HOME WEB NEWS IMAGES CLASSIFIEDS YELLOW PAGESPOLLS - SURVEYS WIKI COUNTRIES PHOTOS US UK INDIA
Cities Stocks Weather Movies Coupons Travel Blogs Health Horoscope Maps ASIA EUROPE Classifieds Yellow Pages
 3
|
Artificial intelligence (or AI) is both the intelligence of machines and the branch of computer science which aims to create it.
Major AI textbooks define artificial intelligence as "the study and design of intelligent agents,"Poole, Mackworth & Goebel 1998, p. 1 (who use the term "computational intelligence" as a synonym for artificial intelligence). Other textbooks that define AI this way include Nilsson (1998), and Russell & Norvig (2003) (who prefer the term "rational agent") and write "The whole-agent view is now widely accepted in the field" (Russell & Norvig 2003, p. 55) where an intelligent agent is a system that perceives its environment and takes actions which maximize its chances of success.This definition, in terms of goals, actions, perception and environment, is due to Russell & Norvig (2003). Other definitions also include knowledge and learning as additional components. AI can be seen as a realization of an abstract intelligent agent (AIA) which exhibits the functional essence of intelligence.Abstract Intelligent Agents: Paradigms, Foundations and Conceptualization Problems, A.M. Gadomski, J.M. Zytkow, in "Abstract Intelligent Agent, 2". Printed by ENEA, Rome 1995, ISSN/1120-558X] John McCarthy, who coined the term in 1956,Although there is some controversy on this point (see Crevier 1993, p. 50), McCarthy states unequivocally "I came up with the term" in a c|net interview. (See Getting Machines to Think Like Us.) defines it as "the science and engineering of making intelligent machines."See John McCarthy, What is Artificial Intelligence?
Among the traits that researchers hope machines will exhibit are reasoning, knowledge, planning, learning, communication, perception and the ability to move and manipulate objects. This list of intelligent traits is based on the topics covered by the major AI textbooks, including: Russell & Norvig 2003, Luger & Stubblefield 2004, Poole, Mackworth & Goebel 1998 and Nilsson 1998. General intelligence (or "strong AI") has not yet been achieved and is a long-term goal of AI research. General intelligence (strong AI) is discussed by popular introductions to AI, such as: Kurzweil 1999, Kurzweil 2005, Hawkins & Blakeslee 2004
AI research uses tools and insights from many fields, including computer science, psychology, philosophy, neuroscience, cognitive science, linguistics, ontology, operations research, economics, control theory, probability, optimization and logic.Russell & Norvig 2003, pp. 5-16 AI research also overlaps with tasks such as robotics, control systems, scheduling, data mining, logistics, speech recognition, facial recognition and many others.See AI Topics: applications Other names for the field have been proposed, such as computational intelligence,Poole, Mackworth & Goebel 1998, p. 1 synthetic intelligence, intelligent systems,The name of the journal Intelligent Systems or computational rationality.Russell & Norvig 2003, p. 17
| | Artificial intelligence Portal |
Contents |
Humanity has imagined in great detail the implications of thinking machines or artificial beings. They appear in Greek myths, such as Talos of Crete, the golden robots of Hephaestus and Pygmalion\'s Galatea.McCorduck 2004, p. 5, Russell & Norvig 2003, p. 939 The earliest known humanoid robots (or automatons) were sacred statues worshipped in Egypt and Greece, believed to have been endowed with genuine consciousness by craftsman.The Egyptian statue of Amun is discussed by Crevier (1993, p. 1). McCorduck (2004, pp. 6-9) discusses Greek statues. Hermes Trismegistus expressed the common belief that with these statues, craftsman had reproduced "the true nature of the gods", their sensus and spiritus. McCorduck makes the connection between sacred automatons and Mosaic law (developed around the same time), which expressly forbids the worship of robots. In medieval times, alchemists such as Paracelsus claimed to have created artificial beings.McCorduck 2004, p. 13-14 (Paracelsus) Realistic clockwork imitations of human beings have been built by people such as Yan Shi,Needham 1986, p. 53 Hero of Alexandria,McCorduck 2004, p. 6 Al-JazariA Thirteenth Century Programmable Robot and Wolfgang von Kempelen.McCorduck 2004, p. 17 Pamela McCorduck observes that "artificial intelligence in one form or another is an idea that has pervaded Western intellectual history, a dream in urgent need of being realized."McCorduck 2004, p. xviii
In modern fiction, beginning with Mary Shelley\'s classic Frankenstein, writers have explored the ethical issues presented by thinking machines.McCorduck (2004, p. 190-25) discusses Frankenstein and identifies the key ethical issues as scientific hubris and the suffering of the monster, e.g. robot rights. If a machine can be created that has intelligence, can it also feel? If it can feel, does it have the same rights as a human being? This is a key issue in Frankenstein as well as in modern science fiction: for example, the film Artificial Intelligence: A.I. considers a machine in the form of a small boy which has been given the ability to feel human emotions, including, tragically, the capacity to suffer. This issue is also being considered by futurists, such as California\'s Institute for the Future under the name "robot rights",Robots could demand legal rights although many critics believe that the discussion is premature.See the Times Online, Human rights for robots? We’re getting carried awayrobot rights: Russell Norvig, p. 964
Science fiction writers and futurists have also speculated on the technology\'s potential impact on humanity. In fiction, AI has appeared as a servant (R2D2), a comrade (Lt. Commander Data), an extension to human abilities (Ghost in the Shell), a conqueror (The Matrix), a dictator (With Folded Hands) and an exterminator (Terminator, Battlestar Galactica). Some realistic potential consequences of AI are decreased labor demand, Russell & Norvig (2003, p. 960-961) the enhancement of human ability or experience,Kurzweil 2004 and a need for redefinition of human identity and basic values.Joseph Weizenbaum (the AI researcher who developed the first chatterbot program, ELIZA) argued in 1976 that the misuse of artificial intelligence has the potential to devalue human life. Weizenbaum: Crevier 1993, pp. 132−144, McCorduck 2004, pp. 356-373, Russell & Norvig 2003, p. 961 and Weizenbaum 1976
Futurists estimate the capabilities of machines using Moore\'s Law, which measures the relentless exponential improvement in digital technology with uncanny accuracy. Ray Kurzweil has calculated that desktop computers will have the same processing power as human brains by the year 2029, and that by 2040 artificial intelligence will reach a point where it is able to improve itself at a rate that far exceeds anything conceivable in the past, a scenario that science fiction writer Vernor Vinge named the "technological singularity".Singularity, transhumanism: Kurzweil 2005, Russell & Norvig 2003, p. 963
"Artificial intelligence is the next stage in evolution," Edward Fredkin said in the 1980s,Quoted in McCorduck (2004, p. 401) expressing an idea first proposed by Samuel Butler\'s Darwin Among the Machines (1863), and expanded upon by George Dyson (science historian) in his book of the same name (1998). Several futurists and science fiction writers have predicted that human beings and machines will merge in the future into cyborgs that are more capable and powerful than either. This idea, called transhumanism, has roots in Aldous Huxley and Robert Ettinger, is now associated with robot designer Hans Moravec, cyberneticist Kevin Warwick and Ray Kurzweil. Transhumanism has been illustrated in fiction as well, for example on the manga Ghost in the Shell.
In the middle of the 20th century, a handful of scientists began a new approach to building intelligent machines, based on recent discoveries in neurology, a new mathematical theory of information, an understanding of control and stability called cybernetics, and above all, by the invention of the digital computer, a machine based on the abstract essence of mathematical reasoning.Among the researchers who laid the foundations of the theory of computation, cybernetics, information theory and neural networks were Claude Shannon, Norbert Weiner, Warren McCullough, Walter Pitts, Donald Hebb, Donald McKay, Alan Turing and John Von Neumann. McCorduck 2004, pp. 51-107, Crevier 1993, pp. 27-32, Russell & Norvig 2003, pp. 15,940, Moravec 1988, p. 3.
The field of modern AI research was founded at conference on the campus of Dartmouth College in the summer of 1956.Crevier 1993, pp. 47-49, Russell & Norvig 2003, p. 17 Those who attended would become the leaders of AI research for many decades, especially John McCarthy, Marvin Minsky, Allen Newell and Herbert Simon, who founded AI laboratories at MIT, CMU and Stanford. They and their students wrote programs that were, to most people, simply astonishing:Russell and Norvig write "it was astonishing whenever a computer did anything kind of smartish." Russell & Norvig 2003, p. 18 computers were solving word problems in algebra, proving logical theorems and speaking English.Crevier 1993, pp. 52-107, Moravec 1988, p. 9 and Russell & Norvig 2003, p. 18-21. The programs described are Daniel Bobrow\'s STUDENT, Newell and Simon\'s Logic Theorist and Terry Winograd\'s SHRDLU. By the middle 60s their research was heavily funded by the U.S. Department of DefenseCrevier 1993, pp. 64-65 and they were optimistic about the future of the new field:
These predictions, and many like them, would not come true. They had failed to recognize the difficulty of some of the problems they faced.See History of artificial intelligence — the problems. In 1974, in response to the criticism of England\'s Sir James Lighthill and ongoing pressure from Congress to fund more productive projects, DARPA cut off all undirected, exploratory research in AI. This was the first AI Winter.Crevier 1993, pp. 115-117, Russell & Norvig 2003, p. 22, NRC 1999 under "Shift to Applied Research Increases Investment." and also see Howe, J. "Artificial Intelligence at Edinburgh University : a Perspective"
In the early 80s, AI research was revived by the commercial success of expert systems; applying the knowledge and analytical skills of one or more human experts. By 1985 the market for AI had reached more than a billion dollars.Crevier 1993, pp. 161-162,197-203 and and Russell & Norvig 2003, p. 24 Minsky and others warned the community that enthusiasm for AI had spiraled out of control and that disappointment was sure to follow.Crevier 1993, p. 203 Beginning with the collapse of the Lisp Machine market in 1987, AI once again fell into disrepute, and a second, more lasting AI Winter began.Crevier 1993, pp. 209-210
In the 90s and early 21st century AI achieved its greatest successes, albeit somewhat behind the scenes. Artificial intelligence was adopted throughout the technology industry, providing the heavy lifting for logistics, data mining, medical diagnosis and many other areas.Russell Norvig, p. 28,NRC 1999 under "Artificial Intelligence in the 90s" The success was due to several factors: the incredible power of computers today (see Moore\'s law), a greater emphasis on solving specific subproblems, the creation of new ties between AI and other fields working on similar problems, and above all a new commitment by researchers to solid mathematical methods and rigorous scientific standards.Russell Norvig, pp. 25-26
| | Mind and Brain Portal |
Can the brain be simulated? Does this prove machines can think?
The philosophy of artificial intelligence considers the question "Can machines think?" Alan Turing, in his classic 1950 paper, Computing Machinery and Intelligence, was the first to try to answer it. In the years since, several answers have been given:All of these positions are mentioned in standard discussions of the subject, such as Russell & Norvig 2003, pp. 947-960 and Fearn 2007, pp. 38-55
While there is no universally accepted definition of intelligence,"We cannot yet characterize in general what kinds of computational procedures we want to call intelligent." John McCarthy, Basic Questions AI researchers have studied several traits that are considered essential.
Early AI researchers developed algorithms that imitated the process of conscious, step-by-step reasoning that human beings use when they solve puzzles, play board games, or make logical deductions.Problem solving, puzzle solving, game playing and deduction: Russell & Norvig 2003, chpt. 3-9, Poole et al. chpt. 2,3,7,9, Luger & Stubblefield 2004, chpt. 3,4,6,8, Nilsson, chpt. 7-12. By the late 80s and 90s, AI research had also developed highly successful methods for dealing with uncertain or incomplete information, employing concepts from probability and economics.Uncertain reasoning: Russell & Norvig 2003, pp. 452-644, Poole, Mackworth & Goebel 1998, pp. 345-395, Luger & Stubblefield 2004, pp. 333-381, Nilsson 1998, chpt. 19
For difficult problems, most of these algorithms can require enormous computational resources — most experience a "combinatorial explosion": the amount of memory or computer time required becomes astronomical when the problem goes beyond a certain size. The search for more efficient problem solving algorithms is a high priority for AI research.Intractability and efficiency and the combinatorial explosion: Russell & Norvig 2003, pp. 9, 21-22
It is not clear, however, that conscious human reasoning is any more efficient when faced with a difficult abstract problem. Cognitive scientists have demonstrated that human beings solve most of their problems using unconscious reasoning, rather than the conscious, step-by-step deduction that early AI research was able to model. Several famous examples: Wason (1966) showed that people do poorly on completely abstract problems, but if the problem is restated to allowed the use of intuitive social intelligence, performance dramatically improves. (See Wason selection task) Tversky, Slovic & Kahnemann (1982) have shown that people are terrible at elementary problems that involve uncertain reasoning. (See list of cognitive biases for several examples). Lakoff & Nunez (2000) have controversially argued that even our skills at mathematics depend on knowledge and skills that come from "the body", i.e. sensorimotor and perceptual skills. (See Where Mathematics Comes From) Embodied cognitive science argues that unconscious sensorimotor skills are essential to our problem solving abilities. It is hoped that sub-symbolic methods, like computational intelligence and situated AI, will be able to model these instinctive skills. The problem of unconscious problem solving, which forms part of our commonsense reasoning, is largely unsolved.
Knowledge representationKnowledge representation: ACM 1998, I.2.4, Russell & Norvig 2003, pp. 320-363, Poole, Mackworth & Goebel 1998, pp. 23-46, 69-81, 169-196, 235-277, 281-298, 319-345, Luger & Stubblefield 2004, pp. 227-243, Nilsson 1998, chpt. 18 and knowledge engineeringKnowledge engineering: Russell & Norvig 2003, pp. 260-266, Poole, Mackworth & Goebel 1998, pp. 199-233, Nilsson 1998, chpt. ~17.1-17.4 are central to AI research. Many of the problems machines are expected to solve will require extensive knowledge about the world. Among the things that AI needs to represent are: objects, properties, categories and relations between objects;Representing categories and relations: Semantic networks, description logics, inheritance (including frames and scripts): Russell & Norvig 2003, pp. 349-354, Poole, Mackworth & Goebel 1998, pp. 174-177, Luger & Stubblefield 2004, pp. 248-258, Nilsson 1998, chpt. 18.3 situations, events, states and time;Representing events and time: Situation calculus, event calculus, fluent calculus (including solving the frame problem): Russell & Norvig 2003, pp. 328-341, Poole, Mackworth & Goebel 1998, pp. 281-298, Nilsson 1998, chpt. 18.2 causes and effects;Causal calculus: Poole, Mackworth & Goebel 1998, pp. 335-337 knowledge about knowledge (what we know about what other people know);Representing knowledge about knowledge: Belief calculus, modal logics: Russell & Norvig 2003, pp. 341-344, Poole, Mackworth & Goebel 1998, pp. 275-277 and many other, less well researched domains. A complete representation of "what exists" is an ontologyOntology: Russell & Norvig 2003, pp. 320-328 (borrowing a word from traditional philosophy), of which the most general are called upper ontologies.
Among the most difficult problems in knowledge representation are:
Intelligent agents must be able to set goals and achieve them.Planning: ACM 1998, ~I.2.8, Russell & Norvig 2003, pp. 375-459, Poole, Mackworth & Goebel 1998, pp. 281-316, Luger & Stubblefield 2004, pp. 314-329, Nilsson 1998, chpt. 10.1-2, 22 They need a way to visualize the future: they must have a representation of the state of the world and be able to make predictions about how their actions will change it. They must also attempt to determine the utility or "value" of the choices available to it.Information value theory: Russell & Norvig 2003, pp. 600-604
In some planning problems, the agent can assume that it is the only thing acting on the world and it can be certain what the consequences of it\'s actions may be.Classical planning: Russell & Norvig 2003, pp. 375-430, Poole, Mackworth & Goebel 1998, pp. 281-315, Luger & Stubblefield 2004, pp. 314-329, Nilsson 1998, chpt. 10.1-2, 22 However, if this is not true, it must periodically check if the world matches its predictions and it must change its plan as this becomes necessary, requiring the agent to reason under uncertainty.Planning and acting in non-deterministic domains: conditional planning, execution monitoring, replanning and continuous planning: Russell & Norvig 2003, pp. 430-449
Multi-agent planning tries to determine the best plan for a community of agents, using cooperation and competition to achieve a given goal. Emergent behavior such as this is used by both evolutionary algorithms and swarm intelligence.Multi-agent planning and emergent behavior: Russell & Norvig 2003, pp. 449-455
Important machine learningLearning: ACM 1998, I.2.6, Russell & Norvig 2003, pp. 649-788, Poole, Mackworth & Goebel 1998, pp. 397-438, Luger & Stubblefield 2004, pp. 385-542, Nilsson 1998, chpt. 3.3 , 10.3, 17.5, 20 problems are:
the agent is rewarded for good responses and punished for bad ones. (These can be analyzed in terms decision theory, using concepts like utility).
Natural language processingNatural language processing: ACM 1998, I.2.7, Russell & Norvig 2003, pp. 790-831, Poole, Mackworth & Goebel 1998, pp. 91-104, Luger & Stubblefield 2004, pp. 591-632 gives machines the ability to read and understand the languages human beings speak. Many researchers hope that a sufficiently powerful natural language processing system would be able to acquire knowledge on its own, by reading the existing text available over the internet. Some straightforward applications of natural language processing include information retrieval (or text mining) and machine translation. Applications of natural language processing, including information retrieval (i.e. text mining) and machine translation Russell & Norvig 2003, pp. 840-857, Luger & Stubblefield 2004, pp. 623-630
ASIMO uses sensors and intelligent algorithms to avoid obstacles and navigate stairs.
The field of roboticsRobotics: ACM 1998, I.2.9, Russell & Norvig 2003, pp. 901-942, Poole, Mackworth & Goebel 1998, pp. 443-460 is closely related to AI. Intelligence is required for robots to be able to handle such tasks as object manipulationMoving and configuration space: Russell Norivg, pp. 916-932 and navigation, with sub-problems of localization (knowing where you are), mapping (learning what is around you) and motion planning (figuring out how to get there).Robotic mapping (localization, etc) Russell Norvig, pp. 908-915
Machine perceptionMachine perception: Russell & Norvig 2003, pp. 537-581, 863-898, Nilsson 1998, ~chpt. 6 is the ability to use input from sensors (such as cameras, microphones, sonar and others more exotic) to deduce aspects of the world. Computer visionComputer vision: ACM 1998, I.2.10, Russell & Norvig 2003, pp. 863-898, Nilsson 1998, chpt. 6 is the ability to analyze visual input. A few selected subproblems are speech recognition,Speech recognition: ACM 1998, ~I.2.7, Russell & Norvig 2003, pp. 568-578 facial recognition and object recognition.Object recognition: Russell & Norvig 2003, pp. 885-892
Kismet, a robot with rudimentary social skills.
Emotion and social skills play two roles for an intelligent agent:Minsky 2007, Picard 1997
Most researchers hope that their work will eventually be incorporated into a machine with general intelligence (known as strong AI), combining all the skills above and exceeding human abilities at most or all of them. A few believe that anthropomorphic features like artificial consciousness or an artificial brain may be required for such a project.
Many of the problems above are considered AI-complete: to solve one problem, you must solve them all. For example, even a straightforward, specific task like machine translation requires that the machine follow the author\'s argument (reason), know what it\'s talking about (knowledge), and faithfully reproduce the author\'s intention (social intelligence). Machine translation, therefore, is believed to be AI-complete: it may require strong AI to be done as well as humans can do it.Shapiro 1992, p. 9
There are as many approaches to AI as there are AI researchers—any coarse categorization is likely to be unfair to someone. Artificial intelligence communities have grown up around particular problems, institutions and researchers, as well as the theoretical insights that define the approaches described below. Artificial intelligence is a young science and is still a fragmented collection of subfields. At present, there is no established unifying theory that links the subfields into a coherent whole.
In the 40s and 50s, a number of researchers explored the connection between neurology, information theory, and cybernetics. Some of them built machines that used electronic networks to exhibit rudimentary intelligence, such as W. Grey Walter\'s turtles and the Johns Hopkins Beast. Many of these researchers gathered for meetings of the Teleological Society at Princeton and the Ratio Club in England. Among the researchers who laid the foundations of cybernetics, information theory and neural networks were Claude Shannon, Norbert Weiner, Warren McCullough, Walter Pitts, Donald Hebb, Donald McKay, Alan Turing and John Von Neumann.
McCorduck 2004, pp. 51-107
Crevier 1993, pp. 27-32,
Russell & Norvig 2003, pp. 15,940,
Moravec 1988, p. 3.
When access to digital computers became possible in the middle 1950s, AI research began to explore the possibility that human intelligence could be reduced to symbol manipulation. The research was centered in three institutions: CMU, Stanford and MIT, and each one developed its own style of research. John Haugeland named these approaches to AI "good old fashioned AI" or "GOFAI".
Haugeland 1985, pp. 112-117
Crevier 1993, pp. 52-54, 258-263, Nilsson 1998, p. 275
See Science at Google Books, and McCarthy\'s presentation at AI@50 His laboratory at Stanford (SAIL) focussed on using formal logic to solve wide variety of problems, including knowledge representation, planning and learning. Work in logic led to the development of the programming language Prolog and the science of logic programming.
Crevier 1993, pp. 193-196
Crevier 1993, pp. 163-176. Neats vs. scruffies: Crevier 1993, pp. 168. and this still forms the basis of research into commonsense knowledge bases (such as Doug Lenat\'s Cyc) which must be built one complicated concept at a time.
During the 1960s, symbolic approaches had achieved great success at simulating high-level thinking in small demonstration programs. Approaches based on cybernetics or neural networks were abandoned or pushed into the background. The most dramatic case of sub-symbolic AI being pushed into the background was the devastating critique of perceptrons by Marvin Minsky and Seymour Papert in 1969. See History of AI, AI winter, or Frank Rosenblatt. (Crevier 1993, pp. 102-105). By the 1980s, however, progress in symbolic AI seemed to stall and many believed that symbolic systems would never be able to imitate all the processes of human cognition, especially perception, robotics, learning and pattern recognition. A number of researchers began to look into "sub-symbolic" approaches to specific AI problems.Nilsson (1998, p. 7) characterizes these newer approaches to AI as "sub-symbolic".
Crevier 1993, pp. 214-215 and Russell & Norvig 2003, p. 25 These and other sub-symbolic approaches, such as fuzzy systems and evolutionary computation, are now studied collectively by the emerging discipline of computational intelligence. See IEEE Computational Intelligence Society
Russell & Norvig 2003, p. 25-26
The "intelligent agent" paradigm became widely accepted during the 1990s. "The whole-agent view is now widely accepted in the field" Russell & Norvig 2003, p. 55. The intelligent agent paradigm is discussed in major AI textbooks, such as:
Russell & Norvig 2003, pp. 27, 32-58, 968-972,
Poole, Mackworth & Goebel 1998, pp. 7-21,
Luger & Stubblefield 2004, pp. 235-240
Although earlier researchers had proposed modular "divide and conquer" approaches to AI, For example, both John Doyle (Doyle 1983) and Marvin Minsky\'s popular classic The Society of Mind (Minsky 1986) used the word "agent" to describe modular AI systems. the intelligent agent did not reach its modern form until Judea Pearl, Alan Newell and others brought concepts from decision theory and economics into the study of AI.
Russell & Norvig 2003, pp. 27, 55
When the economist\'s definition of a rational agent was married to computer science\'s definition of an object or module, the intelligent agent paradigm was complete.
An intelligent agent is a system that perceives its environment and takes actions which maximizes its chances of success. The simplest intelligent agents are programs that solve specific problems. The most complicated intelligent agents would be rational, thinking human beings.
The paradigm gives researchers license to study isolated problems and find solutions that are both verifiable and useful, without agreeing on one single approach. An agent that solves a specific problem can use any approach that works — some agents are symbolic and logical, some are sub-symbolic neural networks and some can be based on new approaches (without forcing researchers to reject old approaches that have proven useful). The paradigm gives researchers a common language to describe problems and share their solutions with each other and with other fields—such as decision theory—that also use concepts of abstract agents.
An agent architecture or cognitive architecture allows researchers to build more versatile and intelligent systems out of interacting intelligent agents in a multi-agent system. Agent architectures, hybrid intelligent systems, and multi-agent systems:
ACM 1998, I.2.11,
Russell & Norvig (1998, pp. 27, 932, 970-972) and
Nilsson (1998, chpt. 25)
A system with both symbolic and sub-symbolic components is a hybrid intelligent system, and the study of such systems is artificial intelligence systems integration. A hierarchical control system provides a bridge between sub-symbolic AI at its lowest, reactive levels and traditional symbolic AI at its highest levels, where relaxed time constraints permit planning and world modelling.Albus, J. S. 4-D/RCS reference model architecture for unmanned ground vehicles. In G Gerhart, R Gunderson, and C Shoemaker, editors, Proceedings of the SPIE AeroSense Session on Unmanned Ground Vehicle Technology, volume 3693, pages 11--20 Rodney Brooks\' subsumption architecture was an early proposal for such a hierarchical system.
In the course of 50 years of research, AI has developed a large number of tools to solve the most difficult problems in computer science. A few of the most general of these methods are discussed below.
Many problems in AI can be solved in theory by intelligently searching through many possible solutions:Search algorithms: Russell & Norvig 2003, pp. 59-189, Poole, Mackworth & Goebel 1998, pp. 113-163, Luger & Stubblefield 2004, pp. 79-164, 193-219, Nilsson 1998, chpt. 7-12 Reasoning can be reduced to performing a search. For example, logical proof can be viewed as searching for a path that leads from premises to conclusions, where each step is the application of an inference rule.Forward chaining, backward chaining, Horn clauses, and logical deduction as search: Russell & Norvig 2003, pp. 217-225, 280-294, Poole, Mackworth & Goebel 1998, pp. ~46-52, Luger & Stubblefield 2004, pp. 62-73, Nilsson 1998, chpt. 4.2, 7.2 Planning algorithms search through trees of goals and subgoals, attempting to find a path to a target goal.State space search and planning: Russell & Norvig 2003, pp. 382-387, Poole, Mackworth & Goebel 1998, pp. 298-305, Nilsson 1998, chpt. 10.1-2 Robotics algorithms for moving limbs and grasping objects use local searches in configuration space. Even some learning algorithms have at their core a search engine.
There are several types of search algorithms:
ACM 1998, ~I.2.3,
Russell & Norvig 2003, pp. 194-310,
Luger & Stubblefield 2004, pp. 35-77,
Nilsson 1998, chpt. 13-16
was introduced into AI research by John McCarthy in his 1958 Advice Taker proposal. The most important technical development was J. Alan Robinson\'s discovery of the resolution and unification algorithm for logical deduction in 1963. This procedure is simple, complete and entirely algorithmic, and can easily be performed by digital computers. Resolution and unification:
Russell & Norvig 2003, pp. 213-217, 275-280, 295-306,
Poole, Mackworth & Goebel 1998, pp. 56-58,
Luger & Stubblefield 2004, pp. 554-575,
Nilsson 1998, chpt. 14 & 16
However, a naive implementation of the algorithm quickly leads to a combinatorial explosion or an infinite loop. In 1974, Robert Kowalski suggested representing logical expressions as Horn clauses (statements in the form of rules: "if p then q"), which reduced logical deduction to backward chaining or forward chaining. This greatly alleviated (but did not eliminate) the problem. History of logic programming:
Crevier 1993, pp. 190-196. Advice Taker:
McCorduck 2004, p. 51,
Russell & Norvig 2003, pp. 19
Logic is used for knowledge representation and problem solving, but it can be applied to other problems as well. For example, the satplan algorithm uses logic for planning, Satplan:
Russell & Norvig 2003, pp. 402-407,
Poole, Mackworth & Goebel 1998, pp. 300-301,
Nilsson 1998, chpt. 21
and inductive logic programming is a method for learning. Explanation based learning, relevance based learning, inductive logic programming, case based reasoning:
Russell & Norvig 2003, pp. 678-710,
Poole, Mackworth & Goebel 1998, pp. 414-416,
Luger & Stubblefield 2004, pp. ~422-442,
Nilsson 1998, chpt. 10.3, 17.5
There are several different forms of logic used in AI research.
Russell & Norvig 2003, pp. 204-233,
Luger & Stubblefield 2004, pp. 45-50
Nilsson 1998, chpt. 13
or sentential logic is the logic of statements which can be true or false.
First order logic and features such as equality:
ACM 1998, ~I.2.4,
Russell & Norvig 2003, pp. 240-310,
Poole, Mackworth & Goebel 1998, pp. 268-275,
Luger & Stubblefield 2004, pp. 50-62,
Nilsson 1998, chpt. 15
also allows the use of quantifiers and predicates, and can express facts about objects, their properties, and their relations with each other.
Russell & Norvig 2003, pp. 526-527
Many problems in AI (in reasoning, planning, learning, perception and robotics) require the agent to operate with incomplete or uncertain information. Starting in the late 80s and early 90s, Judea Pearl and others championed the use of methods drawn from probability theory and economics to devise a number of powerful tools to solve these problems.Russell & Norvig 2003, pp. 25-26 (on Judea Pearl\'s contribution). Stochastic methods are described in all the major AI textbooks: ACM 1998, ~I.2.3, Russell & Norvig 2003, pp. 462-644, Poole, Mackworth & Goebel 1998, pp. 345-395, Luger & Stubblefield 2004, pp. 165-191, 333-381, Nilsson 1998, chpt. 19
Bayesian networksBayesian networks: Russell & Norvig 2003, pp. 492-523, Poole, Mackworth & Goebel 1998, pp. 361-381, Luger & Stubblefield 2004, pp. ~182-190, ~363-379, Nilsson 1998, chpt. 19.3-4 are very general tool that can be used for a large number of problems: reasoning (using the Bayesian inference algorithm), Bayesian inference algorithm: Russell & Norvig 2003, pp. 504-519, Poole, Mackworth & Goebel 1998, pp. 361-381,
