Several high level methodological debates among AI researchers, linguists, psychologists and philosophers, appear to be endless, e.g. about the need for and nature of representations, about the role of symbolic processes, about embodiment, about situatedness, about whether symbol-grounding is needed, and about whether a robot needs any knowledge at birth or can start simply with a powerful learning mechanism. Consideration of the variety of capabilities and development patterns on the precocial-altricial spectrum in biological organisms will help us to see these debates in a new light. 1

This article describes a theory of the computations underlying the selection of coordinated motion patterns, especially in reaching tasks. The central idea is that when a spatial target is selected as an object to be reached, stored postures are evaluated for the contributions they can make to the task. Weights are assigned to the stored postures, and a single target posture is found by taking a weighted sum of the stored postures. Movement is achieved by reducing the distance between the starting angle and target angle of each joint. The model explains compensation for reduced joint mobility, tool use, practice effects, performance errors, and aspects of movement kinematics. Extensions of the model can account for anticipation and coarticulation effects, movement through via points, and hierarchical control of series of movements. The goal of this research is a unified theory of the planning and control of physical action. Such a theory, as several authors have noted (Jeannerod, in press; Rosenbaum, 1991; Wing, 1993), has been lacking. Instead, specialized models have been designed to account for data from different tasks. The sentiment

There are many approaches to the study of mind, and much ambiguity in the use of words like `emotion' and `consciousness'. This paper adopts the design stance and attempts to understand human minds as information processing virtual machines with a complex multi-level architecture whose components evolved at different times and perform different sorts of functions. A multi-disciplinary perspective combining ideas from engineering as well as several sciences helps to constrain the proposed architecture. Variations in the architecture should accommodate infants and adults, normal and pathological cases, and also animals. An analysis of states and processes that each architecture supports provides a new framework for systematically generating concepts of various kinds of mental phenomena. This framework can be used to refine and extend familiar concepts of mind, providing a new, richer, more precise theory-based collection of concepts. Within this unifying framework we hope to explain the ...

Animals and robots perceiving and acting in a world require an ontology that accommodates entities, processes, states of a#airs, etc., in their environment. If the perceived environment includes information-processing systems, the ontology should reflect that. Scientists studying such systems need an ontology that includes the first-order ontology characterising physical phenomena, the second-order ontology characterising perceivers of physical phenomena, and a (recursive) third order ontology characterising perceivers of perceivers, including introspectors. We argue that second- and third-order ontologies refer to contents of virtual machines and examine requirements for scientific investigation of combined virtual and physical machines, such as animals and robots. We show how the CogA# architecture schema, combining reactive, deliberative, and meta-management categories, provides a first draft schematic third-order ontology for describing a wide range of natural and artificial agents. Many previously proposed architectures use only a subset of CogA#, including subsumption architectures, contention-scheduling systems, architectures with `executive functions' and a variety of types of `Omega' architectures.

for Correspondence An agent should adopt different control modes in different situations. Depending on the predictability of its environment and the constraint imposed by its goals, the agent should modulate its sensitivity to run-time events and its commitment to specific actions. We propose an opportunistic control model that supports this flexibility. 3 Abstract Given its multiple goals, limited resources, and dynamic environment, an intelligent agent must decide which of many possible actions to execute at each point in time. Planning and reactive models embody two different modes of control. By contrast, we characterize a two-dimensional space of control modes, each of which maximizes the quality of run-time behavior in the corresponding region of a two-dimensional space of control situations. The situation space is defined by dimensions representing the predictability of the agent's task environment and the constraint imposed by its goals. The space of control modes is defined ...

Clearly we can solve problems by thinking about them. Sometimes we have the impression that in doing so we use words, at other times diagrams or images. Often we use both. What is going on when we use mental diagrams or images? This question is addressed in relation to the more general multi-pronged question: what are representations, what are they for, how many different types are they, in how many different ways can they be used, and what difference does it make whether they are in the mind or on paper? The question is related to deep problems about how vision and spatial manipulation work. It is suggested that we are far from understanding what's going on. In particular we need to explain how people understand spatial structure and motion, and I'll try to suggest that this is a problem with hidden depths, since our grasp of spatial structure is inherently a grasp of a complex range of possibilities and their implications. Two classes of examples discussed at length ...

This paper describes a hierarchy of four navigation strategies --- guidance, place recognition-triggered response, topological navigation and metric navigation. Such a hierarchy can be used to categorize models that are inspired by current knowledge about the way animals navigate in their environments. The main mechanisms implemented in each model are described, together with the basic adaptive capacities that the corresponding strategy affords. Because biomimetic models have seldom been implemented in real robots, it is premature to compare their merits with those of traditional engineering solutions to the navigation problem. Nevertheless, the methodological options that such implementations would entail are discussed in the text. 1 Introduction Animals are living proofs that any system, equipped with proper sensors, proper actuators, and a proper control architecture, can exhibit an adaptive behavior that allows it to survive in environments that can be quite unpredictable and chal...

The idea that natural language grammar and planned action are related systems has been implicit in psychological theory for more than a century. However, formal theories in the two domains have have tended to look very different. This article argues that both faculties share the formal character of applicative systems based on operations corresponding to the same two combinatory operations, namely functional composition and type-raising. Viewing them in this way suggests simpler and more cognitively plausible accounts of both systems, and suggests that the language faculty evolved in the species and develops in children by a rather direct adaptation of a more primitive apparatus for planning purposive action in the world by composing affordances of objects or tools. The knowledge representation that underlies such planning is also reflected in the natural language semantics of tense, mood, and aspect, which the paper begins by arguing provides the key to understanding both systems.

This article, derived from the 1996 American Association for Artificial Intelligence Presidential Address, explores the notion of intelligence from a variety of perspectives and finds that it "are" many things. It has, for example, been interpreted in a variety of ways even within our own field, ranging from the logical view (intelligence as part of mathematical logic) to the psychological view (intelligence as an empirical phenomenon of the natural world) to a variety of others. One goal of this article is to go back to basics, reviewing the things that we, individually and collectively, have taken as given, in part because we have taken multiple different and sometimes inconsistent things for granted. I believe it will prove useful to expose the tacit assumptions, models, and metaphors that we carry around as a way of understanding both what we're about and why we sometimes seem to be at odds with one another

Abstract. This paper introduces a behavior-grounded approach to representing and learning the affordances of tools by a robot. The affordance representation is learned during a behavioral babbling stage in which the robot randomly chooses different exploratory behaviors, applies them to the tool, and observes their effects on environmental objects. As a result of this exploratory procedure, the tool representation is grounded in the behavioral and perceptual repertoire of the robot. Furthermore, the representation is autonomously testable and verifiable by the robot as it is expressed in concrete terms (i.e., behaviors) that are directly available to the robot’s controller. The tool representation described here can also be used to solve tool-using tasks by dynamically sequencing the exploratory behaviors which were used to explore the tool based on their expected outcomes. The quality of the learned representation was tested on extension-of-reach tasks with rigid tools. 1