In light of the evolving landscape of future converged networks, heightened demands for scalability and performance have become paramount, particularly in the industrial context where enhanced flexibility, adaptability, time synchronization and deterministic low latency are key features. Time-Sensitive Networking (TSN) has been introduced to provide converged networks with determinism. To mitigate the complexities associated with cabling requirements, Wireless Time-Sensitive Networking (WTSN) emerges as a more suited solution in industrial applications that need mobility. This study presents an application in smart manufacturing that incorporates WTSN technology. Specifically, it focuses on a scenario where an Unmanned Ground Vehicle (UGV), under the control of an edge controller connected through a wireless link, operates within a critical environment subject to constraints such as to avoid obstacles and to build a real-time map of the surrounding area. The mapping outcome performed by the edge controller demonstrates the effectiveness of the WTSN capabilities.

The demand for precise time synchronization is of great interest in contemporary networked systems, especially in the context of converged networks where seamless communication among devices, actuators, and sensors is imperative. This has led to the development and adoption of Time-Sensitive Networking (TSN) and Wireless TSN (WTSN) technologies, with a particular attention to the IEEE 802.1AS Generalized Precision Time Protocol (gPTP) standard. In this work, we explore the role of time synchronization in a wireless network scenario involving an Unmanned Ground Vehicle (UGV) that has to track a desired time dependent trajectory. The UGV receives trajectory waypoints from a secondary station, emphasizing the importance of precise timing in trajectory tracking. Utilizing the IEEE 802.1AS standard for wireless time synchronization, this study investigates the impact of clock synchronization errors and latency on trajectory tracking. Hence, it demonstrates the capability and benefits of IEEE 802.1AS in managing device clocks and facilitating time correction to ensure precise trajectory tracking despite synchronization errors and latency.

This paper presents a study on transforming a traditional human-operated vehicle into a fully autonomous device. By leveraging previous research and state-of-the-art technologies, the study addresses autonomy, safety, and operational efficiency in industrial environments. Motivated by the demand for automation in hazardous and complex industries, the autonomous system integrates sensors, actuators, advanced control algorithms, and communication systems to enhance safety, streamline processes, and improve productivity. The paper covers system requirements, hardware architecture, software framework and preliminary results. This research offers insights into designing and implementing autonomous capabilities in human-operated vehicles, with implications for improving safety and efficiency in various industrial sectors.

This paper explores the potential benefits and challenges of integrating Electric Vehicles (EVs) and Autonomous Ground Vehicles (AGVs) in industrial settings to improve sustainability and operational efficiency. While EVs offer environmental advantages, barriers like high costs and limited range hinder their widespread use. Similarly, AGVs, despite their autonomous capabilities, face challenges in technology integration and reliability. To address these issues, the paper develops a fleet management tool tailored for coordinating electric AGVs in industrial environments. The study focuses on simulating electric AGV performance in a primary aluminum plant to provide insights into their effectiveness and offer recommendations for optimizing fleet performance.

Nowadays, aerial formations are frequently employed in outdoor scenarios to cooperatively explore and monitor wide areas of interest. In these applications, the vehicles are often exposed to relevant security vulnerabilities, as, for instance, the alteration of navigation signals from an attacker with map counterfeiting (if not even hijacking) purposes. In this work, we focus on an Unmanned Aerial Vehicle (UAV) formation that monitors an area, wherein navigation spoofing attacks may occur. Letting the UAVs cooperate and exploiting the redundancy in the available sensing information, a distributed procedure is proposed to$i$) detect spoofing attacks, and$ii$) support the navigation in adverse conditions. The validity of the designed approach is confirmed by numerical results. Aerial vehicles for outdoor operation are generally endowed with inertial measurements, relative ranging, and GNSS sensing capability. In this work, two cascaded estimation algorithms for concurrent GNSS spoofing detection and localization in a multi-UAV scenario is proposed, to attain robust navigation in areas subject to GNSS spoofing attacks. The attack detection leverages on information theoretic tools to provide a practical threshold test by checking the multimodal measurement consistency. The localization procedures exploit a decision logic relying on measurement reliability to combine information sources that are different in nature, for UAV self-localization in both safe and under-attack conditions. Note to Practitioners—Aerial vehicles for outdoor operation are generally endowed with inertial measurements, relative ranging, and GNSS sensing capability. In this work, two cascaded estimation algorithms for concurrent GNSS spoofing detection and localization in a multi-UAV scenario is proposed, to attain robust navigation in areas subject to GNSS spoofing attacks. The attack detection leverages on information theoretic tools to provide a practical threshold test by checking the multimodal measurement consistency. The localization procedures exploit a decision logic relying on measurement reliability to combine information sources that are different in nature, for UAV self-localization in both safe and under-attack conditions.

Visual inspection has recently gained increasing importance in the manufacturing industry and is often addressed by means of learning methodologies applied to data obtained from specific lighting and camera system setups. The industrial scenario becomes particularly challenging when the inspection regards reflective objects, which may affect both the data acquisition and the classification decision process, thus limiting the overall performance. In this context, we observe that the dynamics of the reflected light is the key aspect to characterize these surfaces and needs to be accurately exploited to improve the performances of the learning algorithms. To this aim, we propose a combined model-based and data-driven approach designed to detect defects on the reflective surfaces of industrial products, captured as video sequences under coaxial structured illumination. Specifically, a tunable spatial-temporal descriptor of the evolution of the reflected light [dynamic evolution of the light (DEL)] is designed and employed within a hybrid learning (HL) framework, where the learning process of a convolutional neural network (CNN) is driven by the model-based descriptor. This approach is also extended by adopting the similar in nature descriptor dynamic image. The proposed HL solutions are validated against a whole spectrum of state-of-the-art learning procedures and different descriptors. Experiments run on a dataset coming from an actual industrial scenario that confirms the ability of DEL to accurately characterize reflective surfaces and the validity of the HL method, which shows remarkably better performance in fault detection even with respect to modern 3-D CNNs with comparable computational effort.

Cooperative robotics is a trending topic nowadays as it makes possible a number of tasks that cannot be performed by individual robots, such as heavy payload transportation and agile manipulation. In this work, we address the problem of cooperative transportation by heterogeneous, manipulator- endowed robots. Specifically, we consider a generic number of robotic agents simultaneously grasping an object, which is to be transported to a prescribed set point while avoiding obstacles. The procedure is based on a decentralized leader-follower Model Predictive Control scheme, where a designated leader agent is responsible for generating a trajectory compatible with its dynamics, and the followers must compute a trajectory for their own manipulators that aims at minimizing the internal forces and torques that might be applied to the object by the different grippers. The Model Predictive Control approach appears to be well suited to solve such a problem, because it provides both a control law and a technique to generate trajectories, which can be shared among the agents. The proposed algorithm is implemented using a system comprised of a ground and an aerial robot, both in the robotic Gazebo simulator as well as in experiments with real robots, where the methodological approach is assessed and the controller design is shown to be effective for the cooperative transportation task.

High definition (HD) maps are one of the key technologies supporting autonomous-driving vehicles (ADVs). Especially in urban scenarios, the field of view of sensors is often limited, and HD map provides critical information about upcoming road environmental data. Maps used for ADVs are high resolution with centimeter-level accuracy and their correctness is fundamental when analyzing the safety of upcoming maneuvers. This paper proposes an approach for online map validation (OMV) based on spatial and temporal correlation of smart-sensors. Smart sensors are capable of analyzing the validity of regions of the map independently from one another. Results from the sensors are then fused over multiple regions and time samples for providing a unified view to software components deciding on upcoming maneuvers which areas of the maps are consistent with sensor data and which are not.

With the rise of Industry 4.0 and of the Industrial Internet, the computing and communication infrastructures achieved an essential role within process and factory automation, and cyberphysical systems in general. In this scenario, the OPC UA standard is currently becoming a widespread opportunity to enable interoperability among heterogeneous industrial systems. Nonetheless, OPC UA is characterized by a complex protocol architecture, that may impair the scalability of applications and may represent a bottleneck for its effective implementation in resource-constrained devices, such as low-cost industrial embedded systems. Several different OPC UA implementations are available, which in some significant cases are released under an open source license. In this context, the aim of this paper is to provide an assessment of the performance provided by some of these different OPC UA implementations, focusing specifically on potential development and resource bottlenecks. The analysis is carried out through an extensive experimental campaign explicitly targeting general purpose low-cost embedded systems. The final goal is to provide a comprehensive performance comparisons to allow devising some useful practical guidelines.

Wireless networks are ever more deployed in industrial automation systems in various types of applications. A significant example in this context is represented by the transmission of safety data that, traditionally, was accomplished by wired systems. In this paper we propose an implementation of the Fail Safe over EtherCAT (FSoE) protocol on the top of IEEE 802.11 WLAN. The paper, after a general introduction of FSoE, focuses on the implementation of such protocol on commercial devices running UDP at the transport layer and connected via the IEEE 802.11 Wireless LAN. Then the paper presents some experimental setups and the tests that have been carried out on them. The obtained results are encouraging, since they show that good safety performance can be achieved even in the presence of wireless transmission media.

Hand motion tracking traditionally requires highly complex and expensive systems in terms of energy and computational demands. A low-power, low-cost system could lead to a revolution in this field as it would not require complex hardware while representing an infrastructure-less ultra-miniature (∼ 100μm — [1]) solution. The present paper exploits the Multiple Point Tracking algorithm developed at the Tyndall National Institute as the basic algorithm to perform a series of gesture recognition tasks. The hardware relies upon the combination of a stereoscopic vision of two novel Lensless Smart Sensors (LSS) combined with IR filters and five hand-held LEDs to track. Tracking common gestures generates a six-gestures dataset, which is then employed to train three Machine Learning models: k-Nearest Neighbors, Support Vector Machine and Random Forest. An offline analysis highlights how different LEDs' positions on the hand affect the classification accuracy. The comparison shows how the Random Forest outperforms the other two models with a classification accuracy of 90–91 %.

Over the past few years, a huge number of distributed camera calibration strategies have been proposed for video surveillance and monitoring systems involving mobile terminals. Many of the proposed solutions rely on consensus-based algorithms, which aim at estimating the configuration of the network via a message passing protocol. In this paper we propose an improved consensus-based distributed camera calibration strategy that exploits a robust initialization, together with a pruning protocol to remove faulty links which could propagate excessively-noisy information through the network reducing the convergence time. The proposed solution seems to improve the state-of-the-art strategies in terms of accuracy, convergence speed, and computational complexity.

In this paper we address the safety strategies for networked electrical drive systems, in the context of industrial automation. Specifically, it is considered the handling of errors and faults that may occur during the execution of safety related functions, on a set of electrical drives. Such devices, which operate in a coordinated way, are connected via an industrial communication network and use a safety industrial protocol. In this respect, a novel approach that exploits a distributed consensus algorithm to identify and possibly recover the aforementioned errors is devised and discussed in comparison with a traditional safe shut-down strategy. The theoretical performance figures and the effectiveness of the proposed approach are evaluated in a real industrial case study considering two different widespread network topologies.

Recently, different communities in computer science, telecommunication, and control systems have devoted a huge effort towards the design of energy efficient solutions for data transmission and network management. This paper collocates along this research line and presents a novel energy efficient strategy conceived for Ethernet networks. The proposed strategy, which exploits the opportunities offered by the IEEE 802.3az amendment to the Ethernet standard (known as energy efficient Ethernet) is based on the possibility of predicting the future traffic from the analysis of the current data flow. In agreement with the results of such a dynamic prediction, Ethernet links can be forced into a low power consumption state for variable intervals. Theoretical bounds are derived to detail how the performance figures depend on the parameters of the designed strategy and scale with respect to traffic load. Furthermore, simulation results carried out with both real and synthetic traffic traces are presented to prove the effectiveness of the strategy, which leads to considerable energy savings at the cost of only a limited bounded delay in data delivery.

Wireless sensor networks (WSNs) can provide numerous benefits in industrial automation. By removing the cable infrastructure, the wireless architecture enables the possibility for nodes in a network to dynamically and autonomously group into clusters according to the communication features and the data they collect. This capability allows to leverage the flexibility and robustness of industrial WSNs in supervisory intelligent systems for high-level tasks, such as, for example, environmental sensing, condition monitoring, and process automation. In this paper, a clustering strategy is studied that partitions a sensor network into a nonfixed number of nonoverlapping clusters according to the communication network topology and measurements distribution: To this aim, both a centralized and a distributed algorithm are designed that do not require a cluster-head structure or other network assumptions. As a validation, these strategies are tested on a real dataset coming from a structured environment and the effectiveness of the clustering procedure is also investigated to perform anomalies detection in an industrial production process.

We consider control of multiple luminaires with a central controller and occupancy and light sensors co-located at the luminaires. The sensors periodically provide local occupancy state and illumination information to the central controller. Using this sensor feedback, the central controller determines the dimming levels of the luminaires so as to adapt artificial light output to changing daylight levels and occupancy conditions, in an energy efficient way. We propose a multivariable feedback controller based on optimizing a cost function with a component corresponding to power consumption and another corresponding to illumination errors at the light sensors. The constraints are that the attained illumination value at the light sensors be no smaller than the reference set-points and that the dimming levels of luminaires are within physical limits. We compare the performance of the proposed controller with a simple stand-alone reference controller. We show via simulations in an open-plan office lighting system that the proposed controller has better performance in terms of achieving the reference set-points.

In this paper, a machine learning (ML) approach is presented that exploits accelerometers data to deal with gesture recognition (GR) problems. The proposed methodology aims at providing high accuracy classification for home automation systems, which are generally user independent, device independent, and device orientation independent, an heterogeneous scenario that has not been fully investigated in previous GR literature. The approach illustrated in this paper is composed of three main steps: event identification; feature extraction; and ML-based classification. The elements of the novelty of the proposed approach are 1) a preprocessing phase based on principal component analysis to increase the performance in real-world scenario conditions and 2) the development of parsimonious novel classification techniques based on sparse Bayesian learning. This methodology is tested on two datasets of four gesture classes (horizontal, vertical, circles, and eight-shaped movements) and on a further dataset with eight classes. In order to authentically describe a real-world home automation environment, the gesture movements are collected from more than 30 people who freely perform any gesture. It results in a dictionary of 12 and 20 different movements, respectively, in the case of the four-class and the eight-class databases.

Industrial communication systems, like the very popular real-time Ethernet networks, are ever more used to carry multimedia traffic, i.e. that generated by applications employing complex sensors such as, for example, video cameras. Ethernet networks, however, revealed to be quite inefficient in terms of energy saving since the power consumption of a link between any two devices does not decrease significantly during the (statistically long) idle periods, i.e. the intervals of time in which the link is not crossed by traffic. In this paper we present a novel traffic shaping technique that aims at saving energy when the multimedia industrial traffic has self similar characteristics. In particular, the proposed method combines the statistical properties of the traffic, with the opportunities offered by the recent amendment to the Ethernet standard, called Energy Efficient Ethernet (EEE), to design a strategy based on the analysis of current traffic levels and the prediction of the incoming data flow. Simulation results are presented to prove the effectiveness of the strategy which leads to considerable energy savings at the expense of only a limited bounded delay in frame delivery.

“Smart City” is a powerful paradigm that applies the most advanced communication technologies to urban environments, with the final aim of enhancing the quality of life in cities and provide a wide set of value-added services to both citizens and administration. A fundamental step towards the practical realization of the Smart City concept consists in the development of a communication infrastructure capable of collecting data from a large variety of different devices in a mostly uniform and seamless manner, according to the Internet of Things (IoT) paradigm. While the scientific and commercial interest in IoT has been constantly growing in the last years, practical experimentation of IoT systems has just begun. In this paper, we present and discuss the Padova Smart City system, an experimental realization of an urban IoT system designed within the Smart City framework and deployed in the city of Padova, Italy. We describe the system architecture and discuss the fundamental technical choices at the base of the project. Then, we analyze the data collected by the system and show how simple data processing techniques can be used to gain insights on the functioning of the monitored system, public traffic lighting in our specific case, as well as other information concerning the urban environment.