Evolutionary robotics: coping with environmental change
Joseba Urzelai, Dario Floreano · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2000
In this paper an evolutionary method con-sisting of encoding a set of local adapta-tion rules that synapses obey while a robot freely moves in the environment is compared to standard evolution of xed-weight con-trol networks. The results show that evo-lutionary adaptive controllers can adapt on-line without additional evolutionary training to strong environmental changes where in-stead the performance of evolutionary xed-weight controllers is signicantly degraded. Two cases are described: transfer of evolved controllers from simulated to real robots and across dierent robotic platforms that vary in size, shape, and sensor response prole. In both cases evolved adaptive controllers autonomously and quickly adjust synaptic weights to successfully accomplish the task in the new conditions. 1