Safety-critical automation often requires redundancy to enable reliable system operation. In the context of integrating sensors into such systems, the one-out-of-two (1oo2) sensor architecture is one of the common used methods used to ensure the reliability and traceability of sensor readings. In taking such an approach, readings from two redundant sensors are continuously checked and compared. As soon as the discrepancy between two redundant lines deviates by a certain threshold, the 1oo2 voter (comparator) assumes that there is a fault in the system and immediately activates the safe state. In this work, we propose a novel fault prognosis algorithm based on the discrepancy signal. We analyzed the discrepancy changes in the 1oo2 sensor configuration caused by degradation processes. Several publicly available databases were checked, and the discrepancy between redundant sensors was analyzed. An initial analysis showed that the discrepancy between sensor values changes (increases or decreases) over time. To detect an increase or decrease in discrepancy data, two trend detection methods are suggested, and the evaluation of their performance is presented. Moreover, several models were trained on the discrepancy data. The models were then compared to determine which of the models can be best used to describe the dynamics of the discrepancy changes. In addition, the best-fitting models were used to predict the future behavior of the discrepancy and to detect if, and when, the discrepancy in sensor readings will reach a critical point. Based on the prediction of the failure date, the customer can schedule the maintenance system accordingly and prevent its entry into the safe state—or being shut down.

Global waste generation is projected to reach 3.40 billion tons by 2050, necessitating improved waste sorting for effective recycling and progress toward a circular economy. Achieving this transformation requires higher sorting intensity through intensified processes, increased efficiency, and enhanced yield. While manual sorting remains common, smaller plants often use positive sorting to recover recyclables, and larger plants combine automated systems with manual sorting. Negative sorting is employed to remove impurities and improve material quality. However, innovation in manual sorting has stagnated. Advances in Machine Learning and Artificial Intelligence offer transformative potential for waste management, with digitalisation and improved recyclate quality becoming priorities. Despite these trends, manual sorting is still largely treated as a digital black box. The presented research outlines the design of a novel, human-centric AI-powered assistance system to support sorting workers by enhancing decision-making and real-time assistance during the sorting process, driving the digitalisation of manual sorting. Potential use cases, system requirements, and essential components were explored. High-quality use case-specific data is essential for model training. Therefore, publicly available datasets were evaluated but found inadequate, necessitating use-case-specific data acquisition through near-industry-scale experiments. This data was used to train and develop key system components, such as object recognition, classification, and action recognition models. Results indicate that transfer learning with a balanced dataset is effective for waste-sorting applications. The classification model achieved 81% accuracy on an experimental acquired balanced dataset, outperforming the accuracy of the pre-trained model on its original dataset.

Achieving the autonomous deployment of aerial robots in unknown outdoor environments using only onboard computation is a challenging task. In this study, we have developed a solution to demonstrate the feasibility of autonomously deploying drones in unknown outdoor environments, with the main capability of providing an obstacle map of the area of interest in a short period of time. We focus on use cases where no obstacle maps are available beforehand, for instance, in search and rescue scenarios, and on increasing the autonomy of drones in such situations. Our vision‐based mapping approach consists of two separate steps. First, the drone performs an overview flight at a safe altitude acquiring overlapping nadir images, while creating a high‐quality sparse map of the environment by using a state‐of‐the‐art photogrammetry method. Second, this map is georeferenced, densified by fitting a mesh model and converted into an Octomap obstacle map, which can be continuously updated while performing a task of interest near the ground or in the vicinity of objects. The generation of the overview obstacle map is performed in almost real time on the onboard computer of the drone, a map of sizeis created in, therefore, with enough time remaining for the drone to execute other tasks inside the area of interest during the same flight. We evaluate quantitatively the accuracy of the acquired map and the characteristics of the planned trajectories. We further demonstrate experimentally the safe navigation of the drone in an area mapped with our proposed approach.

Transformers are a very important asset in the electrical transmission grid, and they can suffer from destructive events—e.g., rare transformer fires. Unfortunately, destructive events often lead to a lack of data available for investigators during post-event forensics and failure analysis. This fact has motivated our design and implementation of a robotic multi-sensor platform and cloud backend solution for the lifecycle monitoring, inspection, diagnostics, and condition assessment of transformers. The robotic platform collects data from specific viewpoints around the transformer during operation and at specific relevant lifecycle milestones of the transformer (e.g., at the factory acceptance test) in an automated, repetitive, precise, and reliable manner. The acquired data are stored in the cloud backend, which also provides computing resources and data access to relevant in- and off-premises services (e.g., respectively, SCADA systems, and weather reports). In this paper, we present the results of our first measurement campaign to showcase the value of our solution for transformer lifecycle monitoring, for anomaly detection, and as a crucial tool for post-event forensics in the case of destructive events.

This paper presents a novel approach to improving wireless communications in harsh propagation environments to achieve higher overall reliability and durability of wireless battery powered sensor systems in the context of in-vehicle communication. The goal is to investigate the physical layer and establish an antenna recommendation system for a specific harsh environment, i.e., an engine compartment of a vehicle. We propose the usage of electromagnetic (EM) and ray tracing simulations as a computationally cost-effective method to establish such a recommendation system, which we test by means of an experimental testbed—or test environment—that consists of both a physical, as well as its identical simulation, model. A pool of antennas is evaluated to identify and verify antenna behavior and properties at specified positions in the harsh environment. We use a vector network analyzer (VNA) for accurate measurements and a received signal strength indicator (RSSI) for a first estimation of system performance. Our analysis of the experimental measurements and its EM simulation counterparts shows that both types of data lead to equivalent antenna recommendations at each of the defined positions and experimental conditions. This evaluation and verification process by measurements on an experimental testbed is important to validate the antenna recommendation process. Our results indicate that—with properly characterized antennas—such measurements can be substituted with EM simulations on an accurate EM model, which can contribute to dramatically speeding up the antenna positioning and selection process.