In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-based image classifier in front of a reinforcement learning algorithm. The classifier partitions the visual space according to the presence or absence of few highly informative local descriptors that are incrementally selected in a sequence of attempts to remove perceptual aliasing. We also address the problem of fighting overfitting in such a greedy algorithm. Finally, we show how high-level visual features can be generated when the power of local descriptors is insufficient for completely disambiguating the aliased states. This is done by building a hierarchy of composite features that consist of recursive spatial combinations of visual features. We demonstrate the efficacy of our algorithms by solving three visual navigation tasks and a visual version of the classical ``Car on the Hill'' control problem.

A large part of the credit for this can be attributed squarely to the invention and deployment of powerful reachability heuristics. Most, if not all, modern reachability heuristics are based on a remarkably extensible data structure called the planning graph, which made its debut as a bit player in the success of GraphPlan, but quickly grew in prominence to occupy the center stage. Planning graphs are a cheap means to obtain informative look-ahead heuristics for search and have become ubiquitous in state-of-the-art heuristic search planners. We present the foundations of planning graph heuristics in classical planning and explain how their flexibility lets them adapt to more expressive scenarios that consider action costs, goal utility, numeric resources, time, and uncertainty.

Recent years have seen a resurgence of interest in the use of metacognition in intelligent systems. This article is part of a small section meant to give interested researchers an overview and sampling of the kinds of work currently being pursued in this broad area. The current article offers a review of recent research in two main topic areas: the monitoring and control of reasoning (metareasoning) and the monitoring and control of learning (metalearning).

The Workshop program of the Twenty-First Conference on Artificial Intelligence was held July 16-17, 2006 in Boston, Massachusetts. The program was chaired by Joyce Chai and Keith Decker. The titles of the 17 workshops were AIDriven Technologies for Service-Oriented Computing; Auction Mechanisms for Robot Coordination; Cognitive Modeling and Agent-Based Social Simulations, Cognitive Robotics; Computational Aesthetics: Artificial Intelligence Approaches to Beauty and Happiness; Educational Data Mining; Evaluation Methods for Machine Learning; Event Extraction and Synthesis; Heuristic Search, Memory- Based Heuristics, and Their Applications; Human Implications of Human-Robot Interaction; Intelligent Techniques in Web Personalization; Learning for Search; Modeling and Retrieval of Context; Modeling Others from Observations; and Statistical and Empirical Approaches for Spoken Dialogue Systems.

Sabater described current research in the area, presenting some of the current research lines and the shortcomings of present approaches. He also outlined some of the topics in which information-fusion and aggregation operators can play a role. The conference papers were published in Springer Verlag's Lecture Notes in Artificial Intelligence series (volume 3885). Further information on the series is available at mdai.cat. The next MDAI conference will be held August 16-18, 2007, in Kitakyushu, Japan.

Accepted papers will be allocated six (6) pages in the conference proceedings.

This article introduces Pyro, an open-source Python robotics toolkit for exploring topics in AI and robotics. We present key abstractions that allow Pyro controllers to run unchanged on a variety of real and simulated robots. We demonstrate Pyro's use in a set of curricular modules. We then describe how Pyro can provide a smooth transition for the student from symbolic agents to real-world robots, which significantly reduces the cost of learning to use robots. Finally we show how Pyro has been successfully integrated into existing AI and robotics courses.

The Representations for Multimodal Generation Workshop was held on April 23-25, 2005, at Reykjavik University, Reykjavik, Iceland. The overall goal of this workshop is to further the state of research on multimodal generation by enabling (and getting) people in the field to work together on building systems capable of real-time face-to-face dialog with people. This report summarizes the activities and progress of that meeting.

Utrecht is more than 1,300 years old and located in the center of the Netherlands, about 40 minutes by train from Amsterdam. School (EASSS 2005) for about 120 students, which was organized by Europe's coordination network for agent systems (AgentLink) and was as successful as previous summer schools in Utrecht, Saarbruecken, Prague, Barcelona, Bologna, and Liverpool. Overall, in the theory and practice of AAMAS 2005 had 778 academic and autonomous agents and multiagent industrial participants from 44 countries systems. AAMAS 2005 is the fourth on six continents. The main room of this can with some justification AAMAS 2005 was held on July building, in which the Treaty of claim to be one of the most active.

Robotics is a remarkable domain that may be successfully employed in the classroom both to motivate students to tackle hard AI topics and to provide students experience applying AI representations and algorithms to real-world problems. This article uses two example robotics problems to illustrate these themes. We show how the robot obstacle-detection problem can motivate learning neural networks and Bayesian networks. We also show how the robot-localization problem can motivate learning how to build complete solutions based on particle filtering. Since these lessons can be replicated on many low-cost robot platforms they are accessible to a broad population of AI students. We hope that by outlining our educational exercises and providing pointers to additional resources we can help reduce the effort expended by other educators. We believe that expanding handson active learning to additional AI classrooms provides value both to the students and to the future of the field itself.