CN119645034B - Unmanned ship path planning and collision avoidance decision-making method and system based on multi-factor fusion - Google Patents
Unmanned ship path planning and collision avoidance decision-making method and system based on multi-factor fusionInfo
- Publication number
- CN119645034B CN119645034B CN202411800413.8A CN202411800413A CN119645034B CN 119645034 B CN119645034 B CN 119645034B CN 202411800413 A CN202411800413 A CN 202411800413A CN 119645034 B CN119645034 B CN 119645034B
- Authority
- CN
- China
- Prior art keywords
- collision
- unmanned
- unmanned ship
- incentive
- path
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
本发明公开了一种基于多因素融合的无人船路径规划和避碰决策方法及系统。包括步骤S1：构建无人船多传感器融合感知网络，实时采集环境数据，并在无人船捕捉碰撞瞬间力学参数，使无人船对碰撞严重性进行感知识别；步骤S2：定义路径跟踪激励函数，并对路径控制过程中所需的动态参数进行适应性调整；步骤S3：设置静态障碍物和动态障碍物避碰的激励机制，对静态障碍物和动态障碍物的威胁程度进行评估；步骤S4：整合路径跟踪响应、静态障碍物和动态障碍物避碰激励机制，使无人船平衡不同任务目标之间的关系，进行多任务下的路径规划和避碰的决策。本发明提供的技术方案有效解决了无人船路径规划和避障的决策问题。
The present invention discloses a method and system for unmanned ship path planning and collision avoidance decision-making based on multi-factor fusion. The method comprises step S1: constructing a multi-sensor fusion perception network for the unmanned ship, collecting environmental data in real time, and capturing mechanical parameters at the moment of collision on the unmanned ship, so that the unmanned ship can perceive and identify the severity of the collision; step S2: defining a path tracking excitation function and adaptively adjusting the dynamic parameters required in the path control process; step S3: setting an incentive mechanism for collision avoidance of static and dynamic obstacles, and evaluating the threat level of static and dynamic obstacles; and step S4: integrating the path tracking response, static and dynamic obstacle collision avoidance incentive mechanism, so that the unmanned ship can balance the relationship between different mission objectives and make path planning and collision avoidance decisions under multiple tasks. The technical solution provided by the present invention effectively solves the decision-making problem of unmanned ship path planning and obstacle avoidance.
Description
Technical Field
The invention relates to the field of autonomous navigation control and path planning of unmanned surface vessels, in particular to an unmanned ship path planning and collision avoidance decision method and system based on multi-factor fusion.
Background
With the rapid development of technology, unmanned ships are increasingly widely used in the ocean field. In the military aspect, the unmanned ship can perform tasks such as reconnaissance, monitoring, anti-diving, anti-mine and the like, can replace a ship with a ship to perform tasks in a dangerous sea area, reduces casualties, improves combat effectiveness and strategic deterrence, has great potential in the civil field in aspects of marine resource exploration, environment monitoring, marine rescue, shipping assistance and the like, and can quickly arrive at an accident site in the marine rescue task, put rescue materials in or provide information support for rescue workers, and improves rescue efficiency.
Reinforcement learning is an important technical means for realizing autonomous navigation of unmanned ships, and the unmanned ships can constantly learn and optimize own behavior strategies according to environmental feedback so as to realize specific targets. However, in practical applications, the process of reinforcement learning faces a number of problems. For example, there is a high degree of complexity and dynamics in terms of inadequate adaptation to complex marine environments, including varying sea conditions (e.g., ocean waves, ocean currents, wind speeds, etc.), different geographical areas (e.g., ports, narrow waterways, open ocean areas, etc.), and various types of obstacles (static islands, reefs, buoys, and other vessels that are dynamic, etc.), conventional reinforcement learning approaches often employ fixed parameters and simple computational patterns that are difficult to accommodate such complex and varying environments, cooperative difficulties with multitasking targets, unmanned vessels are often required to simultaneously address multiple mission targets in actual operation, such as precise path tracking, efficient voyage speeds, safe obstacle avoidance, and satisfaction of mission-specific requirements (e.g., rapid response in rescue mission, accuracy of data in environmental monitoring mission, etc.), conventional approaches have difficulty in finding a reasonable balance between these interrelated and potentially conflicting targets, e.g., potential obstacles may be ignored when pursuing rapid path tracking, or result in greatly reduced voyage efficiency when overshadowing, while the lack of performance of the conventional approaches, and lack of immediate performance of changing the mission. For example, when sudden severe weather or temporarily occurring high priority tasks are encountered, conventional approaches fail to automatically adjust the incentive calculation strategy, so that unmanned ships cannot flexibly deal with the tasks, which may result in task failure or threatened navigation security.
Disclosure of Invention
Aiming at the defects of the related technology, the invention provides the unmanned ship path planning and collision avoidance decision method and system based on multi-factor fusion, which are used for improving the autonomous sailing performance of the unmanned ship, so that the unmanned ship can efficiently and safely execute diversified tasks in a complex and changeable marine environment, and the traditional reinforcement learning process is improved and optimized to overcome the limitations of the prior art.
The technical scheme is as follows:
A multi-factor fusion-based unmanned ship path planning and collision avoidance decision method comprises the following steps:
Step S1, constructing an unmanned ship multi-sensor fusion sensing network, integrating GPS, laser radar, sonar and multispectral vision sensors, collecting environmental data in real time, deploying a high-voltage-sensitive piezoelectric impact sensor and a high-precision optical collision angle measuring instrument in a key collision area of an unmanned ship shell, and capturing a collision instant mechanical parameter to enable the unmanned ship to perform sensing identification on the collision severity;
Step S2, setting an excitation mechanism for the unmanned ship path tracking response, simulating the navigation process of the unmanned ship under various path deviation conditions, defining a path tracking excitation function, and adaptively adjusting dynamic parameters required in the path control process;
step S3, setting an excitation mechanism of static obstacle and dynamic obstacle collision avoidance, determining a static obstacle collision avoidance excitation function and a dynamic obstacle collision avoidance excitation function by using regression analysis and machine learning, and evaluating threat degrees of the static obstacle and the dynamic obstacle by continuously optimizing a sensor data processing algorithm and an excitation function calculation model;
and S4, integrating path tracking response, static obstacle and dynamic obstacle collision avoidance excitation mechanisms, fusing respective excitation functions into an organic whole, balancing the relationship among different task targets by the unmanned ship, and carrying out path planning and collision avoidance decision under multiple tasks.
The unmanned ship path planning and collision avoidance decision system based on the multi-factor fusion is used for realizing the unmanned ship path planning and collision avoidance decision method based on the multi-factor fusion, and comprises the following steps:
The unmanned ship multi-sensor fusion sensing network module is used for integrating GPS, laser radar, sonar and multispectral vision sensors, collecting environmental data in real time, deploying a high-voltage-sensitive piezoelectric impact sensor and a high-precision optical collision angle measuring instrument in a key collision area of an unmanned ship shell, and capturing the mechanical parameters at the moment of collision to enable the unmanned ship to perform sensing identification on the collision severity;
The unmanned ship path tracking response excitation module is used for simulating the navigation process of the unmanned ship under various path deviation conditions, defining a path tracking excitation function and adaptively adjusting dynamic parameters required in the path control process;
The unmanned ship static obstacle and dynamic obstacle collision avoidance excitation module is used for determining a static obstacle collision avoidance excitation function by using regression analysis and machine learning, and evaluating threat degrees of the static obstacle and the dynamic obstacle by continuously optimizing a sensor data processing algorithm and an excitation function calculation model;
The unmanned ship excitation integration module is used for integrating path tracking response, static barriers and dynamic barrier collision avoidance excitation mechanisms, integrating respective excitation functions into an organic whole, enabling the unmanned ship to balance the relation among different task targets, and making path planning and collision avoidance decisions under multiple tasks.
The invention has the following beneficial effects:
The unmanned ship path planning and collision avoidance decision-making method and system based on multi-factor fusion provided by the invention take the game conditions of path planning and obstacle collision avoidance in the running process of an unmanned ship into consideration, creatively propose to integrate path tracking response, static obstacle and dynamic obstacle collision avoidance excitation mechanisms into an organic adult, deeply lapping path tracking excitation in the process, fusing multiple functions and dynamic adaptation parameters, optimizing static obstacle collision avoidance excitation, fusing distance speed perception and multidimensional environment elements, comprehensively advancing dynamic obstacle collision avoidance excitation, deeply fusing COLREGs rules and intelligently regulating dynamic parameters and situation perception factors, systematically optimizing total excitation calculation, integrating multiple elements and realizing task guiding self-adaptive parameter adjustment, innovatively and synergistically acting each step, remarkably improving decision rationality, navigation safety and efficiency, collision avoidance success rate, task suitability and overall task efficiency of the unmanned ship for multi-task execution in a complex environment, and comprehensively enhancing comprehensive performance and adaptability of the unmanned ship.
Drawings
FIG. 1 is a flowchart of an unmanned ship path planning and collision avoidance decision method based on multi-factor fusion provided by an embodiment of the invention;
FIG. 2 is a flow chart of the unmanned ship for perceived recognition of crash severity provided by an embodiment of the present invention;
FIG. 3 is a flow chart of an incentive scheme provided by an embodiment of the present invention for setting up an unmanned ship path tracking response;
FIG. 4 is a flow chart of an excitation mechanism for setting static obstacle and dynamic obstacle collision avoidance for an unmanned ship according to an embodiment of the present invention;
fig. 5 is a block diagram of an unmanned ship path planning and collision avoidance decision system based on multi-factor fusion provided by an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
Referring to fig. 1, the invention provides an unmanned ship path planning and collision avoidance decision method based on multi-factor fusion, which comprises the following steps:
Step S1, constructing an unmanned ship multi-sensor fusion sensing network, integrating GPS, laser radar, sonar and multispectral vision sensors, collecting environmental data in real time, deploying a high-voltage-sensitive piezoelectric impact sensor and a high-precision optical collision angle measuring instrument in a key collision area of an unmanned ship shell, and capturing a collision instant mechanical parameter to enable the unmanned ship to perform sensing identification on the collision severity;
Step S2, setting an excitation mechanism for the unmanned ship path tracking response, simulating the navigation process of the unmanned ship under various path deviation conditions, defining a path tracking excitation function, and adaptively adjusting dynamic parameters required in the path control process;
step S3, setting an excitation mechanism of static obstacle and dynamic obstacle collision avoidance, determining a static obstacle collision avoidance excitation function and a dynamic obstacle collision avoidance excitation function by using regression analysis and machine learning, and evaluating threat degrees of the static obstacle and the dynamic obstacle by continuously optimizing a sensor data processing algorithm and an excitation function calculation model;
and S4, integrating path tracking response, static obstacle and dynamic obstacle collision avoidance excitation mechanisms, fusing respective excitation functions into an organic whole, balancing the relationship among different task targets by the unmanned ship, and carrying out path planning and collision avoidance decision under multiple tasks.
Referring to fig. 2, step S1, constructing an unmanned ship multi-sensor fusion sensing network, integrating a GPS, a laser radar, a sonar and a multispectral vision sensor, collecting environmental data in real time, deploying a high-sensitive piezoelectric impact sensor and a high-precision optical collision angle measuring instrument in a key collision area of an unmanned ship outer shell, capturing a collision instant mechanical parameter, and enabling the unmanned ship to perform sensing recognition on the collision severity, wherein the method specifically comprises the following steps:
step S11, a high-precision global positioning system, a laser radar, a sonar and a vision camera multi-type sensor are deployed on an unmanned ship to construct an omnibearing environment sensing system, a GPS is utilized to acquire accurate geographic position information of the ship, the laser radar and the sonar scan surrounding environment in real time, the position, the distance, the shape and other information of an obstacle are detected, and the vision camera provides visual image data for auxiliary judgment;
Step S12, installing a collision detection device formed by a high-sensitivity combined collision sensor based on a pressure sensor and an accelerometer at a key part of the unmanned ship, precisely measuring the impact force, the direction and the acting time at the moment of collision, further calculating a collision angle theta collision and a collision relative speed v collision, constructing a weighting function omega (theta collision) related to the collision angle by using a data fitting and machine learning algorithm based on a large amount of actual collision test data, and defining a collision excitation function The unmanned ship can perform perception recognition on the collision severity.
In one embodiment provided by the invention, for the frontal collision condition, a larger weighting value (such as 10) is given due to extremely high damage risk to the ship structure and equipment, for the side collision, a smaller weighting value (such as 5) is given due to relatively smaller damage degree, and the calculated collision angle and relative speed are substituted into a collision excitation function to obtain an accurate collision excitation value, so that a strong negative feedback signal is provided for an intelligent agent, and similar high-risk behaviors are avoided in subsequent decisions.
Referring to fig. 3, step S2 is to set an excitation mechanism for the unmanned ship path tracking response, simulate the navigation process of the unmanned ship under various path deviation conditions, define a path tracking excitation function, and adaptively adjust dynamic parameters required in the path control process, specifically:
S21, acquiring transverse error epsilon (t), speed u (t) and heading of the unmanned ship in real time through an inertial navigation system, a GPS and other sensors on the unmanned ship Information;
Step S22, combining an exponential excitation function exp (-gamma ε|ε(t) I) and a Gaussian excitation function Constructing simulation environments according to excitation characteristics in different path error ranges, simulating navigation processes of the unmanned ship under various path deviation conditions, recording and analyzing influences of two excitation functions on the path adjustment behavior of the unmanned ship, setting weights alpha for optimizing, finding alpha value combinations which can enable fusion performance of the two excitation functions to be optimal in different error intervals, designing an adjustment function kappa (epsilon (t)) related to transverse errors, dynamically adjusting the speed and the action intensity of a course excitation term according to the size of the transverse errors, and defining a path tracking excitation function to be:
Wherein gamma ε is a weight coefficient of the coincidence degree of the transverse error and the path, which is used for adjusting the control force, U max is the maximum driving speed of the unmanned ship, and the dynamic parameters required in the path control process are adaptively adjusted.
In one embodiment provided by the invention, the combined action of the exponential excitation function and the Gaussian excitation has an important effect on continuously changing excitation values based on distance (such as yaw error), can encourage the unmanned ship to gradually converge to a desired state, and enables the excitation function to change smoothly and reasonably under different path deviations and ship motion states according to the characteristic of the continuously changing and combined with the speed and heading factors introduced by the unmanned ship. For example, in the process of approaching the unmanned ship from a larger path deviation to an accurate path, the weight of the excitation term based on the speed and the course is better adjusted according to the gradual change characteristic of the combination of the exponential excitation function and the Gaussian excitation, so that the ship can quickly approach the path in the adjustment process and can keep a stable motion state.
In one embodiment of the invention, when the transverse error sensor detects that the I epsilon (t) I is more than or equal to 5, the path deviation is larger, a preset parameter adjustment algorithm is started, the value of gamma ε is increased from 0.5 to 0.8, correction force on transverse errors is enhanced, unmanned ships are enabled to rapidly adjust course and speed, when the I epsilon (t) I is less than or equal to 1, gamma ε is automatically reduced to 0.2 to enable an intelligent agent to keep stable when approaching a path, the type of sea area where the unmanned ships are located is judged according to sea area information or feedback of terrain detection sonar provided by an electronic chart system, sigma=10 in Gaussian excitation is set for giving larger exploration space and capability of coping with environmental changes to the unmanned ships in open sea area, sigma is reduced to 2 in a narrow water channel or high-precision path requirement area, accuracy requirements of path tracking are improved, meanwhile, when the speed of the speed sensor monitors the ship is real-time, when the speed is (t)<0.5Umax, the preset speed is considered to be lower, the speed is enabled to pass through the preset excitation weight item, and the speed is enabled to keep good when the speed is increased by the speed is not encouraging the ship to have the condition of 0.3, and the speed of the tracking performance of the unmanned ships is not enabled to be increased when the speed is not to be equal to the speed is increased by the proper, and the speed is not encouraging the speed is increased by the speed regulation of the speed item 0.
Referring to fig. 4, step S3 is to set an excitation mechanism of static obstacle and dynamic obstacle collision avoidance, determine static obstacle collision avoidance and dynamic obstacle collision avoidance excitation functions by using regression analysis and machine learning, and evaluate threat degrees of the static obstacle and the dynamic obstacle by continuously optimizing a sensor data processing algorithm and an excitation function calculation model, specifically:
Step S31, high-precision laser range finder, doppler radar range finding and speed measuring sensor are arranged on the unmanned ship, and the range change rate between the unmanned ship and the static obstacle is accurately measured in real time Combining with the analysis of a large amount of actual navigation data, determining a weighting coefficient beta by using regression analysis and a machine learning algorithm, and simultaneously acquiring the included angle between the current heading of the unmanned ship and the direction of the obstacle through a ship heading sensor, a steering angle sensor, a water flow sensor and electronic compass equipmentThe ship steering capability parameter omega turn, the water flow speed v current and the direction theta current are used for constructing a static obstacle collision avoidance excitation function together with the obstacle distance x and the angle theta information of the unmanned ship and the obstacle:
Wherein gamma θ,stat is a parameter related to the relative angle of the unmanned ship and the static obstacle, through which the weight of the excitation calculation can be adjusted according to the difference of the relative angle, when the relative angle is positioned right in front, the value of the term is reduced, so that the whole excitation value is reduced, the importance of collision prevention is enhanced, delta is a coefficient for weighting factors related to the position of the static obstacle, gamma x is a distance weighting index, beta is a space change rate weighting coefficient, χ is a ship speed weighting coefficient, Is the steering capability weighting coefficient.
In one embodiment provided by the invention, when the water flow direction is consistent with the direction of the ship towards the obstacle (the included angle between the water flow direction and the ship heading is smaller) and the water flow speed is larger, the excitation term is properly increased through a preset water flow influence compensation algorithm to compensate the influence of the water flow on the speed of the ship approaching the obstacle, and when the steering capacity of the ship is limited (smaller), the excitation weight related to the steering capacity is increased, so that the unmanned ship is promoted to plan a more reasonable collision avoidance path in advance.
Step S32, based on AIS data, radar image recognition and machine learning target classification technology, grasping the condition of a dynamic obstacle target in an unmanned ship navigation area, and optimizing weighting parameters gamma right、γleft and gamma back of the dynamic obstacle approaching the unmanned ship in a starboard area, a port area and a stern area according to COLREGs rules and the azimuth and the speed of the unmanned ship in real time;
In one embodiment provided by the invention, when a dynamic obstacle approaches an unmanned ship from a starboard, the influence weight of the area obstacle on an excitation function is adjusted according to factors such as distance, when the starboard approach target ship approaches, for example, the distance is smaller than 80 meters, gamma right is increased from 0.5 to 0.95, the decision weight of starboard area collision avoidance is greatly increased, USV is caused to take avoidance action preferentially on the target ship approaching from the starboard, the requirement on starboard collision avoidance in COLREGs rule is met, when the dynamic obstacle is in a cross meeting situation, for example, the speed of the dynamic obstacle on the port side is larger than 0.5 times of the maximum speed, and the distance between the dynamic obstacle and the unmanned ship is between 60 meters and 180 meters, gamma left is finely increased, the proper reaction to the dynamic obstacle in the port direction is ensured in a cross scene, the balance between safe collision avoidance and efficient navigation is realized, when the dynamic obstacle approaches from the ship tail rapidly, the value of gamma back is increased, the weight of the obstacle in the excitation function is enhanced, the unmanned ship can perceive the collision avoidance action in time, and dangerous accident prevention measures are effectively taken after the unmanned ship encounters the ship.
Step S33, defining a factor xi (v target,x,θrelative,ωUSV) of dynamic collision avoidance excitation to improve collision avoidance success rate of dynamic obstacle, and defining by analyzing a large amount of actual navigation dataWhere v target is the speed of the dynamic obstacle, x is the relative distance of the unmanned ship from the dynamic obstacle, θ relative is the relative azimuth angle of the unmanned ship from the dynamic obstacle, ω USV is the cornering ability of the unmanned ship;
step S34, constructing a dynamic obstacle collision avoidance excitation function:
Wherein γ θ,dyn is a parameter related to the relative angle of the dynamic obstacle, which can adjust the weight of the term in the excitation calculation according to the difference of the relative angle of the target ship, v y is the velocity component of the dynamic obstacle in the unmanned ship driving direction, and ζ v(θ,vy) is a velocity component weighting parameter based on the angle and the velocity of the dynamic obstacle, which is specifically a piecewise function:
Whereas η 1、η2 and η 3 are constant weighting factors, respectively, representing COLREGs rule compliance level C rules andIs a weight of (2).
S4, integrating path tracking response, static obstacle and dynamic obstacle collision avoidance excitation mechanisms, fusing respective excitation functions into an organic whole, enabling the unmanned ship to balance the relation among different task targets, and making path planning and collision avoidance decision under the condition of multitasking, wherein the method specifically comprises the following steps:
integrating path tracking response, static obstacle and dynamic obstacle collision prevention excitation mechanism, and fusing respective excitation functions into an organic whole, wherein the whole excitation functions are as follows:
Wherein lambda (t) is the weight related to path tracking, and dynamically changes according to different path tracking factors, the role of the lambda (t) is to determine the relative importance of path tracking excitation according to the current situation when calculating total excitation, and 1-lambda (t) represents the game between the path and obstacle collision prevention excitation; Is an additional incentive to include information related to environmental stability, task priority, etc., in terms of environmental stability, if the sea conditions are good, the water flow stability is favorable for the appearance of environmental factors for sailing, In the aspect of task priority, if the currently executed task is an emergency rescue task and the behavior of the unmanned ship helps to improve rescue efficiency, the part related to environmental stability is given a positive incentive, and the positive incentive is given according to the task priority.
In one embodiment provided by the invention, different scene characteristic data comprise typical characteristics such as ports, narrow waterways, open sea areas and the like, after the scene types are determined, the weighting coefficients are initialized to corresponding values according to a preset scene and weighting coefficient mapping table, lambda (t) is set to be a lower value (such as 0.2) under the complex port environment or the narrow waterway scene due to dense obstacles and limited space, importance of collision avoidance excitation is highlighted, and a higher value (such as 0.8) is set in the open and barrier-free sea area scene, so that the basis guidance is provided for subsequent decision focusing on path tracking excitation.
In the embodiment provided by the invention, when the unmanned ship is in an emergency rescue task, the unmanned ship can place a rapid arrival target and safety collision prevention at the primary position according to the task characteristics and parameter adjustment strategies, so that the rescue efficiency is effectively improved, the unmanned ship can obviously shorten the rescue time and increase the probability of successful rescue on the premise of ensuring safety by precisely improving the speed excitation weight and strengthening the obstacle excitation strength of a key area, and the execution efficiency of the emergency rescue task is greatly improved. For example, in the offshore rescue operation, the unmanned ship can quickly pass through the open sea according to the adjusted excitation function, and when approaching the accident scene, the unmanned ship quickly reaches the rescue site by virtue of high vigilance and effective collision avoidance to the obstacle in the key area, so that the survival probability of trapped personnel is improved.
In the embodiment provided by the invention, when the unmanned ship is in a material transportation task, the stable operation and the cargo safety of the ship in the whole transportation process are ensured, the cargo damage risk is reduced, the material transportation integrity is ensured, the ship shaking and cargo displacement risks caused by improper operation of the unmanned ship are effectively inhibited by reasonably reducing the speed excitation weight, increasing the stable sailing excitation and increasing the excitation force affecting the cargo safety operation, the cargo damage possibility in the transportation process is reduced, the cargo can be completely and safely delivered to a destination, and the solid guarantee is provided for the smooth completion of the material transportation task. For example, in long distance material transportation, unmanned ship can keep stable speed and less course adjustment, avoid collision, damage or shift of goods because of violent ship motion, ensure that quality and the quantity of material are not influenced.
In the embodiment provided by the invention, when the unmanned ship aims at a marine monitoring task, the unmanned ship can efficiently carry out monitoring work in a wide marine area, reasonably balances the monitoring range, navigation safety, data quality and other factors, and actively explores more areas and maintains a good navigation state to obtain high-quality monitoring data by expanding the exploration area excitation range, improving the sensor data quality excitation weight and the excitation measures for the bad navigation state, thereby obviously improving the effect and quality of marine monitoring, providing richer and accurate data support for the fields of marine scientific research, environmental protection, resource exploration and the like, and powerfully pushing the development and decision making of the related fields. For example, in a large-area marine monitoring task, the unmanned ship can expand the monitoring range according to the optimized excitation function on the premise of ensuring the accuracy of sensor data, acquire more information about marine environment, ecology and the like, and provide scientific basis for reasonable development of marine resources and formulation of environmental protection policies.
Referring to fig. 5, the present invention provides an unmanned ship path planning and collision avoidance decision system 100 based on multi-factor fusion, which includes:
The unmanned ship multi-sensor fusion sensing network module 101 is used for integrating GPS, laser radar, sonar and multispectral vision sensors, collecting environmental data in real time, deploying a high-voltage-sensitive piezoelectric impact sensor and a high-precision optical collision angle measuring instrument in a key collision area of the unmanned ship outer shell, and capturing the instant mechanical parameters of collision to enable the unmanned ship to perform sensing identification on the severity of collision;
The unmanned ship path tracking response excitation module 102 is used for simulating the navigation process of the unmanned ship under various path deviation conditions, defining a path tracking excitation function and adaptively adjusting dynamic parameters required in the path control process;
The unmanned ship static obstacle and dynamic obstacle collision avoidance excitation module 103 is used for determining a static obstacle collision avoidance excitation function by using regression analysis and machine learning, and evaluating threat degrees of the static obstacle and the dynamic obstacle by continuously optimizing a sensor data processing algorithm and an excitation function calculation model;
the unmanned ship excitation integration module 104 is used for integrating path tracking response, static obstacle and dynamic obstacle collision avoidance excitation mechanism, and integrating respective excitation functions into an organic whole, so that the unmanned ship balances the relation among different task targets and makes path planning and collision avoidance decision under multiple tasks.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411800413.8A CN119645034B (en) | 2024-12-09 | 2024-12-09 | Unmanned ship path planning and collision avoidance decision-making method and system based on multi-factor fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411800413.8A CN119645034B (en) | 2024-12-09 | 2024-12-09 | Unmanned ship path planning and collision avoidance decision-making method and system based on multi-factor fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119645034A CN119645034A (en) | 2025-03-18 |
| CN119645034B true CN119645034B (en) | 2025-09-26 |
Family
ID=94958108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411800413.8A Active CN119645034B (en) | 2024-12-09 | 2024-12-09 | Unmanned ship path planning and collision avoidance decision-making method and system based on multi-factor fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119645034B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120405071B (en) * | 2025-07-01 | 2025-09-05 | 盐城工学院 | Water quality monitoring unmanned ship system and method based on multi-sensor fusion |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107577230A (en) * | 2017-08-16 | 2018-01-12 | 武汉理工大学 | A kind of intelligent avoidance collision system towards unmanned boat |
| CN107748561A (en) * | 2017-09-25 | 2018-03-02 | 华南理工大学 | A kind of unmanned boat part obstacle avoidance system and method based on more parameter sensings |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8380367B2 (en) * | 2009-03-26 | 2013-02-19 | The University Of North Dakota | Adaptive surveillance and guidance system for vehicle collision avoidance and interception |
| US8849483B2 (en) * | 2011-04-13 | 2014-09-30 | California Institute Of Technology | Target trailing with safe navigation with colregs for maritime autonomous surface vehicles |
| US9420958B2 (en) * | 2013-03-15 | 2016-08-23 | Honda Motor Co., Ltd. | System and method for determining changes in a body state |
| CN113485441B (en) * | 2021-08-03 | 2024-08-20 | 国网江苏省电力有限公司泰州供电分公司 | Distribution network inspection method combining unmanned aerial vehicle high-precision positioning and visual tracking technology |
| CN114407931B (en) * | 2022-02-21 | 2024-05-03 | 东南大学 | A highly human-like safe driving decision-making method for autonomous driving commercial vehicles |
| CN116909280B (en) * | 2023-07-20 | 2024-09-13 | 山东科技大学 | Reinforced learning double-layer decision AGV obstacle avoidance method based on visual perception |
| CN118565475A (en) * | 2024-05-16 | 2024-08-30 | 中水珠江规划勘测设计有限公司 | Collaborative navigation system of unmanned ship and underwater robot with dynamic environment adaptation |
| CN118349006A (en) * | 2024-05-24 | 2024-07-16 | 北京矽力科技有限公司 | Mobile robot path planning method in dynamic environment |
-
2024
- 2024-12-09 CN CN202411800413.8A patent/CN119645034B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107577230A (en) * | 2017-08-16 | 2018-01-12 | 武汉理工大学 | A kind of intelligent avoidance collision system towards unmanned boat |
| CN107748561A (en) * | 2017-09-25 | 2018-03-02 | 华南理工大学 | A kind of unmanned boat part obstacle avoidance system and method based on more parameter sensings |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119645034A (en) | 2025-03-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119645034B (en) | Unmanned ship path planning and collision avoidance decision-making method and system based on multi-factor fusion | |
| CN109960262B (en) | Unmanned ship dynamic obstacle avoidance method and system based on geometric method | |
| CN111273670B (en) | Unmanned ship collision prevention method for fast moving obstacle | |
| CN113744570B (en) | Method and device for ship collision avoidance early warning in bridge area waters | |
| Wu et al. | An overview of developments and challenges for unmanned surface vehicle autonomous berthing | |
| Caccia et al. | A practical approach to modeling and identification of small autonomous surface craft | |
| Liu et al. | Cooperative ship formation system and control methods in the ship lock waterway | |
| US20240271943A1 (en) | Assisted navigation systems and methods | |
| CN110837255A (en) | Autonomous danger avoiding method suitable for high-speed water surface unmanned ship | |
| Zhuang et al. | Navigating high‐speed unmanned surface vehicles: System approach and validations | |
| CN119197526A (en) | A method for dynamic ship path adjustment combining visual navigation and radar data | |
| CN120057221B (en) | Wireless monitoring alarm system and method applied to amphibious ship | |
| CN113687349A (en) | Unmanned ship sea surface target tracking method and device based on multi-sensor fusion | |
| CN109765914A (en) | A collision avoidance method for surface unmanned boats based on sliding window particle swarm | |
| CN119356348A (en) | A method for controlling unmanned boat cooperative formation | |
| JP2025511561A (en) | Autonomous Berthing/Unberthing Test Method and System for Unmanned Commercial Ships | |
| Wu et al. | Multi-vessels collision avoidance strategy for autonomous surface vehicles based on genetic algorithm in congested port environment | |
| CN117666557A (en) | An unmanned boat path planning algorithm for ocean current interference | |
| CN113934159A (en) | Unmanned ship reliability test environment model construction method | |
| CN120178923A (en) | Underwater thruster intelligent obstacle avoidance system and control method thereof | |
| EP3420312B1 (en) | Fluid vehicle route optimisation | |
| CN113625723B (en) | A dynamic collision avoidance control system for unmanned ships | |
| CN115731744A (en) | Ship collision avoidance decision-making method based on data fusion trajectory prediction | |
| CN117647981B (en) | Unmanned ship intelligent navigation control method, device and equipment | |
| Ivanovsky et al. | Algorithm design for ship’s steering with specified limitations under various weather conditions |
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 |