This article presents a formal theory of robot perception as a form of abduction. The theory pins down the process whereby low-level sensor data is transformed into a symbolic representation of the external world, drawing together aspects such as incompleteness, top-down information flow, active perception, attention, and sensor fusion in a unifying framework. In addition, a number of themes are identified that are common to both the engineer concerned with developing a rigorous theory of perception, such as the one on offer here, and the philosopher of mind who is exercised by questions relating to mental representation and intentionality.

This paper surveys research in developing computational models for integrating linguistic and visual information. It begins with a discussion of systems which have been actually implemented and continues with computationally motivated theories of human cognition. Since existing research spans several disciplines (e.g., natural language understanding, computer vision, knowledge representation), as well as several application areas, an important contribution of this paper is to categorize existing research based on inputs and objectives. Finally, some key issues related to integrating information from two such diverse sources are outlined and related to existing research. Throughout, the key issue addressed is the correspondence problem, namely how to associate visual events with words and vice versa. 1 Introduction Much has been said about the necessity of linking language and vision in order for a system to exhibit intelligent behaviour [Win73, Wal81]. A complete natural-language und...

. We investigate three approaches to Boolean satisfiability problems. We study and compare the best heuristic algorithm WGSAT and two evolutionary algorithms, an evolution strategy and an evolutionary algorithm adapting its own fitness function while running. The results show that the adaptive EA outperforms the other two approaches. The power of this EA originates from the adaptive mechanism, which is completely problem independent and generally applicable to any constraint satisfaction problem. This suggests that the adaptive EA is not only a good solver for satisfiability problems, but for constraint satisfaction problems in general. 1 Introduction Handling NP-complete problems with evolutionary algorithms (EAs) is a great challenge. In particular, the presence of constraints makes finding solutions difficult for an EA. In this paper, we investigate solving constraint satisfaction problems (CSPs), in particular the 3-SAT problem, and try three different approaches for solving it: O...

In this paper we describe how to modify GSAT so that it can be applied to non-clausal formulas. The idea is to use a function which computes the number of clauses of the CNF conversion of a formula which are false under a certain truth assignment, without constructing the conversion itself. The proposed methodology applies to most variants of GSAT.

this paper we have used the notion of interpretations that are consistent with an image. A formal specification of this notion is given in Reiter & Mackworth (1989), and this component itself can be seen to involve considerable machinery. A second formal issue is that the transitive closure of the elementary preference relations must be a partial order. Ascent through this order and the search for locally maximal nodes raise several technical difficulties that we have ignored. A third important issue is to elaborate the means for recognizing and evaluating incoherent interpretations that leave regularities unexplained (Jepson & Richards, 1993; Geffner, 1989; MacKay, 1978). And finally, considerable experimental work needs to be done to determine appropriate sets of preferences and their correlated regularities: i.e. the modes and their associated elemental preference relations. Acknowledgments

In recent years, there has been an explosion of research in AI into propositional satis ability (or Sat). There are many factors behind the increased interest in this area. One factor is the improvement in search procedures for Sat. New local search procedures like Gsat are able to solve Sat problems with thousands of variables. At the same time, implementations of complete search algorithms like Davis-Putnam have been able to solve open mathematical problems. Another factor is the identi cation of hard Sat problems at a phase transition in solubility. A third factor is the demonstration that we can often solve real world problems by encoding them into Sat. There has also seen an improved theoretical understanding of Sat, particularly in the analysis of such phase transition behaviour. This paper reviews the state of the art for research into satis ability, and discuss applications in which algorithms for satis ability have proved successful.

In this paper, we investigate a family of hill-climbing procedures related to GSAT, a greedy random hill-climbing procedure for satisfiability. These procedures are able to solve large and difficult satisfiability problems beyond the range of conventional procedures like Davis-Putnam. We explore the role of greediness, randomness and hill-climbing in the effectiveness of these procedures. We show that neither greediness nor randomness is crucial to GSAT's performance, and that hill-climbing's importance is limited to a short initial phase of search. In addition, we observe some remarkable and possibly universal features of their search for a satisfying truth assignment. 1 Introduction Many problems in AI are NP-hard and are thus, in general, intractable. A solution to this intractability is to give up completeness; that is, instead of an algorithm which is guaranteed to return an answer, we provide a tractable procedure which will often return an answer but may sometimes term...

This paper investigates perceptual grouping from a logical point of view, defining a grouping interpretation as a particular kind of logical expression, and then developing an explicit inference theory in terms of such expressions. First, a regularity-based interpretation language is presented, in which an observed configuration is characterized in terms of the regularities (special configurational classes, e.g. non-accidental properties) it obeys. The most preferred interpretation in such a system is shown to be the most-regular (maximum "codimension") model the observed configuration obeys, which is also the unique model in which it is generic (typical). Inference then reduces to a straightforward exercise in Logic Programming. Because generic model assignment involves negation, this reduction requires that a version of the Closed World Assumption (CWA) be adopted

Abstract not found

This paper is about database researchers building interactive information systems. It tells the reader of their initial enthusiasm and user-induced frustration, the consequent discovery of both human-computer interaction (hci) world and the concept of system "usability", and finally their quite successful coupling of hci and databases. Key words: User Interface, Information System, Usability 1. INTRODUCTION It is now generally accepted that factors which mainly influence the success of computerized projects are human and organizational, rather than technological. The mere fact of using computer technologies, even if they are reliable, powerful and innovative, cannot solve work organization problems if the acquired instruments are not in harmony with the attitudes, motivations and competencies of workers in that organization, and also with the social and environmental context of their activities.