Alexander Gurko

Bio: Alexander Gurko is an academic researcher from Kharkiv National Automobile and Highway University. The author has contributed to research in topics: Machine vision & Laser scanning. The author has an hindex of 7, co-authored 19 publications receiving 235 citations.

Machine vision system for UAV navigation

Abstract: Unmanned Aerial Vehicle (UAV) navigation requires Machine Vision Systems to determine physical values of near distanced objects. These machine vision systems must respond in sufficiently amount of time using less scanning data from the observed objects. A novel Technical Vision System (TVS), which uses DC motors and laser triangulation to determine spatial coordinates of these objects, is offered and used for UAV navigation. Present paper thereby shows the implementation of open-loop control algorithm, to position the TVS laser ray in the UAV Field of View (FOV). Issues of this implementation, experimental realization and results are presented, as the theoretical concept of a continuous FOV derived.

Resolution improvement of accelerometers measurement for drones in agricultural applications

Abstract: In agricultural tasks, monitoring of large fields is required. In the last years automatic/autonomous monitoring has been researched; where unmanned aerial vehicles (UAV)—commonly known as drones—are used. For these systems, constrains related with autonomy during flight arise. In order to control properly the UAVs during flight, they require to measure physical variables, in a fast and accurate way. Also, the weight of instruments must be reduced for improving autonomy. In general, aerial vehicles obtain parameters like position, velocity and acceleration using inertial navigation systems. Regarding to this concern, in this work application of a novel technique for measurements onboard UAVs—particularly inertial measurement unit or IMU—is proposed. There are accelerometers inside the IMU. These accelerometers have a frequency domain output. The speed and position are calculated by the INS from acceleration. The acceleration is obtained from frequency measurements of the accelerometers output. For this reason an accurate and fast frequency measurement method is required. In this work, for this particular application, frequency measurement using principle of rational approximations is proposed. This technique allows to measure frequency in short time and with high accuracy, using a few electronic components. Due this properties, it perfectly fits requirements for UAVs.

Unmanned Aerial Vehicles in Agriculture: A Review of Perspective of Platform, Control, and Applications

Abstract: For agricultural applications, regularized smart-farming solutions are being considered, including the use of unmanned aerial vehicles (UAVs). The UAVs combine information and communication technologies, robots, artificial intelligence, big data, and the Internet of Things. The agricultural UAVs are highly capable, and their use has expanded across all areas of agriculture, including pesticide and fertilizer spraying, seed sowing, and growth assessment and mapping. Accordingly, the market for agricultural UAVs is expected to continue growing with the related technologies. In this study, we consider the latest trends and applications of leading technologies related to agricultural UAVs, control technologies, equipment, and development. We discuss the use of UAVs in real agricultural environments. Furthermore, the future development of the agricultural UAVs and their challenges are presented.

A Two-Stage Augmented Extended Kalman Filter as an Observer for Sensorless Valve Control in Camless Internal Combustion Engines

Abstract: Camless internal combustion engines offer improvements over traditional engines in terms of improved torque performance and fuel economy, lower emissions, and pumping losses. Theoretically, their control flexibility provides electromagnetic valve actuators with the highest potential for improving efficiency. Sensorless control is one of the most important issues when implementing this new technology. The main contribution of this paper is a proposed observer comprising an augmented extended Kalman filter (EKF) and another EKF, which results in a sensorless control. The observer estimates the inductance of the actuator, which may vary. The proposed combination achieves a numerically efficient estimation. The proposed state observation structure avoids bulky and complicated measurement systems, which is an important advancement for real world applications. The introduced method is general and can be applied to problems in which it is not feasible or affordable to obtain position and velocity measurements. The current is measured, the position and the velocity of the electromagnetic valve are estimated with a robust method. The effectiveness of the proposed method is demonstrated using measured data acquired from an experimental setup based on an innovative electromagnetic valve actuator. A detailed comparative analysis of the arithmetic operations of the algorithm is also reported.

Computational Methods of Acquisition and Processing of 3D Point Cloud Data for Construction Applications

Abstract: 3D point cloud data from sensing technologies such as 3D laser scanning and photogrammetry are able to capture the 3D surface geometries of target objects in an accurate and efficient manner. Due to these advantages, the construction industry has been capturing 3D point cloud data of construction sites, construction works, and construction equipment to enable better decision making in construction project management. The captured point cloud data are utilized to reconstruct 3D building models, check construction quality, monitor construction progress, improve construction safety etc. throughout the project lifecycle from design to construction and facilities management phase. This paper aims to review the state-of-the-art methods to acquire and process 3D point cloud data for construction applications. The different approaches to 3D point cloud data acquisition are reviewed and compared including 3D laser scanning, photogrammetry, videogrammetry, RGB-D camera, and stereo camera. Furthermore, the processing methods of 3D point cloud data are reviewed according to the four common processing procedures including (1) data cleansing, (2) data registration, (3) data segmentation, and (4) object recognition. For each processing procedure, the different processing methods and algorithms are compared and discussed in detail, which provides a useful guidance to both researchers and industry practitioners for adopting point cloud data in the construction industry.

Robustness Analysis and Controller Synthesis of Homogeneous Vehicular Platoons With Bounded Parameter Uncertainty

Abstract: The platooning of automated vehicles can significantly benefit road transportation in terms of traffic capacity, fuel efficiency, etc. This paper presents a robust distributed control method for vehicular platoons with bounded parameter uncertainty and a broad spectrum of interaction topologies. The nonlinear node dynamics are reduced to an uncertain linear model by using inverse model compensation. The interaction topology is modeled as a directed graph, leading to high-dimensional linear platoon dynamics with parameter uncertainties existing in both state matrix and input matrix. For the topologies with real and/or complex eigenvalues, a sufficient condition for robust stability is derived through the similarity transformation and Lyapunov stability theory, whose benefit lies in the fact that this condition is completely defined in real number field. A Riccati inequality-based robust controller synthesis algorithm is presented whose computation complexity is independent of platoon size. The proposed method is validated by a series of simulations with high-order nonlinear vehicle models.

Mobile robot vision system using continuous laser scanning for industrial application

Abstract: The purpose of this paper is the presentation and research of a novel robot vision system, which uses laser dynamic triangulation, to determine three-dimensional (3D) coordinates of an observed object. The previously used physical operation principle of discontinuous scanning method is substituted by continuous method. Thereby applications become possible that were previously limited by this discretization.,The previously used prototype No. 2, which uses stepping motors to realize a discontinuous laser scan, was substituted by the new developed prototype No. 3, which contains servomotors, to achieve a continuous laser scan. The new prototype possesses only half the width and turns out to be significantly smaller and therefore lighter than the old one. Furthermore, no transmissions are used, which reduce the systematic error of laser positioning and increase the system reliability.,By using a continuous laser scan method instead of discontinuous laser scan method, dead zones in the laser scanner field can be eliminated. Thereby, also by changing the physical operation principle, the implementation of applications is allowed, which previously was limited by the fixed step size or by the object distance under observation. By using servomotors instead of stepping motors, also a significant reduced positioning time can be accomplished maintaining the relative positioning error less than 1 per cent.,The originality is based on the substitution of the physical operation principle of discontinuous by continuous laser scan. The previously used stepping motors discretized the laser scanner field and thereby produced dead zones, where 3D coordinates cannot be detected. These stepping motors were substituted by servomotors to revoke these disadvantages and provide a continuous laser scan, where dead zones in the field of view get eliminated and the step response of the laser scanner accelerated.