Robust Distance Estimation of Capacitive Proximity Sensors in HRI using Neural Networks

With Industry 4.0 and the idea of flexible and hybrid manufacturing systems, the need for safe human-robot-interaction has become increasingly important. For this purpose, it is necessary to reliably detect persons in the workspace of a robot. Capacitive sensors mounted to the robot structure can be used to measure the presence of conductive objects and, hence, allow the detection of persons. However, for a reliable detection in an adequate range, it is necessary to compensate for various additional influences on capacitive sensors. In this paper, we propose a segmentation of the world model and the use of machine learning to compensate for the self-influence of the robot. Moreover, a correlation between the measured capacitance and the distance of a human hand can be calculated using machine learning, as well. Finally, it is possible to estimate the distance between capacitive sensors at the robot structure and a human hand while the robot is in motion. A motion capturing system is used as ground truth for the distance.