Showing papers on "Applications of artificial intelligence published in 2013"
TL;DR: An overview of the existing work on AI for real-time strategy (RTS) games focuses on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research.
Abstract: This paper presents an overview of the existing work on AI for real-time strategy (RTS) games. Specifically, we focus on the work around the game StarCraft, which has emerged in the past few years as the unified test bed for this research. We describe the specific AI challenges posed by RTS games, and overview the solutions that have been explored to address them. Additionally, we also present a summary of the results of the recent StarCraft AI competitions, describing the architectures used by the participants. Finally, we conclude with a discussion emphasizing which problems in the context of RTS game AI have been solved, and which remain open.
401 citations
TL;DR: AI Innovation in Industry is a new department for IEEE Intelligent Systems, and this paper examines some of the basic concerns and uses of AI for big data.
Abstract: AI Innovation in Industry is a new department for IEEE Intelligent Systems, and this paper examines some of the basic concerns and uses of AI for big data (AI has been used in several different ways to facilitate capturing and structuring big data, and it has been used to analyze big data for key insights).
363 citations
TL;DR: The overall picture shows that not only are semi-structured resources enabling a renaissance of knowledge-rich AI techniques, but also that significant advances in high-end applications that require deep understanding capabilities can be achieved by synergistically exploiting large amounts of machine-readable structured knowledge in combination with sound statistical AI and NLP techniques.
176 citations
Book•
01 Oct 2013
TL;DR: Through profiles of tech visionaries, industry watchdogs, and groundbreaking AI systems, The authors' Final Invention explores the perils of the heedless pursuit of advanced AI.
Abstract: Artificial Intelligence helps choose what books you buy, what movies you see, and even who you date. It puts the smart in your smartphone and soonit will drive your car. It makes most of the trades on Wall Street, and controls vital energy, water, and transportation infrastructure. But Artificial Intelligence can also threaten our existence. In as little as a decade, AI could match and then surpass human intelligence. Corporations and government agencies are pouring billions into achieving AIs Holy Grailhuman-level intelligence. Once AI has attained it, scientists argue, it will have survival drives much like our own. We may be forced to compete with a rival more cunning, more powerful, and more alien than we can imagine. Through profiles of tech visionaries, industry watchdogs, and groundbreaking AI systems, Our Final Invention explores the perils of the heedless pursuit of advanced AI. Until now, human intelligence has had no rival. Can we coexist with beings whose intelligence dwarfs our own? And will they allow us to?
168 citations
17 Oct 2013
TL;DR: This paper presents an efficient system for modelling abstract RTS combat called SparCraft, which can perform millions of unit actions per second and visualize them, and presents a modification of the UCT algorithm capable of performing search in games with simultaneous and durative actions.
Abstract: Real-time strategy video games have proven to be a very challenging area for applications of artificial intelligence research. With their vast state and action spaces and real-time constraints, existing AI solutions have been shown to be too slow, or only able to be applied to small problem sets, while human players still dominate RTS AI systems. This paper makes three contributions to advancing the state of AI for popular commercial RTS game combat, which can consist of battles of dozens of units. First, we present an efficient system for modelling abstract RTS combat called SparCraft, which can perform millions of unit actions per second and visualize them. We then present a modification of the UCT algorithm capable of performing search in games with simultaneous and durative actions. Finally, a novel greedy search algorithm called Portfolio Greedy Search is presented which uses hill climbing and accurate playout-based evaluations to efficiently search even the largest combat scenarios. We demonstrate that Portfolio Greedy Search outperforms state of the art Alpha-Beta and UCT search methods for large StarCraft combat scenarios of up to 50 vs. 50 units under real-time search constraints of 40 ms per search episode.
120 citations
11 Sep 2013
TL;DR: Game AI Pro2: Collected Wisdom of Game AI Professionals presents cutting-edge tips, tricks, and techniques for artificial intelligence in games, drawn from developers of shipped commercial games as well as some of the best-known academics in the field.
Abstract: Game AI Pro2: Collected Wisdom of Game AI Professionals presents cutting-edge tips, tricks, and techniques for artificial intelligence (AI) in games, drawn from developers of shipped commercial games as well as some of the best-known academics in the field. It contains knowledge, advice, hard-earned wisdom, and insights gathered from across the community of developers and researchers who have devoted themselves to game AI. In this book, 47 expert developers and researchers have come together to bring you their newest advances in game AI, along with twists on proven techniques that have shipped in some of the most successful commercial games of the last few years. The book provides a toolbox of proven techniques that can be applied to many common and not-so-common situations. It is written to be accessible to a broad range of readers. Beginners will find good general coverage of game AI techniques and a number of comprehensive overviews, while intermediate to expert professional game developers will find focused, deeply technical chapters on specific topics of interest to them. Covers a wide range of AI in games, with topics applicable to almost any game Touches on most, if not all, of the topics necessary to get started in game AI Provides real-life case studies of game AI in published commercial games Gives in-depth, technical solutions from some of the industrys best-known games Includes downloadable demos and/or source code, available at http://www.gameaipro.com
68 citations
Book•
23 May 2013
TL;DR: This book serves as a textbook for graduate students in electric power system management and is also be useful for those who are interested in using artificial intelligence in power system optimization.
Abstract: With the considerable increase of AI applications, AI is being increasingly used to solve optimization problems in engineering. In the past two decades, the applications of artificial intelligence in power systems have attracted much research. This book covers the current level of applications of artificial intelligence to the optimization problems in power systems. This book serves as a textbook for graduate students in electric power system management and is also be useful for those who are interested in using artificial intelligence in power system optimization.
56 citations
17 Oct 2013
TL;DR: This research introduces Q-learning behaviour trees (QL-BT), a method for the application of reinforcement learning to behaviour tree design that facilitates AI designers' use of behaviour trees by assisting them in identifying the most appropriate moment to execute each branch of AI logic.
Abstract: Artificial intelligence has become an increasingly important aspect of computer game technology, as designers attempt to deliver engaging experiences for players by creating characters with behavioural realism to match advances in graphics and physics. Recently, behaviour trees have come to the forefront of games AI technology, providing a more intuitive approach than previous techniques such as hierarchical state machines, which often required complex data structures producing poorly structured code when scaled up. The design and creation of behaviour trees, however, requires experience and effort. This research introduces Q-learning behaviour trees (QL-BT), a method for the application of reinforcement learning to behaviour tree design. The technique facilitates AI designers' use of behaviour trees by assisting them in identifying the most appropriate moment to execute each branch of AI logic, as well as providing an implementation that can be used to debug, analyse and optimize early behaviour tree prototypes. Initial experiments demonstrate that behaviour trees produced by the QL-BT algorithm effectively integrate RL, automate tree design, and are human-readable.
46 citations
17 Oct 2013
TL;DR: The rules of the competition, the software used, the voting interface, the scoring procedure, the submitted controllers and the recent results of the Mario AI Championship are presented.
Abstract: The Turing Test Track of the Mario AI Championship focused on developing human-like controllers for a clone of the popular game Super Mario Bros. Competitors participated by submitting AI agents that imitate human playing style. This paper presents the rules of the competition, the software used, the voting interface, the scoring procedure, the submitted controllers and the recent results of the competition for the year 2012. We also discuss what can be learnt from this competition in terms of believability in platform games. The discussion is supported by a statistical analysis of behavioural similarities and differences among the agents, and between agents and humans. The paper is co-authored by the organizers of the competition (the first three authors) and the competitors.
36 citations
TL;DR: A novel simplified compaction table for reusing geomaterials and compaction management in embankments and applied one- and two-dimensional advanced sensitivity analyses to better interpret the proposed data-driven models for the prediction of the deformability modulus of jet grouting field samples are proposed.
Abstract: This paper presents a brief overview of artificial intelligence applications in transportation geotechnics, highlighting new approaches and current research directions, including issues related to data mining interpretability and prediction capacities. Several practical applications to earthworks, including the compaction management and quality control aspects of embankments, as well as pavement evaluation, design and management, and the mechanical behaviour of jet grouting material, are presented to illustrate the advantages of using data mining, including artificial neural networks, support vector machines, and evolutionary computation techniques in this domain. This study also propose a novel simplified compaction table for reusing geomaterials and compaction management in embankments and applied one- and two-dimensional advanced sensitivity analyses to better interpret the proposed data-driven models for the prediction of the deformability modulus of jet grouting field samples. These applications show the capabilities of data mining models to address complex problems in transportation geotechnics involving highly nonlinear relationships of data and optimisation needs.
01 Jan 2013
TL;DR: The logical foundation of Artificial Intelligence with feasible applications is explained and matrix techniques reveal themselves as important.
Abstract: Artificial Intelligence was developed in 1956 and came into existence as a paradigm of cognition. It derived a powerful and lusty philosophical patrimony of functionalism and affirmatism. The history has shown a turn away from the functionalism of standard AI toward an alternative position that re-asserts the priority of development, interaction, and, more recently, emotion in cognitive systems, focusing now more than ever on enactive models of cognition. The method of looking for the solutions to problems, in Artificial Intelligence, can be brought about, in many ways, without cognition of the Domain, and in different situations, with knowledge of it. This procedure is usually called Heuristic Search. In such techniques matrix techniques reveal themselves as important. Their introduction can enable us to understand the precise way to the look for a solution. This paper explains the logical foundation of Artificial Intelligence with feasible applications.
TL;DR: An approach to validating the performance of an artificial intelligence system using a simple artificial intelligence test case producer (AITCP) is presented, which allows the creation and simulation of prospective operating scenarios at a rate far exceeding that possible by human testers.
Abstract: An artificial intelligence system, designed for operations in a real-world environment faces a nearly infinite set of possible performance scenarios. Designers and developers, thus, face the challenge of validating proper performance across both foreseen and unforeseen conditions, particularly when the artificial intelligence is controlling a robot that will be operating in close proximity, or may represent a danger, to humans. While the manual creation of test cases allows limited testing (perhaps ensuring that a set of foreseeable conditions trigger an appropriate response), this may be insufficient to fully characterize and validate safe system performance. An approach to validating the performance of an artificial intelligence system using a simple artificial intelligence test case producer (AITCP) is presented. The AITCP allows the creation and simulation of prospective operating scenarios at a rate far exceeding that possible by human testers. Four scenarios for testing an autonomous navigation control system are presented: single actor in two-dimensional space, multiple actors in two-dimensional space, single actor in three-dimensional space, and multiple actors in three-dimensional space. The utility of using the AITCP is compared to that of human testers in each of these scenarios.
19 Nov 2013
TL;DR: The paper provides set of computational methodologies enabling the development of enhanced Aml healthcare applications that obtains contextual information from embedded sensors, interprets it, and adapting the environment to interpreted needs.
Abstract: Ambient intelligence (AmI) is a computing paradigm wherein conventional input and output media no longer exist. Instead, sensors and processors are integrated into conventional objects that harmonize with people in their living situations. AmI relies on artificial intelligence (AI) to perform these duties. It obtains contextual information from embedded sensors, interprets it, and adapts the environment to interpreted needs. The paper provides set of computational methodologies enabling the development of enhanced Aml healthcare applications.
06 Nov 2013
TL;DR: The book captures the breadth and depth of the medical applications of artificial intelligence, exploring new developments and persistent challenges.
Abstract: Enhanced, more reliable, and better understood than in the past, artificial intelligence (AI) systems can make providing healthcare more accurate, affordable, accessible, consistent, and efficient. However, AI technologies have not been as well integrated into medicine as predicted. In order to succeed, medical and computational scientists must develop hybrid systems that can effectively and efficiently integrate the experience of medical care professionals with capabilities of AI systems. After providing a general overview of artificial intelligence concepts, tools, and techniques, Medical Applications of Artificial Intelligence reviews the research, focusing on state-of-the-art projects in the field. The book captures the breadth and depth of the medical applications of artificial intelligence, exploring new developments and persistent challenges.
TL;DR: Part Two of the special issue of AI Magazine presents articles on some of the most interesting projects at the intersection of AI and Education, as well as technology focused components such as student models and data mining.
Abstract: Part Two of the special issue of AI Magazine presents articles on some of the most interesting projects at the intersection of AI and Education. Included are articles on integrated systems such as virtual humans, an intellgent textbook a game-based learning environment as well as technology focused components such as student models and data mining. The issue concludes with an article summarizing the contemporary and emerging challenges at the intersection of AI and education.
25 May 2013
TL;DR: This paper presents example software-engineering problems with solutions that leverage the synergy of human and artificial intelligence, and illustrates how cooperative testing and analysis can help realize such synergy.
Abstract: To reduce human efforts and burden on human intelligence in software-engineering activities, Artificial Intelligence (AI) techniques have been employed to assist or automate these activities. On the other hand, human's domain knowledge can serve as starting points for designing AI techniques. Furthermore, the results of AI techniques are often interpreted or verified by human users. Such user feedback could be incorporated to further improve the AI techniques, forming a continuous feedback loop. We recently proposed cooperative testing and analysis including human-tool cooperation (consisting of human-assisted computing and human-centric computing) and human-human cooperation. In this paper, we present example software-engineering problems with solutions that leverage the synergy of human and artificial intelligence, and illustrate how cooperative testing and analysis can help realize such synergy.
18 Mar 2013
TL;DR: The goal of the paper is to underline the importance of such cultural phenomena as sci-fi movies for the future of humanity and envision potential problems of social networks and impact of Internet of things facts which is becoming a reality with IPv6 protocol.
Abstract: Sci-fi technological movie domain is an important part of human culture. The paper focus on comparison study of selected robotics sci-fi movie domain from a technological point of view. It is necessary to accomplish technological analysis of studied sci-fi movies and able to distinguish about possible current technology and future direction of the artificial intelligence in the domain of Robot intelligence. The review of existing movies which are in fact influencing thinking of humans is essential since it can influence a future research direction in AI. This information is interesting for inspiration of students and research associates in theory and applications. In conclusion, we envision potential problems of social networks and impact of Internet of things facts which is becoming a reality with IPv6 protocol. The goal of the paper is also to underline the importance of such cultural phenomena as sci-fi movies for the future of humanity.
TL;DR: This paper investigates how knowledge acquired during a post-design phase of modeling can be used to improve the prospective model and argues that such a process is critical for the deployment of AI planning technology in real-world engineering applications.
06 Nov 2013
TL;DR: Artificial intelligence (AI) concepts, techniques, and tools have been utilized in medical applications for over four decades as mentioned in this paper and the overall goal has been to benefit health care by assisting health care professionals in improving their effectiveness, productivity, and consistency.
Abstract: Artificial intelligence (AI) concepts, techniques, and tools have been utilized in medical
applications for over four decades. The overall goal has been to benefit health care by
assisting health care professionals in improving their effectiveness, productivity, and consistency. Improvements in accuracy and efficiency of AI techniques have steadily increased
AI’s viability as a choice for tackling problems in medicine. The availability of AI software
has played a significant role in the further adoption of AI for medical applications.
13 Nov 2013
TL;DR: The proceedings of the 26th Australasian Joint Conference on Artificial Intelligence (AI 2013) as mentioned in this paper constitute the refereed proceedings of this conference and are organized in topical sections as agents; AI applications; cognitive modelling; computer vision; constraint satisfaction, search and optimisation; evolutionary computation; game playing; knowledge representation and reasoning; machine learning and data mining; natural language processing and information retrieval; planning and scheduling.
Abstract: This book constitutes the refereed proceedings of the 26th Australasian Joint Conference on Artificial Intelligence, AI 2013, held in Dunedin, New Zealand, in December 2013. The 35 revised full papers and 19 revised short papers presented were carefully reviewed and selected from 120 submissions. The papers are organized in topical sections as agents; AI applications; cognitive modelling; computer vision; constraint satisfaction, search and optimisation; evolutionary computation; game playing; knowledge representation and reasoning; machine learning and data mining; natural language processing and information retrieval; planning and scheduling.
01 Jan 2013
TL;DR: This paper proposes an ENPS simulator based on GPUs and presents general concepts about its design and some future ideas and perspectives.
Abstract: A P system represents a distributed and parallel computing model in which basic data structures are, for instance, multisets and strings. Enzymatic Numerical P Systems (ENPS) are a type of P systems whose basic data structures are sets of numerical variables. Separately, GPGPU (general-purpose computing on graphics processing units) is a novel technological paradigm which focuses on the development of tools for graphic cards to solve general purpose problems. This paper proposes an ENPS simulator based on GPUs and presents general concepts about its design and some future ideas and perspectives.
Book•
23 Jul 2013
TL;DR: Game AI Scripting in Unity3d will show you how to apply AI techniques to your Unity3D projects using C# as the scripting language, with sample projects that demonstrate finite state machines, pathfinding, steering, navigation graphs, and behavior trees techniques.
Abstract: Learn and implement game AI in Unity3D with a lot of sample projects and next-generation techniques to use in your Unity3D projects Overview A practical guide with step-by-step instructions and example projects to learn Unity3D scripting Learn pathfinding using A* algorithms as well as Unity3D pro features and navigation graphs. Implement finite state machines (FSMs), path following, and steering algorithms. In Detail This book fills the gap between artificial intelligence (AI) books designed to learn underlying AI algorithms and general Unity3D books written to cover basic scene setup and scripting in Unity3D. Game AI Scripting in Unity3D covers implementing AI techniques such as flocking, pathfinding, path following, and behavior trees in Unity3D with example projects. Game AI Scripting in Unity3D will show you how to apply AI techniques to your Unity3D projects using C# as the scripting language. Unlike other AI books and Unity3D books, this book tries to focus more on the application of AI techniques in the Unity3D engine, with sample projects that demonstrate finite state machines (FSMs), pathfinding, steering, navigation graphs, and behavior trees techniques. This book shows how to implement various AI techniques in Unity3D by implementing the algorithm from scratch using C#, applying Unity3D built-in features, or using available scripts and plugins from the Unity Asset Store. For example, well be implementing our own A* algorithm to do pathfinding but will also explore the Unity3D navigation graphs feature. Then well use the Behave plugin to construct behavior trees for intelligent AI character behaviors. Game AI Scripting in Unity3d covers other AI techniques such as flocking behavior, building a sensory system for taking inputs from the environment and other AI agents, and so on. In the final chapter this book will show you how to build a racing game AI project using Unity3D and applying the techniques described in earlier chapters. What you will learn from this book Building finite state machines (FSMs) Implementing a sensory system Applying flocking behavior for a crowd Executing your own A* pathfinding algorithm in Unity3D Applying random and probability techniques in a betting game Using the Unity3D pro feature, navigation graphs, for path finding Learning about behavior trees and the Behave plugin Implementing a racing game AI through the final chapter project Approach Step-by-step practical tutorial Who this book is written for Are you are a programmer with basic knowledge of Unity3D who would like to add AI features to your game? Are you looking for a reference on implementing AI in Unity3D with simple to follow instructions, and lots of sample code and projects? Then this book is for you. You should have some background in C# language as this book will use C# for scripting. However if you know any other language you should be able to follow this book fairly easily.
Proceedings Article•
11 Dec 2013
TL;DR: The proposed modelling method is used to develop an autonomous robot for face-detection and face-recognition, and some experiments were proposed to validate its performances.
Abstract: Cyber-physical systems are now widespread in applications of paramount importance, from traffic control to healthcare and robotics applications. Modelling cyber-physical systems making use of artificial intelligent methodologies is very difficult, because of unpredictability in AI algorithms timing performances. This paper proposes a methodology to model Intelligent Cyber-Physical Systems, relying on hierarchical hybrid models. The proposed modelling method is used to develop an autonomous robot for face-detection and face-recognition, and some experiments were proposed to validate its performances.
18 May 2013
TL;DR: A declarative, domain-specific language (DSL) embedded in the functional programming language Haskell for real-time video games that is used to describe the decision making process of the AI in real- time video games.
Abstract: Many games have computer-controlled agents that play against a player. The behavior of these computer-controlled agents is described by means of the artificial intelligence (AI) in the game. The AI is an important component of the game, and needs to be developed carefully, and adapted regularly. This paper introduces a novel language for describing the decision making process of the AI in real-time video games. We develop a declarative, domain-specific language (DSL) embedded in the functional programming language Haskell for real-time video games. We use the DSL to describe the AI of a prototype real-time video game.
TL;DR: A survey of current industrial experiences is used to discuss different semantic technologies at work in heterogeneous areas, ranging from Web services to semantic search and recommender systems, and allows to sketch a general taxonomy of approaches.
Abstract: Artificial Intelligence technologies are growingly used within several software systems ranging from Web services to mobile applications. It is by no doubt true that the more AI algorithms and methods are used the more they tend to depart from a pure "AI" spirit and end to refer to the sphere of standard software. In a sense, AI seems strongly connected with ideas, methods and tools that are not (yet) used by the general public. On the contrary, a more realistic view of it would be a rich and pervading set of successful paradigms and approaches. Industry is currently perceiving semantic technologies as a key contribution of AI to innovation. In this paper a survey of current industrial experiences is used to discuss different semantic technologies at work in heterogeneous areas, ranging from Web services to semantic search and recommender systems.The resulting picture confirms the vitality of the area and allows to sketch a general taxonomy of approaches, that is the main contribution of this paper.
01 Oct 2013
TL;DR: It is postulate that the famous Turing Test was a noble goal for AI scientists, making key, historical inroads - while it is believed that Biological Systems Intelligence and the Insect/Swarm Intelligence analogy/mimicry represents the key to further developments.
Abstract: During the past 70+ years of research and development in the domain of Artificial Intelligence (AI) we observe three principal, historical waves: embryonic, embedded and embodied AI. As the first two waves have demonstrated huge potential to seed new technologies and provide tangible business results, we describe likely developments of embodied AI in the next 25-35 years. We postulate that the famous Turing Test was a noble goal for AI scientists, making key, historical inroads - while we believe that Biological Systems Intelligence and the Insect/Swarm Intelligence analogy/mimicry, though largely disregarded, represents the key to further developments. We describe briefly the key lines of past and ongoing research, and outline likely future developments in this remarkable field.
14 Nov 2013
TL;DR: This work outlines a didactic concept for teaching AI to Business Information Systems students at the university level and a web-based game server that was implemented to support this concept and shows an improved engagement of students.
Abstract: Games are a classical field of application for concepts of artificial intelligence (AI). We outline a didactic concept for teaching AI to Business Information Systems students at the university level and a web-based game server that was implemented to support this concept. Our results show an improved engagement of students as well as a flexible technical basis for AI education and AI research which can be applied in various learning and research contexts.
17 Oct 2013
TL;DR: This paper proposes combining small, light-weightAI/CI libraries with AI/CI services in the cloud for the heavy lifting, and describes a new mobile game that is built that shows how this can work.
Abstract: Mobile gaming is an arena full of innovation, with developers exploring new kinds of games, with new kinds of interaction between the mobile device, players, and the connected world that they live in and move through. The mobile gaming world is a perfect playground for AI and CI, generating a maelstrom of data for games that use adaptation, learning and smart content creation. In this paper, we explore this potential killer application for mobile intelligence. We propose combining small, light-weight AI/CI libraries with AI/CI services in the cloud for the heavy lifting. To make our ideas more concrete, we describe a new mobile game that we built that shows how this can work.
11 Nov 2013
TL;DR: This paper proposes a method in which reinforcement learning is used to make learning agents as well as a dynamic AI difficulty system based on fuzzy logic and applies this method to an action tower defense game to show how a player can have better experiences while playing against agents who can learn to adapt their behavior to the skill level of the player.
Abstract: The most important functional requirement of a video game is to provide entertainment. Players can always be entertained if they face a challenge according to their own level of skills. While different players owned different levels of skills, the game should not be very hard or very easy for different players with varying levels of skills. Artificial intelligence provides a number of methods to adaptively tune the playing agents in the game with respect to human players. In this paper we propose a method in which reinforcement learning is used to make learning agents as well as a dynamic AI difficulty system based on fuzzy logic. To validate our approach we applied our method to an action tower defense game to show how a player can have better experiences while playing against agents who can learn to adapt their behavior to the skill level of the player.