An accepted belief is a proposition considered likely enough by an agent, to be inferred from as if it were true. This paper bridges the gap between probabilistic and logical representations of accepted beliefs. To this end, natural properties of relations on propositions, describing relative strength of belief are augmented with some conditions ensuring that accepted beliefs form a deductively closed set. This requirement turns out to be very restrictive. In particular, it is shown that the sets of accepted belief of an agent can always be derived from a family of possibility rankings of states. An agent accepts a proposition in a given context if this proposition is considered more possible than its negation in this context, for all possibility rankings in the family. These results are closely connected to the non-monotonic 'preferential' inference system of Kraus, Lehmann and Magidor and the so-called plausibility functions of Friedman and Halpern. The extent to which probability theory is compatible with acceptance relations is laid bare. A solution to the lottery paradox, which is considered as a major impediment to the use of non-monotonic inference is proposed using a special kind of probabilities (called lexicographic, or big-stepped). The setting of acceptance relations also proposes another way of approaching the theory of belief change after the works of Gärdenfors and colleagues. Our view considers the acceptance relation as a primitive object from which belief sets are derived in various contexts.

The classical integrate-and-fire neural network has been studied both in the simpler zero-width [1] action potential and the more involved finite-width [2]cases. In these works every neuron integrates the current coming from neighboring neurons and when the threshold for firing is exceeded, it too sends off an action potential to its neighbors. Hopfield and Herz had found that there is a simple relation between the contributions A from the neighbors and an external current I, with the time period of the firing of the network when phase-lock is established: τ (1 A)/I (1) It has been shown [2] that there is some modification of this formula when the action potential is not exactly a delta function but is spread over time, which is, of course, a more realistic assumption, in biological as well as physical contexts. In view of the recent great interest in quantum computing we think it is worthwhile to investigate the changes if any that would result from converting such networks to a quantum model. As a first step, we have here tried to see the changes when the action potential acts like a quantum radiation to the neighbors, instead of a current, and the firing of the neuron is replaced by induced radiation from it to the neighbors.

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.

The 2003International Conference on Automated Planning and Scheduling (ICAPS-03) was held 9 to 13 June 2003 in Trento, Italy. It was chaired by Enrico Giunchiglia (University of Genova), Nicola Muscettola (NASA Ames), and Dana Nau (University of Maryland). Piergiorgio Bertoli and Marco Benedetti (both from ITC-IRST) were the local chair and the workshop-tutorial coordination chair, respectively.

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.

(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.

"This book will appeal to technophiles, interdisciplinarians, and broad thinkers of all

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.

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.

INTF-1 technical search team as it arrived on site and conducted a reconnaissance of the collapsed building. The scientists also got to observe the process by which the search team manager decided whether to use traditional tools, such as acoustic sensors or search cameras, or a robot (figure 2). The robots were deployed the National Science Foundation's Each scientist went into with rescue workers as they went the rubble at least two times and witnessed through a complete deploy-searchcleanup the deployment of each brand Search and Rescue (CRASAR) at cycle or "evolution." Embedding under such realistic conditions permitted the participants to gain an ethnographic understanding of rescue robotics, direct access to one type of collapse site, and an introduction to standard operating procedures such as decontaminating the robots that might impact the design of better robots and software. The scientists brought sleeping bags and slept during the single four-hour rest cycle allotted to the rescue workers.