Automated Optimization of Walking Parameters for the Nao Humanoid Robot
More Info
expand_more
expand_more
Abstract
This paper describes a framework for optimizing walking parameters for a Nao humanoid robot. In this case an omnidirectional walk is learned. The parameters are learned in simulation with an evolutionary approach. The best performance was obtained for a combination of a low mutation rate and a high crossover rate.
Files
Paper_69.pdf
(pdf | 0.478 Mb)