Minimising the Hardware Resources for a Cellular Automaton with Moving Creatures

Given is the following “creature’s exploration problem”: n creatures are moving around in an unknown environment in order to visit all cells in shortest time. This problem is modelled as a cellular automaton (CA) because the CA model is massively parallel. Therefore, it is perfectly suited to be supported by hardware. We are trying to simulate the CA as fast as possible by the use of the FPGA technology. We need a very fast simulation because we want to observe and evaluate much different behaviours of the creatures. Our main goal in the background is the optimisation of the behaviours of the creatures. In this contribution we have investigated the question how the creature’s exploration problem can be implemented in hardware with a minimum of hardware resources in order to maximise the number of cells which can be computed in parallel (or to speed up the simulation). We have designed and evaluated four different implementations that vary in the combination or separation of the logic for the environment, for the creatures and for the collision detection.