This paper investigates the evolution of modular robots using different selection preferences (i.e., fitness functions), aiming at novelty, speed of locomotion, number of limbs, and com- binations of these. The outcomes are analyzed from differ- ent perspectives: sampling of the search space, evolved mor- phologies, and evolved behaviors. This results in a wealth of findings, including a surprise about the number of sampled regions of the search space and the effect of different fitness functions on the evolved morphologies.
Effects of Selection Preferences on Evolved Robot Morphologies and Behaviors
This item's license is: Attribution 4.0 International