In this paper, we examine the problem of controlling multiple behaviour-based autonomous robots. Based on observations made from the study of social insects, we propose ve simple mechanisms used to invoke group behaviour in simple sensor-based mobile robots. The proposed mechanisms allow populations of behaviour-based robots to perform tasks without centralized control or use of explicit communication. We have veri ed our collective control strategies by designing a robot population simulator called SimbotCity. Wehave also constructed a system of ve homogeneous sensor-based mobile robots, capable of achieving simple collective tasks, to demonstrate the feasibility of some of the control mechanisms.

This paper builds on a previous review of significant research on adaptive behavior in animats. It summarizes the current state of the art and suggests some directions likely to provide interesting results in the near future. 1 Introduction An animat is a simulated animal or a real robot whose rules of behavior are inspired by those of animals. It is usually equipped with sensors, with actuators, and with a behavioral control architecture that allow it to react or to respond to variations in its environment (internal or external), notably to those that might impair its chances of survival. The behavior of an animat is what the animat does. This is characterized by a sequence of actions which reflects the dynamic interplay between the animat and its environment, mediated through the animat's sensors and actuators. The behavior of an animat is adaptive so long as it allows the animat to survive or to fulfill its mission. This requires that the animat's essential variables be monitored a...

. The paper explores a biologically inspired definition of intelligent autonomous agents. Intelligence is related to whether behavior of a system contributes to its self-maintenance. Behavior becomes more intelligent (or copes with more ecological pressures) when it is capable to create and use representations. The notion of representation should not be restricted to formal expressions with a truththeoretic semantics. The dynamics at various levels of intelligent systems plays an essential role in forming representations. Keywords: intelligence, self-organisation, representation, complex dynamical systems. 1 Introduction What exactly are intelligent autonomous agents? Unless we have some good criteria that are clear targets for the field, it will both be difficult to judge whether we have achieved our aims or to set intermediate milestones to measure whether progress has been made. The goal of this paper is to present a definition of intelligent autonomous agents. The definition has t...

As part of an effort to define a unified formal semantics for beliefs, desires and action, this paper sketches a model theory for the axiological aspects of agent theory: hedonic states, likes, goals and values. Particular attention is paid to modelling the intensity of likes. The main intuition underlying the model theory is that the axiological aspects of agent theory can be modelled through computational generalisations of physical dynamics. Computational analogues of force, mass and potential are offered. Introduction An important part of agent theory appears to be the notion of desires. Several formulations of agent theory have adopted beliefs, desires and intentions as a set of basic notions (the so-called BDI models). However, to our knowledge, so far relatively little has been said explicitly in the AI literature about a theory of desires (Cohen and Levesque, 1985 and in press, Moore, 1985a; Kiss, 1988, Shoham, 1989). This paper takes some initial steps towards the explicit f...

. The paper explores a biologically inspired definition of intelligence. Intelligence is related to whether behavior of a system contributes to its self-maintenance. Behavior becomes more intelligent (or copes with more ecological pressures) when it is capable to create and use representations. The notion of representation should not be restricted to formal expressions with a truth-theoretic semantics. The dynamics at various levels of intelligent systems plays an essential role in forming representations. An example is given how behavioral diversity spontaneously emerges in a globally coupled network of agents. Keywords: intelligence, self-organisation, representation, complex dynamical systems. 1 Introduction Artificial intelligence research is concerned with an investigation into the phenomenon of intelligence using the methods of the artificial [24]. This means that systems are built which exhibit intelligent behavior and that this is seen as a way to progressively derive and test...

If behavior networks, which use spreading activation to select actions, are analogous to connectionist methods of pattern recognition, then recurrent behavior networks, which use energy minimization, are analogous to Hopfield networks. Hopfield networks memorize patterns by making them attractors. Similarly, each behavior of a recurrent behavior network should be an attractor of the network, to inhibit fruitless, repeated switching between different behaviors in response to small changes in the environment and in motivations. I overcome two major objections to this view, and demonstrate that the performance in a test domain of the Do the Right Thing recurrent behavior network is improved by redesigning it to create desirable attractors and basins of attraction. I further show that this performance increase is correlated with an increase in persistence and a decrease in undesirable behavior-switching. On a more general level, this work encourages the study of action selection as a dynam...

A conceptual framework is a valuable resource for planning by situated agents. In this paper, wediscuss the acquisition of such a framework. Wetake the position that concepts are abstractions of experience that confer a predictive ability for new situations. Wealso show specific examples which demonstrate the utility of abstract representations of actions, called activity maps, for reasoning about concepts and their entailments.

Optimisation is a requirement of many commercial as well as theoretical problems; the optimal use of available resources, maximising savings, minimising costs, extending useful lives, increasing time available for other tasks, using fewer resources. In many of these problems, there are reasons, geographic, political or arbitrary, for splitting the problem into smaller parts and solving them separately, but the need to optimise the combination is still present. In this report I chart the progress in two problem arenas that offer the potential for the use of a distributed method of optimisation. The first, Teaching Space Utilisation, seeks a union between local and global optima of similar problem solvers operating in a centralisable domain. The second, British Airways' Aircraft Retimer, shares this in part of its problem, but has additional aspects that means it cannot be centralisable, there are non-friendly, potentially hostile peers, as well as the need to integrate heterogeneous pro...

A conceptual framework is a valuable resource for planning by situated agents. In this paper, we discuss the acquisition of such a framework. We take the position that concepts are abstractions of experience that confer a predictive ability for new situations. We also show specific examples which demonstrate the utility of abstract representations of actions, called activity maps, for reasoning about concepts and their entailments. In fact, we make the case that activity maps are concepts themselves. Where appropriate, we draw analogies with related work in nonlinear dynamics. Introduction Reasoning about one's environment, possible actions, and desired outcomes is the basis for planning --- especially interactionist or improvisational planning (Agre & Chapman 1990). Although our current focus is not planning per se, we do address the prerequisite problem of acquiring a conceptual structure for planning. In particular, this research is part of an effort to explain how senso...

This report was originally written in May 1992, following a HCRL internal seminar; and the content hasn't really changed since, although the views---and hopefully the wisdom---of the author have deviated from the text here. Comments will still be gratefully received; email address "S.N.K.Watt@open.ac.uk". Page 1 Introduction