From schemas to neural networks: A multi-level modelling approach to biologically-inspired autonomous robotic systems

Biology has been an important source of inspiration in building adaptive autonomous robotic systems. Due to the inherent complexity of these models, most biologically-inspired robotic systems tend to be ethological without linkage to underlying neural circuitry. Yet, neural mechanisms are crucial in modelling adaptation and learning. The work presented in this paper describes a schema and neural network multi-level modelling approach to biologically inspired autonomous robotic systems. A prey acquisition model with detour behaviour in frogs is presented to exemplify the modelling approach. The model is tested with simulated and physical robots using the ASL/NSL and MIRO robotic system.