The RoboCup Rescue Physical Agent League Competition was held in the summer of 2001 in conjunction with the AAAI Mobile Robot Competition Urban Search and Rescue event, eerily preceding the September 11 World Trade Center (WTC) disaster. Four teams responded to the WTC disaster through the auspices of the Center for Robot-Assisted Search and Rescue (CRASAR), directed by John Blitch. The four teams were Foster- Miller and iRobot (both robot manufacturers from the Boston area), the United States Navy's Space Warfare Center (SPAWAR) group from San Diego, and the University of South Florida (USF). Blitch, through his position as program manager for the Defense Advanced Research Projects Agency (DARPA) Tactical Mobile Robots Program, was a supporter of the competition; he also served as a member of the rules committee and a judge. USF participated by chairing the rules committee, judging, assisting with the logistics, providing commentary, and demonstrating tethered and wireless robots whenever entrants had to skip around during the competition. Based on our experiences and history, we were asked to comment on the validity of the competition. The CRASAR collective experience suggests that most of the basic rules of the competition matched reality because the rules accurately reflected deployment scenarios, but the National Institute of Standards and Technology (NIST) Standard Test Course, and hardware or software approaches forwarded by competitors in last summer's event, missed the mark. This article briefly reviews the types of robots and missions used by CRASAR at the WTC site, then discusses the robotassisted search and rescue effort in terms of lessons for the competition.

"Neats and scruffies alike were mesmerized by the animal-like responses of the robots demonstrated there," says Bonasso. "At the end of "This won't be a slick, polished competition. Over the AAAI Mobile Robot Competition and Exhibition years, the event and AI Magazine have served as was born. The event has endured to a venue for this and several other intellectual become the oldest AIcentric robotics competition debates, including sensing versus modeling, in the world. As we near the end of our color-based versus shape-based object recognition, first decade, it seems worthwhile to reflect on and reactive control versus symbolic what the origins of the event were, how it has planning for robot navigation (Balch et al. evolved, and where it is headed. The contest immediately took on two important but apparently conflicting roles: First, it provided a target for research in AI and robotics; in Pete Bonasso's words, the event was cast "in the spirit of trying to develop as animate, responsive, and intelligent robot behavior as possible" (Dean and Bonasso 1993).

Serving hors d'oeuvres is not as easy as it might For the fifth five entries took on the challenge of devices were connected to both robots. Mannequins creating service robots who can offer hors were mounted on top of each robot to d'oeuvres to attendees of the robot exhibition. The robots communicated area, find and stop at people to offer food and with each other through a local area network interact with them, detect when more food is on wireless network cards on their laptop computers. For example, Ron Nucci from expected responses. The robot had voice-recognition guest, and serves him/her.

The search and rescue efforts involving structural joint rules committee from RoboCup and collapse and other urban environments (Fire AAAI brought two communities together to 1993). The main task of USAR is to recover live develop the rules and scoring method. Robots involved with USAR must were four registered teams in the competition: identify victims and send back the locations to (1) Sharif University, (2) Swarthmore College, trained medical rescue personnel for removal (3) Utah State University, and (4) the University of the victims from the collapsed area. Additionally, several teams Robot Rescue League rules, designed by the exhibited their robots in the rescue arena, rules committee, keep the USAR task in focus including the University of South Florida and by addressing several issues that arise in real the University of Minnesota. This article discusses USAR situations, such as the time to transport the 2001 Robot Rescue event: the and set up the robot; the number of personnel course, the rules, the research approaches of required to run the robot; and, most importantly, the participants, and the final scores.

A short summary of each robot demonstrates the variety in form and function among the exhibitions. Programming a robot is often a complex and Intelligence (AAAI) Mobile Robot involved task. By allowing the robot to learn and wide variety in behavior and form, the robots practice behaviors at run time, Darrin Bentivegna in the exhibition created a sense of the broad aims to create robots that can learn range of function in the robotic community. The exhibition has involving air hockey against a humanoid provided past AI researchers with new perspectives robot. After a human has specified some primitives and ideas.

Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a dialogue policy, which addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We report on the design, construction and empirical evaluation of NJFun, an experimental spoken dialogue system that provides users with access to information about fun things to do in New Jersey. Our results show that by optimizing its performance via reinforcement learning, NJFun measurably improves system performance.

Fusions are a simple way of combining logics. For normal modal logics, fusions have been investigated in detail. In particular, it is known that, under certain conditions, decidability transfers from the component logics to their fusion. Though description logics are closely related to modal logics, they are not necessarily normal. In addition, ABox reasoning in description logics is not covered by the results from modal logics. In this paper, we extend the decidability transfer results from normal modal logics to a large class of description logics. To cover different description logics in a uniform way, we introduce abstract description systems, which can be seen as a common generalization of description and modal logics, and show the transfer results in this general setting.

The conventional wisdom is that backprop nets with excess hidden units generalize poorly. We show that nets with excess capacity generalize well when trained with backprop and early stopping. Experiments suggest tworeasons for this: 1) Overfitting can vary significantly in different regions of the model. Excess capacity allows better fit to regions of high non-linearity, and backprop often avoids overfitting the regions of low non-linearity.

Our algorithm exploitsthe special structure of the sum of squared error measure in Equation (1); hence, the other objective functions are outside the scope of this paper.

Belief propagation (BP) was only supposed to work for treelike networks but works surprisingly well in many applications involving networks with loops, including turbo codes. However, there has been little understanding of the algorithm or the nature of the solutions it finds for general graphs. We show that BP can only converge to a stationary point of an approximate free energy, known as the Bethe free energy in statistical physics.This result characterizes BP fixed-points and makes connections with variational approaches to approximate inference. More importantly, our analysis lets us build on the progress made in statistical physics since Bethe's approximation was introduced in 1935. Kikuchi and others have shown how to construct more accurate freeenergy approximations, of which Bethe's approximation is the simplest.