CN114664118B - Intelligent ship collision avoidance automatic test scene generation method and system - Google Patents
Intelligent ship collision avoidance automatic test scene generation method and system Download PDFInfo
- Publication number
- CN114664118B CN114664118B CN202210269782.3A CN202210269782A CN114664118B CN 114664118 B CN114664118 B CN 114664118B CN 202210269782 A CN202210269782 A CN 202210269782A CN 114664118 B CN114664118 B CN 114664118B
- Authority
- CN
- China
- Prior art keywords
- information
- obtaining
- result
- ship
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims 14
- 238000012360 testing method Methods 0.000 title claims 4
- 235000003642 hunger Nutrition 0.000 claims 7
- 238000004088 simulation Methods 0.000 claims 7
- 238000013210 evaluation model Methods 0.000 claims 6
- 238000012549 training Methods 0.000 claims 6
- 238000012545 processing Methods 0.000 claims 2
- 238000004891 communication Methods 0.000 claims 1
- 238000004590 computer program Methods 0.000 claims 1
- 238000012986 modification Methods 0.000 claims 1
- 230000004048 modification Effects 0.000 claims 1
- 230000037351 starvation Effects 0.000 claims 1
- 230000003827 upregulation Effects 0.000 claims 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
- G08G3/02—Anti-collision systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Databases & Information Systems (AREA)
- Ocean & Marine Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for generating an automatic test scene for intelligent ship collision avoidance, which are used for obtaining first simulation scene information; obtaining first visibility information of a first simulated scene; acquiring basic information of a first ship and a second ship, and using the basic information as first input information; acquiring first captain information of a first ship, and acquiring first decision information as second input information according to first character information and the first visibility information; inputting first input information and second input information into a first result evaluation model to obtain a first output result of the first result evaluation model, and obtaining first simulation position information according to the first simulation scene information; obtaining a first sea beast matching result; and correcting the first output result to obtain second simulated scene information, and storing the second simulated scene information. The technical problems that in the prior art, the scene generation system is low in simulation scene quality, the scene is not real and accurate enough, and the diversity of the scene cannot be reproduced are solved.
Description
Technical Field
The invention relates to the field related to ship test scene generation, in particular to an intelligent ship collision avoidance automatic test scene generation method and system.
Background
In recent years, smart ships have become a research hotspot in the field of water traffic. In a collision avoidance test scene generation system of an intelligent ship, various meeting situations are required to be generated as much as possible, and the credibility of a ship collision avoidance algorithm test is ensured. The generation of the collision avoidance test scene is a key process of collision avoidance algorithm test and evaluation, and the main aim of the generation of the test case set which meets the design target and the design requirement is stored in a scene database system.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventor of the present application finds that the above technology has at least the following technical problems:
the scene generation system in the prior art has the technical problems of low simulation scene quality, unreal and accurate scene and incapability of reproducing the diversity of the scene.
Disclosure of Invention
The embodiment of the application provides an automatic test scene generation method and system for intelligent ship collision avoidance, solves the technical problems that in the prior art, the scene generation system is low in simulation scene quality, the scene is not real and accurate enough, and the diversity of the scene cannot be reproduced, and achieves the technical effects of improving the scene simulation quality and enabling the scene simulation to be more real and accurate.
In view of the foregoing problems, the present application provides an intelligent ship collision avoidance automatic test scene generation method and system.
In a first aspect, an embodiment of the present application provides a method for generating an automatic test scenario for intelligent ship collision avoidance, where the method is applied to an automatic scenario generation system, the automatic scenario generation system is in communication connection with an environment creation module, a target creation module, and a storage module, and the method includes: obtaining first simulation scene information through the environment creation module; obtaining first visibility information of the first simulated scene; acquiring basic information of a first ship and a second ship through the target creation module, and taking the basic information as first input information; obtaining first captain information of a first ship, the first captain information including first character information of the first captain; obtaining first decision information according to the first character information and the first visibility information, and taking the first decision information as second input information; inputting the first input information and the second input information into a first result evaluation model, wherein the first result evaluation model is obtained by training multiple groups of training data, and each group of the multiple groups of training data comprises the first input information, the second input information and identification information for identifying a first result; obtaining a first output result of the first result evaluation model, the first output result comprising a first result of the first vessel after evasion; obtaining first simulation position information according to the first simulation scene information; obtaining a first sea beast matching result according to the first simulation position information and the first visibility information; correcting the first output result according to the first sea beast matching result to obtain second simulated scene information; and storing the second simulation scene information through the storage module.
On the other hand, this application still provides an automatic test scene generation system is kept away to intelligent boats and ships, the system includes: a first obtaining unit, configured to obtain first simulated scene information through an environment creation module; a second obtaining unit, configured to obtain first visibility information of the first simulated scene; a third obtaining unit, configured to obtain basic information of the first ship and the second ship through the target creating module, and use the basic information as first input information; a fourth obtaining unit configured to obtain first captain information of a first ship, the first captain information including first character information of the first captain; a fifth obtaining unit, configured to obtain first decision information according to the first personality information and the first visibility information, and use the first decision information as second input information; a first input unit, configured to input the first input information and the second input information into a first result evaluation model, where the first result evaluation model is obtained through training of multiple sets of training data, and each of the multiple sets of training data includes the first input information, the second input information, and identification information that identifies a first result; a sixth obtaining unit, configured to obtain a first output result of the first result evaluation model, where the first output result includes a first result of the first vessel after the avoidance; a seventh obtaining unit, configured to obtain first simulated position information according to the first simulated scene information; an eighth obtaining unit, configured to obtain a first sea beast matching result according to the first simulated position information and the first visibility information; a ninth obtaining unit, configured to correct the first output result according to the first beast matching result, and obtain second simulated scene information; and the first storage unit is used for storing the second simulation scene information through a storage module.
In a third aspect, the present invention provides an automatic test scenario generation system for intelligent ship collision avoidance, including a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor implements the steps of the method of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the method comprises the steps of obtaining first simulation scene information, obtaining basic information of a first ship and a second ship in a simulation process as first input information, setting characters of the captain to be evaluated according to the first captain information to obtain first character information, obtaining first decision information of the first captain according to the first character information and first visibility information, using the first decision information as second input information, inputting the first input information and the second input information into a first result evaluation model, continuously performing self-correction adjustment on the basis of the model, obtaining a more accurate computer result of scene collision of the first ship and the second ship according to the difference of the first input information and the second input information, further performing scene generation on the result, obtaining sea beast information of a simulation position according to the first simulation position information, matching sea beasts, adding the matched first sea beasts into the first simulation scene information, adjusting the first output result to serve as a second output result, and storing the scene simulation result, so that the real scene simulation effect is more accurate.
The above description is only an overview of the technical solutions of the present application, and the present application may be implemented in accordance with the content of the description so as to make the technical means of the present application more clearly understood, and the detailed description of the present application will be given below in order to make the above and other objects, features, and advantages of the present application more clearly understood.
Drawings
Fig. 1 is a schematic flow chart of a method for generating an automatic test scenario for collision avoidance of an intelligent ship according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an intelligent ship collision avoidance automatic test scene generation system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a fifth obtaining unit 15, a first input unit 16, a sixth obtaining unit 17, a seventh obtaining unit 18, an eighth obtaining unit 19, a ninth obtaining unit 20, a first storage unit 21, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 306.
Detailed Description
The embodiment of the application provides an automatic test scene generation method and system for intelligent ship collision avoidance, solves the technical problems that in the prior art, the scene generation system is low in simulation scene quality, the scene is not real and accurate enough, and the diversity of the scene cannot be reproduced, and achieves the technical effects of improving the scene simulation quality and enabling the scene simulation to be more real and accurate. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
In recent years, smart ships have become a research hotspot in the field of water traffic. In a collision prevention test scene generation system of an intelligent ship, various meeting situations are required to be generated as much as possible, and the credibility of a ship collision prevention algorithm test is ensured. The generation of the collision avoidance test scene is a key process of the test and the evaluation of the collision avoidance algorithm, and the main aim of the generation of the test case set which meets the design aim and the design requirement is stored in a scene database system. However, the scene generation system in the prior art has low simulation scene quality, and the scene is not real and accurate enough, and the diversity of the scene cannot be reproduced.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an automatic test scene generation method for intelligent ship collision avoidance, which is applied to an automatic scene generation system, wherein the automatic scene generation system is in communication connection with an environment creation module, a target creation module and a storage module, and the method comprises the following steps: obtaining first simulation scene information through the environment creation module; obtaining first visibility information of the first simulated scene; obtaining basic information of a first ship and a second ship through the target creation module, and taking the basic information as first input information; obtaining first captain information of a first ship, wherein the first captain information comprises first character information of the first captain; obtaining first decision information according to the first character information and the first visibility information, and taking the first decision information as second input information; inputting the first input information and the second input information into a first result evaluation model, wherein the first result evaluation model is obtained by training multiple groups of training data, and each group of the multiple groups of training data comprises the first input information, the second input information and identification information for identifying a first result; obtaining a first output result of the first result evaluation model, the first output result comprising a first result of the first vessel after avoidance; obtaining first simulation position information according to the first simulation scene information; obtaining a first sea beast matching result according to the first simulation position information and the first visibility information; correcting the first output result according to the first sea beast matching result to obtain second simulated scene information; and storing the second simulation scene information through the storage module.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides a method for generating an automatic test scenario for intelligent ship collision avoidance, where the method is applied to an automatic scenario generation system, the automatic scenario generation system is in communication connection with an environment creation module, a target creation module, and a storage module, and the method includes:
step S100: obtaining first simulation scene information through the environment creation module;
specifically, the environment creating module is a module that sets basic information for the test scenario environment and creates an environment, where a rule refers to a principle of scenario generation. The environment, the own ship and the target ship are created according to the rules. The specific rules include: 1) Setting a water area range, including an open water area and a limited water area; 2) Visibility settings include good visibility and poor visibility. The selection of the area of water also includes a selection of a location of the area of water.
Step S200: obtaining first visibility information of the first simulated scene;
specifically, the visibility refers to the maximum distance at which a person with normal vision can recognize a target object from the background, where the visibility is visibility information set according to the air layer between an observer and the target object, the first visibility information is visibility information of a first simulated scene obtained according to the setting of the first simulated scene information, and the visibility information at least includes the following two situations, namely poor visibility and good visibility.
Step S300: acquiring basic information of a first ship and a second ship through the target creation module, and taking the basic information as first input information;
specifically, the first ship and the second ship are obtained by setting the number of ships, including two ships and a plurality of ships (more than two ships and less than 4 ships); the base information is base information of the first vessel and the second vessel, the base information including: basic ship dynamics including ship dynamic and static data (coordinates and speed), meeting situation, whether collision danger exists or not and basic meeting situation characteristics among ships; the ship autonomous avoidance capability attribute defines whether the ship has the capability of following the collision avoidance rule or not so as to restore the complex situation of the actual marine ship.
Step S400: obtaining first captain information of a first ship, the first captain information including first character information of the first captain;
specifically, the first captain information is captain information of the first ship, which is obtained by the first ship, and the captain information is captain information obtained by setting basic information of the first ship, wherein the captain is captain information of a real ship as a prototype, and the captain information is analyzed and shaped by collecting relevant information, and the first character information of the captain is obtained through the relevant information.
Step S500: obtaining first decision information according to the first character information and the first visibility information, and taking the first decision information as second input information;
specifically, the first decision information is decision information obtained through the first visibility information and the first personality information, the decision information includes decision content and decision time information, the decision time is a time period from when the first captain finds the abnormal condition to when the first ship executes the decision, and the first decision information is used as second input information.
Step S600: inputting the first input information and the second input information into a first result evaluation model, wherein the first result evaluation model is obtained by training multiple groups of training data, and each group of the multiple groups of training data comprises the first input information, the second input information and identification information for identifying a first result;
step S700: obtaining a first output result of the first result evaluation model, the first output result comprising a first result of the first vessel after avoidance;
specifically, the first result evaluation model is a Neural network model in machine learning, and a Neural Network (NN) is a complex Neural network system formed by widely interconnecting a large number of simple processing units (called neurons), which reflects many basic features of human brain functions, and is a highly complex nonlinear dynamical learning system. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (Artificial Neural Networks) are a description of the first-order properties of the human brain system. Briefly, it is a mathematical model. And through training of a large amount of training data, inputting the first input information and the second input information into a neural network model, and outputting first result information containing the first ship after avoidance.
More specifically, the training process is essentially a supervised learning process, each group of supervised data includes the first input information, the second input information and identification information for identifying a first result, the first input information and the second input information are input into a neural network model, the neural network model performs continuous self-correction and adjustment according to the identification information for identifying the first result, and the group of supervised learning is ended and the next group of supervised learning is performed until the obtained output result is consistent with the identification information; when the output information of the neural network model reaches a preset accuracy rate/reaches a convergence state, the supervised learning process is ended. Through the supervised learning of the neural network model, the neural network model can process the input information more accurately, so that a more accurate first result of the first ship after avoidance is obtained, and further more accurate change situation of the first simulation scene is obtained, and further more accurate technical effect of environment situation simulation can be achieved.
Step S800: obtaining first simulation position information according to the first simulation scene information;
step S900: obtaining a first sea beast matching result according to the first simulation position information and the first visibility information;
specifically, the first simulation scene is simulated according to a certain sea area position of a real sea area to obtain first simulation position information of the first simulation scene information, the simulation position information includes the size of the simulation area and the longitude and latitude of the simulation area, marine organism information of the simulation position is obtained according to the simulation position, and the marine organism information is obtained by acquiring information of marine organisms in the simulation area for truly simulating the sea area information to obtain marine organism information of the simulation area in the simulation time.
Step S1000: correcting the first output result according to the first sea beast matching result to obtain second simulated scene information
Step S1100: and storing the second simulation scene information through the storage module.
Specifically, habit information of the first sea beasts is obtained according to information of the first sea beasts, information such as appearance positions and speed of the first sea beasts is obtained according to the habit information, whether the first sea beasts can affect collision avoidance of the first ship and the second ship is judged according to the appearance positions of the first sea beasts, when the first sea beasts affect the first ship and the second ship, a result of the first sea beasts affecting the first ship and the first sea beasts information are used as second simulated scene information, the second simulated scene information is stored, and scene simulation quality is improved by simulating marine organisms in real time and using the influence of the marine organisms on the first ship as new simulated scene information, so that the scene simulation is more real and accurate.
Further, in the step S900 according to the first simulation position information and the first visibility information, a first sea beast matching result is obtained, in this embodiment of the present application, further including:
step S910: obtaining first sea beast information through the first simulation position;
step S920: obtaining first age information and first habit information of the first sea beast according to the first sea beast information;
step S930: performing first volume estimation on the first sea beast according to the first age information and the first habit information to obtain a first volume estimation result;
step S940: obtaining a first probability level based on the first habit information and the first visibility information, the first probability level being a level of probability that the first sea beast is present at the first vessel within a first predetermined range;
step S950: and judging whether to modify the first output result or not according to the first probability grade and the first volume estimation result.
Specifically, the information of the sea animals is sea animal information obtained through an information acquisition device, age information and species information of the first sea animals are obtained, first habit information of the first sea animals is obtained, the first habit information comprises an activity area of the first sea animals at ordinary times, whether activities in the daytime or at night are liked to be moved or liked to be calmed, whether activities in the daytime or at night are liked to be moved, whether the concept of the field is strong or not, whether eating or relative anorexia is liked to be carried out and the like, body types of the first sea animals in the current stage are estimated according to the age information, the species information and the first habit information, a first volume estimation result is obtained, the probability that the first sea animals appear in a first preset range of the first ship is estimated according to the volume information of the first sea animals and current visibility information (including environment information), a first rate grade is obtained, and whether correction processing is carried out on the first output result is judged according to the probability grade and the first volume estimation result. When the first volume estimation result does not affect the first ship, the first output result is not processed, further, when the first volume estimation result affects the first ship, true random simulation is performed according to the probability level, and when the first sea beast appears in a first preset range of the first ship, the first output result is corrected.
Further, in step S940, the obtaining a first probability level according to the first habit information and the first visibility information further includes:
step S941: obtaining a first active area of the first sea beast;
step S942: carrying out probability statistics on the occurrence times of the first sea beasts at different positions of the first activity area;
step S943: obtaining the intersection of the area of a first preset range of the first ship and the area of the first movable area, and obtaining a first probability according to the intersection of the areas;
step S944: obtaining a first noise level of the first vessel;
step S945: matching the influence degree of the first sea beast according to the first noise level to obtain a first influence result;
step S946: and adjusting the first probability according to the first influence result to obtain a first probability level.
Specifically, the activity area of the first sea animal is area information of daily activities of the first sea animal obtained according to first habit information of the first sea animal, the daily behaviors of the first sea animal are analyzed, probabilities of the first sea animal appearing at different positions of the first activity area are counted, the first activity area of the first sea animal is intersected according to a first predetermined range of the first ship, and first probability information of the first sea animal appearing at the intersection is obtained, wherein the first probability information includes a probability that the first sea animal appears at different positions of the intersection and a total probability of the first sea animal appearing at the intersection. Obtaining a first noise level of the first ship, wherein the noise level is a noise level evaluated according to the influence of the engine noise of the ship on marine life in water, obtaining a first noise level of the first ship, judging the influence of the first noise level on the first sea animal according to information such as the type, the habit and the like of the first sea animal, namely, after judging that the sea animal is influenced by the sound wave of the first noise level, evaluating whether the probability of the first sea animal appearing at the region intersection is increased or decreased, adjusting the first probability according to the evaluation result, when the first sea animal is attracted by the noise of the first noise level, properly adjusting the first probability, and when the first sea animal is frightened by the first noise, reducing the first probability. By carrying out refinement evaluation on the occurrence probability of the marine animals, a foundation is laid for whether the marine animals are tamped in a follow-up scene simulation or not, and then a more accurate, intelligent and real test scene is obtained.
Further, the embodiment of the present application further includes:
step S9461: obtaining first volume information of the first ship according to the basic information of the first ship;
step S9462: obtaining a danger coefficient of the first sea beast to the first ship according to the first volume estimation result and the first volume information;
step S9463: obtaining a range rating, wherein the range rating is obtained as a function of a distance from the first vessel;
step S9464: and matching the range grades according to the danger coefficients to obtain a first matching result, wherein the first matching result comprises the first preset range.
Specifically, first volume information of the first ship is obtained according to basic information of the first ship, the volume is volume information reflecting size and draft information of the first ship, a danger coefficient is obtained according to the first volume estimation result and the first volume information, the danger coefficient is higher when the first volume estimation result is larger than the first volume, conversely, the danger coefficient is lower when the first volume estimation result is smaller than the first volume, range classification is obtained, and the range classification is that range classification is performed according to the danger coefficient, wherein the range classification is performed in a one-to-one correspondence manner by taking the first ship as a center, and circular areas with radii of 50m, 100m, 150m, 200m, 300m and 500m are matched according to the danger coefficient, and first preset range information is obtained.
Further, in the step S500 of this embodiment of the present application, the obtaining first decision information according to the first character information and the first visibility information, and using the first decision information as second input information further includes:
step S510: obtaining a first time when the first ship discovers the second ship according to the first visibility information;
step S520: obtaining second time for executing a first decision result according to the first character information of the first captain;
step S530: and obtaining time difference information of the second time and the first time, and taking the time difference information and the first decision result as first decision information.
Specifically, the first time is time point information of finding a second ship by the first ship according to the first visibility information, distance information of the first ship relative to the second ship is obtained according to the first visibility information of the first captain, the event urgency is estimated according to the distance information, a scheme for processing the time by the first captain under the current urgency and a time point for executing the scheme are obtained, the time point is a second time, the scheme is a first decision result, and a time difference between the second time and the first decision result are used as first decision information.
Further, the embodiment of the present application further includes:
step S531: obtaining a hungry state of the first sea beast at the first time;
step S532: obtaining first position information of the first sea beast in the first simulated scene according to the first habit information;
step S533: obtaining first route information of the first sea beast pursuing the first ship according to the first position information;
step S534: obtaining first speed information through the hunger state;
step S535: taking the hunger state, the first habit information, the first position information and the first speed information as basic information of the first sea beast;
step S536: when the judgment result is that the first output result is corrected, a first adding instruction is obtained;
step S537: adding the basic information into the first simulated scene information according to the first adding instruction;
step S538: and obtaining second simulated scene information, wherein the second simulated scene information comprises the first simulated scene information and information for correcting the first output result after the basic information is added.
Specifically, a hungry state of the first sea beast at a first time is obtained according to the setting condition, wherein the first time is a time point when the first ship finds a second ship, when the first sea beast appears in the simulated scene, position information of the first sea beast in the scene is obtained according to the habit, a first pursuit route is obtained according to the position of the first ship and the position of the first sea beast, speed information of the sea beast in the hungry state is obtained according to the hungry state of the first sea beast, the hungry state, the first habit information, the first position information and the first speed information are used as basic information of the first sea beast, and when a judgment result is that the first output result is corrected, a first adding instruction is obtained; adding the basic information into the first simulated scene information according to the first adding instruction; and obtaining second simulated scene information, wherein the second simulated scene information comprises the first simulated scene information and information for correcting the first output result after the basic information is added.
Further, the obtaining first speed information through the hunger status further includes:
step S5341: obtaining a first collection instruction;
step S5342: collecting parameters of the first sea beasts according to the first collection instruction, and constructing a hunger state database according to the collected parameters, wherein the hunger state database comprises different predation speeds of the first sea beasts in different hunger states;
step S5343: obtaining, by the hunger status database, a predetermined hunger status threshold, wherein the predetermined hunger status threshold comprises a first threshold and a second threshold, wherein the first threshold is higher than the second threshold;
step S5344: judging the relation between the starvation state and the first threshold value and the second threshold value;
step S5345: when the hunger state is between the first threshold value and a second threshold value, performing up-regulation processing on the first speed information according to the hunger state database.
Specifically, according to the first collection instruction, constructing a hungry state database for the first sea beasts, wherein the constructing process includes the predation speeds of the first sea beasts in different hungry states, and obtaining a predetermined hungry state threshold according to the constructed hungry state database, the predetermined hungry state threshold is a threshold obtained according to different results of the different hungry states of the first sea beasts on the predation speeds, and the predetermined hungry state threshold includes a first threshold and a second threshold, wherein the hungry state of the first threshold is higher than the second threshold, when the hungry state of the first sea beasts is below the second threshold, the first sea beasts do not have other predation desires, when the hungry state of the first sea beasts is between the second threshold and the first threshold, the first sea beasts are strongly predated, and when the hungry state of the first sea beasts is between the second threshold and the first threshold, the first speed information is subjected to upper adjustment; when the hungry state of the first sea creature is above a first threshold, at which time the physical functioning of the first sea creature is significantly affected, a first speed down-regulation process is performed.
To sum up, the method and the system for generating the intelligent ship collision avoidance automatic test scene have the following technical effects:
1. the method comprises the steps of obtaining first simulation scene information, obtaining basic information of a first ship and a second ship in a simulation process as first input information, setting characters of the captain to be evaluated according to the first captain information to obtain first character information, obtaining first decision information of the first captain according to the first character information and first visibility information, using the first decision information as second input information, inputting the first input information and the second input information into a first result evaluation model, continuously performing self-correction adjustment on the basis of the model, obtaining a more accurate computer result of scene collision of the first ship and the second ship according to the difference of the first input information and the second input information, further performing scene generation on the result, obtaining sea beast information of a simulation position according to the first simulation position information, matching sea beasts, adding the matched first sea beasts into the first simulation scene information, adjusting the first output result to serve as a second output result, and storing the scene simulation result, so that the real scene simulation effect is more accurate.
2. Due to the adoption of the mode of supervising and learning the neural network model, the input information processed by the neural network model is more accurate, so that a more accurate first result of the first ship after avoidance is obtained, a more accurate change situation of the first simulation scene is obtained, and a more accurate technical effect of simulating the environment situation is achieved.
3. Because the mode of carrying out the refined evaluation on the occurrence probability of the marine animals is adopted, the foundation is provided for whether the marine animals are tamped or not in the subsequent scene simulation, and a more accurate, intelligent and real test scene is obtained.
Example two
Based on the same inventive concept as the method for generating the intelligent ship collision avoidance automatic test scene in the foregoing embodiment, the present invention further provides a system for generating an intelligent ship collision avoidance automatic test scene, as shown in fig. 2, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first simulated scene information through an environment creating module;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain first visibility information of the first simulated scene;
a third obtaining unit 13, wherein the third obtaining unit 13 is configured to obtain basic information of the first ship and the second ship through the target creating module, and use the basic information as the first input information;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to obtain first captain information of the first ship, where the first captain information includes first character information of the first captain;
a fifth obtaining unit 15, where the fifth obtaining unit 15 is configured to obtain first decision information according to the first personality information and the first visibility information, and use the first decision information as second input information;
a first input unit 16, where the first input unit 16 is configured to input the first input information and the second input information into a first result evaluation model, where the first result evaluation model is obtained by training multiple sets of training data, and each of the multiple sets of training data includes the first input information, the second input information, and identification information that identifies a first result;
a sixth obtaining unit 17, configured to obtain a first output result of the first result evaluation model, where the first output result includes a first result of the first vessel after avoidance;
a seventh obtaining unit 18, where the seventh obtaining unit 18 is configured to obtain first simulated position information according to the first simulated scene information;
an eighth obtaining unit 19, where the eighth obtaining unit 19 is configured to obtain a first sea animal matching result according to the first simulated position information and the first visibility information;
a ninth obtaining unit 20, where the ninth obtaining unit 20 is configured to correct the first output result according to the first beast matching result, and obtain second simulated scene information;
a first storage unit 21, where the first storage unit 21 is configured to store the second simulated scene information through a storage module.
Further, the system further comprises:
a tenth obtaining unit, configured to obtain first sea beast information through the first simulated position;
an eleventh obtaining unit configured to obtain first age information and first habit information of the first sea beast from the first sea beast information;
a twelfth obtaining unit, configured to perform first volume estimation on the first sea animal according to the first age information and the first habit information, and obtain a first volume estimation result;
a thirteenth obtaining unit configured to obtain a first probability level that the first sea creature is present in the first predetermined range of the first vessel, based on the first habit information and the first visibility information;
a first judging unit, configured to judge whether to perform modification processing on the first output result according to the first probability level and the first volume estimation result.
Further, the system further comprises:
a fourteenth obtaining unit for obtaining a first activity area of the first sea beast;
the first statistical unit is used for carrying out probability statistics on the occurrence times of the first sea beasts at different positions of the first activity area;
a fifteenth obtaining unit configured to obtain an area intersection of a first predetermined range of the first vessel and the first active area, and obtain a first probability according to the area intersection;
a sixteenth obtaining unit, configured to obtain a first noise level of the first ship;
a seventeenth obtaining unit, configured to match the influence degree of the first sea beast according to the first noise level, and obtain a first influence result;
an eighteenth obtaining unit, configured to adjust the first probability according to the first influence result, so as to obtain a first probability level.
Further, the system further comprises:
a nineteenth obtaining unit configured to obtain first volume information of the first ship from the basic information of the first ship;
a twentieth obtaining unit, configured to obtain a risk coefficient of the first sea beast on the first ship according to the first volume estimation result and the first volume information;
a twenty-first obtaining unit configured to obtain a range rating, wherein the range rating is a range rating obtained according to a difference in distance from the first vessel;
a twenty-second obtaining unit, configured to match the range classifications according to the risk coefficients, and obtain a first matching result, where the first matching result includes the first predetermined range.
Further, the system further comprises:
a twenty-third obtaining unit configured to obtain, according to the first visibility information, a first time at which the first vessel discovers the second vessel;
a twenty-fourth obtaining unit, configured to obtain, according to the first personality information of the first captain, a second time for executing the first decision result;
a twenty-fifth obtaining unit, configured to obtain time difference information between the second time and the first time, and use the time difference information and the first decision result as first decision information.
Further, the system further comprises:
a twenty-sixth obtaining unit for obtaining a hunger status of the first sea beast at the first time;
a twenty-seventh obtaining unit, configured to obtain, according to the first habit information, first position information of the first sea beast in the first simulated scene;
a twenty-eighth obtaining unit configured to obtain first route information on which the first sea animal has collided with the first ship, according to the first position information;
a twenty-ninth obtaining unit to obtain first speed information by the hunger status;
a thirtieth obtaining unit, configured to use the hunger status, the first habit information, the first location information, and the first speed information as basic information of the first sea beast;
a thirty-first obtaining unit, configured to obtain a first adding instruction when the determination result is that the first output result is subjected to the correction processing;
a first adding unit, configured to add the basic information to the first simulated scene information according to the first adding instruction;
a thirty-second obtaining unit, configured to obtain second simulated scene information, where the second simulated scene information includes the first simulated scene information and information obtained by adding the basic information and then performing modification processing on the first output result.
Further, the system further comprises:
a thirty-third obtaining unit, configured to obtain the first collection instruction;
the first collection unit is used for collecting parameters of the first sea beasts according to the first collection instruction and constructing a hunger state database according to the collected parameters, wherein the hunger state database comprises different predation speeds of the first sea beasts in different hunger states;
a thirty-fourth obtaining unit, configured to obtain, by the hungry status database, a predetermined hungry status threshold, where the predetermined hungry status threshold includes a first threshold and a second threshold, where the first threshold is higher than the second threshold;
a second determination unit configured to determine a relationship between the hunger state and the first and second thresholds;
a first processing unit, configured to perform, when the starvation status is between the first threshold and a second threshold, an up-regulation process on the first speed information according to the starvation status database.
Various changes and specific examples of the method for generating the intelligent ship collision avoidance automatic test scenario in the first embodiment of fig. 1 are also applicable to the system for generating the intelligent ship collision avoidance automatic test scenario of the present embodiment, and through the foregoing detailed description of the method for generating the intelligent ship collision avoidance automatic test scenario, those skilled in the art can clearly know the method for implementing the system for generating the intelligent ship collision avoidance automatic test scenario in the present embodiment, so for the sake of brevity of the description, detailed descriptions are not repeated here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the intelligent ship collision avoidance automatic test scene generation method in the foregoing embodiment, the present invention further provides an intelligent ship collision avoidance automatic test scene generation system, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the foregoing intelligent ship collision avoidance automatic test scene generation methods are implemented.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the invention provides an intelligent ship collision avoidance automatic test scene generation method, which is applied to an automatic scene generation system, wherein the automatic scene generation system is in communication connection with an environment creation module, a target creation module and a storage module, and the method comprises the following steps: obtaining first simulation scene information through the environment creation module; obtaining first visibility information of the first simulated scene; acquiring basic information of a first ship and a second ship through the target creation module, and taking the basic information as first input information; obtaining first captain information of a first ship, the first captain information including first character information of the first captain; obtaining first decision information according to the first character information and the first visibility information, and taking the first decision information as second input information; inputting the first input information and the second input information into a first result evaluation model, wherein the first result evaluation model is obtained by training multiple groups of training data, and each group of the multiple groups of training data comprises the first input information, the second input information and identification information for identifying a first result; obtaining a first output result of the first result evaluation model, the first output result comprising a first result of the first vessel after avoidance; obtaining first simulation position information according to the first simulation scene information; obtaining a first sea beast matching result according to the first simulation position information and the first visibility information; correcting the first output result according to the first sea beast matching result to obtain second simulated scene information; and storing the second simulation scene information through the storage module. The technical problems that in the prior art, the simulation scene quality of a scene generation system is low, the scene is not real and accurate enough, and the diversity of the scene cannot be reproduced are solved, and the technical effects of improving the scene simulation quality and enabling the scene simulation to be more real and accurate are achieved.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. An intelligent ship collision avoidance automatic test scene generation method is applied to an automatic scene generation system, the automatic scene generation system is in communication connection with an environment creation module, a target creation module and a storage module, and the method comprises the following steps:
obtaining first simulation scene information through the environment creation module;
obtaining first visibility information of the first simulated scene;
acquiring basic information of a first ship and a second ship through the target creation module, and taking the basic information as first input information;
obtaining first captain information of a first ship, wherein the first captain information comprises first character information of the first captain;
obtaining first decision information according to the first character information and the first visibility information, and taking the first decision information as second input information;
inputting the first input information and the second input information into a first result evaluation model, wherein the first result evaluation model is obtained by training multiple groups of training data, and each group of the multiple groups of training data comprises the first input information, the second input information and identification information for identifying a first result;
obtaining a first output result of the first result evaluation model, the first output result comprising a first result of the first vessel after avoidance;
acquiring first simulation position information according to the first simulation scene information;
obtaining a first sea beast matching result according to the first simulation position information and the first visibility information;
correcting the first output result according to the first sea beast matching result to obtain second simulated scene information;
storing the second simulation scene information through the storage module;
wherein, the first sea beast matching result is obtained according to the first simulated position information and the first visibility information, and the method further comprises:
obtaining first sea beast information through the first simulation position;
obtaining first age information and first habit information of the first sea beast according to the first sea beast information;
performing first volume estimation on the first sea beast according to the first age information and the first habit information to obtain a first volume estimation result;
obtaining a first probability level based on the first habit information and the first visibility information, the first probability level being a level of probability that the first sea beast is present at the first vessel within a first predetermined range;
and judging whether to modify the first output result or not according to the first probability grade and the first volume estimation result.
2. The method of claim 1, wherein said obtaining a first level of probability from said first habit information and said first visibility information, further comprises:
obtaining a first active area of the first sea beast;
carrying out probability statistics on the occurrence times of the first sea beasts at different positions of the first activity area;
obtaining the intersection of the area of a first preset range of the first ship and the area of the first movable area, and obtaining a first probability according to the intersection of the areas;
obtaining a first noise level of the first ship;
matching the influence degree of the first sea beast according to the first noise level to obtain a first influence result;
and adjusting the first probability according to the first influence result to obtain a first probability level.
3. The method of claim 2, wherein the method comprises:
obtaining first volume information of the first ship according to the basic information of the first ship;
obtaining a danger coefficient of the first sea beast to the first ship according to the first volume estimation result and the first volume information;
obtaining a range rating, wherein the range rating is a range rating obtained according to a difference in distance from the first vessel;
and matching the range grades according to the risk coefficients to obtain a first matching result, wherein the first matching result comprises the first preset range.
4. The method as claimed in claim 1, wherein said obtaining first decision information based on said first personality information and said first visibility information, said first decision information being taken as a second input information, said method further comprising:
obtaining a first time when the first ship discovers the second ship according to the first visibility information;
obtaining second time for executing a first decision result according to the first character information of the first captain;
and obtaining time difference information of the second time and the first time, and taking the time difference information and the first decision result as first decision information.
5. The method of claim 4, wherein the method further comprises:
obtaining a hungry state of the first sea beast at the first time;
obtaining first position information of the first sea beast in the first simulated scene according to the first habit information;
obtaining first route information of the first sea beast pursuing the first ship according to the first position information;
obtaining first speed information through the hunger state;
taking the hunger state, the first habit information, the first position information and the first speed information as basic information of the first sea beast;
when the judgment result is that the first output result is corrected, a first adding instruction is obtained;
adding the basic information into the first simulated scene information according to the first adding instruction;
and obtaining second simulated scene information, wherein the second simulated scene information comprises the first simulated scene information and information for correcting the first output result after the basic information is added.
6. The method of claim 5, wherein the obtaining first speed information by the starvation status, the method further comprising:
obtaining a first collection instruction;
collecting parameters of the first sea beasts according to the first collection instruction, and constructing a hunger state database according to the collected parameters, wherein the hunger state database comprises different predation speeds of the first sea beasts in different hunger states;
obtaining, by the hungry status database, a predetermined hungry status threshold, wherein the predetermined hungry status threshold comprises a first threshold and a second threshold, wherein the first threshold is higher than the second threshold;
judging the relation between the hunger state and the first threshold value and the second threshold value;
when the hungry state is between the first threshold and the second threshold, performing up-regulation processing on the first speed information according to the hungry state database.
7. An automatic test scene generation system for intelligent ship collision avoidance, wherein the system comprises:
a first obtaining unit, configured to obtain first simulated scene information through an environment creation module;
a second obtaining unit, configured to obtain first visibility information of the first simulated scene;
a third obtaining unit, configured to obtain basic information of the first ship and the second ship through the target creating module, and use the basic information as first input information;
a fourth obtaining unit configured to obtain first captain information of a first ship, the first captain information including first character information of the first captain;
a fifth obtaining unit, configured to obtain first decision information according to the first personality information and the first visibility information, and use the first decision information as second input information;
a first input unit, configured to input the first input information and the second input information into a first result evaluation model, where the first result evaluation model is obtained by training multiple sets of training data, and each of the multiple sets of training data includes the first input information, the second input information, and identification information that identifies a first result;
a sixth obtaining unit configured to obtain a first output result of the first result evaluation model, where the first output result includes a first result of the first vessel after avoidance;
a seventh obtaining unit, configured to obtain first simulated position information according to the first simulated scene information;
an eighth obtaining unit, configured to obtain a first sea beast matching result according to the first simulated position information and the first visibility information;
a ninth obtaining unit, configured to correct the first output result according to the first beast matching result, and obtain second simulated scene information;
the first storage unit is used for storing the second simulation scene information through a storage module;
a tenth obtaining unit, configured to obtain first sea beast information through the first simulated position;
an eleventh obtaining unit configured to obtain first age information and first habit information of the first sea beast from the first sea beast information;
a twelfth obtaining unit, configured to perform first volume estimation on the first sea beast according to the first age information and the first habit information, and obtain a first volume estimation result;
a thirteenth obtaining unit for obtaining a first probability level according to the first habit information and the first visibility information, the first probability level being a probability level of the first sea animal appearing in a first predetermined range of the first vessel;
a first judging unit, configured to judge whether to perform modification processing on the first output result according to the first probability level and the first volume estimation result.
8. An intelligent ship collision avoidance automatic test scenario generation system, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210269782.3A CN114664118B (en) | 2022-03-18 | 2022-03-18 | Intelligent ship collision avoidance automatic test scene generation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210269782.3A CN114664118B (en) | 2022-03-18 | 2022-03-18 | Intelligent ship collision avoidance automatic test scene generation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114664118A CN114664118A (en) | 2022-06-24 |
| CN114664118B true CN114664118B (en) | 2023-04-07 |
Family
ID=82029682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210269782.3A Active CN114664118B (en) | 2022-03-18 | 2022-03-18 | Intelligent ship collision avoidance automatic test scene generation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114664118B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050136B (en) * | 2023-01-28 | 2023-07-21 | 中国船级社 | Method, device and equipment for generating intelligent ship test scene library |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103650016A (en) * | 2011-05-23 | 2014-03-19 | 离子地球物理公司 | Marine threat monitoring and defense system |
| CN105390029A (en) * | 2015-11-06 | 2016-03-09 | 武汉理工大学 | Ship collision avoidance assisted decision-making method and system based on track fusion and track prediction |
| CN109298712A (en) * | 2018-10-19 | 2019-02-01 | 大连海事大学 | Unmanned ship autonomous collision avoidance decision method based on adaptive navigation situation learning |
| WO2019166748A1 (en) * | 2018-03-02 | 2019-09-06 | Airbus Defence And Space Sas | Systems and method for collision avoidance between aircraft or ships |
| CN110400491A (en) * | 2019-06-10 | 2019-11-01 | 北京海兰信数据科技股份有限公司 | A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system |
| CN110422272A (en) * | 2012-05-30 | 2019-11-08 | 赛创尼克株式会社 | The control method monitored by the real-time measurement to marine structure |
| CN113093721A (en) * | 2021-02-04 | 2021-07-09 | 中国船级社 | Automatic concurrent ship collision avoidance testing method and system |
| CN113268850A (en) * | 2021-04-08 | 2021-08-17 | 武汉理工大学 | Dam-crossing ship traffic high-precision simulation method based on multiple intelligent agents and cellular automata |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002222500A (en) * | 2001-01-25 | 2002-08-09 | Univ Nihon | Ship Collision Avoidance System Using Genetic Algorithm |
| CN102236974B (en) * | 2011-03-18 | 2013-11-06 | 重庆大学 | Intelligent auxiliary command system and method for controlling passage of ship in river reach |
| JP6959799B2 (en) * | 2017-08-31 | 2021-11-05 | 川崎重工業株式会社 | Judgment device and judgment method |
| KR102215520B1 (en) * | 2018-09-13 | 2021-02-15 | 주식회사 웨더아이 | Method and server for providing course information of vessel including coast weather information |
| CN110341877B (en) * | 2019-06-04 | 2020-07-03 | 智慧航海（青岛）科技有限公司 | Distributed simulation test system and method for intelligent ship autonomous collision avoidance |
| TWI725677B (en) * | 2019-12-20 | 2021-04-21 | 財團法人船舶暨海洋產業研發中心 | Autonomous vessel simulation system and operating method thereof |
| WO2021161696A1 (en) * | 2020-02-12 | 2021-08-19 | 古野電気株式会社 | Seaway planning device, seaway planning method, and program |
| CN111400864B (en) * | 2020-02-12 | 2022-06-17 | 武汉理工大学 | An optimization method for ship collision avoidance decision-making based on prospect theory |
| CN112560286B (en) * | 2020-12-25 | 2022-07-19 | 武汉理工大学 | A Ship Collision Risk Determination Method Based on Digital Ship Domain Model |
| CN113076338B (en) * | 2021-02-04 | 2023-02-28 | 中国船级社 | Rule-based intelligent ship collision avoidance automatic test scene generation method and system |
| CN113096446B (en) * | 2021-03-30 | 2022-05-03 | 武汉理工大学 | Multi-ship collision avoidance decision-making method, storage medium and processor in mixed navigation scenarios |
-
2022
- 2022-03-18 CN CN202210269782.3A patent/CN114664118B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103650016A (en) * | 2011-05-23 | 2014-03-19 | 离子地球物理公司 | Marine threat monitoring and defense system |
| CN110422272A (en) * | 2012-05-30 | 2019-11-08 | 赛创尼克株式会社 | The control method monitored by the real-time measurement to marine structure |
| CN105390029A (en) * | 2015-11-06 | 2016-03-09 | 武汉理工大学 | Ship collision avoidance assisted decision-making method and system based on track fusion and track prediction |
| WO2019166748A1 (en) * | 2018-03-02 | 2019-09-06 | Airbus Defence And Space Sas | Systems and method for collision avoidance between aircraft or ships |
| CN109298712A (en) * | 2018-10-19 | 2019-02-01 | 大连海事大学 | Unmanned ship autonomous collision avoidance decision method based on adaptive navigation situation learning |
| CN110400491A (en) * | 2019-06-10 | 2019-11-01 | 北京海兰信数据科技股份有限公司 | A kind of Open sea area multiple target auxiliary Decision of Collision Avoidance method and decision system |
| CN113093721A (en) * | 2021-02-04 | 2021-07-09 | 中国船级社 | Automatic concurrent ship collision avoidance testing method and system |
| CN113268850A (en) * | 2021-04-08 | 2021-08-17 | 武汉理工大学 | Dam-crossing ship traffic high-precision simulation method based on multiple intelligent agents and cellular automata |
Non-Patent Citations (1)
| Title |
|---|
| 基于天牛须搜索算法的多船避碰决策方法;刘朝等;《武汉理工大学学报》;第45卷(第5期);第1000-1004页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114664118A (en) | 2022-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220204020A1 (en) | Toward simulation of driver behavior in driving automation | |
| CN110688729B (en) | LSTM-IDM car-following characteristic fusion method, storage medium and equipment based on adaptive Kalman filter | |
| CN107256017B (en) | Route planning method and system | |
| CN114460941B (en) | Robot path planning method and system based on improved sparrow search algorithm | |
| CN114664118B (en) | Intelligent ship collision avoidance automatic test scene generation method and system | |
| CN111709468B (en) | Training method and device for directional artificial intelligence and storage medium | |
| CN112141098A (en) | Obstacle avoidance decision method and device for intelligent driving automobile | |
| CN115056776B (en) | An adaptive driver-following method considering perception process and driver behavior | |
| CN117784615B (en) | Fire control system fault prediction method based on IMPA-RF | |
| CN112365359A (en) | Training method, device, equipment and storage medium for planting decision determination model | |
| CN111898682A (en) | Method and device for correcting new model based on multiple source models and computer equipment | |
| CN114492059A (en) | Method and device for situation assessment of multi-agent confrontation scenarios based on field energy | |
| CN114248780A (en) | IDM-LSTM combined following model establishing method considering driver style | |
| CN115546519B (en) | Matching method of image and millimeter wave radar target for extracting pseudo-image features | |
| CN113589810B (en) | Dynamic autonomous obstacle avoidance movement method and device for intelligent body, server and storage medium | |
| CN119671265A (en) | Ship behavior recognition and dynamic route planning method and system based on artificial intelligence | |
| CN118928464A (en) | Method and device for generating automatic driving decision based on hybrid expert model | |
| CN113269805A (en) | Remote sensing rainfall inversion training sample self-adaptive selection method guided by rainfall event | |
| CN115662163B (en) | ADAS and DSM-based active safety early warning method and system | |
| CN112698578A (en) | Automatic driving model training method and related equipment | |
| CN110866609A (en) | Interpretation information acquisition method, device, server and storage medium | |
| CN115984614A (en) | Image classification method and device, electronic equipment and storage medium | |
| CN113869186A (en) | Model training method and device, electronic equipment and computer readable storage medium | |
| Gross et al. | Sensory-based Robot Navigation using Self-organizing Networks and Q-learning | |
| CN110378460B (en) | Decision making method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230602 Address after: 710000 No. 705-706, Floor 7, Block A, Wangzuo Qujiang, Yanxiang Road, Qujiang New District, Xi'an, Shaanxi Patentee after: Xi'an Zhengshi Technology Co.,Ltd. Address before: 710061 room 1504, building 2, Qujiang e, Wangzuo, Yanxiang Road, Qujiang New District, Xi'an City, Shaanxi Province Patentee before: Shaanxi Zhengji Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |