With the emerging interest in the autonomous driving level at 4 and 5 comes a necessity to provide accurate and versatile frameworks to evaluate the algorithms used in autonomous vehicles. There is a clear gap in the field of autonomous driving simulators. It covers testing and parameter tuning of a key component of autonomous driving systems, SLAM, frameworks targeting off-road and safety-critical environments. It also includes taking into consideration the non-idealistic nature of the real-life sensors, associated phenomena and measurement errors. We created a LiDAR simulator that delivers accurate 3D point clouds in real time. The point clouds are generated based on the sensor placement and the LiDAR type that can be set using configurable parameters. We evaluate our solution based on comparison of the results using an actual device, Velodyne VLP-16, on real-life tracks and the corresponding simulations. We measure the error values obtained using Google Cartographer SLAM algorithm and the distance between the simulated and real point clouds to verify their accuracy. The results show that our simulation (which incorporates measurement errors and the rolling shutter effect) produces data that can successfully imitate the real-life point clouds. Due to dedicated mechanisms, it is compatible with the Robotic Operating System (ROS) and can be used interchangeably with data from actual sensors, which enables easy testing, SLAM algorithm parameter tuning and deployment.

This article presents a new approach to collision avoidance in drone swarms, designed for operations in large drone swarms and dynamic environments. The mechanism uses distributed communication, where drones share information about their positions and planned trajectories to predict and avoid collisions. The proposed mechanism enables drones to autonomously cooperate and maintain safe distances in complex scenarios. It is based on the concept of repulsion vectors. The avoidance response is determined by the level of immersion in the protective sphere of obstacles, including other drones. The advantage of the algorithm lies in its simplicity and low computational complexity, allowing it to be used even in small and inexpensive drones. The algorithm was tested in a developed simulation environment, created to handle swarms of over 20 drones and to demonstrate the scalability of the proposed solution. Two scenarios were analyzed: (i) two swarms, each with nine drones, flying on a collision course; (ii) a swarm of 25 drones changing formation. The results showed that the mechanism is effective in avoiding collisions, maintaining safe distances and adapting to changing conditions. The proposed mechanism represents a significant advancement in swarm coordination, offering a robust and scalable solution for real-world applications.

Introduction. Healthcare-associated infections (HAIs) are a serious problem of modern medicine. Patients hospitalized in intensive care units (ICUs) develop HAI significantly more often than patients in other hospital units. Materials and Methods. Analysis involved HAIs from three ICUs in southern Poland. The study was conducted in 2016–2019 on the basis of methodology recommended by the Healthcare-Associated Infections Surveillance Network (HAI-Net) and European Centre for Disease Prevention and Control (ECDC). The objective was to analyse HAIs, their clinical forms, and microbiological agents. Results. The study included 3028 patients hospitalized for 26,558 person-days (pds) in ICU. A total of 540 HAIs were detected; incidence per 100 hospitalizations was 17.8%, incidence density per 1000 pds was 20.3. The mortality of patients with HAI was 16%, and in Clostridioidesdifficile infection (CDI), the mortality was 28%. The most common clinical form of HAI was bloodstream infection (BSI): 209 cases (incidence rate 6.9%), followed by pneumonia (PN): 131 (incidence rate 4.3%), and urinary tract infection (UTI): 110 cases (incidence rate 3.6%). The most frequently isolated bacteria were Klebsiella pneumoniae 16.4%, Acinetobacter baumannii 14.4%, Staphylococcus aureus 11.8%, and Escherichia coli 11.4%. Conclusions. A two-fold higher incidence rate of BSI was detected compared to the average incidence in European countries. BSI of unknown source (BSI-UNK) was predominant. K. pneumoniae and A. baumannii bacteria were the most often isolated microorganisms causing HAI. Infection control based on incidence rate for each type of infection is necessary in ICU to assess the epidemiological situation.

In the swiftly advancing field of swarm robotics and unmanned aerial vehicles, precise and effective testing methods are essential. This article explores the crucial role of software-in-the-loop (SITL) simulations in developing, testing, and validating drone swarm control algorithms. Such simulations play a crucial role in reproducing real-world operational scenarios. Additionally, they can (regardless of the type of application) accelerate the development process, reduce operational risks, and ensure the consistent performance of drone swarms. Our study demonstrates that different geometrical arrangements of drone swarms require flexible control strategies. The leader-based control model facilitates coherent movement and enhanced coordination. Addressing various issues such as communication delays and inaccuracies in positioning is essential here. These shortcomings underscore the value of improved approaches to collision avoidance. The research described in this article focused on the dynamics of drone swarms in a simulated context and emphasized their operational efficiency and adaptability in various scenarios. Advanced simulation tools were utilized to analyze the interaction, communication, and adaptability of autonomous units. The presented results indicate that the arrangement of drones significantly affects their coordination and collision avoidance capabilities. They also underscore the importance of control systems that can adapt to various situations. The impact of communication delays and errors in positioning systems on the required distance between drones in a grid structure is also presented. This article assesses the impact of different levels of GPS accuracy and communication delays on the coordination of group movement and collision avoidance capabilities.

In this paper the performance of a fractional order PI controller is compared with that of RED, a well-known active queue management (AQM) mechanism. The article uses fluid flow approximation and discrete-event simulation to investigate the influence of the AQM policy on the packet loss probability, the queue length and its variability. The impact of self-similar traffic is also considered.

The paper examines the AQM mechanism based on neural networks. The active queue management allows packets to be dropped from the router’s queue before the buffer is full. The aim of the work is to use machine learning to create a model that copies the behavior of the AQM $P{I}^{\alpha }$ mechanism. We create training samples taking into account the self-similarity of network traffic. The model uses fractional Gaussian noise as a source. The quantitative analysis is based on simulation. During the tests, we analyzed the length of the queue, the number of rejected packets and waiting times in the queues. The proposed mechanism shows the usefulness of the Active Queue Management mechanism based on Neural Networks.