This paper: 1) reviews different combinations between ANN's and evolutionary algorithms (EA's), including using EA's to evolve ANN connection weights, architectures, learning rules, and input features; 2) discusses different search operators which have been used in various EA's; and 3) points out possible future research directions. It is shown, through a considerably large literature review, that combinations between ANN's and EA's can lead to significantly better intelligent systems than relying on ANN's or EA's alone

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...

By beginning with simple reactive behaviors and gradually building up to more memory-dependent behaviors, it may be possible for connectionist systems to eventually achieve the level of planning. This paper focuses on an intermediate step in this incremental process, where the appropriate means of providing guidance to adapting controllers is explored. A local and a global method of reinforcement learning are contrasted---a special form of back-propagation and an evolutionary algorithm. These methods are applied to a neural network controller for a simple robot. A number of experiments are described where the presence of explicit goals and the immediacy of reinforcement are varied. These experiments reveal how various types of guidance can affect the final control behavior. The results show that the respective advantages and disadvantages of these two adaptation methods are complementary, suggesting that some hybrid of the two may be the most effective method. Concluding remarks discus...

We present a novel evolutionary approach to robotic control of a real robot based on genetic programming (GP). Our approach uses genetic programming techniques that manipulate machine code to evolve control programs for robots. This variant of GP has several advantages over a conventional GP system, such as higher speed, lower memory requirements and better real time properties. Previous attempts to apply GP in robotics use simulations to evaluate control programs and have difficulties with learning tasks involving a real robot. We present an on-line control method that is evaluated in two different physical environments and applied to two tasks using the Khepera robot platform: obstacle avoidance and object following. The results show fast learning and good generalization.

From perception to action and from action to perception, all elements of an autonomous agent are interdependent and need to be strongly coherent. The final behavior of the agent is the result of the global activity of this loop and every weakeness or incoherence of a single element has strong consequences on the performances of the agent. We think that, for the purpose of building autonomous robots, all these elements need to be developed together in continuous interaction with the environment. We describe the implementation of a possible solution (artificial neural networks and genetic algorithms) on a real mobile robot through a set of three different experiments. We focus our attention on three different aspects of the control structure: perception, internal representation and action. In all the experiments these aspects are not considered as single processing elements, but as part of an agent. For every experiment, the advantages and disadvantages of this approach are presented and...

This article describes past and current research efforts in evolutionary robotics that have been carried out at the AnimatLab, Paris. Such approaches entail using an artificial selection process to automatically generate developmental programs for neural networks that control rolling, walking, swimming and flying animats or robots. Basically, they complement the underlying evolutionary process with a developmental procedure – in order hopefully to reduce the size of the genotypic space that is explored – and they occasionally call on an incremental approach, in order to capitalize upon solutions to simpler problems so as to devise solutions to more complex problems. This article successively outlines the historical background of our research, the evolutionary paradigm on which it relies, and the various results obtained so far. It also discusses the potentialities and limitations of the approach and indicates directions for future work.

This paper presents an application of a connectionist control-learning system designed for use on an autonomous mini-robot. This system was formerly shown to form useful two-dimensional mappings rapidly when applied to backing a car with a single trailer. In the current paper the learning system is extended to three dimensions and applied to a similar but significantly more difficult problem. The system is shown to be capable of rapid unsupervised learning of output responses in temporal domains through the use of eligibility traces and inter-neural cooperation within topologically defined neighborhoods. 1 Introduction Connectionist control-learning systems have recently received much attention; numerous papers and several books have been published on this topic in the last few years (e.g. [13, 17]). An overview of many such systems as they have been applied to robot control is given by Prabhu and Garg [16]. Most of these works, however, have concentrated on simulated systems and the...

Abstract — Driver assistance systems that monitor driver intent, warn drivers of lane departures, or assist in vehicle guidance are all being actively considered. It is therefore important to take a critical look at key aspects of these systems, one of which being lane position tracking. It is for these driver assistance objectives that motivate the development of the novel “Video Based Lane Estimation and Tracking ” (VioLET) system. The system is designed using steerable filters for robust and accurate lane marking detection. Steerable filters provide an efficient method for detecting circular reflector markings, solid-line markings, and segmented-line markings under varying lighting and road conditions. They help to provide robustness to complex shadowing, lighting changes from overpasses and tunnels, and road surface variations. They are efficient for lane marking extraction because by computing only three separable convolutions we can extract a wide variety of lane markings. Curvature detection is made more robust by incorporating both visual cues (lane markings and lane texture) and vehicle state information. The experiment design and evaluation of the VioLET system is shown using multiple quantitative metrics over a wide variety of test conditions on a large test path using a unique instrumented vehicle. We also present a justification for our choice of metrics based on our work with human factors applications as well as extensive ground-truthed testing from different times of day, road conditions, weather, and driving scenarios. In order to design the VioLET system, we first performed an up-to-date and comprehensive analysis of the current state-of-the-art in lane detection research. In doing so, we present a comparison of a wide variety of methods, pointing out the similarities and differences between methods as well as when and where various methods are most useful.

Genetic Programming is used to create a reactive obstacle avoidance system for an autonomous mobile robot. The evolved programs take a black and white camera image as input and estimate the location of the lowest nonground pixel in a given column. Traditional computer vision operators such as Sobel gradient magnitude, median filters and the Moravec interest operator are combined arbitrarily. Five memory locations can also be read or written to. The first evolved program is now controlling the robot.

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...