Giving robots the ability to operate in the real world has been, and continues to be, one of the most difficult tasks in AI research. Since 1987, researchers at Carnegie Mellon University have been investigating one such task. Their research has been focused on using adaptive, vision-based systems to increase the driving performance of the Navlab line of on-road mobile robots. This research has led to the development of a neural network system that can learn to drive on many road types simply by watching a human teacher. This article describes the evolution of this system from a research project in machine learning to a robust driving system capable of executing tactical driving maneuvers such as lane changing and intersection navigation.

An important problem in geometric reasoning is to find the configuration of a collection of geometric bodies so as to satisfy a set of given constraints. Recently, it has been suggested that this problem can be solved efficiently by symbolically reasoning about geometry. This approach, called degrees of freedom analysis, employs a set of specialized routines called plan fragments that specify how to change the configuration of a set of bodies to satisfy a new constraint while preserving existing constraints. A potential drawback, which limits the scalability of this approach, is concerned with the difficulty of writing plan fragments. In this paper we address this limitation by showing how these plan fragments can be automatically synthesized using first principles about geometric bodies, actions, and topology.

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.

Although most scheduling problems are NP-hard, domain specific techniques perform well in practice but are quite expensive to construct. In adaptive problem-solving solving, domain specific knowledge is acquired automatically for a general problem solver with a flexible control architecture. In this approach, a learning system explores a space of possible heuristic methods for one well-suited to the eccentricities of the given domain and problem distribution. In this article, we discuss an application of the approach to scheduling satellite communications. Using problem distributions based on actual mission requirements, our approach identifies strategies that not only decrease the amount of CPU time required to produce schedules, but also increase the percentage of problems that are solvable within computational resource limitations.

The University of Chicago's robot, CHIP, is part of the Animate Agent Project, aimed at understanding the software architecture and knowledge representations needed to build a general-purpose robotic assistant. CHIP's strategy for the Office Cleanup event of the 1995 Robot Competition and Exhibition was to scan an entire area systematically and, as collectible objects were identified, pick them up and deposit them in the nearest appropriate receptacle. This article describes CHIP and its various systems and the ways in which these elements combined to produce an effective entry to the robot competition.

Woody was one of the founders of AI, making early contributions in pattern recognition and automated reasoning. He continued to make significant contributions to AI throughout his long career. His legacy consists not only of his scientific work but also of several generations of scientists who learned from Woody the joy of scientific research and the way to go about it. Woody's enthusiasm, his perpetual sense of optimism, his can-do attitude, and his deep sense of duty to humanity offered those who knew him the hope and comfort that truly good and great men do exist.

The 1995 Robot Competition and Exhibition was held in Montreal, Canada, in conjunction with the 1995 International Joint Conference on Artificial Intelligence. The competition was designed to demonstrate state-of-the-art autonomous mobile robots, highlighting such tasks as goal-directed navigation, feature detection, object recognition, identification, and physical manipulation as well as effective human-robot communication. The competition consisted of two separate events: (1) Office Delivery and (2) Office Cleanup. The exhibition also consisted of two events: (1) demonstrations of robotics research that was not related to the contest and (2) robotics focused on aiding people who are mobility impaired.

The goal of this workshop was which was held in June 1995 in San istributed artificial intelligence the cooperative solution of "making connections," trying to better Francisco. The DAI Workshop problems in multiagent intelligent understand the connections received financial support from the systems with both computational between DAI and related fields (for American Association for Artificial and human agents. The central problem example, computer-supported cooperative Intelligence as well as the Boeing in DAI is how to achieve coordinated work, group decision support Company. Registration materials for the Thirteenth National Conference on Artificial Intelligence (AAAI-96), the Eighth Innovative Applications of Artificial Intelligence Conference (IAAI-96), and the Second International Conference on Knowledge Discovery and Data Mining (KDD-96) are now available from the AAAI office at ncai@aaai.org Copies of the AAAI-96 registration brochure are being mailed to all AAAI members.

The goal of the Workshop on Adaptation and Learning in Multiagent Systems was to focus on research that addresses unique requirements for agents learning and adapting to work in the presence of other agents. Recognizing the applicability and limitations of current machine-learning research as applied to multiagent problems and developing new learning and adaptation mechanisms particularly targeted to this class of problems were the primary research issues that we wanted the authors to address. This article outlines the presentations that were made at the workshop and the success of the workshop in meeting the established goals. Issues that need to be better understood are also presented.

In 1992, the seemingly unbeatable World Checker Champion Marion Tinsley defended his title against the computer program CHINOOK. After an intense, tightly contested match, Tinsley fought back from behind to win the match by scoring four wins to CHINOOK's two, with 33 draws. This match was the first time in history that a human world champion defended his title against a computer. This article reports on the progress of the checkers (8 3 8 draughts) program CHINOOK since 1992. Two years of research and development on the program culminated in a rematch with Tinsley in August 1994. In this match, after six games (all draws), Tinsley withdrew from the match and relinquished the world championship title to CHINOOK,citing health concerns. CHINOOK has since defended its title in two subsequent matches. It is the first time in history that a computer has won a human-world championship.