Skip to Main Content
This paper presents how neural swimming controllers for a lamprey can be adapted for controlling both the swimming and the walking of a salamander-like animat. Using a Genetic Algorithm (GA), we extend a connectionist model of the biological Central Pattern Generator (CPG) controlling the swimming of a lamprey (Ekeberg, 1993) to control the locomotion of a 2D mechanical simulation of a salamander. We first summarize experiments on the evolution of alternative swimming controllers for the lamprey (Ijspeert et al., 1998). The aim of that work was to study whether there exists other neural configurations than that found in the lamprey which could control swimming with the same efficiency and to develop a method for developing neural locomotion controllers using a GA. We then present how that method, namely a staged evolution of the neural configuration of a connectionist model, can be used to extend swimming controllers to control both swimming and walking. Controllers which, similarly to CPGs of animals, can produce complex oscillations when receiving simple excitatory signals are thus developed. In particular, we generate a controller which can switch from swimming to walking and produce different speeds of motion depending on its excitation.