If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."
However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …
In the synthesis of a plan or computer program, the problem of achieving several goals simultaneously presents special difficulties, since a plan to achieve one goal may interfere with attaining the others. This paper develops the following strategy: to achieve two goals simultaneously, develop a plan to achieve one of them and then modify that plan to achieve the second as well. A systematic program modification technique is presented to support this strategy. The technique requires the introduction of a special "skeleton model" to represent a changing world that can accommodate modifications in the plan. This skeleton model also provides a novel approach to the "frame problem."
The selection of what to do next is often the hardest part of resource-limited problem solving. In planning problems, there are typically many goals to be achieved in some order. The goals interact with each other in ways which depend both on the order in which they are achieved and on the particular operators which are used to achieve them. A planning program needs to keep its options open because decisions about one part of a plan are likely to have consequences for another part. This paper describes an approach to planning which integrates and extends two strategies termed the least-commitment and the heuristic strategies.
In this paper we describe some major new additions to the STRIPS robot problem-solving system. The first addition is a process for generalizing a plan produced by STRIPS so that problem-specific constants appearing in the plan are replaced by problem-independent parameters. The generalized plan, stored in a convenient format called a triangle table, has two important functions. The more obvious function is as a single macro action that can be used by STRIPS-- either in whole or in part--during the solution of a subsequent problem. Perhaps less obviously, the generalized plan also plays a central part in the process that monitors the real-world execution of a plan, and allows the robot to react "intelligently" to unexpected consequences of actions.
This paper explores the truism that people think about what they say. It proposes that, to satisfy their own goals, people often plan their speech acts to affect their listeners' beliefs, goals, and emotional states. Such language use can be modelled by viewing speech acts as operators in a planning system, thus allowing both physical and speech acts to be integrated into plans. Methodological issues of how speech acts should be defined in a planbased theory are illustrated by defining operators for requesting and informing. Plans containing those operators are presented and comparisons ore drawn with Searle's formulation.
The Role of Experiences and Examples in Learning Systems Edwina L. Rissland Oliver G. Selfridge Elliot M. Soloway* Department of Computer and Information Science University of Massachusetts Amherst, MA 01003 Abstract In this paper, we discuss the role of experiences and examples in learning systems. We discuss these issues in the context of three systems in particular: Rissland and Soloway's Constrained Example Generation (CEG) System, Selfridge's COUNT, and Soloway's BASEBALL. Examples provide the basis from which generalizations, concepts and conjectures are made. They also provide the criticisms needed to refute and refine. For instance, in Winston's learning program [Winston 1975], examples of the concept to be learned, e.g., an arch, and non-examples, e.g., "near misses", are the critical input from which his program builds a structural description of a concept.
VICTORIA, B. C. 14, 15, 16 MAY 1980 3. Goal Subsumption - Goal subsumption gives rise to dramatic situations when a subsumption state is terminated. For example, if John is happily married to Mary, and then Mary leaves him, all the goals subsumed by their relationship may now be problematic - John may become lonely, and miss his social interactions with Mary, for instance. Closely related to problems based on goal subsumption are those caused by the elimination of normal physical states. For example, becoming very depressed or losing a bodily function can give rise to the inability to fulfill recurring goals, and can therefore generate some interesting problems. The resolution of goal subsumption termination involves establishing a new subsumption state to re-subsume the recurring goals.
A new predicate calculus deduction system based on production rules is proposed. The system combines several developments in Artificial Intelligence and Automatic Theorem Proving research including the use of domain-specific inference rules and separate mechanisms for forward and backward reasoning. It has a clean separation between the data base, the production rules, and the control system. Goals and subgoals are maintained in an AND/OR tree structure. Logical deduction is a basic activity in many artificial intelligence (Al) systems.
In the synthesis of a plan or computer program, the problem of achieving several goals simultaneously presents special difficulties, since a plan to achieve one goal may interfere with attaining the others. This paper develops the following strategy: to achieve two goals simultaneously, develop a plan to . A systematic program modification technique is presented to support this strategy. The technique requires the introduction of a special "skeleton model" to represent a changing world that can accommodate modifications in the plan. This skeleton model also provides a novel approach to the "frame problem."
For the past several years research on robot problem-solving methods has centered on what may one day be called'simple' plans: linear sequences of actions to be performed by single robots to achieve single goals in static environments. Recent speculation and preliminary work at several research centers has suggested a variety of ways in which these traditional constraints could be relaxed. In this paper we describe some of these possible extensions, illustrating the discussion where possible with examples taken from the current Stanford Research Institute robot system. A major theme in current artificial intelligence research is the design and construction of programs that perform robot problem solving. The usual formulation begins with the assumption of a physical device like a mechanical arm or a vehicle that can use any of a preprogrammed set of actions to manipulate objects in its environment.
The frame problem in representing natural-language information is discussed. It is argued that the problem is not restricted to problem-solving-type situations, in which it has mostly been studied so far, but also has a broader significance. A new solution to the frame problem, which arose within a larger system for representing natural-language information, is described. The basic idea is to extend the predicate calculus notation with a special operator, Unless, with peculiar properties. Some difficulties with Unless are described.