An agent architecture for long-term robustness

Authors:
John R. Rose;Michael N. Huhns;Soumik Sinha Roy;William H. Turkett, Jr.
Affiliations:
University of South Carolina, Columbia, SC;University of South Carolina, Columbia, SC;University of South Carolina, Columbia, SC;University of South Carolina, Columbia, SC
Venue:
Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 3
Year:
2002

Citing 9
Cited 2

Coherent cooperation among communicating problem solvers

IEEE Transactions on Computers
Social conceptions of knowledge and action: DAI foundations and open systems semantics

Artificial Intelligence
Modeling reactive behaviour in vertically layered agent architectures

ECAI-94 Proceedings of the workshop on agent theories, architectures, and languages on Intelligent agents
Modelling social action for AI agents

Artificial Intelligence - Special issue: artificial intelligence 40 years later
Cognitive Agents

IEEE Internet Computing
Software Engineering with Agents: Pitfalls and Pratfalls

IEEE Internet Computing
Building Dynamic Agent Organizations in Cyberspace

IEEE Internet Computing
Trust and Persistence

IEEE Internet Computing
Deliberative Normative Agents: Principles and Architecture

ATAL '99 6th International Workshop on Intelligent Agents VI, Agent Theories, Architectures, and Languages (ATAL),

A distributed task environment for teaching artificial intelligence with agents

Proceedings of the 35th SIGCSE technical symposium on Computer science education
MAGEFRAME: A Modular Agent Framework to Support Various Communication Schemas Based on a Self-embedding Algorithm

Agent Computing and Multi-Agent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes an architecture for enabling robust autonomous decision making and task execution. A key feature of the architecture is that agent behavior is constrained by sets of agent societal laws similar to Asimov's laws of robotics. In accordance with embedded philosophical principles, agents use decision theory in their negotiations to evaluate the expected utility of proposed actions and use of resources. This results in planning and task execution that is dynamic, rational, distributed, occurs at multiple levels of granularity, and can be trusted. We report on our initial investigations of agent architectures that embody philosophical and social layers. Our investigations have included the effect of misinformation among cooperative agents in worth-oriented domains, and active countermeasures for dealing with the misinformation. We examine the agents" use of philosophical principles for mission preeminence and rational progress towards goals.