This thesis addresses situated, embodied agents interacting in complex domains. It focuses on two problems: 1) synthesis and analysis of intelligent group behavior, and 2) learning in complex group environments. Basic behaviors, control laws that cluster constraints to achieve particular goals and have the appropriate compositional properties, are proposed as effective primitives for control and learning. The thesis describes the process of selecting such basic behaviors, formally specifying them, algorithmically implementing them, and empirically evaluating them. All of the proposed ideas are validated with a group of up to 20 mobile robots using a basic behavior set consisting of: safe--wandering, following, aggregation, dispersion, and homing. The set of basic behaviors acts as a substrate for achieving more complex high--level goals and tasks. Two behavior combination operators are introduced, and verified by combining subsets of the above basic behavior set to implement collective flocking, foraging, and docking. A methodology is introduced for automatically constructing higher--level behaviors

Developmental robotics is an emerging field located at the intersection of robotics, cognitive science and developmental sciences. This paper elucidates the main reasons and key motivations behind the convergence of fields with seemingly disparate interests, and shows why developmental robotics might prove to be beneficial for all fields involved. The methodology advocated is synthetic and two-pronged: on the one hand, it employs robots to instantiate models originating from developmental sciences; on the other hand, it aims to develop better robotic systems by exploiting insights gained from studies on ontogenetic development. This paper gives a survey of the relevant research issues and points to some future research directions.

its performance. In fact, we use the expression robot shaping to denote the use of learning as a means to translate suggestions coming from an external trainer into an effective control strategy that allows a robot to achieve a goal. We borrowed the term shaping from experimental psychology (Skinner, 1938), because training an artificial robot somewhat resembles what experimental psychologists do in their laboratories, when they train an experimental subject to produce a predefined response. The important point, which differentiates our approach from most current research on learning autonomous agents, is that the trainer plays a fundamental role in the learning process: most of the book is aimed at showing how to use a trainer to develop control systems for simulated and real robots. We also use the term behavior engineering to characterize a new technological discipline, the objective of which is to provide techniques, methodologies and t

The paper documents a case study in the design and implementation of a robotic multi-agent system. It illustrates known design guidelines, namely that the physics of the environment must be exploited, that behavior is the result from the interaction dynamics between the agent and the environment, and that emergent behavior can and must be utilised whenever possible. But the case study also challenges certain views, such as the subsumption architecture, the need for an action selection mechanism, the goal-oriented design methodology dominating the literature on planning, and the algorithmic style of writing control programs. Alternatives are explored in the form of a cooperative, parallel, behavior-oriented design. 1 Introduction An autonomous agent is a physical system that has its own resources to operate independently in a dynamically changing real world environment. The resources include energy, computational power, sensors, actuators, and body parts. A multi-agent system is an e...

Direct interaction and explicit communication are not always the best approaches for achieving coherent systemic behaviour in the context of Multi-Agent Systems (MAS). This is evident when taking into account recent approaches dealing with environment-based coordination such as stigmergy and, more generally, mediated interaction. In this paper we propose a conceptual, formal and engineering framework based on the notion of coordination artifact, which aims at generally systematising implicit communication and environment-based coordination for heterogeneous, possibly intelligent agents. The features and benefits of our approach are exemplified in the Follow-me situation, where an agent’s action/plan is considered as a model for the action/plan of other agents. We model this class of problems in terms of coordination artifacts, from simple to more challenging cases, stressing the advantages with respect to more “standard ” MAS approaches. 1.

This chapter addresses embodied social interaction inlif6 like agents. Embodiment is discussedf rom both arti cial intelligence and psychology viewpoints. Di#erent degreesof embodiment in biological, virtual and robotic agents are discussed, given the example of a bottomup, behavior-oriented, dynamic control of virtual robots. A `dancing with strangers' experiment shows how the same principles can be applied to physical robot-human interaction. We then discuss the issue of sociality which di#ers in di#erent academic communities with respect to which roles are attributed to genes, memes, and the individual embodied agent.

This paper presents an analysis of an artificially evolved dynamical network-based control system for a simulated autonomous mobile robot engaged in simple visually guided tasks.

. 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...

This paper appeared in Trends in Cognitive Science, Vol. 2, No. 3, March 1998, 82-87.)

The paper proposes an architecture for the online evolution of new behavioral competences on a robotic agent. Some experimental results for evolving a set of primitive behaviors are presented. Introduction A central question in ALife research is how new complexity and new functionality may emerge [Steels1994]. Selectionism and self-organisation have so far been put forward as the key explanatory principles [Langton1989]. These principles have been been applied at many level of biological systems, from the chemical reactions that explain the origin of life [Kaufmann1993] to the interaction between individuals in societies [Deneubourg1993]. This paper explores in how far selectionism and selforganisation may lead to the build up of behavioral complexity in animals. In the tradition of Alife research, this exploration takes place by building artificial systems, i.c. robotic agents. There has already been a large amount of work attempting to use selectionist techniques for evolving behavi...