ErgoAssist: An assistance system to maintain ergonomie guidelines at workplaces

Abstract

We propose an assistance system which observes a process involving humans and automatically takes measures in situations where ergonomic guidelines are violated. The system uses a Microsoft Kinect Sensor to capture a depth map of the scene. Using this sensory information, the system extracts working pose and assesses ergonomics in the current situation. If an ergonomically critical situation occurs, the system flexibly adjusts the height of a workpiece during a process in order to enable the worker to adapt a more comfortable pose. First experiments show the potential of the method but also reveal the remaining technological challenge in capturing the pose. As future work, we plan to extend our existing pose capturing method for the 3D case. Moreover, we plan to conduct studies in order to analyse the acceptance of such a system in production environment.

Automated vision-based live ergonomics analysis in assembly operations

“…The workplace automatically adjusts the height in case the worker's current posture does not allow comfortable working [8]. For this application, the accuracy of the hand position identification is still not satisfactory (see Fig.…”

“…The novelty is that the system can be used during the performance of a process and is able to provide feedback within a few seconds. The processing speed enables the usage of this system for the assistance of the worker such as proposed in Nguyen et al [8]. Moreover, the method is able to identify the body parameters without markers attached giving the worker natural freedom in the movement.…”

Human-Centred Automation to Simplify the Path to Social and Economic Sustainability

“…The WPC uses a consumer depth camera to acquire the input data. Afterwards, a markerless motion capture algorithm (Nguyen et al 2014) is developed to determine the coordinates of each limb. Having obtained the coordinates, classifiers are trained on training datasets to recognise the posture.…”

An Effective Scheme of a Depth Sensor Set Up for a Real-Time Ergonomics Assessment by the Gesture Confidence Level

“…Furthermore, the digital real-time data captured by Microsoft Kinect V1.0 facilitates human digital modelling in the virtual reality area. Besides the great potential of digital data collection for the real-time ergonomic assessment, some studies suggest that the accuracy of the captured data relates to its placement [11], [12]. Evaluation by [11] proposes that placing Kinect V1.0 in between 1 m to 3 m from the object and at 54° and 39.1° horizontal and vertical field produces accurate skeletal data for ergonomic assessment.…”