This article reports on the RoboCup-2003 event. RoboCup is no longer just the Soccer World Cup for autonomous robots but has evolved to become a coordinated initiative encompassing four different robotics events: (1) Soccer, (2) Rescue, (3) Junior (focused on education), and (4) a Scientific Symposium. RoboCup-2003 took place from 2 to 11 July 2003 in Padua (Italy); it was colocated with other scientific events in the field of AI and robotics. In this article, in addition to reporting on the results of the games, we highlight the robotics and AI technologies exploited by the teams in the different leagues and describe the most meaningful scientific contributions.

To submit a candidate's name for consideration, please send the individual's name, address, telephone number, and email address to Carol Nominators should contact candidates prior to submitting their names to verify that they are willing to serve, should they be elected. "AI in the News" section of the AI Intelligence will be held at 12:45 PM, October 22-24, 2004, at the Hyatt (see www.aaai.org/aitopics/assets/ If you are a Washington, DC. Cochairs: Simon that the use of such excerpts is past president. Ross Gayler personal and does not amount to, or year four new councilors are elected (r.gayler@mbox.com.au), and Pentti result in, commercial distribution.

Ohio State University) focused on the use of case-based reasoning for both planning and world modeling. Nicola Muscettola (NASA Ames) focused on reactive behaviors. Laboratory) described an approach Within this general theme, to planning with multiagent the aim was to bring together researchers execution. The presentation ecent developments in multiagent shown promising results in the robotics, intelligent autonomous of Thomas Wagner (University of modeling of autonomous, collaborative vehicles). The common denominator Brement), Christoph Schlieder (University behavior between agents in different that these groups share is the pragmatic of Bamberg), and Ubbo Visser environments.

A synthesisof methods from cybernetics and AI yields a concept of intelligence for autonomous mobile systems that integrates closed-loop visual perception and goal-oriented action cycles using spatiotemporal models. In a layered architecture, systems dynamics methods with differential models prevail on the lower, data-intensive levels, but on higher levels, AI-type methods are used. Knowledge about the world is geared to classes of objects and subjects. Subjects are defined as objects with additional capabilities of sensing, data processing, decision making, and control application. Specialist processes for visual detection and efficient tracking of class members have been developed. On the upper levels, individual instantiations of these class members are analyzed jointly in the task context, yielding the situation for decision making. As an application, vertebrate-type vision for tasks in vehicle guidance in naturally perturbed environments was investigated with a distributed PC system. Experimental results with the test vehicle VAMORS are discussed.

The integration of AI and vision has been a longterm goal of both disciplines for more than three decades. This special issue illustrates some recent work on bridging the gap.

This eclectic keepsake provides a sampling in action' for the first time. Its destruction "You may have read about the outsourcing of what can be found (with links to the full Please may well have been saved, the company today, in cover articles in Time, Wired, keep in mind that (1) the mere mention of said. 'It was a special moment--a robot Business Week.... In New Hampshire, John anything here does not imply any endorsement got blown up instead of a person,' said Kerry was asked about the problem. His whatsoever; (2) the excerpt might not iRobot CEO Colin Angle.... Between 50 answer: 'We have to create the next wave reflect the overall tenor of the article; (3) although and 100 PackBots are now being used in of those kinds of jobs that come from the the articles were initially available Iraq and Afghanistan for battlefield reconnaissance, fact that we're highly educated and deeply online and without charge, few things that "'Conscious robot is not an oxymoron -- Dial'em for Mumbai.

Incremental search reuses information from previous searches to find solutions to a series of similar search problems potentially faster than is possible by solving each search problem from scratch. This is important because many AI systems have to adapt their plans continuously to changes in (their knowledge of) the world. In this article, we give an overview of incremental search, focusing on LIFELONG PLANNING A*, and outline some of its possible applications in AI.

(ICKEDS 2004). This book looks at some of the results of the synergy among AI, cognitive science, and education. Examples include virtual students whose misconceptions force students to reflect on their own knowledge, intelligent tutoring systems, and speech-recognition technology that helps students learn to read. Some of the systems described are already used in classrooms and have been evaluated; a few are still laboratory efforts. The book also addresses cultural and political issues involved in the deployment of new educational technologies.

A method for unrestricted recognition of three-dimensional objects was developed. By unrestricted, we imply that the recognition will be done independently of object position, scale, orientation, and pose against a structured background. It does not assume any preceding segmentation or allow a reasonable degree of occlusion. The method uses a hierarchy of triplet feature invariants, which are at each level defined by a learning procedure. In the feedback learning procedure, percepts are mapped on system states corresponding to manipulation parameters of the object. The method uses a learning architecture with channel information representation. This article discusses how objects can be represented. We propose a structure to deal with object and contextual properties in a transparent manner.

An adequate natural language description of developments in a real-world scene can be taken as proof of "understanding what is going on." An algorithmic system that generates natural language descriptions from video recordings of road traffic scenes can be said to "understand" its input to the extent that algorithmically generated text is acceptable to the humans judging it. A fuzzy metrictemporal Horn logic (FMTHL) provides a formalism for representing both schematic and instantiated conceptual knowledge about the depicted scene and its temporal development. The resulting conceptual representation mediates in a systematic manner between the spatiotemporal geometric descriptions extracted from video input and a module that generates natural language text. This article outlines a 30-year effort to create such cognitive vision system, indicates its current status, summarizes lessons learned along the way, and discusses open problems against this background.