Human–Robot Collaboration Solution for Folding Fabrics Based on RGB-D Force and Kalman Filters

This article investigates the task of folding a fabric using a human–robot collaboration (HRC) solution. HRC is a widely adopted concept in the industrial realm, as physical interaction between operators and robots has enabled the former to focus on high-value tasks and the latter to complete repetitive, physically strenuous, and risky tasks. This article proposes a robust framework based on Kalman filter pose estimation, for the human–robot comanipulation in folding of fabrics. The framework utilizes the Kinect 2 tracking algorithm to find the location of the operator and then performs Kalman filtering to eliminate noise and improve the tracking of the operator’s position. The robot reacts to the operator’s movement, by moving to the same hand direction and distance on each iteration, to assist in the folding of a rectangular fabric. The proposed system was tested in a real use case scenario, where the collaborative task is the fold of a rectangular fabric, and the presented results showed that the system is capable of tracking the human motion to assist him.