The large-scale adoption of occupational exoskeletons (OEs) will only happen if clear evidence of effectiveness of the devices is available. Performing product-specific field validation studies would allow the stakeholders and decision-makers (e.g., employers, ergonomists, health, and safety departments) to assess OEs’ effectiveness in their specific work contexts and with experienced workers, who could further provide useful insights on practical issues related to exoskeleton daily use. This paper reviews present-day scientific methods for assessing the effectiveness of OEs in laboratory and field studies, and presents the vision of the authors on a roadmap that could lead to large-scale adoption of this technology. The analysis of the state-of-the-art shows methodological differences between laboratory and field studies. While the former are more extensively reported in scientific papers, they exhibit limited generalizability of the findings to real-world scenarios. On the contrary, field studies are limited in sample sizes and frequently focused only on subjective metrics. We propose a roadmap to promote large-scale knowledge-based adoption of OEs. It details that the analysis of the costs and benefits of this technology should be communicated to all stakeholders to facilitate informed decision making, so that each stakeholder can develop their specific role regarding this innovation. Large-scale field studies can help identify and monitor the possible side-effects related to exoskeleton use in real work situations, as well as provide a comprehensive scientific knowledge base to support the revision of ergonomics risk-assessment methods, safety standards and regulations, and the definition of guidelines and practices for the selection and use of OEs.

This paper provides a review of the literature on vision-based on-board obstacle detection and distance estimation in railways. Environment perception is crucial for autonomous detection of obstacles in a vehicle’s surroundings. The use of on-board sensors for road vehicles for this purpose is well established, and advances in Artificial Intelligence and sensing technologies have motivated significant research and development in obstacle detection in the automotive field. However, research and development on obstacle detection in railways has been less extensive. To the best of our knowledge, this is the first comprehensive review of on-board obstacle detection methods for railway applications. This paper reviews currently used sensors, with particular focus on vision sensors due to their dominant use in the field. It then discusses and categorizes the methods based on vision sensors into methods based on traditional Computer Vision and methods based on Artificial Intelligence.

Robotic harvesting in the open field demands innovative solutions in robot perception and mechanics to cope with environmental challenges. In this paper, a prototype robotic harvester that is able to cope with the challenges of selective harvesting of green asparagus is presented. The harvester is able to drive along an asparagus dam in the field, detect asparagus stalks, identify stalks that are ready for harvesting, and perform harvesting without damaging. These system abilities are enabled by a novel vision perception module and a novel harvesting mechanism. The perception module is based on three-dimensional-point cloud processing, and it is able to reliably and robustly detect the asparagus stalks, their positions, and dimensions. A novelty of the proposed harvesting mechanism is a multi-tools solution to increase harvesting productivity. The results of the first outdoor field tests demonstrate the applicability of the presented robotic harvester.

This paper presents an on-board multi-sensor system which is able to detect obstacles and estimate their distances in railway scenes in different illumination conditions. The system was developed within the H2020 Shift2Rail project SMART (Smart Automation of Rail Transport) and aims at increasing the safety of rail transport by detecting obstacles on the rail tracks ahead of a moving train in order to reduce the number of collisions. The system hardware consists of cameras of different types integrated into a specially designed housing, mounted on the front of the train. Multiple vision sensors complement each other in order to handle different illumination and environmental conditions. The system software uses a novel machine learning-based method that is suited to a particular challenge of railway operations, the need for long-range obstacle detection and distance estimation. The development of this method used a long-range railway dataset, which was specifically generated for this project. Evaluation results of reliable obstacle detection in various environmental conditions using the SMART RGB camera in day light illumination conditions and using the SMART Night Vision sensor in poor (night) illumination conditions are presented. The results demonstrate both the potential of the on-board SMART obstacle detection system in the operational railway environment and the benefit of the use of different cameras to be more independent of light and environmental conditions.