Evolution of Complex Autonomous Robot Behaviors using Competitive Fitness
Andrew L. Nelson, Edward Grant, Gregory Barlow, and Mark White

Evolutionary Robotics (ER) employs population-based artificial evolution
to develop behavioral robotics controllers. In this paper we focus on the
formulation and application of a fitness selection function for ER that
makes use of intra-population competitive selection. In the case of
behavioral tasks, such as game playing, intra-population competition can
lead to the evolution of complex behaviors. In order for this competition
to be realized, the fitness of competing controllers must be based mainly
on the aggregate success or failure to complete an overall task. However,
because initial controller populations are often subminimally competent,
and individuals are unable to complete the overall competitive task at
all, no selective pressure can be generated at the onset of evolution (the
Bootstrap Problem). In order to accommodate these conflicting elements in
selection, we formulate a bimodal fitness selection function. This
function accommodates sub-minimally competent initial populations in early
evolution, but allows for binary success/failure competitive selection of
controllers that have evolved to perform at a basic level. Large
arbitrarily connected neural network-based robot controllers were evolved
to play the competitive team game Capture the Flag. Results show that
neural controllers evolved under a variety of conditions were competitive
with a hand-coded knowledge-based controller and could win a modest
majority of games in a large tournament.