We address two issues in Evolutionary Robotics, namely the genetic encoding
and the performance criterion, also known as the fitness function. For the
first aspect, we suggest to encode mechanisms for parameter self-organizat
ion, instead of the parameters themselves as in conventional approaches. We
argue that the suggested encoding generates systems that can solve more co
mplex tasks and are more robust to unpredictable sources of change. We supp
ort our arguments with a set of experiments on evolutionary neural controll
ers for physical robots and compare them to conventional encoding. In addit
ion, we show that when also the genetic encoding is left free to evolve, ar
tificial evolution will select to exploit mechanisms of self-organization.
For the second aspect, we shall discuss the role of the performance criteri
on, also known as fitness function, and suggest Fitness Space as a framewor
k to conceive fitness functions in Evolutionary Robotics. Fitness Space can
be used as a guide to design fitness functions as well as to compare diffe
rent experiments in Evolutionary Robotics. (C) 2000 Elsevier Science Ltd. A
ll rights reserved.