In this article, we describe the milestone of our research efforts in our work for the RoboCup middle-size league competition. Reinforcement learning in applying it to real robot applications; we then give our method of coping with these has recently been receiving increased attention issues in the context of RoboCup. Finally, we as a method for robot learning with little or no show our system and the experimental results a priori knowledge and a higher capability for of RoboCup-97. The robot senses the current state First, we follow the explanation of Q-learning of the environment and selects an action. For a more thorough treatment, Based on the state and the action, the environment see Watkins and Dayan (1992).

Please send papers to: AAAI-99--American Association for Artificial Intelligence 445 Burgess Drive Menlo Park, CA 94025-3442 Registration and call clarification inquiries (only) may be sent to ncai@aaai.org.

The first Hors d'Oeuvres, Anyone? event at the Association for the Advancement of Artificial Intelligence Mobile Robot Competition was held in 1997. Five teams entered their robotic waiters into the contest. After a preliminary round to judge the safety of the robots, the robots served conference attendees at the opening reception of the Fourteenth National Conference on Artificial Intelligence.

Points were awarded for picking up objects of a specific type (ball, cube, or moving squiggle ball) and specific color (figure 2). Penalty points were deducted for he Mars Pathfinder Mission, featuring for the Find-Life-on-Mars event. The general colliding with rocks, placing an object in the concept was to have the robots locate, collect, wrong door, and traveling within the danger and deliver a variety of "life forms," zones. We also specified penalties for modifying including both stationary and moving objects. the lander, although no group took advantage Technically, the event was designed to highlight of this option. No other modification of mobile manipulation, object recognition, the environment was allowed.

In July 1997, the Sixth Annual Association for the Advancement of Artificial Intelligence (AAAI) Mobile Robot Competition and Exhibition was held. The competition consisted of four new events: (1) Find Life on Mars; (2) Find the Remote; (3) Home Vacuum; and (4) Hors d'Oeuvres, Anyone? The robot exhibition was the largest in AAAI history. This article presents the history, motivation, and contributions for the event.

To remain competitive, enterprises must become increasingly agile and integrated across their functions. Enterprise models play a critical role in this integration, enabling better designs for enterprises, analysis of their performance, and management of their operations. This article motivates the need for enterprise models and introduces the concepts of generic and deductive enterprise models. It reviews research to date on enterprise modeling and considers in detail the Toronto virtual enterprise effort at the University of Toronto.

Details about program does not provide any scholarship information, please contact AAAI at these programs will also be mailed to funds, and is designed for local fss@aaai.org

"environment" is a key principle of dynamic, crowded environment. The robots were "costumed" through reception area, recognition of humans, The guests Although all our competitors chose voicesynthesis one foot tall. A number of people were impressed were programmed to switch behavioral other (see figure). Robotics has since used these techniques not acknowledging humans. Credits: Directed by Barry Brian Werger. of the real world would result in numerous from walls, robots, and people; rotation for Seth Landsman, Dan Griffin, and Andy becoming involved with the other social response to "humanlike" sonar signatures.

We applied mobile computing to community support and explored mobile computing with a large number of terminals. This article reports on the Second International Conference on Multiagent Systems (ICMAS'96) Mobile Assistant Project that was conducted at an actual international conference for multiagent systems using 100 personal digital assistants (PDAs) and cellular telephones. We supported three types of service: (1) communication services such as e-mail and net news; (2) information services such as conference, personal, and tourist information; and (3) community support services such as forum and meeting arrangements. Participants showed a deep interest in mobile computing for community support.

A computer program that uses AI planning techniques is now the world champion computer program in the game of Contract Bridge. As reported in The New York Times and The Washington Post, this program -- a new version of Great Game Products' BRIDGE BARON program -- won the Baron Barclay World Bridge Computer Challenge, an international competition hosted in July 1997 by the American Contract Bridge League. It is well known that the game tree search techniques used in computer programs for games such as Chess and Checkers work differently from how humans think about such games. This article gives an overview of the planning techniques that we have incorporated into the BRIDGE BARON and discusses what the program's victory signifies for research on AI planning and game playing.