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...

For robots to be truly flexible, they need to be able to learn to adapt to partially known or dynamic environments, to teach themselves new tasks, and to compensate for sensor and effector defects. The problem of robot learning has been an intensively studied research topic over the last decade. In this paper we critically examine four major formulations of the robot learning problem: inductive concept learning, explanation-based learning, reinforcement learning, and evolutionary learning. We describe some well-known examples of systems that fit under each formulation, and discuss their strengths and limitations.

This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system is to speed up learning by decomposing complex tasks into hierarchies of simple behaviours which can be learnt more easily. Behaviours learnt in this way can subsequently be re-used to solve a variety of problems, reducing the need to learn every new task from scratch. It is even possible to learn multiple behaviours simultaneously, thus making more efficient use of experience. We demonstrate these advantages in a simple simulated environment.

The development of techniques for autonomous navigation in real-world environments constitutes one of the major trends in the current research on robotics. An important problem in autonomous navigation is the need to cope with the large amount of uncertainty that is inherent of natural environments. Fuzzy logic has features that make it an adequate tool to address this problem. In this paper, we review some of the possible uses of fuzzy logic in the field of autonomous navigation. We focus on four issues: how to design robust behaviorproducing modules; how to coordinate the activity of several such modules; how to use data from the sensors; and how to integrate high-level reasoning and low-level execution. For each issue, we review some of the proposals in the literature, and discuss the pros and cons of fuzzy logic solutions.

. Concept learning in robotics is an extremely challenging problem. Sensory data is often high-dimensional, and noisy due to specularities and other irregularities. In this paper, we investigate two general strategies to speed up learning, based on spatial decomposition of the sensory representation, and simultaneous learning of multiple classes using a shared structure. We study two concept learning scenarios: a hallway navigation problem, where the robot has to induce feature detectors such as "opening" or "wall". The second task is recycling, where the robot has to learn to recognize objects, such as a "trash can". We use a common underlying function approximator in both studies in the form of a feedforward neural network, with several hundred input units and multiple output units. Despite the high degree of freedom afforded by such an approximator, we show the two strategies provide sufficient bias to achieve rapid learning. We provide detailed experimental studies on an actual mobile robot called PAVLOV to illustrate the effectiveness of this approach.

Autonomous robots need the ability to move purposefully and without human intervention in real-world environments that have not been specifically engineered for them. These environments are characterized by the pervasive presence of uncertainty: the need to cope with this uncertainty constitutes a major challenge for autonomous robots. In this note, we discuss this challenge, and present some specific solutions based on our experience on the use of fuzzy logic in mobile robots. We focus on three issues: how to realize robust motion control; how to flexibly execute navigation plans; and how to approximately estimate the robot's location.

In this paper I explore the hypothesis that some of today robots might possess a form of consciousness whose substrate is a mere algorithm. First, consciousness is defined within an evolutionary framework as awareness of one's own state in relation to the external environment. Then, the basic prerequisites for such conscious activity are discussed, namely embodiment, autonomy, and adaptation mechanisms. Artificial evolution, rather than evolutionary optimisation, is presented as a viable methodology to create conscious robots, accompanied by some examples of behaviours of artificially evolved robots. Finally, I argue that what might be problematic with the concept of robot consciousness is not the robot, but the notion of consciousness itself. 1 Paving the Road to Robot Consciousness Could the ordered list of operations which forms any computer algorithm constitute the basis of consciousness for a robot? "Of course not", would be the sensible answer probably given by most readers with...

Abstract — Robot learning is a growing area of research at the intersection of robotics and machine learning. The main contributions of this article include a review of how machine learning has been used on Sony AIBO robots and at RoboCup with a focus on the four-legged league during the years 1998– 2004. The review shows that the application oriented use of machine learning in the four-legged league was still conservative and restricted to a few well-known and easy to use methods such as standard decision trees, evolutionary hill climbing, and support vector machines. Method oriented spin-off studies emerged more frequently and increasingly addressed new and advanced machine learning techniques. Further the article presents some details about the growing impact of machine learning in the software system developed by authors ’ robot soccer team—the NUbots.

Abstract — Classical reinforcement learning mechanisms and a modular neural network are unified to conceive an intelligent autonomous system for mobile robot navigation. The conception aims at inhibiting two common navigation deficiencies: generation of unsuitable cyclic trajectories and ineffectiveness in risky configurations. Different design apparatuses are considered to compose a system to tackle with these navigation difficulties, for instance: 1) neuron parameter to simultaneously memorize neuron activities and function as a learning factor, 2) reinforcement learning mechanisms to adjust neuron parameters (not only synapse weights), and 3) a inner-triggered reinforcement. Simulation results show that the proposed system circumvents difficulties caused by specific environment configurations, improving the relation between collisions and captures. R I.

An autonomous robot need not be given all the details of the environment in which it is going to act: it can acquire them by direct interaction. One approach to learn by interaction is reinforcement learning, though, the robot has also to be able to autonomously categorize the input data it receives from the environment, deal with the stability-plasticity dilemma, and learn very rapidly. In this paper we present a digital artificial brain architecture capable of dealing with such problems. Furthermore, we present its use for controlling a mobile autonomous robot in an obstacle avoidance task in a real arena. Keywords. Artificial neural networks, mobile autonomous robots, neurocontrol. 1 Introduction Programming an autonomous robot so that it reliably acts in an unknown or a dynamic environment is a difficult thing to do. This is due to missing information during programming, the dynamic nature of the environment and the inherent noise in the robot's sensors and actuators [1]. One com...