This article discusses five years of experience using three international mobile robot competitions as the foundation for educational projects in undergraduate and graduate computer science courses. The three competitions -- (1) AAAI Mobile Robot, (2) AUVS Unmanned Ground Robotics, and (3) IJCAI RoboCup -- were used in different years for an introductory undergraduate robotics course, an advanced graduate robotics course, and an undergraduate practicum course. Based on these experiences, a strategy is presented for incorporating competitions into courses in such a way as to foster intellectual maturation as well as learn lessons in organizing courses and fielding teams. The article also provides a classification of the major robot competitions and discusses the relative merits of each for educational projects, including the expected course level of computer science students, equipment needed, and costs.

This he reinforcement learning problem microcosm; how can we build then tied back together in a unified history is an early example of a series an agent that can plan, learn, perceive, way. Innovations such as backup diagrams, of detailed literature reviews, found at and act in a complex world? There's a which decorate the book cover, the end of each chapter, which could great new book on the market that help convey the power and excitement alone justify the expense of purchasing lays out the conceptual and algorithmic behind reinforcement learning the book.

The robot exhibition had a very successful 1998. At the conference, we had 11 robot demonstrations (including three multirobot demos), 5 oral presentations, and an additional 5 video or poster submissions. The exhibition also included a published video proceedings for the first time. One of the most interesting features of the exhibition was the variety of capabilities shown. From a mechanical point of view, indoor wheeled robots were, as usual, the most common form of robot, but the exhibit also featured several outdoor wheeled robots, several legged robots, two humanoids, a snake, and a plant. From a software perspective, the exhibit featured general-purpose robot-control software, vision, teleoperation, language learning, teamwork and expression of emotion. A significant number of entries addressed the important, emerging research area of robot-human interaction, both for entertainment purposes and ease of use.

Sony has provided a robot platform for research and development in physical agents, namely, fully autonomous legged robots. In this article, we describe our work using Sony's legged robots to participate at the RoboCup-98 legged robot demonstration and competition. Robotic soccer represents a challenging environment for research in systems with multiple robots that need to achieve concrete objectives, particularly in the presence of an adversary. Furthermore, RoboCup offers an excellent opportunity for robot entertainment. We introduce the RoboCup context and briefly present Sony's legged robot. We developed a vision-based navigation and a Bayesian localization algorithm. Team strategy is achieved through predefined behaviors and learning by instruction.

Robotic soccer is an ideal task to demonstrate new techniques and explore new problems. Moreover, problems and solutions can easily be communicated because soccer is a well-known game. Our intention in building a robotic soccer team and participating in RoboCup-98 was, first, to demonstrate the usefulness of the self-localization methods we have developed. Second, we wanted to show that playing soccer based on an explicit world model is much more effective than other methods. Third, we intended to explore the problem of building and maintaining a global team world model. As has been demonstrated by the performance of our team, we were successful with the first two points. Moreover, robotic soccer gave us the opportunity to study problems in distributed, cooperative sensing.

Although our previous and processes the images, giving the positions team had accurate navigation, it was not easily of each robot and the ball. This information is interruptible, which is necessary for operating sent to an off-board controller and distributed in a highly dynamic environment. The final design includes a battery of inherent mechanical inaccuracies and module supplying three independent unforeseen interventions from other agents. It also includes a single board RoboCup competition in Paris (Stone, Veloso, containing all the required electronic circuitry and Riley 1999; Kitano et al. 1997). These improvements by an array of four infrared sensors, which include a robust low-level control algorithm, which handles a moving target with is enabled or disabled by the software control.

We view robotic soccer as an example of a periodic team synchronization (PTS) domain. By perceiving the with no adverse effects on the achievement world, each fully distributed agent builds a of G. Then, based can be thought of as times at which the on a complex set of behaviors, it chooses an team is "offline." In general (that is, when the agents are Although acting autonomously, each agent "online"), the domain is dynamic and real time, contributes to the overall team's goal. Agents receive sensory p at time t.

The Robot World Cup Soccer Games and Conferences (RoboCup) are a series of competitions and events designed to promote the full integration of AI and robotics research. Following the first RoboCup, held in Nagoya, Japan, in 1997, RoboCup-98 was held in Paris from 2-9 July, overlapping with the real World Cup soccer competition. RoboCup-98 included competitions in three leagues: (1) the simulation league, (2) the real robot small-size league, and (3) the real robot middle-size league. Champion teams were cmunited-98 in both the simulation and the real robot small-size leagues and cs-freiburg (Freiburg, Germany) in the real robot middle-size league. RoboCup-98 also included a Scientific Challenge Award, which was given to three research groups for their simultaneous development of fully automatic commentator systems for the RoboCup simulator league. Over 15,000 spectators watched the games, and 120 international media provided worldwide coverage of the competition.

First, I would The editorial board members will play an active role in like to welcome B. Chandrasekaran, guiding the magazine, monitoring progress across the field of The Ohio and assuring that the magazine has timely, high-quality State University, as the articles on significant new developments. I expect the editorial new book review editor, board to have a considerable impact on the magazine, and Robert Morris, of and I am very grateful to the board members for NASA Ames Research Center, accepting this responsibility. I know that they will do an Finally, to expedite the processing of submissions, AI outstanding job, and I urge the AI community to actively Magazine will now accept submissions in electronic form. Full submission guidelines are available on the AI Magazine Chandrasekaran has prepared an editorial, appearing in home page, www.aaai.org/Magazine. I look forward to your this issue, presenting his vision for the book review section.

A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem being learnt, yet small enough to ensure reliable generalization from reasonably-sized training sets. Typically such bias is supplied by hand through the skill and insights of experts. In this paper a model for automatically learning bias is investigated. The central assumption of the model is that the learner is embedded within an environment of related learning tasks. Within such an environment the learner can sample from multiple tasks, and hence it can search for a hypothesis space that contains good solutions to many of the problems in the environment. Under certain restrictions on the set of all hypothesis spaces available to the learner, we show that a hypothesis space that performs well on a sufficiently large number of training tasks will also perform well when learning novel tasks in the same environment. Explicit bounds are also derived demonstrating that learning multiple tasks within an environment of related tasks can potentially give much better generalization than learning a single task.