Learning the odometry on a small humanoid robot

Abstract

Odometry is an important element for the localization of mobile robots. For humanoid robots, it is very prone to integration errors, due to mechanical complexity, uncertainties and foot/ground contacts. Most of the time, a visual odometry is then used to encompass these problems. In this work we propose a method to compensate for odometry drifting using machine learning on a small size low-cost humanoid without vision. This method is tested on different ground conditions and exhibits a significant improvement in odometry accuracy.