My dissertation describes an approach to automatically formulating or selecting models of a target physical system for a given qualitative reasoning task. It was motivated by two observations regarding modeling in general and work in qualitative physics in particular. First, all model-based reasoning is only as good as the model used (Davis and Hamscher 1988). Second, no single model is adequate or appropriate for a wide range of tasks (Weld 1989).

The first Robotics Exhibition and Competition sponsored by the Association for the Advancement of Artificial Intelligence was held in San Jose, California, on 14-16 July 1992 in conjunction with the Tenth National Conference on AI. This article describes the history behind the competition, the preparations leading to the competition, the threedays during which 12 teams competed in the three events making up the competition, and the prospects for other such competitions in the future.

My Ph.D. dissertation describes PAGODA (probabilistic autonomous goal-directed agent), a model for an intelligent agent that learns autonomously in domains containing uncertainty. The ultimate goal of this line of research is to develop intelligent problem-solving and planning systems that operate in complex domains, largely function autonomously, use whatever knowledge is available to them, and learn from their experience. PAGODA was motivated by two specific requirements: The agent should be capable of operating with minimal intervention from humans, and it should be able to cope with uncertainty (which can be the result of inaccurate sensors, a nondeterministic environment, complexity, or sensory limitations). I argue that the principles of probability theory and decision theory can be used to build rational agents that satisfy these requirements.

The University of Michigan's CARMEL and SRI International's FLAKEY were the first- and second-place finishers, respectively, at the 1992 Robot Competition sponsored by the Association for the Advancement of Artificial Intelligence. The two teams used vastly different approaches in the design of their robots. Many of these differences were for technical reasons, although time constraints, financial resources, and long-term research objectives also played a part. This article gives a technical comparison of CARMEL and FLAKEY, focusing on design issues that were not directly reflected in the scoring criteria.

The Association for the Advancement of Artificial Intelligence held its 1992 Fall Symposium Series on October 23-25 at the Royal Sonesta Hotel in Cambridge, Massachusetts. This article contains summaries of the five symposia that were conducted: Applications of AI to Real-World Autonomous Mobile Robots, Design from Physical Principles, Intelligent Scientific Computation, Issues in Description Logics: Users Meet Developers, and Probabilistic Approaches to Natural Language.

Although knowledge representation is one of the central and, in some ways, most familiar concepts in AI, the most fundamental question about it -- What is it? Numerous papers have lobbied for one or another variety of representation, other papers have argued for various properties a representation should have, and still others have focused on properties that are important to the notion of representation in general. In this article, we go back to basics to address the question directly. We believe that the answer can best be understood in terms of five important and distinctly different roles that a representation plays, each of which places different and, at times, conflicting demands on the properties a representation should have.

This article informally examines the role of stored internal state (that is, memory) in the control of autonomous mobile robots. The difficulties associated with using stored internal state are reviewed. It is argued that the underlying cause of these problems is the implicit predictions contained within the state, and, therefore, many of the problems can be solved by taking care that the internal state contains information only about predictable aspects of the environment. One way of accomplishing this is to maintain internal state only at a high level of abstraction. The resulting information can be used to guide the actions of a robot but should not be used to control these actions directly; local sensor information is still necessary for immediate control. A mechanism to detect and recover from failures is also required. A control architecture embodying these design principles is briefly described. This architecture was successfully used to control real-world and simulated real-world autonomous mobile robots performing complex navigation tasks. The architecture is able to incorporate standard AI planning and world-modeling algorithms into a real-time situated framework.

Although knowledge representation is one of the central and, in some ways, most familiar concepts in AI, the most fundamental question about it -- What is it? -- has rarely been answered directly. Numerous papers have lobbied for one or another variety of representation, other papers have argued for various properties a representation should have, and still others have focused on properties that are important to the notion of representation in general. In this article, we go back to basics to address the question directly. We believe that the answer can best be understood in terms of five important and distinctly different roles that a representation plays, each of which places different and, at times, conflicting demands on the properties a representation should have. We argue that keeping in mind all five of these roles provides a usefully broad perspective that sheds light on some longstanding disputes and can invigorate both research and practice in the field.

Thus, an estimate of the current task state can be viewed as a combination of sensory data and expectation. The estimate of a future state, resulting from a hypothetical affects an alarming number of robots, action, would be pure expectation. In some Victims of sensor abuse sometimes forget situations, sensor use is advisable, perhaps all about expectation and become obsessed even unavoidable. However, there is an with immediate sensory data. This obsession important difference between sensor use and might be the result of excessive introspection sensor abuse.

Sensor abuse is a serious and debilitating condition. However, one must remember that it is a disease, not a crime.1 As such, it can be treated. This article presents a case study in sensor abuse. This particular subject was lucky enough to pull himself out of his pitiful condition, but others are not so lucky. The article also describes a 12- step behavior-modification program modeled on this and other successful case studies.