Occupational ergonomics in healthcare is an increasing challenge we have to handle in the near future. Physical assistive systems, so-called exoskeletons, are promising solutions to prevent work-related musculoskeletal disorders (WMSDs). Manual handling like pushing, pulling, holding and lifting during healthcare activities require practical and biomechanical effective assistive devices. In this article, a musculoskeletal-model-based development of an assistive exoskeleton is described for manual patient transfer in the surgery waiting room. For that purpose, kinematic data collected with an experimental set-up reproducing real patient transfer conditions are first used to define the kinetic boundary conditions for the model-based development approach. Model-based analysis reveals significant relief potential in the lower back and shoulder area of the musculoskeletal apparatus. This is corroborated by subjective feedback collected during measurements with real surgery assistants. A shoulder–arm exoskeleton design is then proposed, optimized and evaluated within the same simulation framework. The presented results illustrate the potential for the proposed design to reduce significantly joint compressions and muscle activities in the shoulder complex in the considered patient transfer scenarios.

Weld quality inspection allows the detection of defects that may compromise the quality and strength of the weld. Although visual optical inspection offers lower reliability than other non-destructive methods, it enables weld analysis at a significantly lower cost. In this context, developing machine learning-based algorithms for automatic optical weld quality recognition requires acquiring large amounts of data for training. This entails high costs in terms of time, material and energy required for test preparation. However, one possible approach to tackling the problem with limited datasets is to use synthetic data. Using such data increases the amount and variety of data available to the detection algorithm. With a focus on the context of welding, this paper presents an approach that uses synthetic data as a form of data augmentation to improve the performance of the optical detection of weld seams. Specifically, we propose a generative neural network for semantic image synthesis using a limited starting dataset. The network generates new data instances by receiving as input a semantic map of the image to be represented. Weld defects such as porosity or weld spatter are added to the semantic map so that the network synthesizes corresponding defect images. Analysing the performance on a segmentation network, experimental results show how adding synthetic data to the original data can ensure improvements in network performance.