Corrado Santoro

This paper presents a maritime Internet of Things anti-theft architecture based on an ESP32 onboard node, local motion analysis, and LoRa mesh communication. The proposed detection pipeline uses a one-dimensional convolutional autoencoder trained on stationary vessel data and applied to sliding windows of X- and Z-axis angular velocity measurements. During deployment, a calibration phase estimates the reconstruction-error threshold from the local motion profile of the moored vessel, reducing the dependence on labelled theft examples. The communication layer combines an Elliptic Curve Cryptography setup phase with symmetric payload encryption for alert packets, while ESP32 hardware security features are used to protect firmware and stored credentials. The mesh network uses controlled flooding. A Godot-based simulation environment was used to generate stationary and towing scenarios under different wave configurations. In the current simulation campaign, towing windows produced a higher mean reconstruction error than stationary windows. The results support the feasibility of the architecture and also show that event-level alert logic is required to aggregate window-level anomaly scores into reliable alarms.

Viticulture is facing growing economic and environmental pressures that demand a transition toward intelligent and autonomous crop management systems. Phytopathologies remain one of the most critical threats, causing substantial yield losses and reducing grape quality, while regulatory restrictions on agrochemicals and sustainability goals are driving the development of precision agriculture solutions. In this context, early disease detection is crucial; however, current visual inspection methods are hindered by subjectivity, cost, and delayed symptom recognition. This study presents a fully autonomous robotic platform developed within the Agrimet project, enabling continuous, high-frequency monitoring in vineyard environments. The system integrates a tracked mobility base, multimodal sensing using RGB-D and thermal cameras, an AI-based perception framework for leaf localisation, and a compliant six-axis manipulator for biological sampling. A custom control architecture bridges standard autopilot PWM signals with industrial CANopen motor drivers, achieving seamless coordination among all subsystems. Field validation in a Sicilian vineyard demonstrated the platform’s capability to navigate autonomously, acquire multimodal data, and perform precise georeferenced sampling under unstructured conditions. The results confirm the feasibility of holistic robotic systems as a key enabler for sustainable, data-driven viticulture and early disease management. The YOLOv10s detection model achieved good precision and F1-score for leaf detection, while the integrated Kalman filtering visual servoing system demonstrated low spatial tolerance under field conditions despite foliage sway and vibrations.

Digital Twins are emerging as one of the core technologies in robotics, enabling real-time simulation, optimisation and predictive maintenance. This article proposes a Distributed Multi-Agent Digital Twin Environment, a scalable architecture to maximise robotic system performance and safety. Through the combination of real-time virtual models and physical robotic agents, Distributed Multi-Agent Digital Twin Environment enables adaptive decision-making, multi-agent collaboration and optimal task completion in dynamic environments. The architecture is geared towards the support of single-agent and multi-agent systems through advanced communication protocols that enable synchronisation and real-world usage. The system leverages the Digital Twin Protocol over UDP for real-time synchronisation, ensuring the communication between digital twins and physical robots. Experimental results, conducted on a TurtleBot, demonstrate the system’s ability to optimise the navigation of robots, avoid collisions, and improve operational effectiveness. This work provides the gateway to more intelligent, responsive, and adaptive robotic systems in numerous industrial applications.

This work presents the design and evaluation of a distributed IoT protocol for intelligent parking management. It exploits the communication protocol LoRa and is designed to operate fully autonomously, without requiring Internet connectivity, enabling real-time parking slot detection and allocation through long-range wireless communication. The protocol also includes an optional MQTT-based synchronisation layer to support data exchange between gateways and with a central collector, allowing for telemetry, system monitoring, and analytics. We performed a set of experiments, proving that the protocol holds system resilience and scalability, which are key aspects for deployment in urban environments with unreliable or limited network access. We also observed a significant reduction in parking search time while preserving acceptable levels of system latency. To complete our evaluation, we deployed, in our laboratory, a test-bed made by ESP32-based nodes and simulated gateway breakage and replacement, in order to prove the fault recovery capabilities of the entire network. Finally, we conducted a few empirical stress tests simulating high communication traffic and interactions, confirming acceptable effectiveness and stability for real urban contexts.

The rapid proliferation of Internet of Things (IoT) devices has raised significant concerns regarding the trustworthiness of IoT devices, which is becoming a crucial aspect of our daily lives. In this paper, we deal with this important aspect by taking into account Meshtastic, a dynamic mesh networking protocol that offers robustness and adaptability, important characteristics for the dynamic and heterogeneous IoT environment. LoRaWAN (Low-Range Wide Area Network), a low-power, long-range wireless communication standard, introduces energy efficiency and extends the reach of IoT networks, enabling secure communication over extended distances. To improve the trustworthiness of IoT devices, we present an integrated approach that leverages the strengths of Meshstastic’s dynamic mesh networking capabilities and LoRa’s low-power, long-range communication, along with the integration of a reputation model specifically designed for IoT. We evaluated the performance of the proposed solution through several simulations and real-world experiments. The results show that the devices’ measured values of trust reflect the real behaviour of the devices. These findings underscore the viability and applicability of the Meshtastic protocol utilising LoRa technology as a pivotal step towards establishing resilient and trustworthy IoT infrastructures in the face of evolving security challenges.

In this contribution we extend an ontology for modelling agents and their interactions, called Ontology for Agents, Systems, and Integration of Services (in short, OASIS), with conditionals and ontological smart contracts (in short, OSCs). OSCs are ontological representations of smart contracts that allow to establish responsibilities and authorizations among agents and set agreements, whereas conditionals allow one to restrict and limit agent interactions, define activation mechanisms that trigger agent actions, and define constraints and contract terms on OSCs. Conditionals and OSCs, as defined in OASIS, are applied to extend with ontological capabilities digital public ledgers such as the blockchain and smart contracts implemented on it. We will also sketch the architecture of a framework based on the OASIS definition of OSCs that exploits the Ethereum platform and the Interplanetary File System.

The rapid evolution of autonomous flight technologies has highlighted the challenge of indoor Unmanned Aerial Vehicle missions. To address this, we introduce Twinflie, a groundbreaking virtual digital twin environment that bridges virtual and real worlds to revolutionise indoor UAV operations. In-door environments present unique navigation and safety challenges, distinct from outdoor spaces where GPS is prevalent. Twinflie stands out by seamlessly interfacing with both virtual and real drones, providing a collaborative space for precise indoor drone mission simulations and intricate scenario orchestration. It mitigates the high costs and limitations associated with real-world indoor tests, enabling the exploration of dynamic scenarios and enhancing operational efficiency with the Digital Twin environment.

Robot visual navigation is a relevant research topic. Current deep navigation models conveniently learn the navigation policies in simulation, given the large amount of experience they need to collect. Unfortunately, the resulting models show a limited generalization ability when deployed in the real world. In this work we explore solutions to facilitate the development of visual navigation policies trained in simulation that can be successfully transferred in the real world. We first propose an efficient evaluation tool to reproduce realistic navigation episodes in simulation. We then investigate a variety of deep fusion architectures to combine a set of mid-level representations, with the aim of finding the best merge strategy that maximize the real world performances. Our experiments, performed both in simulation and on a robotic platform, show the effectiveness of the considered mid-level representations-based models and confirm the reliability of the evaluation tool. The 3D models of the environment and the code of the validation tool are publicly available at the following link: https://iplab.dmi.unict.it/EmbodiedVN/.