... the last 5 years. We explain and justify our distinctive approaches to (artificial) evolution, and to the nature of robot control systems that are evolved. Results are presented from research with evolved controllers for autonomous mobile robots; simulated robots, coevolved animats, real robots with software controllers, and a real robot with a controller directly evolved in hardware.

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.

This paper will look at an evolutionary approach to robotics; partly at pragmatic issues, but primarily at theoretical issues associated with the evolutionary algorithms which are appropriate. Genetic Algorithms are not suitable in their usual form for the evolution of cognitive structures, which must be in an incremental fashion. SAGA -- Species Adaptation Genetic Algorithms -- is a conceptual framework for extending GAs to variable length genotypes, where evolution allows a species of individuals to evolve from simple to more complex. In the context of species evolution the metaphor of hill-crawling as opposed to hill-climbing is introduced,

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.

This paper provides a high-level review of current and recent work in the use of genetic algorithm based techniques to develop sensorimotor control systems for autonomous agents. It focuses on network-based controllers and genetic encoding issues associated with them. The paper closes with a discussion of the possibility of using arti cial evolutionary techniques to help tackle more specifically scientific questions about natural sensorimotor systems.

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...

Abstract not found

. Evolutionary robotics--- as other adaptive methods, such as reinforcement learning and learning classifier systems---can take considerable time and resources which require a careful evaluation of the hardware tools and methodologies employed. We outline a set of hardware solutions and working methodologies that can be used for successfully implementing and extending the evolutionary approach to complex environments, robots, and real-world applications. The issues discussed include the integration of simulation and real robots, design issues of evolvable robots, hardware requirements for incremental evolution, and hardware and software tools for monitoring and analysis. 1 Introduction Evolutionary techniques applied to robot control can generate efficient, smart, and creative solutions which match the constraints imposed by the environment and the selection criterion. The power, flexibility, and generality of artificial evolution has often been exploited both for finding engineering ...

We present results from the concurrent evolution of visual sensing morphologies and sensory-motor controller-networks for visually guided robots. In this paper we analyse two (of many) networks which result from using incremental evolution with variable-length genotypes. The two networks come from separate populations, evolved using a common fitness function. The observable behaviours of the two robots are very similar, and close to the optimal behaviour. However, the underlying sensing morphologies and sensory-motor controllers are strikingly different. This is a case of convergent evolution at the behavioural level, coupled with divergent evolution at the morphological level. The action of the evolved networks is described. We discuss the process of analysing evolved artificial networks, a process which bears many similarities to analysing biological nervous systems in the field of neuroethology.

Abstract: We propose a modular architecture for autonomous robots which allows for the implementation of basic behavioral modules by both programming and training, and accommodates for an evolutionary development oftheinter-connections among modules. This architecture can implement highly complex controllers and allows for incremental shaping of the robot behavior. Our pro-posal is exempli ed and evaluated experimentally through a number of mobile robotic tasks involving exploration, battery recharging and object manipulation.