Control of the Physical World by Intelligent Agents: Putting the Pieces Together

This article contains summaries of the five symposia that were conducted: (1) Control of the Physical World by Intelligent Agents, (2) Improving Instruction of Introductory AI, (3) Knowledge Representation for Natural Language Processing in Implemented Systems, (4) Planning and Learning: On to Real Applications, and (5) Relevance. Proceedings of most of the symposia are available as technical reports from AAAI. Control of the physical world, whether by mobile robots or by chemical process controllers, involves many disciplines, including conventional process control, neural networks, fuzzy logic, decision theory, planning, and vision. This workshop brought together researchers from these and other fields with the aim of enumerating the methods available; making a stab at generating a framework for putting them together; and addressing questions such as, How can control help AI? and How can AI help control? A recurring theme was the benefits--or lack thereof--of hierarchical systems: A majority of the attendees supported the position that hierarchy was necessary: Low-level subsystems process sensory input and execute control strategies, and higher-level systems select control strategies appropriate for the task at hand, especially by planning and, perhaps, developing and using maps of the environment.