|
1. |
DESIGN FOR AUTONOMY: An Overview |
|
Applied Artificial Intelligence,
Volume 6,
Issue 1,
1992,
Page 1-18
JERZYW. ROZENBLIT,
Preview
|
PDF (554KB)
|
|
摘要:
This paper discusses desiderata for support of high-autonomy systems design. Knowledge-based design techniques are presented. Requirements for high autonomy are defined, and a design methodology for achieving them is described. The suggested techniques provide high-level aids for developing architectures and integrating high-autonomy systems with environments in which they are developed. The design methodology presented here stems from a multifaceted stimulation-modeling framework.
ISSN:0883-9514
DOI:10.1080/08839519208949939
出版商:Taylor & Francis Group
年代:1992
数据来源: Taylor
|
2. |
ENDOMORPHIC MODELING CONCEPTS FOR HIGH-AUTONOMY ARCHITECTURES |
|
Applied Artificial Intelligence,
Volume 6,
Issue 1,
1992,
Page 19-43
BERNARDP. ZEIGLER,
Preview
|
PDF (917KB)
|
|
摘要:
Autonomy is an extended paradigm that subsumes both control and artificial intelligence (AI) paradigms, each of which is limited by its own abstractions. Control theory has run up against the limitations of its rigorous, but sparcely applicable, mathematical framework.AIresearch has lived under the illusion that intelligence can be demonstrated in abstract symbol spaces bereft of a rich, continuous coupling to the real world. Autonomy, as a design goal, offers an arena where both control and Al paradigms must be applied—and a challenge to the viability of both as independent entities. We discuss model-based architectures in which such paradigms can be integrated. Modeling principles for development of such architectures are proposed and illustrated. Endomorphic modeling plays a fundamental role since high autonomy requires models at different levels of abstraction that are homomorphically interrelated. Benchmarks are given for levels of autonomy that arise out of the model-based architecture.
ISSN:0883-9514
DOI:10.1080/08839519208949940
出版商:Taylor & Francis Group
年代:1992
数据来源: Taylor
|
3. |
D DESIGN-FLOW MODELING AND KNOWLEDGE-BASED MANAGEMENT |
|
Applied Artificial Intelligence,
Volume 6,
Issue 1,
1992,
Page 45-57
FELIX BRETSCHNEIDER,
HELMUT LAGGER,
Preview
|
PDF (414KB)
|
|
摘要:
With rapidly growing complexity in the field of design, system engineers and designers are confronted with a constantly increasing variety of highly specialized tools, which have to be integrated and operated. Advanced computer-aided design (CAD) framework techniques are urgently needed to provide infrastructure and support to CAD system engineers as well as designers
ISSN:0883-9514
DOI:10.1080/08839519208949941
出版商:Taylor & Francis Group
年代:1992
数据来源: Taylor
|
4. |
PERFORMANCE-DRIVEN AUTONOMOUS DESIGN OF PATTERN-RECOGNITION SYSTEMS |
|
Applied Artificial Intelligence,
Volume 6,
Issue 1,
1992,
Page 59-77
LOUISA. TAMBURINO,
MATEENM. RIZKI,
Preview
|
PDF (583KB)
|
|
摘要:
The closed-loop design experiment described in this paper demonstrates a three-phase automated design approach to pattern recognition. The experiment generates morphological feature detectors and then uses a novel application of genetic algorithms to select cooperative sets of features to pass to a neural net classifier. The self-organizing hybrid learning approach embodied in this closed-loop design methodology is complementary to conventional artificial intelligence (AI) expert systems that utilize rule-based approaches and a specific set of design elements. This experiment is part of a study directed to emulating the nondirected processes of biological evolution. The approach we discuss is semiautomatic in that initialization of computer programs requires human experience and expertise to select representations, develop search strategies, choose performance measures, and devise resource-allocation strategies. The hope is that these tasks will become easier with experience and will provide the means to exploit parallel processing without the need to analyze or program an entire design solution.
ISSN:0883-9514
DOI:10.1080/08839519208949942
出版商:Taylor & Francis Group
年代:1992
数据来源: Taylor
|
5. |
Adaptive Default Hierarchy Formation |
|
Applied Artificial Intelligence,
Volume 6,
Issue 1,
1992,
Page 79-102
ROBERTE. SMITH,
DAVIDE. GOLDBERG,
Preview
|
PDF (1090KB)
|
|
摘要:
Autonomous systems are likely to be required to face situations that cannot be foreseen by their designers. The potential for perpetually novel situations places a premium on mechanisms that allow for automatic adaptation in a general setting. The term reinforcement learning problems (Mendel and McLaren, 1970) generally describes problems where a control system must adapt based on performance-only feedback. This paper considers the learning classifier system (LCS) as an approach to reinforcement learning problems. An LCS is a type of adaptive expert system that uses a knowledge base of production rules in a low-level syntax that can be manipulated by a genetic algorithm (GA) (Holland. 1975; Goldberg, 1989) Genetic algorithms comprise a class of computerized search procedures that are based on the mechanics of natural genetics (Goldberg, 1989; Holland. 1975). An important feature of the LCS paradigm is the possible adaptive formation of default hierarchies (layered sets of default and exception rules) )Holland et al., 1986). This paper examines the problem of default hierarchy formation under the conventional bid-competition method of LCS conflict resolution, and suggests the necessity auction and a separate priority factor as modifications to this method. Simulations show the utility of this method. Final discussion presents conclusions and suggests avenues for further research
ISSN:0883-9514
DOI:10.1080/08839519208949943
出版商:Taylor & Francis Group
年代:1992
数据来源: Taylor
|
6. |
ACHIEVING FLEXIBLE AUTONOMY IN MULTIAGENT SYSTEMS USING CONSTRAINTS |
|
Applied Artificial Intelligence,
Volume 6,
Issue 1,
1992,
Page 103-126
MARK EVANS,
JOHN ANDERSON,
GEOFF CRYSDALE,
Preview
|
PDF (801KB)
|
|
摘要:
Organizations influence many aspects of our lives. They exist for one reason: they can accomplish things that individuals cannot. While recent work in high-autonomy systems has shown that autonomy is a critical issue in artificial intelligence (AI) systems, these systems must also be able to cooperate with and rely on one another to deal with complex problems. The autonomy of such systems must be flexible, in order that agents may solve problems on their own as well as in groups. We have developed a model of distributed problem solving in which coordination of problem-solving agents is viewed as a multiagent constraint-satisfaction planning problem. This paper describes the experimental testbed that we are currently developing to facilitate the investigation of various constraint-based strategies for addressing the coordination issues inherent in cooperative distributed problem-solving domains.
ISSN:0883-9514
DOI:10.1080/08839519208949944
出版商:Taylor & Francis Group
年代:1992
数据来源: Taylor
|
|