Traffic control in urban environments is a complex and critical challenge, with growing urbanisation and increasing vehicular congestion necessitating innovative solutions. Reinforcement learning has emerged as a promising approach to optimise traffic control and improve overall transportation efficiency, thanks to its ability to grasp the intricacies of complex issues without human involvement autonomously. In this paper, we propose a modified version of the SUMO-RL package and demonstrate its advantages in the context of our ongoing research regarding traffic control in the city of Zilina. The proposed modifications include support for custom reward functions for different agents and custom observation functions, representing a crucial design component when solving traffic signal control as a multi-agent reinforcement learning problem. We also present our preliminary results, which demonstrate the potential of reinforcement learning in addressing traffic control challenges.

The increasing demand for efficient parking space utilisation has triggered the development of vacancy detection systems, with a particular focus on addressing the unique environmental constraints imposed by winter conditions. In this paper we present vacancy detection tool trained on our dataset that was collected in the parking lot of the University of Zilina, capturing unique winter conditions from December to January. The dataset includes diverse weather scenarios, such as snowfall or early morning conditions where light is reflected directly into the camera. Leveraging YOLOv4, Faster R-CNN, and PKLot dataset, WinterWatch demonstrates good performance in real-time vacancy detection under these challenging circumstances. WinterWatch not only contributes to the evolution of smart parking systems but also underscores the importance of tailored solutions for diverse environmental settings, ensuring year-round efficiency in outdoor parking management.

This article deals with the generic model for object monitoring and tracking in an industrial environment and manufacturing. We focus on the design of generic IoT Edge device model that enables the integration of various LoRa sensors independently on vendor solutions for common use cases. Our model is based on the MQTT protocol, which is proven for sensor applications and gives needed independency on proprietary protocols. The model was implemented in Node-RED software and subsequently validated with sensors of different vendors to confirm the generic approach and base for independent object tracking solutions. The proposed Edge device model supports independent object tracking, such as object status monitoring, localization and triggered events, giving independent approach for tailored solutions and wide application portfolio based on combined different sensors and devices.

Integrating digital data and human sensory input in real-world settings offers new possibilities in device diagnostics and maintenance. In this study, we utilized the EcoStruxure Augmented Operator Advisor to develop an augmented reality application for a family house heating system. Our application was designed without access to the real heating system; instead, we simulated its operation with a programmable logic controller. Our final application includes three primary scenes: the heat pump, its indoor unit, and the engine room. Drawing on our practical experience, we discuss the benefits of our approach and the software tools used and summarize our subjective opinions.

Our article deals with the Edge device model focusing on high-availability of Long-Range Wide Area (LoRaWAN) sensors for business-critical applications. We focus on creating a suitable Edge device model that ensures the high availability of sensor data for specific critical applications. The model was implemented in Node-RED software, based on the MQTT protocol, and subsequently validated to confirm the required duplication of LoRaWAN sensors values for application. In case of single failure, Edge model enables uninterrupted flow of sensors data for their processing by critical applications.

The article deals with the integration of Lo(ng) Ra(nge) Wide Area Network (LoRaWAN) sensors with generic manufacturing applications and Industrial Internet of Things (IIoT) use-cases. The focus is on creating a suitable Edge device model that enables the integration of specific Long Range (LoRa) sensors together with the other generic Internet of Things (IoT/IIoT). The model is based on the Open Platform Communications Unified Architecture (OPC UA) standard, which is the most suitable integration platform for various control systems and manufacturing applications. The model was implemented in Node-RED software and subsequently validated to confirm the required integration of LoRaWAN sensors within OPC UA models. In contrast to other approaches based on integration gateway or LoRaWAN/OPC UA protocol convertors, the proposed model utilizes extended capabilities of Edge computing. It enables Edge processing and data transformation of LoRaWAN sensors data transferred by Message Queuing Telemetry Transport (MQTT) protocol from the network server, based on requirements of manufacturing applications for cloud solutions.

The autonomous movement of the mobile robotic system is a complex problem. If there are dynamic objects in the space when performing this task, the complexity of the solution increases. To avoid collisions, it is necessary to implement a suitable detection algorithm and adjust the trajectory of the robotic system. This work deals with the design of a method for the detection of dynamic objects; based on the outputs of this method, the moving trajectory of the robotic system is modified. The method is based on the SegMatch algorithm, which is based on the scan matching, while the main sensor of the environment is a 2D LiDAR. This method is successfully implemented in an autonomous mobile robotic system, the aim of which is to perform active simultaneous localization and mapping. The result is a collision-free transition through a mapped environment. Matlab is used as the main software tool.

The paper proposes a method for detection of a fire inside the road tunnel without direct view on the fire, using on-board vehicle technologies. The system is based on comparing the measured development of temperature and smoke with model scenarios precomputed for a given road tunnel. The fire scenarios are computed by HW/SW tool TuSim regarding the parameters of the real road tunnel and then the results are presented to the vehicles via car-to-infrastructure communication link. The proper detection of the fire allows early evacuation of the vehicle passengers, which will significantly increase chance of their survival. The computed scenarios also provide supporting information for the rescue teams.

Safety-related communication system SR-ComS uses a safety code for achieving the integrity of messages transferred between safety-related devices. In most cases, it is a block systematic code that uses syndromic decoding technique. The authors discuss the possibilities of using the convolutional structures for safety-related applications requiring creation of safety case based on quantitative assessment in relation to the transmission integrity level. This assessment is based on code analysis focused mainly on the error probability calculation. The results published in the practical part are obtained using a model created in Matlab environment, in which the chosen convolutional structures were tested. These tests were focused on the transmission error probability analysis provided by a binary symmetric channel, and also on optimization of other parameters affecting the residual error in the decoding algorithm. The results are generalized into concept of methodology for the convolutional codes safety assessment in compliance with standards for safety-related applications.

Safety programmable logic controllers (S-PLCs) provide broad application options and are being used to perform control but primarily safety functions (SFs) on the process control level. An essential part of control systems based on S-PLC is the sensors and actuators. In order to ensure the SF with high safety integrity level (SIL), the control system performing this SF has to dispose of a suitable failure detection mechanism and a mechanism providing its safe reaction in case of a failure detection. The diagnostics provided by S-PLC is mainly focused on its own components, and the diagnostics of sensors and actuators has to be resolved on the application program level while respecting some specific properties of S-PLC. This paper addresses the analysis of the influence of S-PLC parameters and diagnostic parameters on the safety function SIL, which is performed by a safety relevant electronic system. In the practical part is described the implementation of application diagnostics in S-PLC and the results of diagnostic parameters influence on safety integrity of SF for a selected example connected to a practical application.

Freeway networks reach their limits, since it is usually impossible to increase traffic volumes by indefinitely extending transport infrastructure through adding new traffic lanes. One of the possible solutions is to use advanced intelligent transport systems, particularly ramp metering systems. The paper shows how two particular algorithms of local and traffic-responsive control (Zone, ALINEA) can be adapted to simplified conditions corresponding to Slovak freeways. Both control strategies are modelled and simulated using PTV Vissim software, including the module VisVAP. Presented results demonstrate the properties of both control strategies, which are compared mutually as well as with the initial situation in which no control strategy is applied.

In the paper the authors focus on models construction of transport scenarios with orientation to security analysis of C2C communications. In the practical part two transport scenarios are analysed on a sample of real captured transport data via Riverbed Modeler tool. The computational complexity of ECDSA digital signature schemes was determined according to several selected EC curves and the efficiency of a PC. For the worst case transport scenario, the parameters throughput of network and delay between transmitted and received messages were analysed according to the number of nodes and message lengths.

In recent years the topic of Cooperative Intelligent Transportation Systems is widely studied. Interconnected vehicles able of information exchange can reduce traffic accident ratio significantly. To allow reliable, low latency Vehicle-to-Vehicle communication new network technologies are needed. This paper proposes hybrid network topology for V2V communication scenario to prevent network overload when transmitting safety oriented information. Properties of the proposed topology are evaluated by network simulation.

The paper is focused on the description of modern image processing methods within vehicles with orientation on Lane Departure Warning Systems (LDWS), which are a part of modern Cooperative-Intelligent Transportation Systems (C-ITS). A solution is described for searching of horizontal traffic signs using a segmentation method based on Hough transform. The practical part states the results of software implementation testing, with input image data gathered from a traffic scene using a camera located near vehicle's inner rear mirror. The authors aimed at the task of correct setting of alarm zone for a safe and timely detection of horizontal traffic sign crossing.

The authors of this contribution focus on analysis of V2V communication security solutions in Cooperative - Intelligent Transportation Systems (C-ITS). They emerge from the current state of risks and potential security incidents within communication between moving nodes. In more detail, they focus on the service of message nonrepundation and message recency, which utilises the cryptographic digital signatures techniques in combination with timestamps. The experimental part analyses security solutions with three types of cryptographic digital signatures techniques for two traffic scenarios based on actual traffic data from the D1 highway. The results are studied in dependence on the most frequent required application parameters for the transmission of safety relevant messages, like message length, cryptographic header length, message processing time and delay in relation to network throughput.

The paper is concerned with safety appraisal of safety-related communication systems (SRComSs) with open transmission system, where except in addition to message transmission integrity also confidentiality is recommended to be provided. The authors focused on safety analysis of safety-related messages transmission secured using cryptographic and safety code mechanisms and on the possibilities of modelling safety-related industrial communication system, where a high safety integrity level SIL3 is required to be guaranteed. The paper features mathematical procedures to calculate the rate of hazardous transmission failure of safety-related messages in the result of electromagnetic interference (EMI) effects in the communication channel and by the presence of random hardware failures of SRComS. The theoretical techniques and safety analyses emerge from risk analysis and are compared with the knowledge gained by the authors during safety verifications of such systems for transportation applications. It is a little explored area, because the standards concerning safety-related control systems (SRCSs) did not support any cryptography-based methods. A quantitative safety integrity analysis of SRComS is based on utilisation of Markov's processes. The proposed Markov's model is applied on an open transmission system built on the IEEE 802.11g standard, which is complemented by cryptographic and safety code. The calculations are performed using Mathematica software tool. The proposed base model is universal and can be modified (simplified) in dependence on the parameters of a specific SRComS.

Safety programmable logic controller (S-PLC) is primarily being utilised to perform safety functions of safety-related control systems (SRCS) on the process level. The SRCS also consists of sensors output circuits (including actuators), which can take part on execution of the individual safety functions. In this case the detection of their failures and an early reaction on the detected failure can be an unavoidable mean to achieve the required safety integrity level (SIL) of the performed safety function. In SRCS with S-PLC the failure detection of sensors and output circuits has to be implemented in the application program while considering some specific properties of S-PLC. The paper deals with the new problem of some relations between S-PLC parameters, diagnostics options and mathematical expression of safety integrity of a SRCS with S-PLC. In the practical part implementation of application diagnostics in S-PLC is mentioned and results of diagnostics parameters influence on safety integrity of SRCS for selected example connected to practical applying are introduced.

This keynote paper creates the framework for the 2nd EAI International Conference on Mobility in the Internet of Things (IoT). The IoT offers advanced connectivity of devices, systems, and services that goes beyond machine-to-machine communications and covers a variety of domains and applications. The interconnection of embedded devices is expected in many fields including Mobility and Intelligent Transport. In the light of the latest knowledge and scientific projects findings the authors present actual R&D trends in the given field. New ideas, cutting-edge innovations and technologies for mobility agenda are needed together with a multidisciplinary perspective approach. The paper indicates most common recent aspects for future development of the IoT applications for support of Mobility and Intelligent Transport. Research and innovations projects including ERA Chair project in ITS at the University of Žilina are presented as examples of solutions for IoT applications for benefits of citizens (motorized and non-motorized public).

Intelligent transportation systems (ITS) bring advanced applications that provide innovative services for various transportation modes in the area of traffic control, and enable better awareness for different users. Communication connections between intelligent vehicles with the use of wireless communication standards, so called Vehicular Ad Hoc Networks (VANETs), require ensuring verification of validity of provided services as well as services related to transmission confidentiality and integrity. The goal of this paper is to analyze secure mechanisms utilised in VANET communication within Cooperative Intelligent Transportation Systems (C-ITS) with a focus on safety critical applications. The practical part of the contribution is dedicated to modelling of security properties of VANET networks via OPNET Modeler tool extended by the implementation of the OpenSSL library for authentication protocol realisation based on digital signature schemes. The designed models simulate a transmission of authorised alert messages in Car-to-Car communication for several traffic scenarios with recommended Elliptic Curve Integrated Encryption Scheme (ECIES). The obtained results of the throughput and delay in the simulated network are compared for secured and no-secured communications in dependence on the selected digital signature schemes and the number of mobile nodes. The OpenSSL library has also been utilised for the comparison of time demandingness of digital signature schemes based on RSA (Rivest Shamir Adleman), DSA (Digital Signature Algorithm) and ECDSA (Elliptic Curve Digital Signature Algorithm) for different key-lengths suitable for real time VANET communications for safety-critical applications of C-ITS.