The SNePS knowledge representation, reasoning, and acting system has several features that facilitate metacognition in SNePS-based agents. The most prominent is the fact that propositions are represented in SNePS as terms rather than as sentences, so that propositions can occur as argu- ments of propositions and other expressions without leaving first-order logic. The SNePS acting subsystem is integrated with the SNePS reasoning subsystem in such a way that: there are acts that affect what an agent believes; there are acts that specify knowledge-contingent acts and lack-of-knowledge acts; there are policies that serve as "daemons," triggering acts when certain propositions are believed or wondered about.

The American Association for Artificial Intelligence was pleased to present the AAAI 2006 Fall Symposium Series, held Friday through Sunday, October 13-15, at the Hyatt Regency Crystal City in Washington, DC. The titles were (1) Aurally Informed Performance: Integrating Ma- chine Listening and Auditory Presentation in Robotic Systems; (2) Capturing and Using Patterns for Evidence Detection; (3) Developmental Systems; (4) Integrating Reasoning into Everyday Applications; (5) Interaction and Emergent Phenomena in Societies of Agents; (6) Semantic Web for Collaborative Knowledge Acquisition; and (7) Spacecraft Autonomy: Using AI to Expand Human Space Exploration.

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.

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.

Imagine an Internet-scale knowledge system where people and intelligent agents can collaborate on solving complex problems in business, engineering, science, medicine, and other endeavors. Its resources include semantically tagged websites, wikis, and blogs, as well as social networks, vertical search engines, and a vast array of web services from business processes to AI planners and domain models. Research prototypes of decentralized knowledge systems have been demonstrated for years, but now, thanks to the web and Moore's law, they appear ready for prime time. This article introduces the architectural concepts for incrementally growing an Internet-scale knowledge system and illustrates them with scenarios drawn from e-commerce, e-science, and e-life.

But, I argue, the consequences are actually far worse: because of the very nature of intelligence, the centrifugal force on the field could thwart the very mission that drives it by leaving no place for the study of the interaction and synergy of the many coupled components that individually in isolation are not intelligent but, when working together, yield intelligent behavior. To raise awareness of the need to reintegrate AI, I contemplate the role of systems integration and the value and challenge of architecture. Illustrating some reason for optimism, I briefly outline some promising developments in large projects that are helping to increase the centripetal force on AI. I conclude by discussing how it is critical that the field focus its attention back on its original mission, led by a heavy dose of integrated systems thinking and grand challenges, and why after its first quarter century, AAAI is more essential than ever.

The Dartmouth College Artificial Intelligence Conference: The Next 50 Years (AI@50) took place July 13-15, 2006. The conference had three objectives: to celebrate the Dartmouth Summer Research Project, which occurred in 1956; to assess how far AI has progressed; and to project where AI is going or should be going. AI@50 was generously funded by the office of the Dean of Faculty and the office of the Provost at Dartmouth College, by DARPA, and by some private donors.

This article is my personal account on the work at Stanford on Stanley, the winning robot in the DARPA Grand Challenge. Between July 2004 and October 2005, my then-postdoc Michael Montemerlo and I led a team of students, engineers, and professionals with the single vision of claiming one of the most prestigious trophies in the field of robotics: the DARPA Grand Challenge (DARPA 2004). The Grand Challenge, organized by the U.S. government, was unprecedented in the nation's history. Instead, this is my personal story of leading the Stanford Racing Team.

The Twenty-First National Conference on Artificial Intelligence and the Nineteenth Innovative Applications of Artificial Intelligence Conference commemorated fifty years of artificial intelligence research in Boston, Massachusetts this past July.

Dynamic scripting is a reinforcement learning approach to adaptive game AI that learns, during gameplay, which game tactics an opponent should select to play effectively. We introduce the evolutionary state-based tactics generator (ESTG), which uses an evolutionary algorithm to generate tactics automatically. Experimental results show that ESTG improves dynamic scripting's performance in a real-time strategy game. We conclude that high-quality domain knowledge can be automatically generated for strong adaptive game AI opponents.