Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 90

Liczba wyników na stronie
first rewind previous Strona / 5 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  collision avoidance
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 5 next fast forward last
EN
The collision regulations include several qualitative terms without providing guidance as to how these terms could be understood in quantitative terms. These terms must therefore be interpreted by navigators, which poses a problem for autonomous ships. Extend the knowledge of how navigators interpret the collision regulations, with a specific focus on how they interpret the rule covering the requirement to proceed at a safe speed. Qualitative study based on interviews of a convenience sample of eight Norwegian navigators. Data was analysed with systematic text condensation. Navigators characterise safe speed as a speed in which they have control. Navigators do not look at different factors mentioned in the collision regulations in isolation, but within the context of the situation. Determining the safe speed of a vessel is more complicated than made out in the literature. As autonomous ships will have to cooperate with conventional vessels, their programming must include the knowledge of how the collision regulations are interpreted by human navigators.
EN
Automation transparency is a means to provide understandability and predictability of autonomous systems by disclosing what the system is currently doing, why it is doing it, and what it will do next. To support human supervision of autonomous collision avoidance systems, insight into the system’s internal reasoning is an important prerequisite. However, there is limited knowledge regarding transparency in this domain and its relationship to human supervisory performance. Therefore, this paper aims to investigate how an information processing model and a cognitive task analysis could be used to drive the development of transparency concepts. Also, realistic traffic situations, reflecting the variation in collision type and context that can occur in real-life, were developed to empirically evaluate these concepts. Together, these activities provide the groundwork for exploring the relation between transparency and human performance variables in the autonomous maritime context.
EN
The article presents an approach to formulating a ship control process model in order to solve the problem of determining a safe ship trajectory in collision situations. Fuzzy process properties are included in the model to bring it closer to reality, as in many situations the navigator makes a subjective decision. A special neural network was used to solve the presented problem. This artificial neural network is characterized by minimum and maximum operations when set. In order to confirm the correctness of the operation of the proposed algorithm, the results of the simulations obtained were presented and an discussion was conducted.
EN
Graphical tools have been proposed to facilitate the selection, evaluation, and correction of anticollision actions in situations with moving and stationary obstacles, assuming that such situations are not extreme or ordinary with sailing vessels and that the target movement parameters are constant or their upcoming change is known. The choice of evasive combined Z‐manoeuvre (both course and speed change at one point and return to the original values of these parameters at another point) and one combined action (both course and speed alteration at the selected point) were considered. The graphical tools developed contain diagrams, showing eight zones of actions, and special marks of targets at the moment of their closest approach to the own ship. In view of the COLREG and good seamanship, these zones were arranged in order of application priority. The results of the enumeration of a representative discrete set of possible manoeuvre variants were used to construct the diagrams.
EN
Groundings and collisions still represent the highest percentage of marine accidents despite the current attention on Maritime Education and Training and the improvement of sensor capability. Most of the time, a collision is caused by a human error with consequences ranging from moderate to severe, with a substantial impact on both environment and life safeguarded at sea. In this paper, a brief statistical data regarding human element as a root cause of marine incidents together with collision regulations misunderstanding is presented as a background chapter. Furthermore, the present work discusses a decision support system architecture to suggest an appropriate action when the risk of a potential collision is detected. The proposed architecture system is based on various modules integrated with proper sensor input data regarding the surrounding navigation area. As a result, the tool can support the Officers of Watch in the decision-making process providing an early suggestion in compliance with the COLlision REGulations. The proposed system is intended to be used onboard independently from the degree of automation of the ship, and it is based on AIS, which is mandatory, making it widely applicable. The proper use of the system can considerably reduce the number of collisions, as demonstrated by the obtained results.
PL
Właściwe określenie istotnych czynników wpływających na przebieg obliczeń manewru uniknięcia kolizji z ruchomymi przeszkodami jest niezbędne w celu zapewnienia wyliczenia dostatecznie wiarygodnych wyników opisujących proponowaną trajektorię tego manewru oraz jego realizację. Istotnym wskaźnikiem weryfikującym przebieg manewru omijania jest zachowanie żądanych separacji między samolotem a przeszkodami. Przedmiotem pracy jest wybór odpowiednich matematycznych modeli dla poszczególnych faz przygotowania przebiegu trajektorii omijania przeszkód. Badano wpływ różnych uproszczeń matematycznych modeli na przebieg manewru antykolizyjnego z uwzględnieniem deformacji trajektorii i zmian przebiegu odległości samolotu od ruchomych przeszkód. Rozważania zostały zilustrowane wybranymi wynikami z symulacji komputerowych wybranego manewru ominięcia przeszkód przez samolot.
EN
A relevant identification of significant factors affecting the process of anti collision manoeuvre computation in case of moving obstacles, is necessary for getting results reliable enough and describing a proposed trajectory of such a manoeuvre as well as its realisation. The requirement for the appropriate separation, the airplane to obstacle distance, is treated as the relevant index for verification of the course of passing by manoeuvre. Subject matter of this work is the appropriate selection of mathematical models for the subsequent phases of preparation of flight trajectory passing by the obstacles. The impact of selected simplifications of mathematical model on the shape of flight trajectory and the distance between the airplane and obstacles have been studied. Considerations have been illustrated by the results of selected computer simulations of an airplane while carrying out an obstacle avoiding manoeuvre.
EN
The era of autonomous ships has already begun in maritime transport. The 30-year forecast for the development of marine technologies predicts many autonomous vessels at sea. This will necessitate radical implementation of new intelligent maritime navigation systems. One of the intelligent systems that has to be implemented is a collision avoidance system. The inference process is a key element of autonomous manoeuvres. These authors propose an inference process that enables exchange of information, intentions and expectations between autonomous vessels and gives them an opportunity to negotiate a safe manoeuvre satisfying all the parties concerned. The model of inference in the communication process has been presented. Methods and algorithms for information exchange and negotiation have been developed. These models were implemented and tested under various conditions. The results of case studies indicate that it is possible to effectively communicate and negotiate used the developed method. To demonstrate the effectiveness of the presented approach over 30 random simulations have been carried out. After successful laboratory tests, over 100 scenarios were executed in quasi-real conditions and fully operational conditions. Tests were carried out in the center of the Foundation for the Safety of Navigation and Environmental Protection on Lake Silm in Iława, Poland. In the framework of project AVAL (Autonomous Vessel with an Air Look) POIR.04.01.04-00-0025-16, 82 random scenarios involving four vessels were performed and 60 random scenarios with two vessels. In 2020 tests were carried out in real conditions on the ferries Wolin and m/f Gryf. The communication and negotiation system presented in the article has been designed and developed specially for maritime navigation purposes. The authors believe that the presented solution can be one of various solutions implemented in autonomous shipping in the near future.
EN
China's extensive inland navigable water system determines that inland navigation must be an important part of China's shipping industry. The collision process of ship striking the anti-collision pier is analyzed through simulation experiment in this paper. The results show that the collision process usually lasts less than 2 seconds, and the peak value of the collision force, friction and resultant force appears 0.5 after the start of the collision.
PL
Właściwe określenie istotnych czynników wpływających na przebieg wyliczanego manewru uniknięcia kolizji z ruchomymi przeszkodami jest niezbędne w celu zapewnienia bezpiecznego ominięcia ruchomej przeszkody. Jednocześnie w trakcie manewru omijania wymagane jest zachowanie żądanej separacji między samolotem a przeszkodami. Przedmiotem pracy jest analiza sposobu w jaki czynniki wpływają na przebieg manewru antykolizyjnego z uwzględnieniem deformacji trajektorii i zmian przebiegu odległości samolotu od wykrytych przeszkód. Skupiono się na wewnętrznych oddziaływaniach, które wynikają z istotnych zmian zachowania się samolotu. Rozważania zostały zilustrowane wybranymi wynikami z symulacji komputerowych typowych manewrów ominięcia przeszkód, poddanych negatywnym wpływom wybranych czynników. Zaproponowano wytyczne, które powinny umożliwić przeciwdziałanie niekorzystnym oddziaływaniom na realizację wyliczonego manewru.
EN
The exact identification of essential factors affecting the course of evasive manoeuvre, that has been computed to avoid a collision with moving obstacles, is necessary to ensure a safe passing by a moving obstacle. At the same time, during the evasive manoeuvre the pre-defined separation between the airplane and obstacles is required. The matter of presented work is defined as the analysis of influence of factors on execution of anti collision manoeuvre taking into account deformation of flight trajectory and changes of time histories of distance from the airplane to detected obstacles. Attention has been focused on internal interactions, resulting from the essential changes of the airplane’s behaviour. Discussion has been illustrated by selected results of computer simulations, executed for typical manoeuvres performed to avoid obstacles, while affected by adverse impacts of selected factors. The appropriate guidelines have been proposed, that should counteract these adverse effects on realisation of computed manoeuvre.
EN
The article considers the problem of autonomous control of the underwater remotely operated vehicle mini Remotely Operated Vehicle (ROV) in a collision situation with a stationary obstacle. The control of the collision avoidance process is presented as a synthesis of fuzzy proportional-differential controllers for the control of distance and orientation concerning the detected stationary obstacle. The control of the submergence depth of the underwater vehicle has been adopted as a separate control flow. A method to obtain the main motion parameters of the underwater vehicle relative to the detected stationary obstacle using a Laser-based Vision System (LVS) and a pressure sensor coupled to an Inertial Measurement Unit (IMU) is described and discussed. The result of computer implementation of the designed fuzzy controllers for collision avoidance is demonstrated in simulation tests and experiments carried out with the mini ROV in the test pool.
EN
The continuous development of autonomous and unmanned technology is accelerating the adop-tion of unmanned vessels for various maritime operations. Despite the technological develop-ments there is still a lack of clear regulatory and organizational frameworks for testing and exploiting the potential of unmanned surface vessels (USVs) in real-world maritime conditions. Such real-world testing becomes ever more complex when operating in multiple nations territo-rial waters. In May 2019 USV ‘Maxlimer’ crossed the North Sea from the United Kingdom to Bel-gium and back, carrying goods, to demonstrate the ability of unmanned surface vessels to interact with real marine traffic in an uncontrolled environment. The paper presents this mission in light of the current state of marine autonomy projects as well as the regulatory works con-ducted by various organizations worldwide.
EN
Navigation traffic and the danger of collision are steadily increasing. Features of navigation in narrow corridors (water, air, etc.) require the development of modern methods for assessing the situation of convergence and the choice of maneuvering divergence of vessels. A method is proposed for forming the area of inadmissible values of the parameters of the movement of any vehicles (including marine) with remote control of the process of their divergence. Situations are considered when a collision of sea vessels can be avoided only by changing the speed in case such vessels cannot change course. The proposed method can be generalized to any environment of navigation.
PL
W artykule przedstawiono wyniki pomiarów, których celem było zbadanie możliwości zwiększenia efektywności działania modelu mikroelektrowni wiatrowej przez zastosowanie zmiennego kąta ustawienia łopat. Badania przeprowadzono na stanowisku pomiarowym zbudowanym do realizacji prac nad opracowywanymi wstępnie projektami mikroelektrowni wiatrowych. Stanowisko umożliwia przeprowadzenie pomiarów związanych z doborem optymalnej geometrii śmigła oraz opracowaniem i testowaniem działania algorytmów optymalnego sterowania pracą mikroelektrowni. Omówiono podstawy fizyczne działania turbiny wiatrowej i sposoby optymalnego jej sterowania. Zakres przeprowadzonych badań obejmuje wykonanie pomiarów dla przypadku wybranej geometrii łopaty śmigła z możliwością zmiany jej kąta ustawienia. Jako generator zastosowano prądnicę prądu stałego z obciążeniem o charakterystyce nieliniowej w postaci ogniwa akumulatora Li-Po. Przedstawiono wyniki działania prostego algorytmu sterowania MPPT. Brak układów optymalnego sterowania pracą mikroelektrowni podyktowany jest ogólnym przekonaniem, o wysokich kosztach jego wytworzenia w stosunku do możliwej poprawy efektywności mikroelektrowni. Ponadto stosowane w praktyce sposoby sterowania większymi turbinami wiatrowymi o mocach przekraczających wartość kilkuset kilowatów nie są optymalne dla mniejszych turbin o mocach do 1 kW. Przeprowadzone badania koncentrowały się na określeniu możliwości zastosowania w elektrowniach wiatrowych o mocach do 1 kW, turbin o zmiennym kącie ustawienia łopat w zależności od jej prędkości obrotowej. W większych elektrowniach wiatrowych zmianę kąta ustawienia łopat stosuje się głównie do ograniczenia mocy turbiny przy dużej prędkości wiatru. W mikroelektrowniach wiatrowych takie rozwiązania, ze względów ekonomicznych, nie są stosowane. Jednak zastosowanie prostego mechanizmu zmiany kąta ustawienia łopat w zależności od prędkości obrotowej śmigła może zwiększyć efektywność pracy turbiny w szerszym zakresie prędkości wiatru. Niewielkie wymiary modelu badawczego pozwalają na szybkie i tanie opracowywanie wstępnych prototypów łopat turbiny dzięki możliwości wykorzystania technologii druku 3D.
EN
The article presents the results of research into the operation of a model of a wind micropower plant with a variable blade angle. The research was carried out on a miniature model of a measuring stand built for the purpose of carrying out work on pre-developed projects of wind micro power plants. The stand allows to carry out measurements related to the selection of the optimal propeller geometry, as well as the development and testing of algorithms for optimal control of the micropower plant. The physical basics of wind turbine operation and the methods of its optimal control are presented. The results of the performed measurements for the selected propeller blade geometry with the possibility of changing its setting angle are presented. A DC generator with a load with a non-linear characteristic in the form of a Li-Po battery cell was used. The results of operation of a simple MPPT control algorithm are presented. The lack of optimal control systems for the operation of micropower plants is dictated by the general belief that the costs of its production are high in relation to the possible improvement of the efficiency of micropower plants. Moreover, the practical methods of controlling larger wind turbines are not optimal for small and very small turbines. The conducted research focused on determining the possibility of using turbines with variable blade angles depending on its rotational speed. In larger wind farms, changing the blade angle is mainly used to limit the power of the turbine at high wind speeds. In micro wind power plants such solutions are not used for economic reasons. However, the use of a simple mechanism for changing the angle of the blades depending on the rotational speed of the propeller can increase the efficiency of the turbine in a wider range of wind speeds. The small dimensions of the research model allow for quick and cheap development of preliminary prototypes of turbine blades thanks to the possibility of using 3D printing technology.
PL
Sukces uniknięcia kolizji z ruchomymi przeszkodami zależy od rozwiązania najistotniejszych problemów takich jak: szybkie wykrycie przeszkód, sprawdzenie czy stanowią zagrożenie oraz podjęcie właściwej decyzji o sposobie ich ominięcia. Do podjęcia tej decyzji niezbędna jest właściwa identyfikacja rodzaju zagrożenia, w tym między innymi czy wykryte przeszkody należy potraktować jako jedną zagregowaną grupę. Do typowych przypadków zalicza się agregację ruchomych przeszkód poruszających się blisko siebie. Opisano sytuacje, gdy dołączeniu do grupy podlegają obiekty przemieszczające się w większej odległości od siebie. Zaprezentowano algorytm podejmowania decyzji przypisania (zagregowania) ruchomych przeszkód do danej grupy. Przedstawiono sposób wyliczania jej charakterystycznych parametrów. Omawiane zagadnienia zostały zilustrowane wynikami symulacji manewrów omijania zagregowanej grupy ruchomych przeszkód dla wybranych scenariuszy.
EN
Successful avoidance of a mid air collision with moving obstacles depends on solutions of some most essential problems, e.g.: quick detection of an obstacle, verification whether detected obstacle is a critical one and making right decision on evasive manoeuvre. This decision-making process requires an appropriate identification of a threat’s nature, including whether detected obstacles should be treated as one aggregated group. Aggregation of obstacles moving in short distance one to the other is a typical case. The paper addresses also the case of inclusion the obstacle to the group objects moving in longer distances one to the other. The algorithm used for deciding whether a moving obstacle should be added to (aggregated with) a given group has been presented. A method for computing its characteristic parameters has been presented too. Selected scenarios of avoiding the aggregated group of moving obstacles have been simulated and results obtained illustrates problems considered.
15
Content available The Machine Learning Method of PIDVCA
EN
Building a dynamic collision knowledge base of self-learning is one of the core contents of implementing "personified intelligence" in Personifying Intelligent Decision-making for Vessel Collision Avoidance (short for PIDVCA). In the paper, the machine learning method of PIDVCA combined with offline artificial learning and online machine learning is proposed. The static collision avoidance knowledge is acquired through offline artificial learning, and the isomeric knowledge representation integration method with process knowledge as the carrier is established, and the Dynamic collision avoidance knowledge is acquired through online machine learning guided by inference engine. A large number of simulation results show that the dynamic collision avoidance knowledge base constructed by machine learning can achieve the effect of anthropomorphic intelligent collision avoidance. It is verified by examples that the machine learning method of PIDVCA can realize target perception, target cognition and finally obtain an effective collision avoidance decision-making.
PL
Do rozwiązania problemu unikania kolizji przez samolot w przestrzeni powietrznej niezbędne jest wykrycie przeszkody, sprawdzenie czy stanowi zagrożenie dla bezpieczeństwa samolotu oraz podjęcie właściwych decyzji o odpowiednim sposobie jej ominięcia. To wszystko są istotne fazy poprzedzające automatyczne ominięcie ruchomej przeszkody. W pracy zaprezentowano algorytm omijania ruchomej przeszkody o niedających się przewidzieć zmianach jej ruchu. Przedstawiono schemat logicznych działań mających na celu nie tylko bezpieczne uniknięcie kolizji z manewrującą przeszkodą, ale także powrót do lotu wzdłuż zaplanowanej przed startem trasy. Zaproponowaną metodę zilustrowano symulacyjnym przykładem automatycznego ominięcia wspomnianej przeszkody dla wybranego scenariusza.
EN
To solve the problem of aircraft avoiding collision, it is necessary to detect an obstacle, check if it poses a threat to the safety of the aircraft and make the right decisions about the appropriate way to bypass it. These are all important phases preceding the automatic bypassing of a moving obstacle. The work presents an algorithm for bypassing a moving obstacle with unpredictable changes in its movement. A diagram of logical actions was presented to not only safely avoid collision with a maneuvering obstacle, but also to return to flight along the route planned before the start. The proposed method is illustrated by a simulation example of automatically bypassing an obstacle for the selected scenario.
EN
The speed ratio is an important factor that must be considered when two vessels will course change to avoid collision. In the process of the research on Personifying Intelligent Decision-making for Vessel Collision Avoidance (short for PIDVCA), it is found that the effect of collision avoidance based on the existing “International Regulations for Prevention Collision at sea” (short for COLREGS) is greatly affected by the high speed ratio (k=Vt/V0≥1.5). Through the analysis on the geometric change law of two vessels’ relative motion in Open waters, the effects of the responsibility for the ship collision avoidance under the COLREGS and special case for high-speed ratio is discussed. According to the collision avoidance measures taken for two vessels encounter situation, some reasonable suggestions are put forward and the simulation experiments that based on ship's intelligent collision avoidance simulation platform are given to support the idea.
EN
In order to give consideration to both comprehensive evaluation and efficient decision-making in collision avoidance decision-making process, a collision avoidance decision-making model based on collision circle is proposed by introducing the concept of collision circle. Firstly, the factors causing ship collision are analyzed. Secondly, the static and dynamic characteristics of collision circles are analyzed and summarized by using collision circle simulation cases. Thirdly, based on the static characteristics, a reasonably distributed collision avoidance decision model of (Possible Point of Collision,PPC) was established. Finally, the spatial data operations core algorithm (Java Topology Suite, JTS) is used for logical operation and visualization, so as to realize the ship collision avoidance evaluation and decision. The decision model was used to verify the accident scenario of "SANCHI", and the results showed that the obtained collision avoidance scheme was reasonable and in line with the "International Regulations for Preventing Collisions at Sea" and safety requirements, thus providing a reference for maritime operators to avoid collisions between ships.
19
Content available Neuroevolutionary approach to COLREGs ship maneuvers
EN
The paper describes the usage of neuroevolutionary method in collision avoidance of two power-driven vessels approaching each other regarding COLREGs rules. This may be also be seen as the ship handling system that simulates a learning process of a group of artificial helmsmen - autonomous control units, created with artificial neural networks. The helmsman observes an environment by its input signals and according to assigned CORLEGs rule, he calculates the values of required parameters of maneuvers (propellers rpm and rudder deflection) in a collision avoidance situation. In neuroevolution such units are treated as individuals in population of artificial neural networks, which through environmental sensing and evolutionary algorithms learn to perform given task safely and efficiently. The main task of this project is to evolve a population of helmsmen which is able to effectively implement chosen rule: crossing or overtaking.
EN
This research article formulates a mathematical model of the matrix game of the safe ship control process containing: state variables and control, collision risk definition and the form of a collision risk matrix. Multicriteria optimization of the matrix game was introduced, leading to non-cooperative and cooperative game control algorithms and non-game control. Simulation safe trajectories of own ship for various types of control were compared to the example of the real situation at sea.
first rewind previous Strona / 5 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.