Showing papers in "Ai Magazine in 2001"
TL;DR: This book provides a comprehensive overview of the multiagent systems and distributed AI field and is an excellent collection of closely related papers that provides a wonderful introduction to the field.
Abstract: As the title indicates, Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence covers the design and development of multiagent and distributed AI systems. The purpose of this book is to provide a comprehensive overview of the field. It is an excellent collection of closely related papers that provides a wonderful introduction to multiagent systems and distributed AI.
999 citations
TL;DR: This book is an introduction to support vector machines and related kernel methods in supervised learning, whose task is to estimate an input-output functional relationship from a training set of examples.
Abstract: This book is an introduction to support vector machines and related kernel methods in supervised learning, whose task is to estimate an input-output functional relationship from a training set of examples. A learning problem is referred to as classification if its output take discrete values in a set of possible categories and regression if it has continuous real-valued output.
689 citations
TL;DR: It is suggested that interactive computer games provide a rich environment for incremental research on human-level AI and the research issues and AI techniques that are relevant to each of these roles.
Abstract: Although one of the fundamental goals of AI is to understand and develop intelligent systems that have all the capabilities of humans, there is little active research directly pursuing this goal. We propose that AI for interactive computer games is an emerging application area in which this goal of human-level AI can successfully be pursued. Interactive computer games have increasingly complex and realistic worlds and increasingly complex and intelligent computer-controlled characters. In this article, we further motivate our proposal of using interactive computer games for AI research, review previous research on AI and games, and present the different game genres and the roles that human-level AI could play within these genres. We then describe the research issues and AI techniques that are relevant to each of these roles. Our conclusion is that interactive computer games provide a rich environment for incremental research on human-level AI.
455 citations
TL;DR: Fast-forward (FF) as mentioned in this paper was the most successful automatic planner in the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS '00) planning systems competition, which relies on forward search in the state space guided by a heuristic that estimates goal distances by ignoring delete lists.
Abstract: Fast-forward (FF) was the most successful automatic planner in the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS '00) planning systems competition. Like the well-known hsp system, FF relies on forward search in the state space, guided by a heuristic that estimates goal distances by ignoring delete lists. It differs from HSP in a number of important details. This article describes the algorithmic techniques used in FF in comparison to hsp and evaluates their benefits in terms of run-time and solution-length behavior. Humans have a remarkable capability to perform a wide variety of physical and mental tasks without any measurements and any computations. Familiar examples are parking a car, driving in city traffic, playing golf, cooking a meal, and summarizing a story. In performing such tasks, humans use perceptions of time, direction, speed, shape, possibility, likelihood, truth, and other attributes of physical and mental objects. Reflecting the bounded ability of the human brain to resolve detail, perceptions are intrinsically imprecise. In more concrete terms, perceptions are f-granular, meaning that (1) the boundaries of perceived classes are unsharp and (2) the values of attributes are granulated, with a granule being a clump of values (points, objects) drawn together by indistinguishability, similarity, proximity, and function. For example, the granules of age might be labeled very young, young, middle aged, old, very old, and so on. F-granularity of perceptions puts them well beyond the reach of traditional methods of analysis based on predicate logic or probability theory. The computational theory of perceptions (CTP), which is outlined in this article, adds to the armamentarium of AI a capability to compute and reason with perception-based information. The point of departure in CTP is the assumption that perceptions are described by propositions drawn from a natural language; for example, it is unlikely that there will be a significant increase in the price of oil in the near future. In CTP, a proposition, p, is viewed as an answer to a question, and the meaning of p is represented as a generalized constraint. To compute with perceptions, their descriptors are translated into what is called the generalized constraint language (GCL). Then, goal-directed constraint propagation is utilized to answer a given query. A concept that plays a key role in CTP is that of precisiated natural language (PNL). The computational theory of perceptions suggests a new direction in AI -- a direction that might enhance the ability of AI to deal with realworld problems in which decision-relevant information is a mixture of measurements and perceptions. What is not widely recognized is that many important problems in AI fall into this category.
399 citations
TL;DR: The results of a 10-year effort building robust spoken dialogue systems at the University of Rochester are described, which show that speech-driven interfaces to computers are starting to appear feasible.
Abstract: The belief that humans will be able to interact with computers in conversational speech has long been a favorite subject in science fiction, reflecting the persistent belief that spoken dialogue would be the most natural and powerful user interface to computers. With recent improvements in computer technology and in speech and language processing, such systems are starting to appear feasible. There are significant technical problems that still need to be solved before speech-driven interfaces become truly conversational. This article describes the results of a 10-year effort building robust spoken dialogue systems at the University of Rochester.
382 citations
TL;DR: A new generation of intelligent tutoring systems that hold mixed-initiative conversational dialogues with the learner, and help students actively construct knowledge through conversations are presented.
Abstract: Many of the intelligent tutoring systems that have been developed during the last 20 years have proven to be quite successful, particularly in the domains of mathematics, science, and technology. They produce significant learning gains beyond classroom environments. They are capable of engaging most students' attention and interest for hours. We have been working on a new generation of intelligent tutoring systems that hold mixed-initiative conversational dialogues with the learner. The tutoring systems present challenging problems and questions to the learner, the learner types in answers in English, and there is a lengthy multiturn dialogue as complete solutions or answers evolve. This article presents the tutoring systems that we have been developing. AutoTutor is a conversational agent, with a talking head, that helps college students learn about computer literacy. andes, atlas, and why2 help adults learn about physics. Instead of being mere information-delivery systems, our systems help students actively construct knowledge through conversations.
370 citations
TL;DR: An approach to intelligent user interfaces, based on the idea of making the computer a collaborator, and an application-independent technology for implementing such interfaces are described.
Abstract: We describe an approach to intelligent user interfaces, based on the idea of making the computer a collaborator, and an application-independent technology for implementing such interfaces.
303 citations
TL;DR: The algorithmic techniques used in FF in comparison to hsp are described and their benefits in terms of run-time and solution-length behavior are evaluated.
Abstract: Fast-forward (FF) was the most successful automatic planner in the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS '00) planning systems competition. Like the well-known hsp system, FF relies on forward search in the state space, guided by a heuristic that estimates goal distances by ignoring delete lists. It differs from HSP in a number of important details. This article describes the algorithmic techniques used in FF in comparison to hsp and evaluates their benefits in terms of run-time and solution-length behavior.
274 citations
TL;DR: It is argued that each kinds of representation (of the system, information and the world, the interaction) is key to how users make the kind of attributions of intelligence that facilitate their interactions with intelligent systems.
Abstract: How do we decide how to represent an intelligent system in its interface, and how do we decide how the interface represents information about the world and about its own workings to a user? This article addresses these questions by examining the interaction between representation and intelligence in user interfaces. The rubric representation covers at least three topics in this context: (1) how a computational system is represented in its user interface, (2) how the interface conveys its representations of information and the world to human users, and (3) how the system's internal representation affects the human user's interaction with the system. I argue that each of these kinds of representation (of the system, information and the world, the interaction) is key to how users make the kind of attributions of intelligence that facilitate their interactions with intelligent systems. In this vein, it makes sense to represent a systmem as a human in those cases where social collaborative behavior is key and for the system to represent its knowledge to humans in multiple ways on multiple modalities. I demonstrate these claims by discussing issues of representation and intelligence in an embodied conversational agent -- an interface in which the system is represented as a person, information is conveyed to human users by multiple modalities such as voice and hand gestures, and the internal representation is modality independent and both propositional and nonpropositional.
273 citations
TL;DR: A detailed analysis of the task domain is presented and characteristics necessary for multiagent and intelligent systems for this domain are elucidated and an overview of the RoboCup Rescue project is presented.
Abstract: Disaster rescue is one of the most serious social issues that involves very large numbers of heterogeneous agents in the hostile environment. The intention of the RoboCup Rescue project is to promote research and development in this socially significant domain at various levels, involving multiagent teamwork coordination, physical agents for search and rescue, information infrastructures, personal digital assistants, a standard simulator and decision-support systems, evaluation benchmarks for rescue strategies, and robotic systems that are all integrated into a comprehensive system in the future. For this effort, which was built on the success of the RoboCup Soccer project, we will provide forums of technical discussions and competitive evaluations for researchers and practitioners. Although the rescue domain is intuitively appealing as a large-scale multiagent and intelligent system domain, analysis has not yet revealed its domain characteristics. The first research evaluation meeting will be held at RoboCup-2001, in conjunction with the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI-2001), as part of the RoboCup Rescue Simulation League and RoboCup/AAAI Rescue Robot Competition. In this article, we present a detailed analysis of the task domain and elucidate characteristics necessary for multiagent and intelligent systems for this domain. Then, we present an overview of the RoboCup Rescue project.
196 citations
TL;DR: The edited volume provides a sample of important works on unsupervised learning, which cut across the fields of neural networks, and some of the most influential titles of late.
Abstract: Unsupervised Learning: Foundations of Neural Computation is a collection of 21 papers published in the journal Neural Computation in the 10-year period since its founding in 1989 by Terrence Sejnowski Neural Computation has become the leading journal of its kind The editors of the book are Geoffrey Hinton and Terrence Sejnowski, two pioneers in neural networks The selected papers include some of the most influential titles of late, for example, "What Is the Goal of Sensory Coding" by David Field and "An Information-Maximization Approach to Blind Separation and Blind Deconvolution" by Anthony Bell and Terrence Sejnowski The edited volume provides a sample of important works on unsupervised learning, which cut across the fields of
TL;DR: An overview of the AIPS'00 planning competition is presented and the main results are reviewed.
Abstract: The planning competition has become a regular part of the biennial Artificial Intelligence Planning and Scheduling (AIPS) conferences. AIPS'98 featured the very first competition, and for AIPS'00, we built on this foundation to run the second competition. The 2000 competition featured a much larger group of participants and a wide variety of different approaches to planning. Some of these approaches were refinements of known techniques, and others were quite different from anything that had been tried before. Besides the dramatic increase in participation, the 2000 competition demonstrated that planning technology has taken a giant leap forward in performance since 1998. The 2000 competition featured planning systems that were orders of magnitude faster than the planners of just two years prior. This article presents an overview of the competition and reviews the main results.
TL;DR: The terms knowledge-based and primitive-action planning are defined and an analogy from the current focus of the planning community on disjunctive planners to the experiences of the machine learning community over the past decade is drawn.
Abstract: We are interested in solving real-world planning problems and, to that end, argue for the use of domain knowledge in planning. We believe that the field must develop methods capable of using rich knowledge models to make planning tools useful for complex problems. We discuss the suitability of current planning paradigms for solving these problems. In particular, we compare knowledge rich approaches such as hierarchical task network planning to minimal-knowledge methods such as STRIPS-based planners and disjunctive planners. We argue that the former methods have advantages such as scalability, expressiveness, continuous plan modification during execution, and the ability to interact with humans. However, these planners also have limitations, such as requiring complete domain models and failing to model uncertainty, that often make them inadequate for real-world problems. In this article, we define the terms knowledge-based and primitive-action planning and argue for the use of knowledge-based planning as a paradigm for solving real-world problems. We next summarize some of the characteristics of real-world problems that we are interested in addressing. Several current real-world planning applications are described, focusing on the ways in which knowledge is brought to bear on the planning problem. We describe some existing knowledge-based approaches and then discuss additional capabilities, beyond those available in existing systems, that are needed. Finally, we draw an analogy from the current focus of the planning community on disjunctive planners to the experiences of the machine learning community over the past decade.
TL;DR: This article describes agent-centered search (also called real-time search or local search) and illustrates this planning paradigm with examples and discusses the design and properties of several agent- centered search methods, focusing on robot exploration and localization.
Abstract: In this article, I describe agent-centered search (also called real-time search or local search) and illustrate this planning paradigm with examples. Agent-centered search methods interleave planning and plan execution and restrict planning to the part of the domain around the current state of the agent, for example, the current location of a mobile robot or the current board position of a game. These methods can execute actions in the presence of time constraints and often have a small sum of planning and execution cost, both because they trade off planning and execution cost and because they allow agents to gather information early in nondeterministic domains, which reduces the amount of planning they have to perform for unencountered situations. These advantages become important as more intelligent systems are interfaced with the world and have to operate autonomously in complex environments. Agent-centered search methods have been applied to a variety of domains, including traditional search, strips-type planning, moving-target search, planning with totally and partially observable Markov decision process models, reinforcement learning, constraint satisfaction, and robot navigation. I discuss the design and properties of several agent-centered search methods, focusing on robot exploration and localization.
TL;DR: This work uses ontologies as a conceptual backbone for providing, accessing, and structuring information in a comprehensive approach for building and maintaining knowledge portals.
Abstract: Knowledge portals provide views onto domain-specific information on the World Wide Web, thus helping their users find relevant, domain-specific information. The construction of intelligent access and the contribution of information to knowledge portals, however, remained an ad hoc task, requiring extensive manual editing and maintenance by the knowledge portal providers. To diminish these efforts, we use ontologies as a conceptual backbone for providing, accessing, and structuring information in a comprehensive approach for building and maintaining knowledge portals. We present one research study and one commercial case study that show how our approach, called seal (semantic portal), is used in practice.
[...]
TL;DR: The past successes, current projects, and future research directions for AI using computer games as a research test bed are reviewed.
Abstract: In 1950, Claude Shannon published his seminal work on how to program a computer to play chess. Since then, developing game-playing programs that can compete with (and even exceed) the abilities of the human world champions has been a long-sought-after goal of the AI research community. In Shannon's time, it would have seemed unlikely that only a scant 50 years would be needed to develop programs that play world-class backgammon, checkers, chess, Othello, and Scrabble. These remarkable achievements are the result of a better understanding of the problems being solved, major algorithmic insights, and tremendous advances in hardware technology. Computer games research is one of the important success stories of AI. This article reviews the past successes, current projects, and future research directions for AI using computer games as a research test bed.
TL;DR: An overview of TALplanner, a forward-chaining planner that utilizes domain-dependent knowledge to control search in the state space generated by action invocation, which won the Outstanding Performance Award in the Domain-Dependent Planning Competition.
Abstract: TALplanner is a forward-chaining planner that utilizes domain-dependent knowledge to control search in the state space generated by action invocation. The domain-dependent control knowledge, background knowledge, plans, and goals are all represented using formulas in a temporal logic called tal, which has been developed independently as a formalism for specifying agent narratives and reasoning about them. In the Fifth International Artificial Intelligence Planning and Scheduling Conference planning competition, TALplanner exhibited impressive performance, winning the Outstanding Performance Award in the Domain-Dependent Planning Competition. In this article, we provide an overview of TALplanner
TL;DR: A considerable body of literature on creativity is summarized to show how to turn some of the best ideas about creativity into programs that are demonstrably more creative than any the authors have seen to date.
Abstract: Creativity is sometimes taken to be an inexplicable aspect of human activity. By summarizing a considerable body of literature on creativity, I hope to show how to turn some of the best ideas about creativity into programs that are demonstrably more creative than any we have seen to date. I believe the key to building more creative programs is to give them the ability to reflect on and modify their own frameworks and criteria. That is, I believe that the key to creativity is at the metalevel.
TL;DR: This article gives a brief introduction to, and explains the basic planning algorithm used by, mips, using a simple logistics problem as an example.
Abstract: Mips is a planning system that applies binary decision diagrams (BDDs) to compactly represent world states in a planning problem and efficiently explore the underlying state space. It was the first general planning system based on model-checking methods. It can handle the strips subset of the pddl language and some additional features from adl, namely, negative preconditions and (universal) conditional effects. At the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS'00), mips was one of five planning systems to be awarded for distinguished performance in the fully automated track. This article gives a brief introduction to, and explains the basic planning algorithm used by, mips, using a simple logistics problem as an example.
TL;DR: The hsp2.0 planning algorithm that entered the second planning contest held at the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS'00) is described and its performance is compared with two other optimal planners, stan and blackbox.
Abstract: We describe the hsp2.0 planning algorithm that entered the second planning contest held at the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS'00). hsp2.0 is a domain-independent planning algorithm that implements the family of heuristic search planners that are characterized by the state space that is searched (either progression or regression space), the search algorithm used (variants of best-first search), and the heuristic function extracted from the problem representation. This general planner implements a scheduler that tries different variants concurrently with different (time) resource bounds. We also describe how hsp2.0 can be used as an optimal (and near-optimal) planning algorithm and compare its performance with two other optimal planners, stan and blackbox.
TL;DR: The development of the personalized television listings system (PTV) is described, which tackles the information-overload problem associated with modern TV listings data by providing an Internet-based personalized TV listings service so that each registered user receives a daily TV guide that has been specially compiled to suit his/her particular viewing preferences.
Abstract: Although today's world offers us unprecedented access to greater and greater amounts of electronic information, we are faced with significant problems when it comes to finding the right information at the right time -- the essence of the information-overload problem. One of the proposed solutions to this problem is to develop technologies for automatically learning about the implicit and explicit preferences of individual users to customize and personalize the search for relevant information. In this article, we describe the development of the personalized television listings system (PTV),1 which tackles the information-overload problem associated with modern TV listings data by providing an Internet-based personalized TV listings service so that each registered user receives a daily TV guide that has been specially compiled to suit his/her particular viewing preferences.
TL;DR: An overview of current research on animated pedagogical agents at the Center for Advanced Research in Technology for Education (CARTE) at the University of Southern California/Information Sciences Institute is given.
Abstract: This article gives an overview of current research on animated pedagogical agents at the Center for Advanced Research in Technology for Education (CARTE) at the University of Southern California/Information Sciences Institute Animated pedagogical agents, nicknamed guidebots, interact with learners to help keep learning activities on track They combine the pedagogical expertise of intelligent tutoring systems with the interpersonal interaction capabilities of embodied conversational characters They can support the acquisition of team skills as well as skills performed alone by individuals At CARTE, we have been developing guidebots that help learners acquire a variety of problem-solving skills in virtual worlds, in multimedia environments, and on the web We are also developing technologies for creating interactive pedagogical dramas populated with guidebots and other autonomous animated characters
TL;DR: LifeCode is a natural language processing (NLP) and expert system that extracts demographic and clinical information from free-text clinical records that has a unique "self-awareness" feature that enables it to recognize the limits of its competence and ask for assistance from a human expert when faced with information that is beyond the bounds of its Competence.
Abstract: LifeCode is a natural language processing (NLP) and expert system that extracts demographic and clinical information from free-text clinical records. The initial application of LifeCode is for the emergency medicine clinical specialty. An application for diagnostic radiology went into production in October 2000. The LifeCode NLP engine uses a large number of specialist readers whose particular output are combined at various levels to form an integrated picture of the patient's medical condition(s), course of treatment, and disposition. The LifeCode expert system performs the tasks of combining complementary information, deleting redundant information, assessing the level of medical risk and level of service represented in the clinical record, and producing an output that is appropriate for input to an electronic medical record (EMR) system or a hospital information system. Because of the critical nature of the tasks, LifeCode has a unique "self-awareness" feature that enables it to recognize the limits of its competence and, thus, ask for assistance from a human expert when faced with information that is beyond the bounds of its competence. The LifeCode NLP and expert systems reside in various delivery packages, including online transaction processing, a web browser interface, and an automated speech recognition (ASR) interface.
TL;DR: In this report, I present a summary of the activities that took place during the Fourth International Conference on Autonomous Agents, which took place in Barcelona Spain from 3 to 7 June 2000.
Abstract: In this report, I present a summary of the activities that took place during the Fourth International Conference on Autonomous Agents, which took place in Barcelona Spain from 3 to 7 June 2000.
TL;DR: In the article, reference is made to some prototypes developed at IRST that were conceived for this specific area of language processing, and the combination of two forms of navigation taking place at the same time -- one in information space, the other in physical space.
Abstract: Language processing has a large practical potential in intelligent interfaces if we take into account multiple modalities of communication. Multi-modality refers to the perception of different coordinated media used in delivering a message as well as the combination of various attitudes in relation to communication. In particular, the integration of natural language processing and hypermedia allows each modality to overcome the constraints of the other, resulting in a novel class of integrated environments for complex exploration and information access. Information presentation is a key element of such environments; generation techniques can contribute to their quality by producing texts ex novo or flexibly adapting existing material to the current situation. A great opportunity arises for intelligent interfaces and language technology of this kind to play an important role for individual-oriented cultural tourism. In the article, reference is made to some prototypes developed at IRST that were conceived for this specific area. A recent project concentrated on the combination of two forms of navigation taking place at the same time -- one in information space, the other in physical space. Collaboration, an important topic for intelligent interfaces, is also discussed.
TL;DR: This contribution revisits some of past and ongoing projects to motivate an evolution of character-based presentation systems and argues that a central planning component for automated agent scripting is not always a good choice, especially not in the case of interactive performances where the user might take on an active role as well.
Abstract: Lifelike characters, or animated agents, provide a promising option for interface development because they allow us to draw on communication and interaction styles with which humans are already familiar. In this contribution, we revisit some of our past and ongoing projects to motivate an evolution of character-based presentation systems. This evolution starts from systems in which a character presents information content in the style of a TV presenter. It moves on with the introduction of presentation teams that convey information to the user by performing role plays. To explore new forms of active user involvement during a presentation, the next step can lead to systems that convey information in the style of interactive performances. From a technical point of view, this evaluation is mirrored in different approaches to determine the behavior of the employed characters. By means of concrete applications, we argue that a central planning component for automated agent scripting is not always a good choice, especially not in the case of interactive performances where the user might take on an active role as well.
TL;DR: Using static domain analysis techniques, this work has been able to identify certain commonly occurring subproblems within planning domains, making it possible to abstract these subpro problems from the overall goals of the planner and deploy specialized technology to handle them in a way integrated with the broader planning activities.
Abstract: Planning domains often feature subproblems such as route planning and resource handling. Using static domain analysis techniques, we have been able to identify certain commonly occurring subproblems within planning domains, making it possible to abstract these subproblems from the overall goals of the planner and deploy specialized technology to handle them in a way integrated with the broader planning activities. Using two such subsolvers our hybrid planner, stan4, participated successfully in the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS'00) planning competition.
TL;DR: Shop is a hierarchical task network planning algorithm that is provably sound and complete across a large class of planning domains and allows a high degree of expressive power in its knowledge bases.
Abstract: Shop is a hierarchical task network planning algorithm that is provably sound and complete across a large class of planning domains. It plans for tasks in the same order that they will later be executed, and thus, it knows the current world state at each step of the planning process. shop takes advantage of this knowledge by allowing a high degree of expressive power in its knowledge bases. For example, shop's preconditions can include logical inferences, complex numeric computations, and calls to external programs. shop is powerful enough that an implementation of it is being used as an embedded planner in the Naval Research Laboratory's hicap system.
TL;DR: The development of the critiquing agent was done by importing ontological knowledge from cyc and teaching the agent how an expert performs thecritiquing task, demonstrating good results.
Abstract: This article presents a learning agent shell and methodology for building knowledge bases and agents and their innovative application to the development of a critiquing agent for military courses of action, a challenge problem set by the Defense Advanced Research Projects Agency's High-Performance Knowledge Bases Program. The learning agent shell includes a general problem-solving engine and a general learning engine for a generic knowledge base structured into two main components: (1) an ontology that defines the concepts from an application domain and (2) a set of task-reduction rules expressed with these concepts. The development of the critiquing agent was done by importing ontological knowledge from cyc and teaching the agent how an expert performs the critiquing task. The learning agent shell, the methodology, and the developed critiquer were evaluated in several intensive studies, demonstrating good results.
TL;DR: The robots, developed by Swarthmore College, all used a modular hybrid architecture designed to enable reflexive responses to perceptual input, and integrated visual sensing, speech synthesis and recognition, the display of an animated face, navigation, and interrobot communication.
Abstract: This article describes the winning entries in the 2000 Association for the Advancement of Artificial Intelligence Mobile Robot Competition. The robots, developed by Swarthmore College, all used a modular hybrid architecture designed to enable reflexive responses to perceptual input. Within this architecture, the robots integrated visual sensing, speech synthesis and recognition, the display of an animated face, navigation, and interrobot communication. In the Hors d'Oeuvres, Anyone? event, a team of robots entertained the crowd while they interactively served cookies; and in the Urban Search-and-Rescue event, a single robot autonomously explored a section of the test area, identified interesting features, built an annotated map, and exited the test area within the allotted time.