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

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