In this article we describe a methodology for evolving neurocontrollers of autonomous mobile robots without human intervention. The presentation, which spans from technological and methodological issues to several experimental results on evolution of physical mobile robots, covers both previous and recent work in the attempt to provide a uni ed picture within which the reader can compare the effects of systematic variations on the experimental settings. After describing some key principles for building mobile robots and tools suitable for experiments in adaptive robotics, we give an overview of different approaches to evolutionary robotics and present our methodology. We start reviewing two basic experiments showing that different environments can shape very different behaviors and neural mechanisms under very similar selection criteria. We then address the issue of incremental evolution in two different experiments from the perspective of changing environments and robot morphologies. Finally, we investigate the possibility of evolving plastic neurocontrollers and analyze an evolved neurocontroller that relies on fast and continuously changes synapses characterized by dynamic stability. We conclude by reviewing the implications of this methodology for engineering, biology, cognitive science, and artificial life, and point at future directions of research.

Recently, a new approach that involves a form of simulated evolution has been proposed for the building of autonomous robots. However, it is still not clear if this approach may be adequate to face real life problems. In this paper we show how control systems that perform a non-trivial sequence of behaviors can be obtained with this methodology by carefully designing the conditions in which the evolutionary process operates. In the experiment described in the paper, a mobile robot is trained to locate, recognize, and grasp a target object. The controller of the robot has been evolved in simulation and then downloaded and tested on the real robot.

This paper introduces a new type of artificial neural network (GasNets) and shows that it is possible to use evolutionary computing techniques to find robot controllers based on them. The controllers are built from networks inspired by the modulatory effects of freely diffusing gases, especially nitric oxide, in real neuronal networks. Evolutionary robotics techniques were used to develop control networks and visual morphologies to enable a robot to achieve a target discrimination task under very noisy lighting conditions. A series of evolutionary runs with and without the gas modulation active demonstrated that networks incorporating modulation by diffusing gases evolved to produce successful controllers considerably faster than networks without this mechanism. GasNets also consistently achieved evolutionary success in far fewer evaluations than were needed when using more conventional connectionist style networks. 1 Introduction 1.1 Robots Over the past decade there has been renewe...

In the simplest scenario of two coevolving populations in competition with each other, tness progress is achieved at disadvantage of the other population's fitness. The everchanging fitness landscape caused by the competing species (named the "Red Queen effect") makes the system dynamics more complex, but it also provides a set of advantages with respect to single-population evolution. Here we present results from an experiment with two mobile robots, a predator equipped with vision and a much faster prey...

In the last few years several researchers have resorted to artificial evolution (e.g. genetic algorithms) and learning techniques (e.g. neural networks) for studying the interaction between learning and evolution. These studies have been conducted for two different purposes: (a) looking at the performance advantages obtained by combining these two adaptive techniques

Co-evolution of competitive species provides an interesting testbed to study the role of adaptive behavior because it provides unpredictable and dynamic environments. In this paper we experimentally investigate some arguments for the co-evolution of different adaptive protean behaviors in competing species of predators and preys. Both species are implemented as simulated mobile robots (Kheperas) with infrared proximity sensors, but the predator has an additional vision module whereas the prey has a maximum speed set to twice that of the predator. Different types of variability during life for neurocontrollers with the same architecture and genetic length are compared. It is shown that simple forms of proteanism affect co-evolutionary dynamics and that preys rather exploit noisy controllers to generate random trajectories, whereas predators benefit from directional-change controllers to improve pursuit behavior.

In this paper I claim that one of the main characteristics that makes the Evolutionary Robotics approach suitable for the study of adaptive behavior in natural and artificial agents is the possibility to rely largely on a self-organization process. Indeed by using Artificial Evolution the role of the designer may be limited to the specification of a fitness function which measures the ability of a given robot to perform a desired task. From an engineering point of view the main advantage of relying on self-organization is the fact that the designer does not need to divide the desired behavior into simple basic behaviors to be implemented into separate layers (or modules) of the robot control system. By selecting individuals for their ability to perform the desired behavior as a whole, simple basic behaviors can emerge from the interaction between several processes in the control system and from the interaction between the robot and the environment. From the point of view of ...

Abstract not found

This paper reports on an experiment in evolving the morphology of an artificial compound eye with 16 light sensors on a robot. A special robot was designed and constructed that is able to autonomously modify the angular positions of the individual light sensors within the compound eye. The task of the robot was to employ motion parallax to estimate a critical distance to obstacles. This task was achieved by adapting the morphology of the compound eye by an evolutionary algorithm while using a fixed neural network to control the robot. 1

We will discuss in which conditions we can expect the emergence of agents able to integrate sensory-motor information over time and later use this information to modulate their behavior accordingly. In doing so we will illustrate the problems that these agents should be able to solve and the processes that might lead to a transition from simple agents that only rely on sensory information or on their internal dynamic to agents that are also able to integrate information over time. The analysis of evolved individuals revealed that: (1) individuals able to integrate information over time rely on mixed strategy in which basic sensory-motor mechanisms are complemented and enhanced with additional internal mechanisms; (2) evolved individuals tend to rely on partial, action-oriented, and action-mediated representations of the external environment. 1