Behavior-oriented AI is a scientific discipline that studies how behavior of agents emerges and becomes intelligent and adaptive. Success of the field is defined in terms of success in building physical agents that are capable of maximising their own self-preservation in interaction with a dynamically changing environment. The paper addresses this artificial life route towards artificial intelligence and reviews some of the results obtained so far. 1 Official reference: Steels, L. (1994) The artificial life roots of artificial intelligence. Artificial Life Journal, Vol 1,1. MIT Press, Cambridge. 1 Introduction For several decades, the field of Artificial Intelligence has been pursuing the study of intelligent behavior using the methodology of the artificial [104]. But the focus of this field, and hence the successes, have mostly been on higher order cognitive activities such as expert problem solving. The inspiration for AI theories has mostly come from logic and the cognitive...

In this report, I discuss the use of vision to support concrete, everyday activity. I will argue that a variety of interesting tasks can be solved using simple and inexpensive vision systems. I will provide a number of working examples in the form of a state-of-the-art mobile robot, Polly, which uses vision to give primitive tours of the seventh floor of the MIT AI Laboratory. By current standards, the robot has a broad behavioral repertoire and is both simple and inexpensive (the complete robot was built for less than $20,000 using commercial board-level components). The approach I will use will be to treat the structure of the agent's activity--- its task and environment---as positive resources for the vision system designer. By performing a careful analysis of task and environment, the designer can determine a broad space of mechanisms which can perform the desired activity. My principal thesis is that for a broad range of activities, the space of applicable mechanisms will be broad...

This paper discusses how a behavior-based robot can construct a “symbolic process” that accounts for its deliberative thinking processes using models of the environment. The paper focuses on two essential problems; one is the symbol grounding problem and the other is how the internal symbolic processes can be situated with respect to the behavioral contexts. We investigate these problems by applying a dynamical system’s approach to the robot navigation learning problem. Our formulation, based on a forward modeling scheme using recurrent neural learning, shows that the robot is capable of learning grammatical structure hidden in the geometry of the workspace from the local sensory inputs through its navigational experiences. Furthermore, the robot is capable of generating diverse action plans to reach an arbitrary goal using the acquired forward model which incorporates chaotic dynamics. The essential claim is that the internal symbolic process, being embedded in the attractor, is grounded since it is self-organized solely through interaction with the physical world. It is also shown that structural stability arises in the interaction between the neural dynamics and the environmental dynamics, which accounts for the situatedness of the internal symbolic process. The experimental results using a mobile robot, equipped with a local sensor consisting of a laser range finder, verify our claims. 1 1

s: Jan. 1992 -- Dec. 1994 ffl CTI: Current Technology Index Jan./Feb. 1993 -- Jan./Feb. 1994 ffl DAI: Dissertation Abstracts International: Vol. 53 No. 1 -- Vol. 55 No. 4 (1994) ffl EEA: Electrical & Electronics Abstracts: Jan. 1991 -- Dec. 1994 ffl P: Index to Scientific & Technical Proceedings: Jan. 1986 -- Feb. 1995 (except Nov. 1994) ffl EI A: The Engineering Index Annual: 1987 -- 1992 ffl EI M: The Engineering Index Monthly: Jan. 1993 -- Dec. 1994 The following GA researchers have already kindly supplied their complete autobibliographies and/or proofread references to their papers: Dan Adler, Patrick Argos, Jarmo T. Alander, James E. Baker, Wolfgang Banzhaf, Ralf Bruns, I. L. Bukatova, Thomas Back, Yuval Davidor, Dipankar Dasgupta, Marco Dorigo, Bogdan Filipic, Terence C. Fogarty, David B. Fogel, Toshio Fukuda, Hugo de Garis, Robert C. Glen, David E. Goldberg, Martina Gorges-Schleuter, Jeffrey Horn, Aristides T. Hatjimihail, Mark J. Jakiela, Richard S. Judson, Akihiko Konaga...

. Synthetic ethology is proposed as a means of conducting controlled experiments investigating the mechanisms and evolution of communication. After a discussion of the goals and methods of synthetic ethology, two series of experiments are described based on at least 5000 breeding cycles. The first demonstrates the evolution of cooperative communication in a population of simple machines. The average fitness of the population and the organization of its use of signals are compared under three conditions: communication suppressed, communication permitted, and communication permitted in the presence of learning. Where communication is permitted the fitness increases about 26 times faster than when communication is suppressed; with communication and learning the rate of fitness increase is about 100 fold. The second series of experiments illustrates the evolution of a syntactically simple language, in which a pair of signals is required for effective communication. Keywords: artificial lif...

Agent architectures need to organize themselves and adapt dynamically to changing circumstances without top-down control from a system operator. Some researchers provide this capability with complex agents that emulate human intelligence and reason explicitly about their coordination, reintroducing many of the problems of complex system design and implementation that motivated increasing software localization in the first place. Naturally occurring systems of simple agents (such as populations of insects or other animals) suggest that this retreat is not necessary. This paper summarizes several studies of such systems, and derives from them a set of general principles that artificial multi-agent systems can use to support overall system behavior significantly more complex than the behavior of the individuals agents. 1.

Designers often improve the performance of artifical agents by specializing them. We can make a rough, but useful distinction between specialization to a task and specialization to an environment. Specialization to an environment can be difficult to understand: it may be unclear on what properties of the environment the agent depends, or in what manner it depends on each individual property. In this paper, I discuss a method for analyzing specialization into a series of conditional optimizations: formal transformations which, given some constraint on the environment, map mechanisms to more efficient mechanisms with equivalent behavior. I apply the technique to the analysis of the vision and control systems of a working robot system in dayto day use in our laboratory.

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...

We argue that the analysis of agent#environmentinteractions should be extended to include the conventions and invariants maintained by agents throughout their activity. We refer to this thicker notion of environmentasalifeworld and present a partial set of formal tools for describing structures of lifeworlds and the ways in which they computationally simplify activity. As one speci#c example, we apply the tools to the analysis of the Toast system and showhowversions of the system with very di#erent control structures in fact implement a common control structure together with di#erent conventions for encoding task state in the positions or states of objects in the environment.

This work describes a control architecture based on a hierarchical classifier system. This architecture, which uses both reactive and planning rules, implements a motivationally autonomous animat that chooses the actions it will perform according to the expected consequences of the alternatives. The adaptive faculties of this animat are illustrated through various examples.