In this study is proposed and evaluated an adaptive traffic signal control system designed to synchronize the road and railway signaling, minimize collision risks, and improve traffic flow. Results show that adaptive control reduced average queue length for over 46%, cut vehicle delay for 34%, lowered stop frequency for 74%, and decreased CO2 emissions for nearly 46% compared to static control. Further analysis examined the effect of varying the distance between intersections and railway crossings, revealing significant safety and efficiency gains when the separation exceeded 80 m. The findings demonstrate that intelligent, sensor driven traffic management can substantially enhance both safety and throughput in these complex transport nodes, while delivering environmental benefits.

Autonomous vehicles are widely used in many applications in both indoor and outdoor settings. In practical situations with limited global navigation satellite systems (GNSS) signals or degraded lighting conditions, the navigation solution may rely only on inertial sensors and, as a result, drift in time due to errors in the inertial measurement. In this work, we propose WiCHINS, a wheeled and chassis inertial navigation system by combining wheel-mounted inertial sensors with a chassis-mounted inertial sensor for accurate pure inertial navigation. To that end, we derive a three-stage framework, each with a dedicated extended Kalman filter (EKF). This framework utilizes the benefits of each location (wheel/body) during the estimation process. To evaluate our proposed approach, we employed a dataset with five inertial measurement units (IMUs) with a total recording time of 228.6. We compare our approach with four other inertial baselines and demonstrate an average position error of 11.4 m, which is 2.4% of the average traveled distance, using two wheels and one body IMUs. As a consequence, our proposed method enables robust navigation in challenging environments and helps bridge the pure-inertial performance gap.

This paper presents the implementation of ORB-SLAM3 for visual odometry on a low-power ARM-based system, specifically the Jetson Nano, to track a robot’s movement using RGB-D cameras. Key challenges addressed include the selection of compatible software libraries, camera calibration, and system optimization. The ORB-SLAM3 algorithm was adapted for the ARM architecture and tested using both the EuRoC dataset and real-world scenarios involving a mobile robot. The testing demonstrated that ORB-SLAM3 provides accurate localization, with errors in path estimation ranging from 3 to 11 cm when using the EuRoC dataset. Real-world tests on a mobile robot revealed discrepancies primarily due to encoder drift and environmental factors such as lighting and texture. The paper discusses strategies for mitigating these errors, including enhanced calibration and the potential use of encoder data for tracking when camera performance falters. Future improvements focus on refining the calibration process, adding trajectory correction mechanisms, and integrating visual odometry data more effectively into broader systems.

A wheel-mounted inertial sensor mitigates inertial drift more effectively than an inertial sensor mounted on the vehicle chassis. Although their usage is increasing, there is no publicly available dataset for wheel-mounted inertial sensors. To fill this gap, this work presents the wheel-mounted inertial (WMI) dataset. WMI was recorded using two platforms: an omni-directional robot equipped with 5 IMUs, and a passenger car equipped with 9 IMUs. Each platform features IMUs mounted on every wheel. In total 64.04 minutes of recordings for each IMU (490 minutes for all IMUs) were made with associated ground truth trajectory. This versatile dataset will help develop model-based and data-driven approaches with wheel mounted inertial sensors.

The cloud computing revolution has changed the concept of data management, where organizations no longer rely on traditional physical data centers but instead look for scalable, flexible, and cost-effective solutions. The paper describes the basic characteristics of cloud computing, its benefits, challenges, with particular attention to the aspect of security risks and strategies for mitigation. With the shared responsibility model, an organization and cloud provider work together to safeguard data and resources by implementing key measures like identity and access management, encryption, and monitoring. Security challenges include the protection of data, hypervisor vulnerabilities, and data leaks, put against emerging solutions such as Zero Trust architecture, which is designed to enhance risk management through principles such as minimal permissions and continuous monitoring. Performing a comparative analysis on AWS versus Microsoft Azure, two of the leading cloud providers, shows their respective strengths in global infrastructure and ecosystem integration. This enables organizations to carve out their cloud adoption needs. Practical implementations, including the hosting of static websites, demonstrate the application of cloud services in modern business environments through containerization. This research brings to the fore the importance of robust security strategies in the dynamically changing cloud landscape and provides a base for organizations to make informed decisions and improve their cybersecurity posture.

The paper discusses cybersecurity issues within the concept of Industry 4.0 as a whole and frequently references its implementation within the specific IoT system in the laboratories of the University of Zilina. The first part deals with an analysis of the aspects concerning study of cybersecurity in Industry 4.0, and more specifically, in IoT, OT and cloud technologies. The next section, in the framework of Industry 4.0, places forward a proposal to classify data in terms of their cybersecurity risks within the various component parts of the system of "Asset Management". In the practical section an IoT system used for educational purposes is designed, built with defined security measures, and then underwent stress testing to establish the efficiency of the built-in measures against cyber threats. The output is an IoT system with tested security features in the laboratory of the University of Žilina, which may be used for the education of students.

Global satellite navigation systems (GNSSs) are the most-used technology for the localization of vehicles in the outdoor environment, but in the case of a densely built-up area or during passage through a tunnel, the satellite signal is not available or has poor quality. Inertial navigation systems (INSs) allow localization dead reckoning, but they have an integration error that grows over time. Inexpensive inertial measurement units (IMUs) are subject to thermal-dependent error and must be calibrated almost continuously. This article proposes a novel method of online (continuous) calibration of inertial sensors with the aid of the data from the GNSS receiver during the vehicle’s route. We performed data fusion using an extended Kalman filter (EKF) and calibrated the input sensors through error backpropagation. The algorithm thus calibrates the INS sensors while the GNSS receiver signal is good, and after a GNSS failure, for example in tunnels, the position is predicted only by low-cost inertial sensors. Such an approach significantly improved the localization precision in comparison with offline calibrated inertial localization with the same sensors.

This paper presents a comprehensive exploration into the critical aspect of effector design within the context of mobile platforms utilised during emergency scenarios. In times of crisis, ranging from natural disasters to man-made incidents, the efficiency and versatility of mobile platforms equipped with specialised effectors play a pivotal role in ensuring effective response and mitigation. The proposed robotic system consists of a universal platform, a robotic arm, and a custom effector with controls. Our experimental verification of the system shows promising results and the feasibility of the proposed system.

Data acquisition is a critical aspect of modern vehicle and aircraft design, as it provides engineers and researchers with essential information on the performance and behaviour of these vehicles in various operating conditions.In this paper, we present a data acquisition unit (DAU) for road vehicle or aircraft that utilizes various sensors, including GNSS, INS, RPM measurement, barometric altimeter, and ESP32 microcontroller.The DAU consists of multiple sensors, including a GNSS receiver to determine the vehicle's position, speed, and heading.An inertial navigation system (INS) is used to measure the vehicle's acceleration and angular rate.RPM sensors are used to measure engine speed, and a barometric altimeter is used to measure the altitude of the vehicle.An ESP32 microcontroller is used to acquire, process, and store the data from these sensors.In the end the design and utilisation of DAU was success gaining data for research in field of road and air transport.

The article deals with sensor fusion and real-time calibration in a homogeneous inertial sensor array. The proposed method allows for both estimating the sensors' calibration constants (i.e., gain and bias) in real-time and automatically suppressing degraded sensors while keeping the overall precision of the estimation. The weight of the sensor is adaptively adjusted according to the RMSE concerning the weighted average of all sensors. The estimated angular velocity was compared with a reference (ground truth) value obtained using a tactical-grade fiber-optic gyroscope. We have experimented with low-cost MEMS gyroscopes, but the proposed method can be applied to basically any sensor array.

Microcontrollers are reaching into our lives from all sides and, over time, have replaced mechanically and electrically complex solutions, rendering them obsolete. They find their place in solutions ranging from the simplest handheld devices to advanced solutions for homes and professionals to highly demanding industry, science, and technology applications. They also have an indispensable place in automated control, from the most straightforward sensors, through actuators and actuators, to programmable logic controllers and control panels. Microcontrollers can be programmed using several familiar techniques. Assembler is suitable for handling the lowest registers, peripherals, and routines. For standard designs, the C language is used. For rapid prototyping, several solutions are available such as Micropython, Circuitpython, and similar. For this publication, Micropython has been chosen as an implementation of the higher-level Python language for selected microcontrollers. A problem with a PID controller was chosen as an example of rapid device prototyping. It is broadly used in industrial automation, and its control algorithm is one of the most used in industry. The purpose of the PID controller in this example is to control the output value according to the desired setpoint so that the system’s output is achieved as accurately as possible. When selecting the type of controller, it is necessary to determine the transfer function of the controlled system and take them into account.

GNSS spoofing is a technique used to deceive Global Navigation Satellite Systems (GNSS) receivers by broadcasting fake signals that appear to be genuine. To detect GNSS spoofing, a receiver can use various techniques such as monitoring signal strength, cross-checking data from multiple satellites, comparing the signal characteristics with the expected patterns, and analyzing the timing and location information. Advanced detection methods may use machine learning algorithms to identify anomalies and patterns in the signal data. In addition, the use of encrypted signals and multiple frequency bands can make spoofing more difficult, and the implementation of spoofing-resistant hardware and software can further enhance detection capabilities. In this article various techniques of manipulation and detection of spoofing and experiments are described. There is no 100% method for spoofing detection.

This paper discusses the safety of mobile robots and proposes improvements by specific methods of collision avoidance, and by changes of logical architecture or the communication protocol. The proposed architecture is semi-distributed, which allows optimalization of the load balance among components while supporting strict safety rules. Such approach allows development of small-size mobile intelligent robots using low-cost computational hardware.

The aim of this paper was to propose a design of a module that has several inertial sensors of the same type in order to test various approaches of homogeneous sensor fusion. According to the statistics the mean of readings from the same-type sensors should have higher precision than a single sensor. However, this statement is not always correct for real sensors, as identical sensors may not have the same error characteristics. Sensor manufacturers state the typical sensor RMS (root mean square) error, the actual sensor RMS error can differ significantly from piece to piece. When averaging a sensor output from the same manufacturer, we can under certain conditions, obtain a worse value than the output error of the best sensor. This error can be eliminated by fusing the sensors using weighing. To verify this statement, we decided to assemble with as many identical sensors as possible. The IMU (inertial measurement unit) sensor, which measures acceleration, angular acceleration, and magnetic field in three axes, was chosen as the sensor for the variety of measurements. Thanks to this, we can compare up to 9 different outputs at the same time. In the end, we designed a module that has 16 IMUs. As the number of sensors increases, the resulting error decreases on average. However, weighting based on calibration errors did not prove to be the optimal solution because the sensors contain not only stochastic but also systematic errors. The module designed by us will be used mainly for further scientific research in the field of IMU sensor fusion in order to reduce the error.

With the development of MEMS sensors, the magnetometer has increasingly become a part of various wearable devices. The magnetometer measures the intensity of the magnetic field in all three axes, resulting in a 3D vector-direction and power. Calibration must be done before using a magnetometer, especially in wearable electronics, due to the low quality of the sensor and high proximity to other electromagnetic emission sources. Several magnetometer calibration algorithms exist in the literature, with most of them requiring multi-sided rotation. However, such calibration is highly impractical when the sensor is mounted on larger objects, e.g., vehicles, which cannot easily be rotated. Vehicles contain a large amount of ferromagnetic soft and hard material that affects the measured magnetic field. A magnetometer can be useful for an INS system in a car as long as it does not drift over time. This article describes how to calibrate a magnetometer using the GNSS motion vector. The calibration is performed using data from the initial section of the vehicle's trajectory. The quality of the calibration is then validated using the remaining section of the trajectory, comparing the deviation between the azimuth obtained by GNSS and by the calibrated magnetometer. Based on the azimuth and speed of the vehicle, we predicted the position of the vehicle and plotted the prediction on the map. The experiment showed that such calibration is functional. The uncalibrated data were unusable due to the strong effect of ferromagnetic soft and hard materials in the vehicle.

The multiagent approach to modelling, traditionally dedicated for distributed systems, can be applied on any platform where there are more processes or control threads. The world of surface transport is a typical example of such a situation where high numbers of dynamic entities (agents) interacting with each other represent a complex problem to solve, analyse and visualise. The main focus of this paper is on functional description of the traffic control problem at the rail-road intersection. Unlike conventional approaches, this model assumes usage of modern (infrastructure-to-vehicle, vehicle-to-vehicle) communication technologies as an essential base of cooperative intelligent transportation systems. The authors use the development toolkit NetLogo, explaining step-by-step the key programming details, to get a comprehensive overview of the operation of the entire system through simple definitions of a number of simple cooperating agents. The introduced model is implementation free and shows newly offered functionalities on the principal level, while a minimum theory of collective intelligence hidden in the background is needed.

The paper presents algorithms of on-line methods of discrete parametric identification of pollutant concentrations in a tunnel tube and comparison of their properties. It describes the characteristics of an individual methods and a detailed evaluation in order to select the most suitable method for the identification of dynamical systems with a significant stochastic component and changing parameters. The aim of the paper is to propose discrete parametric identification methods for systems that have variable parameters. It is a choice of model structure and design of an algorithm that is able to monitor changes in system parameters. The article also describes ways to implement identification algorithms in PLC (Programmable Logic Controller) by programming the target device directly from the simulation environment MATLAB Simulink using the toolbox "B&R Automation Studio Target for Simulink". From a practical point of view, these algorithms serve to create an apparatus for optimizing the ventilation control in the tunnel and thus ensure the safe passage of vehicles through the tunnel.

This paper describes the development of a Data Acquisition Unit (DAU). The device is primarily designed for light aircraft; however, it allows data collection from road vehicles (equipped with Bluetooth module to measure the engine and vehicle data from onboard diagnostics interface). The primary purpose of DAU is the Internet of Things (IoT) based tracking of aircraft operated by the Air Training and Educational Centre (LVVC) of the University of Žilina. If some flight parameters exceed the given limitations, the data file is marked as a non-compliance flight record. LVVC utilises this to get the information if unauthorised manoeuvres with the aeroplane were performed. The device is also used as a real-time tracker and anti-collision system. Several test flights were performed to proof of concept. The acquired data will also be used for analysing localisation algorithms at the Department of control and information systems of the University of Žilina and is the predecessor of the proposed APVV project.

This work deals with the construction of an electric vehicle. This vehicle is designed to transport one person for shorter distances in urban areas. The main control member is a microcontroller from Atmel corporation. The aim was to construct vehicle in the best possible ratio of price and quality. The device consists of a mechanical part, a drive part and a control part. The whole vehicle is powered by a battery. A PID controller is used to balance the vehicle.

This paper examines the purpose of light-sport aircraft (LSA) tracking using our proposed electronic on board unit. LSA are attracting an increasing interest due to their affordability and technological advancement. Increasing the volume of this traffic, however, can lead to dangerous situations, such as mid-air collisions. Previous studies indicate that despite the commonly used concept "see and avoid", there are dozens of collisions in general aviation every year. The paper presents innovative methods of tracking the position of light aircraft. It is mainly focused on the well-known technology FLARM – the traffic awareness and collision avoidance system for gliders, LSA, and UAVs. The main goal is to design and build an on board FLARM compatible device that will transmit aircraft position, which can be observed on an online map in real-time. The major drawback of this approach is the need for ground infrastructure such as receivers which have limited coverage and must be constantly online. The advantage of the proposed device is the implementation of a system for logging flight parameters on an SD card. The distinguishing feature of the OBU is the ripple from the 28V mains, which can be used to diagnose the aircraft’s electrical system. In order to identify the overall functionality and capabilities of the device, preliminary flight tests were performed. The overall results and limitations are summarized in the discussion. The OBU is designed and tailored mostly for declared training organizations and aeroplane rentals.