M. Peniak, D.Marocco, A. Cangelosi (2009). Co-evolving controller and sensing abilities in a simulated Mars Rover explorer. IEEE Congress on Evolutionary Computation (CEC) 2009. Trondheim, Norway, 18th-21nd May
Theoretically if we were able to communicate with planetary rovers instantaneously we might not really need a robot to be autonomous. Because it takes so long for radio waves to propagate it is absolutely vital for a planetary robot to be fully autonomous. Moreover, such missions are normally prepared and planned for a very long time and therefore we must be absolutely Sure that all systems are reliable and safe.
The fundamental requirement of an autonomous planetary rover is the ability to avoid obstacles. Currently the obstacle avoidance on both Spirit and Opportunity rovers is done by means of heavy processing of stereo images obtained through stereo cameras. We aim to develop a fast lightweight obstacle avoidance system that would minimize processing power needed
ANNs as a simplified model of a brain and GA to simulate natural evolution