Tri-Mode Capacitive Proximity Detection Towards Improved Safety in Industrial Robotics

Abstract

This paper presents a multi-functional capacitive sensor that is developed to improve the worker safety during the industrial human-robot interactions. The sensor is to be mounted on the worker and used to maintain a safe distance between the workers and robots or automotive parts moved by the robots. The response of a capacitive proximity sensor is a function of the distance to an object as well as the dielectric/conductance and geometry properties of the object. This uncertainty can lead to a wrong distance estimation or possibly a missed detection. The presented approach alleviates this issue by implementing three sensing capabilities including distance measurement, motion tracking, and profile recognition in a single platform. The presented sensor employs a capacitive sensing element coupled to reprogrammable interface electronics. The sensing element features a matrix of electrodes that can be reconfigured to various arrangements at run-time by controlling the interface electronics to obtain a more detailed perception of the ambient environment. Quantitative regression models are built to seek out distances while an adaptive classification tool based on support vector machines is employed to recognize the surface profiles. The performance of the sensing modalities has been experimentally assessed. Experimental results are provided to demonstrate that the system is able to detect a metallic object at distances of up to 18 cm with high resolutions, track its motion, and provide an estimate for its shape.