Document Type

Conference Proceeding

Publication Date



Co-evolving a robot’s sensor morphology and control program increases the potential that it can effectively complete its tasks and provides a means for adapting to changes in the environment. In previous work, we presented a learning system where the angle, range, and type of sensors on a hexapod robot, along with the control program, were evolved. Although three sensor stimuli were detectable by the system, it used only two due to the relative importance of these two stimuli in completing the task. In the research presented in this paper, we used the same system, but reduced the availability of a key stimuli; the most effective solution now required the use of all three stimuli. The learning system still performed well by pacing sensors appropriate for the third stimuli and creating a program that utilized these sensors to successfully solve the problem.




The views expressed in this paper are solely those of the author.