Barbara Siemiątkowska

The field of ophthalmic surgery demands accurate identification of specialized surgical instruments. Manual recognition can be time-consuming and prone to errors. In recent years neural networks have emerged as promising techniques for automating the classification process. However, the deployment of these advanced algorithms requires the collection of large amounts of data and a painstaking process of tagging selected elements. This paper presents a novel investigation into the application of neural networks for the detection and classification of surgical instruments in ophthalmic surgery. The main focus of the research is the application of active learning techniques, in which the model is trained by selecting the most informative instances to expand the training set. Various active learning methods are compared, with a focus on their effectiveness in reducing the need for significant data annotation – a major concern in the field of surgery. The use of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to achieve high performance in the task of surgical tool detection is outlined. The combination of artificial intelligence (AI), machine learning, and Active Learning approaches, specifically in the field of ophthalmic surgery, opens new perspectives for improved diagnosis and surgical planning, ultimately leading to an improvement in patient safety and treatment outcomes.

This article introduces an algorithm for detecting glucose and silicon levels in solution. The research focuses on addressing the critical need for accurate and efficient glucose monitoring, particularly in the context of diabetic management. Understanding and monitoring silicon levels in the body is crucial due to its significant role in various physiological processes. Silicon, while often overshadowed by other minerals, plays a vital role in bone health, collagen formation, and connective tissue integrity. Moreover, recent research suggests its potential involvement in neurological health and the prevention of certain degenerative diseases. Investigating silicon levels becomes essential for a comprehensive understanding of its impact on overall health and well-being and paves the way for targeted interventions and personalized healthcare strategies. The approach presented in this paper is based on the integration of hyperspectral data and artificial intelligence techniques. The algorithm investigates the effectiveness of two distinct models utilizing SVMR and a perceptron independently. SVMR is employed to establish a robust regression model that maps input features to continuous glucose and silicon values. The study outlines the methodology, including feature selection, model training, and evaluation metrics. Experimental results demonstrate the algorithm’s effectiveness at accurately predicting glucose and silicon concentrations and showcases its potential for real-world application in continuous glucose and silicon monitoring systems.

The article presents a navigation system that utilizes a semantic map created on a hexagonal grid. The system plans the path by incorporating semantic and metric information while considering the vehicle’s dynamic constraints. The article concludes by discussing a low-level control algorithm used in the system. This solution’s advantages include using a semantic map on a hexagonal grid, which enables more efficient and accurate navigation. Creating a map of allowable speeds based on the semantic map provides an additional layer of information that can help optimize the vehicle’s trajectory. Incorporating both semantic and metric information in the path-planning process leads to a more precise and tailored navigation solution that accounts for the vehicle’s capabilities and the environment it is operating in. Finally, the low-level control algorithm ensures that the vehicle follows the planned trajectory while considering real-time sensor data and other factors affecting its movement. Through this article, we aim to provide insights into the cutting-edge advancements in path planning techniques and shed light on the potential of combining hexagonal grids, vehicle dynamics constraints, and semantic awareness. These innovations have the potential to revolutionize autonomous navigation systems, enabling vehicles to navigate complex environments with greater efficiency, safety, and adaptability.

The article presents the application of a hyperspectral camera in mobile robot navigation. Hyperspectral cameras are imaging systems that can capture a wide range of electromagnetic spectra. This feature allows them to detect a broader range of colors and features than traditional cameras and to perceive the environment more accurately. Several surface types, such as mud, can be challenging to detect using an RGB camera. In our system, the hyperspectral camera is used for ground recognition (e.g., grass, bumpy road, asphalt). Traditional global path planning methods take the shortest path length as the optimization objective. We propose an improved A* algorithm to generate the collision-free path. Semantic information makes it possible to plan a feasible and safe path in a complex off-road environment, taking traveling time as the optimization objective. We presented the results of the experiments for data collected in a natural environment. An important novelty of this paper is using a modified nearest neighbor method for hyperspectral data analysis and then using the data for path planning tasks in the same work. Using the nearest neighbor method allows us to adjust the robotic system much faster than using neural networks. As our system is continuously evolving, we intend to examine the performance of the vehicle on various road surfaces, which is why we sought to create a classification system that does not require a prolonged learning process. In our paper, we aimed to demonstrate that the incorporation of a hyperspectral camera can not only enhance route planning but also aid in the determination of parameters such as speed and acceleration.

This article presents an energy-efficient method of controlling unmanned aircraft (fixed-wing UAVs), which consists of three groups of algorithms: aerial vehicle route planning, in-flight control, and algorithms to correct the preplanned flight trajectory. All algorithms shall take into account the existence of obstacles that the UAV must avoid and wind gusts in the UAV’s area of operation. Tests were carried out on the basis of the UAV mathematical model, stabilization and navigation algorithms, and Dryden turbulence model, considering the parameters of the UAV’s propulsion system. The work includes a detailed description of constructing a network of connection that is used to plan a UAV mission. It presents the algorithm for determining the actual distances between the different points in the field of action, which takes into account the existence of obstacles. The algorithm shall be based on methods for determining the flight trajectory on a hexagonal grid. It presents the developed proprietary UAV path planning algorithm based on a model from a group of algorithms of mixed integer linear problem (MILP) optimization. It presents the manner in which the pre-prepared flight path was used by UAV controllers that supervised the flight along the preset path. It details the architecture of contemporary unmanned aerial vehicles, which have embedded capability to realize autonomous missions, which require the integration of UAV systems into the route planning algorithms set out in the article. Particular attention has been paid to the planning and implementation methods of UAV missions under conditions where wind gusts are present, which support the determination of UAV flight routes to minimize the vehicle’s energy consumption. The models developed were tested within a computer architecture based on ARM processors using the hardware-in-the-loop (HIL) technique, which is commonly used to control unmanned vehicles. The presented solution makes use of two computers: FCC (flight control computer) based on a real-time operating system (RTOS) and MC (mission computer) based on Linux and integrated with the Robot Operating System (ROS). A new contribution of this work is the integration of planning and monitoring methods for the implementation of missions aimed at minimizing energy consumption of the vehicle, taking into account wind conditions.

The article presents real-time object detection and classification methods by unmanned aerial vehicles (UAVs) equipped with a synthetic aperture radar (SAR). Two algorithms have been extensively tested: classic image analysis and convolutional neural networks (YOLOv5). The research resulted in a new method that combines YOLOv5 with post-processing using classic image analysis. It is shown that the new system improves both the classification accuracy and the location of the identified object. The algorithms were implemented and tested on a mobile platform installed on a military-class UAV as the primary unit for online image analysis. The usage of objective low-computational complexity detection algorithms on SAR scans can reduce the size of the scans sent to the ground control station.

The paper addresses the problem of mobile robots’ navigation using a hexagonal lattice. We carried out experiments in which we used a vehicle equipped with a set of sensors. Based on the data, a traversable map was created. The experimental results proved that hexagonal maps of an environment can be easily built based on sensor readings. The path planning method has many advantages: the situation in which obstacles surround the position of the robot or the target is easily detected, and we can influence the properties of the path, e.g., the distance from obstacles or the type of surface can be taken into account. A path can be smoothed more easily than with a rectangular grid.

Radar machine vision is an emerging research field in the mobile robotics. Because Synthetic ApertureRadars (SAR) are robust against weather and light condition, they provide more useful and reliable in formation than optical images. On the other hand, the data processing is more complicated and less researched than visible light images processing. The main goal of our reasarch is to build simple and efficient method of SAR image analysis. In this article we describe our research related to SAR image segmenta tion and attempts to detect elements such as the build ings, roads and forest areas. Tests were carried out for the images made available by Leonardo Airborne & Space System Company.

This article presents a framework for planning a drone swarm mission in a hostile environment. Elements of the planning framework are discussed in detail, including methods of planning routes for drone swarms using mixed integer linear programming (MILP) and methods of detecting potentially dangerous objects using EO/IR camera images and synthetic aperture radar (SAR). Methods of detecting objects in the field are used in the mission planning process to re-plan the swarm’s flight paths. The route planning model is discussed using the example of drone formations managed by one UAV that communicates through another UAV with the ground control station (GCS). This article presents practical examples of using algorithms for detecting dangerous objects for re-planning of swarm routes. A novelty in the work is the development of these algorithms in such a way that they can be implemented on mobile computers used by UAVs and integrated with MILP tasks. The methods of detection and classification of objects in real time by UAVs equipped with SAR and EO/IR are presented. Different sensors require different methods to detect objects. In the case of infrared or optoelectronic sensors, a convolutional neural network is used. For SAR images, a rule-based system is applied. The experimental results confirm that the stream of images can be analyzed in real-time.