Wyniki wyszukiwania - BazTech

1

Ensuring cyber resilience of ship information systems

Onishchenko O., Shumilova K., Volyanskyy S., Volyanskaya Y., Volianskyi Y.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2022

|

Vol. 16 No. 1

43--50

EN

The Covid-19 pandemic brought a problem related to the inability to timely update security systems on ships during a voyage and the need to encrypt data stored in ship information systems (SISs) and shipping company information systems. The analysis of new types of worldwide cyberattacks showed that they were set off by an increase in the use of remote-controlled autonomous technologies and a spread of telework. It was proved that on ships: a) there are no cybersecurity specialists; b) there is no means of identification of cyber threats and no response plans; c) there is a lack of cybersecurity training for crews; d) encryption of confidential ship data is barely used; e) crew is a vulnerability factor in ship's security. The analysis of cyber incidents allowed us to develop a basic response plan to protect ship control systems. It was demonstrated that the basic plan can be continuously updated and improved in accordance with: a) the real state of ship systems; b) the results of performance analysis of crew actions; c) the emergence of new types of cyberattacks. To improve the security of confidential data in ship information networks theoretical framework for the development of encrypted data search engines with the identification of “dangerous” keywords for the ship information systems (SISs) was proposed. A data exchange protocol, basic requirements for SISs, and an algorithm for detecting “dangerous” keywords in messages were developed. A test search engine on encrypted data was presented, and the main components of the system were highlighted. The functionality of the system was experimentally proved, and the accuracy and speed of search on encrypted data were determined.

2

Differentiable programming for the autonomous movement planning of a small vessel

Bahls C., Schubert A.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2021

|

Vol. 15 No. 3

493--499

EN

In this work we explore the use of differentiable programming to allow autonomous movement planning of a small vessel. We aim for an end to end architecture where the machine learning algorithm directly controls engine power and rudder movements of a simulated vessel to reach a defined goal. Differentiable programming is a novel machine learning paradigm, that allows to define a systems parameterized response to control commands in imperative computer code and to use automatic differentiation and analysis of the information flow from the controlling inputs and parameters to the resulting trajectory to compute derivatives to be used as search directions in an iterative algorithm to optimize a goal function. Initially the method does not know about any manoeuvring or the vessels response to control commands. The method autonomously learns the vessels behaviour from several simulation runs. Finally, we will show how the simulated vessel is able to fulfil some small missions, like crossing a flowing river while avoiding crossing traffic.

3

Mobile robots interacting with obstacles control based on artificial intelligence

Chuyen Tran Duc, Hoa Roan Van, Dien Nguyen Duc, Nguyen Tung Lam

Annals of Computer Science and Information Systems

|

2021

|

Vol. 27

13--16

EN

In this paper, research on the applications of artificial intelligence in implementing Deep Deterministic Policy Gradient (DDPG) on Gazebo model and the reality of mobile robot has been studied and applied. The goal of the experimental studies is to navigate the mobile robot to learn the best possible action to move in real-world environments when facing fixed and mobile obstacles. When the robot moves in an environment with obstacles, the robot will automatically control to avoid these obstacles. Then, the more time that can be maintained within a specific limit, the more rewards are accumulated and therefore better results will be achieved. The authors performed various tests with many transform parameters and proved that the DDPG algorithm is more efficient than algorithms like Q-learning, Machine learning, deep Q-network, etc. Then execute SLAM to recognize the robot positions, and virtual maps are precisely built and displayed in Rviz. The research results will be the basis for the design and construction of control algorithms for mobile robots and industrial robots applied in programming techniques and industrial factory automation control.

4

Teraźniejszość i przyszłość autonomicznej nawigacji

Woś G.

Prace Wydziału Nawigacyjnego Akademii Morskiej w Gdyni

|

2018

|

Z. 33

112--124

PL

Wraz z nieustannym postępem techniki automatyzacja obejmuje coraz więcej czynności wykonywanych do tej pory przez człowieka. Jej głównym celem jest ułatwienie naszego życia i pracy. W artykule przedstawiono aktualną sytuację oraz plany i projekty wprowadzenia szeroko pojętej automatyzacji na statkach handlowych oraz nowej ery nawigacji, którą zapoczątkują jednostki autonomiczne i bezzałogowe.

EN

Along with the continuous progress of technology, automation absorbs more and more activities performed so far by human. Its main purpose is to facilitate our life and work. The publication presents the current situation and projects for the introduction of broadly understood automation on commercial vessels and a new era of navigation, which will be initiated by unmanned and autonomous vessels.

5

Zakłócenia elektromagnetyczne w ochronie przed dronami

Witczak A., Czopik G., Gruca M.

Elektronika : konstrukcje, technologie, zastosowania

|

2016

|

Vol. 57, nr 7

19--22

PL

Rozwój technik Bezpilotowych Obiektów Latających jest zarówno elementem postępu cywilizacyjnego jak i zagrożeniem dla bezpieczeństwa ludzi. Stąd konieczne jest budowanie systemów, które pozwolą zabezpieczać miejsca lub rejony przed nieuprawnionym użyciem dronów. W artykule przedstawiono ideę oraz wybrane wyniki badań eksperymentalnych w zakresie stosowania zakłóceń mylących i blokujących układy zdalnego sterowania dronów.

EN

Development of Unmanned Aerial Vehicle is equal part of civilization progress as well as threats for people safety. That why it is necessary to build systems, which can protect places or areas against unentitled use of drones. In the article idea and some experimental results of the different jamming and spoofing interference signal use for block remote control of few types of drones system.

6

Interaction of Harsh Weather Operation and Collision Avoidance in Autonomous Navigation

Burmeister H.-C., Bruhn W. C., Walther L.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2015

|

Vol. 9, no. 1

31--40

EN

Taking into account the autonomous navigation system design and today’s state of the art navigation with regards to weather and collision avoidance this paper presents the architecture of the integrated approach, its links to existing rules and regulations and the test scenarios. These demonstrate how safe and efficient navigation of autonomous vessels can be achieved by showing the module's interaction and validating the feasibility of the approach. These analyses will be based on historical traffic data sets as well as simulation results.

7

Computationally inexpensive appearance based terrain learning in unknown environments

Mishra P., Viswanathan A.

Journal of Artificial Intelligence and Soft Computing Research

|

2013

|

Vol. 3, No. 3

201--213

EN

This paper describes a computationally inexpensive approach to learning and identification of maneuverable terrain to aid autonomous navigation. We adopt a monocular vision based framework, using a single consumer grade camera as the primary sensor, and model the terrain as a Mixture of Gaussians. Self-supervised learning is used to identify navigable terrain in the perception space. Training data is obtained using pre-filtered pixels, which correspond to near-range traversable terrain. The scheme allows for on-line, and in-motion update of the terrain model. The pipeline architecture used in the proposed algorithm is made amenable to real-time implementation by restricting computations to bit-shifts and accumulate operations. Color based clustering using dominant terrain texture is then performed in perception sub-space. Model initialization and update follows at the coarse scale of an octave image pyramid, and is back projected onto the original fine scale. We present results of terrain learning, tested in heterogeneous environments, including urban road, suburban parks, and indoors. Our scheme provides orders of magnitude improvement in time complexity, when compared to existing approaches reported in literature.

8

Reinforcement Learning in Discrete and Continuous Domains Applied to Ship Trajectory Generation

Rak A., Gierusz W.

Polish Maritime Research

|

2012

|

S 1

31-36

EN

This paper presents the application of the reinforcement learning algorithms to the task of autonomous determination of the ship trajectory during thein-harbour and harbour approaching manoeuvres. Authors used Markov decision processes formalism to build up the background of algorithm presentation. Two versions of RL algorithms were tested in the simulations: discrete (Q-learning) and continuous form (Least-Squares Policy Iteration). The results show that in both cases ship trajectory can be found. However discrete Q-learning algorithm suffered from many limitations (mainly curse of dimensionality) and practically is not applicable to the examined task. On the other hand, LSPI gave promising results. To be fully operational, proposed solution should be extended by taking into account ship heading and velocity and coupling with advanced multi-variable controller.

9

System nawigacji autonomicznych obiektów mobilnych z wykorzystaniem techniki RFID

Kalita W., Skoczylas M.

Elektronika : konstrukcje, technologie, zastosowania

|

2010

|

Vol. 51, nr 8

81-85

PL

W pracy przedstawiono koncepcję kompleksowego systemu nawigacji autonomicznych obiektów mobilnych. Umożliwiającej przemieszczanie się Ich w przestrzeni o zróżnicowanej strukturze geometryczno-materiałowej, w otoczeniu przeszkód statycznych i dynamicznych. Zasada działania i specyfika pracy systemu RFID umożliwia nie tylko wyznaczenie położenia obiektu mobilnego, ale również realizację procesów jego samolokalizacji oraz autonomiczności podczas ruchu Identyfikator RFID pełni tutaj role swego rodzaju sensora, dostarczając wszelkich informacji potrzebnych do działania systemu. Zaprezentowano, jako kontynuację rozważań, zawartych w pracach, przedstawionych w Nr 6/2010 Elektroniki, wybrane uwarunkowania telekomunikacyjne, mające wpływ na realizowalność i jakość procesów wyznaczania lokalizacji obiektu mobilnego, wykrywania przeszkód oraz planowania ruchu.

EN

In the paper, the concept of a comprehensive system of autonomous navigation of mobile objects has been presented. The system enables the objects surrounded by static and dynamic obstacles to move in space with diversified geometric and material structure. The principle of the RFID system operation and its nature makes possible to determine the location of mobile object and also to determine the location of mobile object and also to ensure the autonomy of movements. The RfiD tags play role of sensors providing all information that is necessary for the system operation. Some important telecommunication conditions and factors affecting the reliability and quality of the location processes, obstacles detection and traffic planning have been presented. The paper is a continuation of articles featured in issue 6/2010 Electronics Journal.

10

Koncepcja autonomicznego robota pola walki przeznaczonego do zadań zwiadu i wykrywania min

Jeżewski S., Sankowski D., Dadan W.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

2009

|

T. 13, z. 3/1

1107-1116

PL

W artykule przedstawiono ideę systemu operacyjnego dla autonomicznego robota pola walki przeznaczonego do zadań zwiadu i wykrywania min. Autorzy dokonali przeglądu konstrukcji militarnych robotów mobilnych czołowych firm w kraju i na świecie. Dokonując przeglądu, skupili się na obszarach zastosowań i zadaniach realizowanych przez roboty, by na tej podstawie zaprezentować ideę konkurencyjnego technicznie robota pola walki. Planowany zrobotyzowany system to 6-kołowa bezzałogowa, autonomiczna platforma jezdna wyposażona w system kamer światła widzialnego, systemy noktowizji biernej, mikrofony kierunkowe, czujniki optyczne, czujniki laserowe, czujniki ultradźwiękowe oraz rozbudowane mikroprocesorowe systemy analizy danych pozwalające na autonomiczne lub półautonomiczne poruszanie się w terenie miejskim i pozamiejskim. Najbardziej złożonym komponentem robota jest modułowy, hierarchiczny system sterowania - system operacyjny robota mobilnego. Autorzy na potrzeby projektowanego przez siebie robota przyjęli architekturę 7-warstwową, w której układy mikroprocesorowe i oprogramowanie są podzielone zadaniowo i znaczeniowo.

EN

The paper presents the idea of operating system for autonomous mobile robot designed for observation task and mines detection tasks. Authors present overview of the constructions of small military mobile robots (UGV) offered by most advanced enterprises in Poland and worldwide. The review is focused on application of the robots, variety of tasks performed by robots and finally leads authors for the idea competitive military robot. Planned robotic system is a 6 wheeled platform equipped with system of visible range cameras, night vision camera, and directional microphones, optical sensors, lasers sensors, ultrasound sensors and advanced microprocessors systems for data analysis. The system will be capable to autonomously or semiautonomously navigate in urban or rural environment. The most complex component of the robot is modular and hierarchical controlling system - robot's operating system. Authors propose operating system divided into 7 layers, in which the microprocessors and programming tasks are divided semantically.

11

Tworzenie map otoczenia robota mobilnego na podstawie wskazań skanera 3D

Siemiątkowska B., Gnatowski M., Zychewicz A.

Pomiary Automatyka Robotyka

|

2007

|

R. 11, nr 2

PL

W referacie przedstawiona zostanie metoda budowy map otoczenia robota mobilnego wyposażonego w skaner laserowy 3D. Zaletą opisywanej metody jest to, że tworzenie mapy odbywa się w czasie rzeczywistym, mapa umożliwia generowanie bezkolizyjnej trasy oraz lokalizację robota poruszającego się wewnątrz budynków.

EN

The paper presents the method which allows on-line map building based on 3D laser scanner indications. The grid-based representation is used. In each cell of the map information about 3D objects is stored. The map is used for path planning and localization.

12

Architecture of Mobile Robotics Platform planned for Intelligent Robotic Porter System - IRPS project

Wołoszczuk A., Andrzejczak M., Szynkarczyk P.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2007

|

Vol. 1, No. 3

59-63

EN

The aim of this paper is to present the Intelligent Robotic Porter System with respect to architecture of Mobile Robotic Platform. The set of requirements for Mobile Robotic Platform was defined and analyzed. Main engineering problems that occurred during the development of Mobile Robotic Platform's architecture were specified and described. Problems were confronted with PIAP's proposed solutions for technical issues at this stage of the project.