On-board Computer System Research Articles

Real-Time Deep Learning Framework for Accurate Speed Estimation of Surrounding Vehicles in Autonomous Driving

Accurate speed estimation of surrounding vehicles is of paramount importance for autonomous driving to prevent potential hazards. This paper emphasizes the critical role of precise speed estimation and presents a novel real-time framework based on deep learning to achieve this from images captured by an onboard camera. The system detects and tracks vehicles using convolutional neural networks and analyzes their trajectories with a tracking algorithm. Vehicle speeds are then accurately estimated using a regression model based on random sample consensus. A synthetic dataset using the CARLA simulator has been generated to validate the presented methodology. The system can simultaneously estimate the speed of multiple vehicles and can be easily integrated into onboard computer systems, providing a cost-effective solution for real-time speed estimation. This technology holds significant potential for enhancing vehicle safety systems, driver assistance, and autonomous driving.

Comparative analysis of single-board computers for the development of a microarchitectural computing system for fire detection

Objectives. The purpose of the work is to select the basic computing microplatform of the onboard microarchitectural computing complex for the detection of anomalous situations in the territory of the Republic of Belarus from space on the basis of artificial intelligence methods.Methods. The method of comparative analysis is used to select a computing platform. A series of performance tests and comparative analysis (benchmarking) are performed on the selected equipment. The methods of comparative and benchmarking analysis are performed in accordance with the terms of reference to the current project.Results. A comparative analysis and performance testing of Raspberry Pi 4 Model B and Cool Pi 4 Model B single-board computers, as well as AI-accelerator Google Coral USB Accelerator with Google Edge TPU have been performed. The comparative analysis showed that Raspberry Pi 4 Model B and Cool Pi 4 Model B fully meet the terms of reference to the current project. At the same time Cool Pi 4 Model B handles neural network calculations well, but four times slower than similar calculations on Google Coral USB Accelerator. Neural network computations on the Raspberry Pi 4 Model B are 22 times slower than similar computations on the Google Coral USB Accelerator. Cool Pi 4 Model B outperforms Raspberry Pi 4 Model B by the factor of two to three for data copying and compression and almost six times faster for neural network computations.Conclusion. Despite the fact that Raspberry Pi 4 Model B meets the terms of reference to the project as a computational basis, when developing an on-board microarchitectural computing system for detecting anomalous situations, it is worth using more powerful alternatives with built-in AI-accelerators (e.g., Radxa Rock 5 Model A) or with an additional external AI-accelerator (e.g., a combination of Cool Pi 4 Model B and Google Coral USB Accelerator). Using a Raspberry Pi 4 Model B with an additional AI-accelerator is also acceptable and will speed up computations by several dozen times. AI-accelerators provide the fastest neural network computations, but there are features related to the novelty of the technology that will be explored in further development.

Solution of the local boundary problem for nonlinear stationary system with account of the computer systems verification

In the article an algorithm of construction of the control function that garantees the translation of nonlinear stationary system of the ordinary differential equations from initial state to origin of the coordinate system with account of the possibility of the onboard computer systems verification is suggested. A constructive sufficient conditions that garafntee an existence of the problem solution are found. An efficiency of the algorithm is shown by numerical modelling of the specific practical problem.

A Novel Efficient Dual-Gate Mixed Dilated Convolution Network for Multi-Scale Pedestrian Detection

With the increasing use of onboard high-speed computing systems, vehicle manufacturers are offering significant advanced features of driver assistance systems. Pedestrian detection is one of the major requirements of such systems, which commonly use cameras, radar, and ultrasonic sensors. Image recognition based on captured image streams is one of the powerful tools used for the detection of pedestrians, which exhibits similarities and distinguishing features compared to general object detection. Although pedestrian detection has advanced significantly along with deep learning, some issues still need to be addressed. Pedestrian detection is essential for several real-world applications and is an initial step in outdoor scene analysis. Typically, in a crowded situation, conventional detectors are unable to distinguish persons from each other successfully. This study presents a novel technique, based on the Dual Gate Mixed Dilated Convolution Network, to address this problem by adaptively filtering spatial areas where the patterns are still complicated and require further processing. The proposed technique manages obscured patterns while offering improved multiscale pedestrian recognition accuracy.

Detection of dangerously approaching vehicles over onboard cameras by speed estimation from apparent size

Autonomous driving requires information such as the velocity of other vehicles to prevent potential hazards. This work proposes a real-time deep learning-based framework to estimate vehicle speeds from image captures through an onboard camera. Vehicles are detected and tracked by the proposed deep neural networks and a tracking algorithm, which analyzes the trajectories. Finally, a linear regression model estimates the speed of a vehicle based on its position and size in the camera frame. This proposal has been tested with two sequences of the Prevention dataset with satisfactory results. The system can estimate the speed of multiple vehicles simultaneously. It can be integrated easily with onboard computer systems, thus allowing to development of a low-cost solution for speed estimation in an everyday vehicle. The potential applications include vehicle safety systems, driver assistance, and autonomous driving technologies.

A double-layer fault diagnosis strategy for electric vehicle batteries based on Gaussian mixture model

Battery fault diagnosis is essential to ensure the safe operation of electric vehicles (EVs). In this paper, due to the complexity of EVs’ battery thermal runaway tracing investigation and the limited capacity of on-board computing system, a double-layer fault diagnosis strategy for abnormal cells is proposed. The method bases on probability distribution, which can accurately trace a faulty cell and avoid misinterpreting a normal cell. In this method, unified statistical features are extracted from the big data during vehicle charging, and the corresponding statistical values are analyzed based on Gaussian mixture model and abnormal alarm is made based on the risk accumulation in double-layer diagnostics. The electric vehicles with thermal runaway accident are taken as examples to verify the method, and based on the data of normal-running vehicles, the false alarm tests are carried out. The verification results show that the proposed method can not only successfully identify the outlier cells, but also not generate false alarm, which is conducive to the practical application of fault diagnosis in the on-board battery management system.

THE TERM COMBINATION AND THE METAPHOR IN THE OFFICIAL BUSINESS DOCUMENT: COGNITIVE ASPECT

THE TERM COMBINATION AND THE METAPHOR IN THE OFFICIAL BUSINESS DOCUMENT: COGNITIVE ASPECT

Планирование заданий в бортовой вычислительной системе

The problem of rational resource allocation in the on-board computing system of a robotic complex is considered. As a first step, the possibility of using online scheduling algorithms without preemptive for distributed systems, the Round Robin cyclic algorithm, is analyzed. To demonstrate the basic capabilities of the developed scheduler, a video stream segmentation task is used. The peculiarities of task processing for real-time vision systems are demonstrated. The problem of inter-node synchronization of sensor data is solved. A feature of on-board robotics resources, such as the need for a linking software in the form of Robot Operation System, is taken into account. To develop the task scheduler, the C++ programming language and the ROS2 framework, which provides asynchronous networking, are used. A scheduling model and software implementing this model are being built to perform tasks in a distributed environment in order to control the processing of video streams in a vision system.

Efficient MCC Self Driven Car Using Dynamic Priority Based Resource Allocation Algorithm

Abstract: Smart vehicles are equipped with a variety of sensing devices that provide a variety of multimedia applications and services related to smart driving assistance, weather forecasting, traffic congestion information, road safety alarms, and a variety of entertainment and comfort-related applications in an intelligent transportation system. Due to their limited computational capacity and storage capabilities, these smart cars generate a tremendous volume of multimedia-related data that requires quick and real-time processing, which can't be completely handled by independent on-board computer systems. As a result, changing the underpinning networking and computing architectures was required to handle such multimedia applications and services

Use of Harvester Data to Estimate the Amount of Merchantable Non-Utilized Woody Material Remaining after Mechanized Cut-to-Length Forest Operations

An agreement between the provincial government of Québec, Canada and the forest industry executing forest management activities on public lands has been established regarding non-utilized woody material (NUWM) left on the cutting area. Problems linked to this agreement are compounded by labor shortages, which have an impact on the precision of the mandatory inventories. The objectives of this study were to: (1) reconstruct and estimate the merchantable NUWM volume beyond the last processed log of balsam fir and white spruce with the use of harvester on-board computer (OBC) data, (2) design a software tool to estimate and spatialize merchantable NUWM, and (3) perform an explorative comparison between the OBC method and conventional field inventory. In total, five sites were harvested to develop the volume algorithms. Each site was harvested by a single-grip harvester operating a different OBC system (OPTI4G, Log Mate 500, and Log Mate 510). Results suggest that, with Varjo’s model and linear regression, estimation of NUWM volume using OBC data is possible. The spatialization tool positioned NUWM within the harvest area for StanForD and StanForD 2010. The explorative comparison highlighted a possible cost reduction of approx. 36.8 $/ha and an increase of precision for the OBC method.

ВЫЧИСЛИТЕЛЬНЫЕ МОДУЛИ COM-EXPRESS НА БАЗЕ МИКРОПРОЦЕССОРОВ ЭЛЬБРУС ДЛЯ БОРТОВЫХ ВЫЧИСЛИТЕЛЬНЫХ КОМПЛЕКСОВ

Research in the field of creating specialized computing systems for robots is conducted inmany world scientific centers, including our country. The development of capabilities of sensorsystems, global navigation systems, growth of computing power and improvement of algorithmsallow creating onboard computing systems with broad intellectual capabilities. An important, butunsolved problem remains the equipping of such computing systems with domestically producedmicroprocessors. The need to take into account the maximum weight and size characteristics, therequirements for the cooling system of the computing complex, the requirements for on-boardpower supply and power consumption, performance requirements and external interfaces causethe complexity and high cost of developing on-board computing systems. The lack of unification ofcomputing modules during development creates additional difficulties for developers of robots,increases the final cost of the robot and complicates its modernization. The use of a standardizedform factor such as COM-Express makes it possible to divide the onboard computing complex intoa universal high-tech system part and a carrier board. The microprocessor, peripheral interfacecontroller, RAM and hard disk are placed on the system module, which is produced in large quantitiesand can be replaced with a newer one when new generations of domestic computing equipmentappear. The carrier board, in turn, is easy to develop and cheap to manufacture, and accordingto its characteristics can be configured for a specific robotic complex. This article discussesCOM-Express modules based on domestic Elbrus microprocessors. Their applicability for thecreation of promising on-board computing systems is shown. The results obtained by the authorsindicate the prospects of import substitution in the field of robotics.

КОРРЕЛЯЦИОННЫЙ АЛГОРИТМ АВТОМАТИЧЕСКОГО ОБНАРУЖЕНИЯ И СОПРОВОЖДЕНИЯ С ОБУЧЕНИЕМ В РЕАЛЬНОМ ВРЕМЕНИ

In order to develop a stable algorithm for automatic detection and tracking of nondeterministicobjects with real-time learning for embedded computing systems with optoelectronicdevices, within the framework of this work, a study and analysis of the existing world scientific andtechnical experience in the field of automatic tracking algorithms for general purposes was carriedout. The article shows that the most stable modern automatic tracking algorithms are a systemthat makes a decision about the current position, size and other parameters of the trackedimage based on the model being trained. The authors of the study identified the most effective ofthe applied basic algorithms suitable for use in embedded computing systems of robotic complexes,and developed a new algorithm for automatic detection and maintenance of non-deterministicobjects. A semi-natural testing of the developed algorithm was carried out and its effectivenesswas evaluated in solving problems not only of automatic tracking of objects, but also problems ofautomatic detection of objects using several reference images. In conclusion, proposals are presentedfor further improving the accuracy of the developed algorithm and for its optimization andimplementation in the special software of on-board computer systems of aircraft.

Lightweight Challenge-Response Authentication in SDN-Based UAVs Using Elliptic Curve Cryptography

Unmanned aerial vehicles (UAVs) (also known as drones) are aircraft that do not require the presence of a human pilot to fly. UAVs can be controlled remotely by a human operator or autonomously by onboard computer systems. UAVs have many military uses, including battlefield surveillance, effective target tracking and engagement in air-to-ground warfare, and situational awareness in challenging circumstances. They also offer a distinct advantage in various applications such as forest fire monitoring and surveillance. Surveillance systems are developed using advanced technologies in the modern era of communications and networks. As a result, UAVs require enhancements to control and manage systems efficiently. Network security is a critical concern with respect to UAVs due to the risk of surveillance information theft and physical misuse. Although several new tools have been introduced to secure networks, attackers can use more advanced methods to get into a UAV network and create problems that pose an organizational threat to the entire system. Security mechanisms also reduce the performance of systems because some restrictive measures prevent users from accessing specific resources, but a few techniques and tools have overcome the problem of performance reduction in various scenarios. There are many types of attacks, i.e., denial of service attacks (DOS), distributed denial of service attacks (DDOS), address resolution protocol (ARP) spoofing, sniffing, etc., that make it challenging to maintain a UAV network. This research paper proposes a lightweight challenge-response authentication that can overcome the previously mentioned problems. As security is provided by utilizing a minimum number of bits in memory, this technique offers the same security features while using fewer network resources, low computing resources, and low power consumption.

Magnetometer Calibration and Missile Attitude Filtering Method Based on Energy Estimation

Estimating the flying attitude of the missile body during flight is vitally important for the intelligent ammunition. The earlier and more accurate the posture information is obtained, the more conducive it is to the control process of the intelligent ammunition. The magnetometer is commonly used to measure the roll attitude of the missile. However, the cumbersome calibration steps and noise interference of the missile usually cause the delay in the attitude calculation and inaccurate measurement. To solve these issues, an adaptive reconfigurable unscented Kalman filter (ARUKF) method based on energy estimation is proposed. The magnetic field measured by the magnetometer is analyzed in real time based on the roll characteristic of the intelligent ammunition to achieve the initial calibration of the magnetometer parameters. With the obtained calibrated parameters, the filter state variables are estimated by establishing the residual estimation function in the UKF, which guides the reconstruction of the UKF to minimize the computational cost of the attitude estimation process. Simultaneously, the on-board computer system feeds back the action of the rudder system in real time to guide the configuration of the noise parameters in the UKF process, which can effectively reduce the interference of the magnetic field generated by the rudder system on the attitude estimation. The numerical simulation and experiments show that the proposed method performs better in terms of parameter convergence speed and estimation accuracy, compared with the traditional UKF method, which has great application prospect in the field of intelligent ammunition.

Electromagnetic uncoordinated control of a ChipSats swarm using magnetorquers

A swarm of ChipSats equipped with miniature magnetorquers is considered, the electromagnetic interaction force is used for relative motion control at extremely short relative distances up to several centimetres. A ChipSat is a satellite printed on 3.5 × 3.5 cm circuit board with a set of sensors, solar panels, onboard computer, and communication system. Assuming the relative motion between each satellite is known, a Lyapunov-based control algorithm is proposed to achieve bounded relative trajectories. A centralized and a decentralized control approaches are implemented. For the centralized approach, a CubeSat is considered as the main satellite after swarm deployment, producing a high value magnetic dipole moment which interacts with the magnetic dipole of the surrounding ChipSats in order to stop relative drift. For the decentralized approach, the ChipSats are linked in interchangeable pairs in order to apply the electromagnetic control force and reduce the relative drift between the satellites to the vicinity of zero. Two different pairing selection methods are proposed in the paper, based on the closest satellite and on the satellite with highest relative drift. Both translational and rotational motion of satellites are considered. The magnetic dipole moments are used for angular velocity damping when orbit control is not required, and a repulsive collision avoidance electromagnetic control is applied when two ChipSats are within dangerously close proximity to each other. The proposed control schemes performance is studied numerically with different algorithm and ChipSats parameters. The influence of these parameters on the swarm separation is obtained using Monte-Carlo simulations.

Optimization of a heterogeneous computing system architecture based on its coordination with a sensors group of a mobile unmanned platform

This article analyses the existing variety of sensors used in robotics and related fields and also proposes the architecture of a heterogeneous computing system designed to analyze data obtained from sensors of a mobile unmanned platform (MUP). A feature of unmanned platforms is the presence of tasks that require a significantly different level of performance of the on-board computing system for processing data from sensors of the corresponding type. Therefore, the adaptation of existing universal computing systems seems to be impractical, compared to the development of a specialized computing system with a heterogeneous architecture. The computing system is designed to solve problems of local navigation, stabilize the position of the MUP and control its movement, as well as control special equipment installed on the MUP. Often, if the goal is to ensure maximum efficiency, expressed in speed, accuracy and reliability, it is necessary to develop specialized devices. The article provides information on sensors of the main types used in robotics and indicates the requirements for the performance of a computing system necessary for processing data from sensors of this type. This, in turn, made it possible to propose a heterogeneous architecture containing processor subsystems focused on processing data from sensors requiring low, medium and high performance according to the considered classification.

Reliability of computer structures of integrated modular avionics for hardware configurations

The problem of designing advanced computing systems in the class of structures of integrated modular avionics is considered. The unified topology of the internal network of the computer on the basis of Space Wire exchange channels and variants of its execution for various onboard applications is offered. Equivalent reliability schemes of each of the specific structures are introduced and the probabilities of trouble-free operation of each structure are analyzed. Families of graphic dependencies are given. The analysis of the existing principles and algorithms for testing multiprocessor multimodal onboard digital computer systems is given; the new testing algorithm for the multiprocessor systems which follows the software design standards for products of integrated modular avionics is offered. The structure of the unified automated workplace for checking the functional modules of integrated modular avionics is considered. Specific requirements inherent in the workplaces for testing integrated avionics are identified: an increased level of control of the hardware component of products; the ability to simulate the failure state of individual components of avionics to check the mode of reconfiguration of the computer system; modular construction of software with the division of verification tests into components performed at the level of each CPM and the computer as a whole in single-task and multitasking modes; openness of architecture of a workplace, which provides an ability to change the level of control complexity of a product and control of one class of complexity; intra-project unification of both hardware and software of the workstation of the inspection.

Compact Optical Systems for Space Applications

Some optical schemes of lenses for spacecraft developed by the author are considered. The main optical characteristics of telescope lenses of various architectures are compared. We propose compact solutions of mirror, lens-mirror, and lens systems with maximum available angular resolutions and other parameters. Examples of calculating the optical systems of lenses used for various tasks both in the field of astronomy and in the field of remote sensing of the Earth and other planets are given. The example of onboard computer system is discussed. Practical recommendations on the development and use of telescope lenses are given.

ON ONE APPROACH TO SOLVING THE TRAVELING SALESMAN PROBLEM FOR AUTONOMOUS UNMANNED AERIAL VEHICLE PLANNING OF TARGET FLIGHT PATHS

Objective. Develop a principle of constructing tools and procedures for optimal routing of targets by an autonomous uncrewed aerial vehicle, which have an acceptable complexity for implementation on an onboard computer. Methods . The rules for optimizing the terrain map with the located targets, creating a penalty matrix that considers the disturbing factors of the unstable air environment in the planning process, and building a reference tree for finding the minimum route for the accepted cost of flying around the targets. Results . A principle is proposed to develop effective procedures for planning minimum cost-effective routes to fly around targets in an unstable air environment. The basis for behavior planning is the optimization of the formal description of a given terrain map, which leads to a significant reduction in the number of alternatives compared in the process of searching for a minimum route to fly around targets. This, in turn, makes it possible to implement planning procedures on the onboard computer system of an autonomous uncrewed aerial vehicle. A statement is proved to justify the existence of a minimum route for the accepted cost of overflying targets in the formal description of the terrain map obtained as a result of converting its original representation based on the developed optimization rules. Conclusion . The considered approach effectively solves various types of issues reduced to the traveling salesman problem, including planning the minimum route of flying around targets by an autonomous uncrewed aerial vehicle in an unstable air environment under uncertainty conditions.

ВЫСОКОПРОИЗВОДИТЕЛЬНЫЙ ИНФОРМАЦИОННО-УПРАВЛЯЮЩИЙ КОМПЛЕКС ДЛЯ ПЕРСПЕКТИВНОГО ВЫСОКОСКОРОСТНОГО ВЕРТОЛЕТА

Relevance Onboard computing systems (OCS) of modern aircraft (AC) have a system-oriented decentralized structural organization. The decentralized principle provides that the OCS is built in the form of a certain set of subsystems, between which the functional distribution of tasks is carried out. In this case, each of the specialized subsystems performs its functional task, exchanging, if necessary, information with other subsystems through the corresponding information transmission channels. However, as the functional tasks become more complex and their number increases, the decentralized principle of building on-board systems has largely exhausted its capabilities. First of all, this concerns such promising developments as the project to create a high-speed helicopter. The implementation of the concept of a promising high-speed helicopter requires the development of a high-performance on-board information and control complex capable of performing various functions in order to ensure high speed and long flight range, as well as the possibility of landing on unprepared sites. Aim of research The aim of research is to increase the performance of the on-board computer complex by forming an open architecture based on combining COST products, planning computing processes and choosing the optimal structural organization of the hardware. The objectives of the research project: 1. creation of a high-performance information and control complex based on open architectures and on the basis of integrated modular avionics; 2. using the optimization method of this complex to select the optimal possible solution to problems for a high-speed promising helicopter. Methods of research Method of generalized ranks is being worked out in detail. Ranking is made according to four criteria: total product volume, product weight, product availability, and product performance evaluation. Results The scientific novelty of this research project lies in solving problems associated with the formalization of procedures for the optimal configuration of the onboard information and control complex, based on the choice of methods for forming a set of acceptable options for onboard equipment that meet the modern concept of modular avionics, and the principles of heuristic optimization of the vector optimization base. The methods proposed in the work make it possible to improve the quality of the tasks assigned to high-speed helicopters by introducing a high-speed on-board information and control complex that meets the optimal requirements for performing the tactical and technical characteristics of a combat vehicle, which uses optimal COTS modules used on the basis of integral modular avionics. The introduction of the results of the research project into the development of promising high-speed helicopters will, according to estimates, increase the performance of the assigned tasks in front of the combat vehicle by 5–10 %.