The University of Sussex

Evolutionary robotics and the radical envelope of noise hypothesis

Nick Jakobi

For several years now, various researchers have endeavoured to apply artificial evolution to the automatic design of control systems for real robots. One of the major challenges they face concerns the question of how to assess the fitness of evolving controllers when each evolutionary run typically involves hundreds of thousands of such assessments. This paper outlines new ways of thinking about and building simulations upon which such assessments can be performed. It puts forward sufficient conditions for the successful transfer of evolved controllers from simulation to reality, and develops a potential methodology for building simulations in which evolving controllers are forced to satisfy these conditions if they are to be reliably fit. As long as simulations are built according to this methodology, it is hypothesised, then it does not matter how inaccurate or incomplete they are: controllers that have evolved to be reliably fit in simulation will still transfer into reality. Two sets of experiments are reported, both of which involve minimal look-up-table based simulations built according to these guidelines. In the first set, controllers were evolved that allowed a Khepera robot to perform a simple memory task in the real world, and in the second set controllers were evolved for the Sussex University gantry robot that were able to visually distinguish a triangle from a square, under extremely noisy real world conditions, and steer the robot towards it. In both cases, controllers that were reliably fit in simulation displayed extremely robust behaviour when downloaded into reality


Download compressed postscript file