/16/01 3:00 PM
Intelligent Systems: Overview file:///C|/WINDOWS/Desktop/Misc/Book/overview.html

approach facilitates the integration of diverse techniques for automated diagnosis. Overall, the
work shows how various intelligent control techniques can be integrated to perform a complex
task for a difficult problem facing a wide variety of industries today.

This book represents the collective effort of many researchers in the field of intelligent
control who thought that such book would be helpful in introducing the major topics in the area
and providing a description of the state-of-the-art techniques. We would like to thank all the
contributors who dedicated a significant amount of time and effort to make such an enterprise
possible. We sincerely hope that the reader finds the study of this book rewarding and sees it as
the beginning of many exciting and challenging new endeavors.

Panos Antsaklis, Notre Dame, Indiana also London, England and Athens, Greece

Kevin Passino, Columbus, Ohio

5 of 5 8/16/01 3:00 PM
Intelligent Systems: Preface file:///C|/WINDOWS/Desktop/Misc/Book/preface.html

Preface
Intelligent Control is presently a well established field within the discipline of Control Systems.
It represents a generalization of the concept of control, to include autonomous anthropomorphic
interactions of a machine with the environment. It has been successfully represented by a
Technical Committee of the EEE Control Systems Society, and the technical results of many
researchers in the area are regularly reported in many of the annual conferences in the USA and
around the world. The recent appearance in the technical literature of monographs on the subject
matter is a strong indication that the area has entered a period of maturity.

However, it was only in 1971, that Saridis made the first attempts to analytically investigate
control systems with cognitive capabilities, that could successfully interact with the
environment, and Albus presented his Cerebellar Model Articulation Controller, resembling a
human behavioral control system. Since then, Intelligent Control, was postulated by Saridis, as
the process of autonomous decision making in structured or unstructured environments, based on
the interaction of the disciplines of Artificial Intelligence, Operations Research, and Automatic
Controls.

The name Intelligent Control was coined by K.S. Fu in 1971, when he was asked to define the
area beyond Adaptive and Learning Control. The presentation was part of debate at the time,
about the evolution of the Theory of Control Systems. Tracking the chronological development
one may go back to the 1940's and 50's where Classical Control was formulated, using frequency
domain techniques. In the 1960's, with the discovery of Pontryagin's Maximum Principle,
Optimal Control Theoly flourished. Stochastic Optimal Control, was a by-product of this theory,
introducing the concept of uncertainty in the design process. In the late 1960's, when structural
uncertainties were accepted as part of the systems to be controlled, Adaptive Control was
introduced as the methodology to manage systems of higher sophistication. They were using
implicit or explicit system identification to provide optimal decision making for the best
performance. In the meanwhile considerable progress was made in the behavioral sciences,
regarding the collection and use of information about the environment for decision making by
humans. It was then only natural to apply behavioral techniques to Control System Theory to
improve the performance of a system operating in an uncertain environment. The approach was
called Learning Control, and it utilized methods considered as predecessors of the modern
Neural Net Theory. Self-Organizing Controls were formalized in the same period, to handle
cases of autonomous management of uncertain processes in unfamiliar environments.

The evolution of Control System Theory, followed a trend of increasing autonomy, as was
recognized by Antsaklis and Passino in many of their publications. Therefore, a more general
definition of control is imperative in order to handle more sophisticated processes which interact
with the environment. Here is one such definition: Control is driving a process to attain a
prespecified goal.

Intelligent Controls, follow the above definition, in order to manage complex processes in
uncertain environments in an anthropomorphic manner, by using cognitive engineering systems
and the tremendous power of modern computer technology. Typical examples are modern

1 of 2 8/16/01 3:03 PM
Intelligent Systems: Preface file:///C|/WINDOWS/Desktop/Misc/Book/preface.html

Intelligent Robotic Systems. They are usually stratified in three levels with possible multiple
substates in each level. Saridis has proposed an analytic formulation of such a system, based on a
Principle of Increasing Precision with Decreasing Intelligence. Such a machine is structured in
three levels; the Organization level, the Coordinatio)l level, and the Execution level. They follow
a hierarchical order of decrease of machine intelligence with an increase of complexity, for most
efficient operation. Neural Net, Petri Net, and Optimal Control technologies have been utilized
in these three levels, with Entropy as the common measure of performance. Albus et al.,
developed NASREM, which represents another successful Hierarchical Intelligent Control
System that uses a behavioral approach. Several other Intelligent Control methods that are also
described in this volume, have various applications, especially to autonomous Robotic Systems.

The present volume is a collection of representative publications on the state of the art of
Intelligent, Knowledge-based, Learning and Hierarchical Control Systems, demonstrating a high
level of autonomy. It may serve as a reference to the researcher as well as the practitioner who
wants to design highly sophisticated control systems that operate in remote, hazardous and
unfamiliar environments. The material may be grouped into several categories according to their
approach. In the category of Hierarchical or Model-based Architectures one may include the
chapters by Antsaklis and Passino, Albus, Zeigler and Chi, and Meystel. In the category of
Distributed Intelligence belong the chapters by Acar and Ozguner, and Levis while the chapters
by Astrom and Arzen, Passino and Antsaklis, Berenji, Nguyen and Stephanou, Belkin and
Stengel, Seetharaman and Valavanis, and Prasad and Davis deal with Knowledge-based Control
Systems and their applications. Finally, the chapters by Farrell and Baker, Kokar, and Grant treat
the subject of Learning Controls. It is interesting to notice that these chapters cover the whole
spectrum from theory to design and applications of Intelligent and Autonomous Control
Systems.

Finally, I believe that the editors should be congratulated for their thorough effort of collecting
and publishing a comprehensive volume of major contributions in the field of Intelligent Control
Systems, an area which is fast growing and is finding many applications in industry, medicine,
and space exploration. One looks forward to new additions to the technical literature of the same
caliber.

George N. Saridis, Albany New York Spring 1992

2 of 2 8/16/01 3:03 PM
Intelligent Systems: Table of Contents file:///C|/WINDOWS/Desktop/Misc/Book/contents.html

Table of Contents
Preface: George N. Saridis.....ix

Overview: Panos J. Antsaklis and Kevin M. Passino.....xi

Part I: Theory and Architectures

Chapter1:Introduction to Intelligent Control Systems with High Degrees of Autonomy.....1
Panos J. Antsaklis and Kevin M. Passino
Chapter 2: A Reference Model Architecture for Intelligent Systems Design.....27
James S. Albus
Chapter 3:Model-Based Architecture Concepts for Autonomous Systems Design and
Simulation.....57
Bernard P. Zeigler and Sungdo Chi
Chapter 4:Design of Structure-Based Hierarchies for Distributed Intelligent Control.....79
Levent Acar and Umit Ozguner
Chapter 5: Modeling and Design of Distributed Intelligence Systems.....109
Alexander H. Levis
Chapter 6: Nested Hierarchical Control.....129
Alex Meystel

Part II: Design Approaches and Techniques

Chapter 7: Expert Control.....163
Karl J. Astrom and Karl-Erik Arzen
Chapter 8: Modeling and Analysis of Artificially Intelligent Planning Systems.....191
Kevin M. Passino and Panos J. Antsaklis
Chapter 9: Fuzzy and Neural Control.....215
Hamid R. Berenji
Chapter 10: Learning Control Systems.....237
Jay Farrell and Walter Baker
Chapter 11: Learning Control: Methods, Needs and Architectures.....263
Mieczyslaw M. Kokar
Chapter 12: Learning in Control.....283
Edward Grant

Part III: Applications

Chapter 13: Intelligent Robot Prehension.....319
Thang N. Nguyen and Harry Stpehanou
Chapter 14: Modeling of MultiSensory Robotic Systems with Failure Diagnostic
Capabilities.....349
Guna Seetharaman and Kimon P. Valavanis
Chapter 15: AUTOCREW: A Paradigm for Intelligent Flight Control.....371
Brenda L. Belkin and Robert F. Stengel
Chapter 16: A Framework for Knowledge-Based Diagnosis in Process Operations.....401
P.R. Prasad and James F. Davis

Index .....423

1 of 1 8/16/01 2:46 PM