Good Old Fashioned Artificial Intelligence and Robotics (GOFAIR) relies on a set of restrictive Omniscient Fortune Teller Assumptions about the agent, the world and their relationship. The emerging Situated Agent paradigm is challenging GOFAIR by grounding the agent in space and time, relaxing some of those assumptions, proposing new architectures and integrating perception, reasoning and action in behavioral modules. GOFAIR is typically forced to adopt a hybrid architecture for integrating signal-based and symbol-based approaches because of the inherent mismatch between the corresponding on-line and off-line computational models. It is argued that Situated Agents should be designed using a unitary on-line computational model. The Constraint Net model of Zhang and Mackworth satisfies that requirement. Two systems for situated perception built in our laboratory are described to illustrate the new approach: one for visual monitoring of a robot's arm, the other for real-time visual control of multiple robots competing and cooperating in a dynamic world.

This work analyzes the central role of interpretation in non-routine design. Based on this analysis, a theory of computer support for interpretation in cooperative design is constructed. The theory is grounded in studies of design and interpretation. It is illustrated by mechanisms provided by a software substrate for computer-based design environments, applied to a sample task of lunar habitat design. Computer support of

The knowledge required for action is generally indexical rather than objective. For example, a robot that knows the relative position of an object is generally able to go and pick it up; he need not know its absolute position. Agents may have very incomplete knowledge of their situation in terms of what objective facts hold and still be able to achieve their goals. This paper presents a formal theory of knowledge and action, embodied in a modal logic, that handles the distinction between indexical and objective knowledge and allows a proper specification of the knowledge prerequisites and effects of action. Several kinds of robotics situations involving indexical knowledge are formalized within the framework; these examples show how actions can be specified so as to avoid making excessive requirements upon the knowledge of agents. 1 Introduction 1.1 Motivation Designing autonomous robots or other kinds of agents that interact in sophisticated ways with their environment is hard; yo...

This essay continues my investigation of `syntactic semantics': the theory that, pace Searle's Chinese-Room Argument, syntax does suffice for semantics (in particular, for the semantics needed for a computational cognitive theory of natural-language understanding). Here, I argue that syntactic semantics (which is internal and first-person) is what has been called a conceptual-role semantics: The meaning of any expression is the role that it plays in the complete system of expressions. Such a `narrow', conceptual-role semantics is the appropriate sort of semantics to account (from an `internal', or first-person perspective) for how a cognitive agent understands language. Some have argued for the primacy of external, or `wide', semantics, while others have argued for a two-factor analysis. But, although two factors can be specified---one internal and first-person, the other only specifiable in an external, third-person way---only the internal, first-person one is needed for understanding how someone understands. A truth-conditional semantics can still be provided, but only from a third-person perspective.

The computer metaphor of cognitivism that has had such a strong influence on cognitive science over recent decades seems to be confronted (again) by a competitor: the brain metaphor put forward by connectionism (e.g. [McClelland and Rumelhart 1986] and [Sejnowski et al. 1988]). Connectionism assumes that mental phenomena can be explained in terms of the parallel activation and interaction of a large number of units (model neurons). These units are linked by connections (artificial synapses) which modulate the transmitted activity. Knowledge is represented in these connections between the units and learning takes place by adjusting their strength. An important, and much emphasized, aspect of connectionist models is their emergent behaviour. The massive parallel interaction of a large number of simple units can lead to qualitatively different and more interesting forms of behaviour. Successes of this connectionist approach range from models of human

Much of the natural language text found on the web contains various kinds of generic or “common sense ” knowledge, and this information has long been recognized by artificial intelligence as an important supplement to more formal approaches to building Semantic Web knowledge bases. Consequently, we are exploring the possibility of automatically identifying “common sense” statements from unrestricted natural language text and mapping them to RDF. Our hypothesis is that common sense knowledge is often expressed in the form of generic statements such as Coffee is a popular beverage, and thus our work has focussed on the challenge of automatically identifying generic statements. We have been using the Wikipedia xml corpus as a rich source of common sense knowledge. For evaluation, we have been using the existing annotation of generic entities and relations in the ace 2005 corpus.

It is claimed that there are pre-objective phenomena, which cognitive science should explain by employing the notion of non-conceptual representational content. It is argued that a match between parallel distributed processing (PDP) and non-conceptual content (NCC) not only provides a means of refuting recent criticisms of PDP as a cognitive architecture; it also provides a vehicle for NCC that is required by naturalism. A connectionist cognitive mapping algorithm is used as a case study to examine the affinities between PDP and NCC.

Abstract not found

What is the computational notion of "implementation"? It is not individuation, instantiation, reduction, or supervenience. It is, I suggest, semantic interpretation. This document is Technical Report 97-15 (Buffalo: SUNY Buffalo Department of Computer Science) and Technical Report 97-5 (Buffalo: SUNY Buffalo Center for Cognitive Science). 1 INTRODUCTION Consider the relationships among algorithms, computer programs, and the computers that execute them. An algorithm is (roughly) a procedure for computing a function (for more details, see Soare 1996; Rapaport, forthcoming). A program is a more specific and detailed textual expression of an algorithm, expressed in a programming language. Often, it is said that the program "implements" the algorithm. A computer process is an algorithm being executed (see Rapaport 1988, 1995; Smith 1997). It is a physical device (a computer) behaving in a certain way ; the way is described (or specified) by the program, and the physical device running the ...

This work analyzes the central role of interpretation in non-routine design. Based on this analysis, a theory of computer support for interpretation in cooperative design is constructed. The theory is grounded in studies of design and interpretation. It is illustrated by mechanisms provided by a software substrate for computer-based design environments, applied to a sample task of lunar habitat design.