To achieve trust and acceptance from people, robots that navigate complex human environments should be able to explain their behavior. In an online between-subjects study, this paper explores the impact of explanation detail on human understanding, trust, and comfort with robot navigators. It compares three conditions: no textual information, a simple action description, and a detailed explanation. Results indicate that while detailed explanations improve users' confidence in the robot's navigation ability, simpler descriptions are easier to understand. Participants who received detailed explanations, however, also indicated a better overall understanding of the robot's behavior and decision-making process. These findings highlight how varied levels of detail in explanations can build trust and comprehension.

Roughly every decade, the ACM and IEEE professional organizations have produced recommendations for the education of undergraduate computer science students. These guidelines are used worldwide by research universities, liberal arts colleges, and community colleges. For the latest 2023 revision of the curriculum, AAAI has collaborated with ACM and IEEE to integrate artificial intelligence more broadly into this new curriculum and to address the issues it raises for students, instructors, practitioners, policy makers, and the general public. This paper describes the development process and rationale that underlie the artificial intelligence components of the CS2023 curriculum, discusses the challenges in curriculum design for such a rapidly advancing field, and examines lessons learned during this three-year process.

This paper reports on a robot controller that learns and applies a cognitively-based spatial model as it travels in challenging, real-world indoor spaces. The model not only describes indoor space, but also supports robust, model-based planning. Together with the spatial model, the controller’s reasoning framework allows it to explain and defend its decisions in accessible natural language. The novel contributions of this paper are an enhanced cognitive spatial model that facilitates successful reasoning and planning, and the ability to explain navigation choices for a complex environment. Empirical evidence is provided by simulation of a commercial robot in a large, complex, realistic world.

Virtual screening based on protein-ligand docking is widely applied at the early stage of drug discovery. Scoring functions from a diverse set of existing protein-ligand docking tools, however, often poorly distinguish bioactive compounds from inactive ones. As a result, considerable effort has been devoted to the combination of multiple scoring functions for more reliable evaluation. State-of-the-art consensus scoring or ensemble learning methods assume each scoring function performs uniformly for all cases. Case-based meta-learning (CBML), the method we have developed, is fundamentally different. It identifies the best predictor for a specific new case based on its similarity to old cases and uses that method to predict rather than average the performance of all predictors. Our large-scale benchmark studies clearly indicate that CBML outperforms consensus-based scoring and significantly improves the performance of structure-based virtual screening. The CBML paradigm can be extended to other applications in bioinformatics and chemoinformatics for robust and reliable predictive modeling.

This paper introduces two adaptive paradigms that parallelize search for solutions to constraint satisfaction problems. Both are intended for any sequential solver that uses contention-oriented variable-ordering heuristics and restart strategies. Empirical results demonstrate that both paradigms improve the search performance of an underlying sequential solver, and also solve challenging problems left open after recent solver competitions.

As graphemetophoneme methods proliferate, their careful evaluation becomes increasingly important. This paper explores a variety of metrics to compare the automatic pronunciation methods of three freelyavailable graphemetophoneme packages on a large dictionary. Two metrics, presented here for the first time, rely upon a novel weighted phonemic substitution matrix constructed from substitution frequencies in a collection of trusted alternate pronunciations. These new metrics are sensitive to the degree of mutability among phonemes. An alignment tool uses this matrix to compare phoneme substitutions between pairs of pronunciations. Index Terms: graphemetophoneme, edit distance, substitution matrix, phonetic distance measures

This paper reports on a novel approach to the design and implementation of a spoken dialogue system. A human subject, or wizard, is presented with input of the sort intended for the dialogue system, and selects from among a set of pre-defined actions. The wizard has access to hypotheses generated by noisy automated speech recognition and queries a database with them using partial matching. During the ambitious study reported here, different wizards exhibited different behaviors, elicited different degrees of caller affinity for the system, and achieved different degrees of accuracy on retrieval of the requested items. Our data illustrates that wizards did not trust automated speech recognition hypotheses when they could not lead to a correct database match, and instead asked informed questions. The wealth of data and the richness of the interactions are a valuable resource with which to model expert wizard behavior.

Traditional global search heuristics to solve constraint satisfaction problems focus on properties of an individual variable that mandate early search attention. If however, one could predict crucial subproblems (the portions of a constraint satisfaction problem likely to cause each other particular difficulty) in advance, search could address them first. This paper postulates several types of crucial subproblems, and shows how local search can be harnessed to identify them before global search for a solution. A variety of heuristics and metrics are then used to guide traditional constraint heuristics with those crucial subproblems. On certain classes of structured problems, such search outperforms traditional heuristics by at least an order of magnitude in both time and space

This paper describes the Adaptive Constraint Engine (ACE), an ambitious ongoing research project to support constraint programmers, both human and machine. The program begins with substantial knowledge about constraint satisfaction. The program harnesses a cognitively-oriented architecture (FORR) to manage search heuristics and to learn new ones. ACE can transfer what it learns on simple problems to solve more difficult ones, and can readily export its knowledge to ordinary constraint solvers. It currently serves both as a learner and as a test bed for the constraint community.

As they gain expertise in problem solving, people increasingly rely on patterns and spatially oriented reasoning. This paper describes an associative visual‐pattern classifier and the automated acquisition of new, spatially oriented reasoning agents that simulate such behavior. They are incorporated into a multi‐agent game‐learning program whose architecture robustly combines agents with conflicting perspectives. When tested on three games, the visual‐pattern classifier learns meaningful patterns, and the pattern‐based, spatially oriented agents generalized from these patterns are generally correct. The accuracy of the contribution of each of the newly created agents to the decision‐making process is measured against an expert opponent, and a perceptron‐Iike algorithm is used to learn game‐specific weights for these agents. Much of the knowledge encapsulated by the new agents was previously inexpressible in the program's representation and in some cases is not readily deducible from the rules.

Rather than search exhaustively in large problem spaces, people use heuristics that entail minimal search and yet support intelligent decisions. Human performance in such spaces is robust and improves with experience. Game playing is a good example. the traditional AI approach to game playing, however, has been to build a program that plays only a single game, and plays it very well. Because exhaustive search of the game graph and minimax of the resultant values guarantees perfect play, programmed champions rely on deep, fast, efficient search. Despite their more limited, fallible memories and arguably slower processors, human masters often defeat a program whose search is incomplete. People search less, remember less, and somehow make the right choices. This article describes HOYLE, a program that learns to play specific games under the direction of a weak theory, clearly delineated prior knowledge about games in general. HOYLE differs from most game-playing programs in two ways: it is able to play any of a broad class of games according to the rules, and it improves its performance through a variety of learning paradigms. HOYLE shows that, for a class of related problems, it is possible to replace deep search with a weak theory based upon heuristically selective cache memories and a consensus about action among reliable rationales.

The Graph Theorist, GT, is a system that performs mathematical research in graph theory. From the definitions in its input knowledge base, GT constructs examples of mathematical concepts, conjectures and proves mathematical theorems about concepts, and discovers new concepts. Discovery is driven both by examples and by definitional form. The discovery processes construct a semantic net that links all of GT's concepts together. Each definition is an algebraic expression whose semantic interpretation is a stylized algorithm to generate a class of graphs correctly and completely. From a knowledge base of these concept definitions, GT is able to conjecture and prove such theorems as “The set of acyclic, connected graphs is precisely the set of trees” and “There is no odd‐regular graph on an odd number of vertices.” GT explores new concepts either to develop an area of knowledge or to link a newly acquired concept into a pre‐existing knowledge base. New concepts arise from the specialization of an existing concept, the generalization of an existing concept, and the merger of two or more existing concepts. From an initial knowledge base containing only the definition of “graph,” GT discovers such concepts as acyclic graphs, connected graphs, and bipartite graphs.

The Graph Theorist (GT) is a system intended to perform mathematical research in graph theory. This paper focuses upon GT's ability to discover new mathematical concepts by varying the definitions in its input knowledge base. Each new definition is a correct and complete generator for a class of graphs. the new concepts arise from the specialization of an existing concept, the generalization of an existing concept, and the merger of two or more existing concepts. Discovery is driven both by examples (specific graphs) and by definitional form (algorithms). GT explores new concepts either to develop an area of knowledge or to link a newly-acquired concept into a pre-existing knowledge base. From an initial knowledge base containing only the definition of “graph,” GT discovers such concepts as acyclic graphs, connected graphs and bipartite graphs. Given an input concept, such as “star,” GT discovers “trees” while searching for the appropriate links to integrate star into its knowledge base. the discovery processes construct a semantic net linking frames for all of GT's concepts together.