The construction of computer systems that are intelligent, collaborative problem-solving partners is an important goal for both the science of AI and its application. From the scientific perspective, the development of theories and mechanisms to enable building collaborative systems presents exciting research challenges across AI subfields. From the applications perspective, the capability to collaborate with users and other systems is essential if large-scale information systems of the future are to assist users in finding the information they need and solving the problems they have. In this address, it is argued that collaboration must be designed into systems from the start; it cannot be patched on. Key features of collaborative activity are described, the scientific base provided by recent AI research is discussed, and several of the research challenges posed by collaboration are presented. It is further argued that research on, and the development of, collaborative systems should itself be a collaborative endeavor -- within AI, across subfields of computer science, and with researchers in other fields.

The Association for the Advancement of Artificial Intelligence held its 1996 Spring Symposia Series on March 27 to 29 at Stanford University. This article contains summaries of the eight symposia that were conducted: (1) Acquisition, Learning, and Demonstration: Automating Tasks for Users; (2) Adaptation, Coevolution, and Learning in Multiagent Systems; (3) Artificial Intelligence in Medicine: Applications of Current Technologies; (4) Cognitive and Computational Models of Spatial Representation; (5) Computational Implicature: Computational Approaches to Interpreting and Generating Conversational Implicature; (6) Computational Issues in Learning Models of Dynamic Systems; (7) Machine Learning in Information Access; and (8) Planning with Incomplete Information for Robot Problems.

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 presents new experimental evidence against the utility of Occam's razor. A~systematic procedure is presented for post-processing decision trees produced by C4.5. This procedure was derived by rejecting Occam's razor and instead attending to the assumption that similar objects are likely to belong to the same class. It increases a decision tree's complexity without altering the performance of that tree on the training data from which it is inferred. The resulting more complex decision trees are demonstrated to have, on average, for a variety of common learning tasks, higher predictive accuracy than the less complex original decision trees. This result raises considerable doubt about the utility of Occam's razor as it is commonly applied in modern machine learning.

Speedup learning seeks to improve the computational efficiency of problem solving with experience. In this paper, we develop a formal framework for learning efficient problem solving from random problems and their solutions. We apply this framework to two different representations of learned knowledge, namely control rules and macro-operators, and prove theorems that identify sufficient conditions for learning in each representation. Our proofs are constructive in that they are accompanied with learning algorithms. Our framework captures both empirical and explanation-based speedup learning in a unified fashion. We illustrate our framework with implementations in two domains: symbolic integration and Eight Puzzle. This work integrates many strands of experimental and theoretical work in machine learning, including empirical learning of control rules, macro-operator learning, Explanation-Based Learning (EBL), and Probably Approximately Correct (PAC) 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.

Inductive theorem provers often diverge. This paper describes a simple critic, a computer program which monitors the construction of inductive proofs attempting to identify diverging proof attempts. Divergence is recognized by means of a ``difference matching'' procedure. The critic then proposes lemmas and generalizations which ``ripple'' these differences away so that the proof can go through without divergence. The critic enables the theorem prover Spike to prove many theorems completely automatically from the definitions alone.

Termination of logic programs with negated body atoms (here called general logic programs) is an important topic. One reason is that many computational mechanisms used to process negated atoms, like Clark's negation as failure and Chan's constructive negation, are based on termination conditions. This paper introduces a methodology for proving termination of general logic programs w.r.t. the Prolog selection rule. The idea is to distinguish parts of the program depending on whether or not their termination depends on the selection rule. To this end, the notions of low-, weakly up-, and up-acceptable program are introduced. We use these notions to develop a methodology for proving termination of general logic programs, and show how interesting problems in non-monotonic reasoning can be formalized and implemented by means of terminating general logic programs.

LOLA's entry in the Office Delivery event of the 1995 Robot Competition and Exhibition, held in conjunction with the Fourteenth International Joint Conference on Artificial Intelligence, was the culmination of a three-month design and implementation period for an indoor navigation system for topological maps. This article describes the major components of the robot's navigation architecture. It also summarizes the experiences and lessons learned from the competition.

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.