Showing papers on "Applications of artificial intelligence published in 2001"
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: A variety of new AI tools have become available in recent years that can function as intelligent assistants to clinicians, constantly monitoring electronic data streams for important trends, or adjusting the settings of bedside devices.
Abstract: ObjectiveTo review the history and current applications of artificial intelligence in the intensive care unit.Data SourcesThe MEDLINE database, bibliographies of selected articles, and current texts on the subject.Study SelectionThe studies that were selected for review used artificial intelligence
176 citations
TL;DR: The Quakebot uses Soar-an engine for making and executing decisions-as its underlying AI engine for controlling a single player.
Abstract: Building software agents that can survive in the harsh environment of a popular computer game (Quake II) provides fresh insight into the study of artificial intelligence (AI). Our Quakebot uses Soar-an engine for making and executing decisions-as its underlying AI engine for controlling a single player. We chose Soar as our AI engine because our real research goal is to understand and develop general integrated intelligent agents.
163 citations
01 Dec 2001
TL;DR: The paper explores the use of AI in games focusing on difficulties faced by game developers and techniques that have proven useful, and an argument is presented for the value of collaboration between the game and academic AI communities.
Abstract: Artificial intelligence (AI) is playing an increasingly important role in the success or failure of computer games. The paper explores the use of AI in games focusing on difficulties faced by game developers and techniques that have proven useful. An argument is presented for the value of collaboration between the game and academic AI communities.
66 citations
01 Jan 2001
TL;DR: The paper concludes with desiderata for a theoretical understanding of argumentation schemes, motivated by the demands of the AI applications discussed, with the aim of stimulating and outlining further foundational research in the area.
Abstract: Argumentation schemes capture common, stereotypical patterns of reasoning which are nondeductive and nonmonotonic. As interest in understanding these schemes from a theoretical point of view grows, so too does an awareness within computational work that these schemes might yield powerful techniques in a range of domains. This paper aims to perform two functions. First, to briefly review the literature on argumentation schemes, including the key works by Hastings, Walton and Kienpointner, and to set it in a broader context, adducing concerns from deductivism and presumptive, nonmonotonic reasoning. The second is to consider the various roles argumentation schemes might play in Artificial Intelligence, and in particular to consider (i) how schemes might be characterized as planning operators in domains such as natural language generation, with operationalized schemes representing means of achieving specific (e.g. persuasive) goals; (ii) how schemes might be exploited in AI domains typically characterized by a deductive (if argumentation theoretic) basis for communication, such as communication between intelligent agents; (iii) how schemes might be used in teaching critical thinking, and how they might be characterized in pedagogical software; (iv) more broadly, the representation tasks that can be facilitated using argumentation schemes (drawing particularly upon the wide-ranging discussions held at the Symposium on Argument and Computation held in Scotland in July 2000); and (v) the role that critical questions associated with schemes have in generative, representational and pedagogical aspects of argumentation in AI. The paper concludes with desiderata for a theoretical understanding of argumentation schemes, motivated by the demands of the AI applications discussed, with the aim of stimulating and outlining further foundational research in the area.
41 citations
10 Oct 2001
TL;DR: In this paper, the authors report their experience using robots in the artificial intelligence course they taught in Fall 2000, and discuss their choice of robot, describe the projects they assigned and list the problems their students encountered carrying out those projects.
Abstract: In this paper, we report our experience using robots in the artificial intelligence course we taught in Fall 2000. Our objective was to use robots to reinforce the traditional concepts of search and expert systems. We wanted the robots to be simple to build, yet powerful enough to illustrate AI concepts. In this paper, we discuss our choice of robot, describe the projects we assigned and list the problems our students encountered carrying out those projects. We surveyed our class regarding the use of robots in this course at the end of the semester. We discuss the results of this survey, which we believe, make a strong case for using robots in the AI course.
40 citations
TL;DR: The Laboratory for Research on Artificial Intelligence Applied to Petroleum Engineering (LIAP) at Unicamp has, during the last 10 years, dedicated research efforts to build intelligent systems in well drilling and petroleum production fields as mentioned in this paper.
23 citations
TL;DR: The expert system technology is successfully integrated into the system to provide help for model parameter selection or model selection, and to make the numerical model system more accessible for non-expert users.
22 citations
07 Oct 2001
TL;DR: Sociologists have been all but absent from the various efforts to build artificial life and intelligence, and even from the more recent research and development in social and humanoid robotics, but sociologists who have addressed issues in AI and social robotics have adopted contrary positions based on shared premises.
Abstract: Sociologists have been all but absent from the various efforts to build artificial life and intelligence, and even from the more recent research and development in social and humanoid robotics. Those sociologists who have addressed issues in AI and social robotics have adopted contrary positions based on shared premises. H. Collins, for example, is a sociological skeptic. He claims that the very idea of an intelligent machine contradicts "a basic premise of knowledge science because a machine is not a community or a member of society." Collins is one of the pioneers in the study of knowledge, science, and belief as social constructions. In his analyses of AI, he focuses on the constraints imposed on machines as potentially thinking, conscious, and emotional entities. If we are going to have 19 machines who think" we are going to have to have "machines who live with us and share our society". As long as machines are not members of our society, they cannot "imitate our intelligent, activities".
20 citations
TL;DR: The motion picture "AI" lets the AI profession squirm in the glory of misrepresentation, and reinforces the dream of the android just when many who work toward "truly" intelligent technologies are cutting loose from the dream's more surrealistic aspects.
Abstract: The motion picture "AI" lets the AI profession squirm in the glory of misrepresentation. It's not fun, especially when one's field suffers from waves of innovation/hype/backlash. The problem is that the film "AI" reinforces the dream of the android just when many who work toward "truly" intelligent technologies are cutting loose from the dream's more surrealistic aspects. People are asking new questions: Is the Turing test really the right kind of standard? If not, what is better? Must we define intelligence in reference to humans? Must intelligent technology be boxes chock-full of this thing we call intelligence, or should it operate as a "cognitive prosthesis" to amplify or extend human perceptual, cognitive and collaborative capabilities? Must intelligence always be in some individual thing - either a headbone or a box - or is intelligence a system property that is definable only in terms of the triple of humans-machines-contexts?.
19 citations
14 Jun 2001
TL;DR: This work proposes formulas to calculate the probability values within the uncertainty vectors representing the resulting relations of the reasoning operations of the proposed representation and reasoning mechanism.
Abstract: A wide range of AI applications should manage time varying information. Many published research articles in the area of temporal representation and reasoning assume that temporal data is precise and certain, even though in reality this assumption is often false. However, in many real applications temporal information is imperfect and there is a need to find some way of handling it. An uncertain relation between two temporal points is represented as a vector with three probability values denoting the probabilities of the three basic relations: " " (after). The reasoning mechanism includes inversion, composition, addition, and negation operations. We propose formulas to calculate the probability values within the uncertainty vectors representing the resulting relations of the reasoning operations. We also consider an example of using the proposed representation and reasoning mechanism.
01 Jan 2001
TL;DR: An overview of two promising techniques: machine learning and Bayesian networks is provided and how the use of these techniques changes the knowledge engineering requirements of building an ILE is examined.
Abstract: The field of AI & Education has been distancing itself from artificial intelligence. This is unfortunate, as AI can contribute greatly to the design of intelligent learning environments (ILE). AI allows the use of more complex models of student behavior, and has the potential to decrease the cost and complexity of building instruction systems. Furthermore, ILE’s can be made more adaptive in their interactions with students through the use of AI. We discuss reasons the field may be undergoing this shift in emphasis away from AI. We provide an overview of two promising techniques: machine learning and Bayesian networks. We then describe how these techniques have been applied to existing systems, and how they provide an advantage over traditional methods. We also discuss possible future extensions of these techniques. Finally, we conclude by examining how the use of these techniques changes the knowledge engineering requirements of building an ILE.
25 Sep 2001
TL;DR: The notion of topological distance defined in terms of games over S4u models is recalled, and it is shown how it is effectively computed for a specific class of models: the class of polygons of the real plane, a class ofTopological models widely used in computer science and AI applications.
Abstract: The multi-modal logic S4u, known in the field of qualitative spatial reasoning to be a decidable formalism for expressing topological and mereological properties, can also be exploited to define a distance measure among patterns. Here, we recall the notion of topological distance defined in terms of games over S4u models, and show how it is effectively computed for a specific class of models: the class of polygons of the real plane, a class of topological models widely used in computer science and AI applications. Finally, we briefly overview an implemented system based on the presented framework. This paper is the practical counterpart of, and continuation to [1].
Proceedings Article•
21 May 2001TL;DR: This paper presents a method and implementation resuits for the transformation of WordNet glosses into logic forms, useful for logic proofs, inference, and many other AI applications and demonstrates their applicability to a Question Answering system.
Abstract: This paper presents a method and implementation resuits for the transformation of WordNet glosses into logic forms. The glosses, currently expressed in English are a rich source of world knowledge. Logic forms are useful for logic proofs, inference, and many other AI applications. We demonstrate their applicability to a Question Answering system.
TL;DR: The results from the application of ``learning from examples'' methods, namely ANNs and DTs, for the fast dynamic security assessment of the power system of Lemnos island are presented and comparatively assessed.
Abstract: The paper presents two applications of Artificial Intelligence techniques, namely Artificial Neural Networks (ANNs) and Decision Trees (DTs), in wind power generation.
The first concerns the design procedure of a permanent magnet generator for a 20 kW wind turbine prototype. This work has been developed in the frame of a research project funded by the General Secretariat for Research and Technology of Greece, concerning the design and construction of a gear-less wind turbine for both autonomous and interconnected operation with the electrical grid.
The second application concerns the security assessment of networks including wind farms and has been developed in the frame of JOULE-II European Community research programme. The results from the application of ``learning from examples'' methods, namely ANNs and DTs, for the fast dynamic security assessment of the power system of Lemnos island are presented and comparatively assessed.
01 Feb 2001
TL;DR: This paper includes the syllabus for such an "open AI" course and discusses experiences, positive and negative, with it.
Abstract: Upper-division courses contain some of the most attractive topics in computer science, such as artificial intelligence (AI). Unfortunately, layers of prerequisites restrict AI to advanced computer science students and a separate course for non-majors is not always curricularly feasible. Instead, upper-division AI can be taught in a way that has no prerequisites while retaining the rigor of an upper-division course. This paper includes the syllabus for such an "open AI" course and discusses experiences, positive and negative, with it.
01 Jan 2001
TL;DR: In this panel, a socket-based communication protocol is designed and implemented that allows HAG to send basic commands to units in the game, and will be used by GRASP to control units in both Dark Reign and Battlezone.
Abstract: Creating complex AI applications and creating games involves many of the same problems Both AI applications and games are often simulations, both must coordinate multiple agents, deal with real-time issues, and ensure intelligent and efficient control of the involved units In the Experimental Knowledge Systems Laboratory, we have created a number of complex simulators Examples are: PHOENIX (Cohen et al 1989), a system to combat forest fires; ACS, an air campaign simulator; and CtF, a testbed based on a variant of the game "Capture the Flag" which deals with the problems of designing and evaluating military landbased campaigns (Atkin, Westbrook, & Cohen 1999; Atkin et al 2000; Atkin, Westbrook, & Cohen 2000; Atkin & Cohen 2000) We are interested in applying our agent design technology, specifically our agent control architecture, HAC, and our real-time planner, GRASP, to actual commercial games In this panel, we would like to share our experiences establishing ties to game companies, and discuss some of the issues that came up in the process We have been working primarily with two Activision games, Dark Reign and Battlezone We have designed and implemented a socket-based communication protocol that allows HAG to send basic commands to units in the game HAG also receives information about the state of the game world and the map This information will be used by GRASP to control units in both these games
Proceedings Article•
07 Aug 2001
01 Jun 2001
TL;DR: The potential use of Artificial Intelligence techniques in management, specifically in decision-making, is presented and several of these techniques are discussed based on its function (potentials) and contribution to decision- making process.
Abstract: Decision-making is a complex process that involves data that is derived based on set of rules.Conventional computer programs that executes the rules structurally, limits the decision-making process. In addition, the computer (or machine) itself does not have power to think and formulate the rules by itself (based on experience). This paper presents the potential use of Artificial Intelligence (AI) techniques in management, specifically in decision-making. A1 is a science that tries to emulate human "technology" onto a computer or machine. AI contributes to a highly
complex decision making procedure exhibits from a set of predefined rules. Some of AI techniques can learn patterns, mapping, optimizing and interprets fuzziness. Several of these techniques are discussed based on its function (potentials) and contribution to decision-making process.
TL;DR: The paper discusses the main stages for integrating artificial vision in manufacturing and to rend it efficient and reports some results in the field that have been obtained in the Robotics & AI Laboratories of the Universities of Bucharest and Murcia.
TL;DR: Common techniques used for planning, a chronology of planning systems, and some of the problems that planning addresses: reasoning about time, physical constraints on solutions, execution uncertainty, perception, and multi-agent systems are discussed.
01 Jan 2001
TL;DR: It is shown how how AI software has already influenced many disciplines and is very much an accepted tool in the industry.
Abstract: This paper is a survey of how Artificial Intelligen ce (AI) has gradually matured into a technology, from pure theory and research. We have briefly reviewed the various streams of AI such as Neural Networks, Fuzzy Logic, Agents, Genetic Algorithms, Natural Language Processing and Knowledge Based Systems. The stress is more on the usage than on the concept itself. Through this paper we s how how AI software has already influenced many disciplines and is very much an accepted tool in the industry.
01 Jan 2001
TL;DR: A methodology for using Rough Set for preference modeling in decision problem is presented, where a new approach for deriving knowledge rules from medical database based on Rough Set combined with Genetic Programming is introduced.
Abstract: A methodology for using Rough Set for preference modeling in decision problem is presented in this paper; where we will introduce a new approach for deriving knowledge rules from medical database based on Rough Set combined with Genetic Programming. Genetic Programming belongs to the most newly techniques in applications of Artificial Intelligence. Rough Set Theory, which emerged about twenty years ago, is nowadays rapidly developing branch of Artificial Intelligence and soft computing. At the first glance the two methodologies we talk about have not in common. Rough Set constructs representation of knowledge in terms of attributes, semantic decision rules, etc. On the contradictory, Genetic Programming attempts to automatically create computer programs from a high-level statement of the problem requirements. But, in spite of these differences, it is interesting to try to incorporate both approaches into combined system. The challenge is to get as much as possible from this association.
TL;DR: The most important steps of the application of pattern recognition techniques, expert systems, artificial neural networks, fuzzy systems, and nowadays hybrid artificial intelligence techniques in manufacturing can be regarded as consecutive elements of a process started two decades ago are outlined.