Visual-inertial ego-motion estimation for humanoid platforms

Abstract

We describe an ego-motion estimation system developed specifically for humanoid robots, integrating visual and inertial sensors. It addresses the challenge of significant scale changes due to forward motion with a finite field of view by using recent sparse multi-scale feature tracking techniques. Additionally, it addresses the challenge of long-range temporal correlation due to walking gaits by employing a kinematic-statistical model that does not require accurate knowledge of the robot dynamics and calibration. Our system achieves performance comparable to the state of the art at a fraction of the (inertial measurement unit) cost, on a challenging dataset that we have created.