The evolution of a population can be guided by phenotypic traits acquired by members of that population during their lifetime. This phenomenon, known as the Baldwin effect, can speed the evolutionary process as traits that are initially acquired become genetically specified in later generations. This paper presents conditions under which this genetic assimilation can take place. As well as the benefits that lifetime adaptation can give a population, there may be a cost to be paid for that adaptive ability. It is the evolutionary trade-off between these costs and benefits that provides the selection pressure for acquired traits to become genetically specified. It is also noted that genotypic space, in which evolution operates, and phenotypic space, in which adaptive processes (such as learning) operate, are, in general, of a different nature. To guarantee that an acquired characteristic can become genetically specified, these spaces must have the property of neighborhood correlation, which means that a small distance between two individuals in phenotypic space implies that there is a small distance between the same two individuals in genotypic space.

We report on recent work in which we employed artificial evolution to design neural network controllers for small, homogeneous teams of mobile autonomous robots. The robots were evolved to perform a formation-movement task from random starting positions, equipped only with infrared sensors. The dual constraints of homogeneity and minimal sensors make this a non-trivial task. We describe the behaviour of a successful system in which robots adopt and maintain functionally distinct roles in order to achieve the task. We believe this to be the first example of the use of artificial evolution to design coordinated, cooperative behaviour for real robots.