Humanoid push recovery using sensory reweighting

In this paper we propose a novel system that uses sensory input from both vision and inertial sensors for an improved perception of the robot current status of equilibrium. We use MonoSLAM vision odometry as a basis for the visual perception and a gyro for angular velocity measurements; and we devise a reweighting method within a Kalman filter framework. Moreover, our approach is designed to be robust against visual and measurement noise such as blur, poor lighting conditions, and faulty sensory output. The novelty in this work is a robust humanoid fall avoidance system, which relies on the fusion of sensory input, mainly gyroscope and visual odometry, taking into account changes in the environment. The fusion of the mentioned sensors in addition to the image quality assessment, ensure a more human-like fall avoidance in comparison to currently existing systems. We implement our method on the NAO humanoid, where seven sets of experiments are performed to assess the effectiveness of our approach. The fusion of camera and gyro information not only enables a more human-like behavior, but also provides more humanoid stability and faster recovery, and thus leads to more robust fall avoidance.