An unmanned ship laser ranging optimization method and system based on dynamic environment perception

Abstract

The present invention provides an unmanned ship laser ranging optimization method and system based on dynamic environment perception, which relates to the field of navigation and obstacle avoidance technology of unmanned ships. The method includes: sensing the surrounding environment data in real time through sensors to obtain obstacle position, speed and heading information; based on the dynamic characteristics of the environment, using an adaptive algorithm to dynamically adjust the measurement frequency and angle of the laser rangefinder to optimize the measurement accuracy; combining the environmental data with the laser ranging results, using a path planning algorithm to optimize the obstacle avoidance route, and adjusting the heading in real time; adjusting the laser ranging parameters according to dynamic feedback information to ensure the stability of navigation and obstacle avoidance performance. The present invention can effectively improve the laser ranging accuracy of unmanned ships in complex dynamic environments, optimize navigation safety and obstacle avoidance capabilities, and has broad application prospects.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation and obstacle avoidance of unmanned ships, and in particular to an unmanned ship laser ranging optimization method and system based on dynamic environment perception. Background Art

[0002] With the development of unmanned ship technology, unmanned ships have been widely used in marine transportation, environmental monitoring, military reconnaissance, marine scientific research and other fields. The autonomous navigation and obstacle avoidance capabilities of unmanned ships are the key to their safe and efficient operation. However, in actual applications, unmanned ships need to cope with complex and changeable marine environments, including sea surface fluctuations, uneven distribution of obstacles, interference from dynamic objects, etc. The traditional navigation and obstacle avoidance methods based on a single sensor can no longer meet the requirements for high precision, high efficiency and real-time performance.

[0003] As an accurate distance measurement technology, laser ranging has been widely used in environmental perception and navigation control of unmanned ships. However, due to the influence of complex environmental factors (such as obstacles, sea surface fluctuations, etc.), the accuracy of laser ranging is often disturbed, especially in highly dynamic or highly complex environments, the reliability and accuracy of laser ranging data are easily reduced. In addition, traditional laser ranging algorithms are usually difficult to dynamically adjust parameters according to real-time environmental changes, resulting in a decrease in ranging accuracy, which in turn affects path planning and navigation control.

[0004] At present, many path planning methods mainly focus on navigation control based on static environments, ignoring the impact of dynamic obstacles, and most algorithms use the input of a single sensor, resulting in limited navigation performance in dynamic environments. In order to improve the autonomous navigation capabilities of unmanned ships in complex environments, researchers have begun to explore the combined application of technologies such as multi-sensor fusion, dynamic environment modeling, and real-time path planning. However, existing technologies have not been able to effectively solve key issues such as real-time detection and trajectory prediction of dynamic obstacles and optimization of ranging accuracy.

[0005] Therefore, how to optimize the laser ranging accuracy in real time based on multi-sensor data fusion technology in a complex dynamic environment, and combine the dynamic environment model for path planning, has become an urgent need to improve the autonomous obstacle avoidance and navigation capabilities of unmanned ships. Based on this demand, the present invention proposes an unmanned ship laser ranging optimization method based on dynamic environment perception, which solves many problems in the prior art by integrating laser ranging, visual sensing, sonar and radar equipment, and combining dynamic environment models with path planning algorithms, and has important technical innovation significance and application value. Summary of the invention

[0006] In order to solve the technical problems in the prior art that the laser ranging accuracy is disturbed by environmental factors, the dynamic obstacle detection is inaccurate, and the path planning efficiency is low, the present invention provides an unmanned ship laser ranging optimization method and system based on dynamic environment perception.

[0007] The technical solution provided by the present invention is as follows:

[0008] First aspect:

[0009] The present invention provides an unmanned ship laser ranging optimization method based on dynamic environment perception, comprising:

[0010] S1. The laser rangefinder, visual sensor, sonar device and radar device carried by the unmanned ship collect the surrounding environment data in real time. The data includes sea surface fluctuation information, obstacle location and motion trajectory of dynamic objects. All collected environmental data are processed by multi-sensor fusion algorithm to remove noise and integrate them into unified environmental status information for subsequent dynamic model construction.

[0011] S2. Based on the environmental data collected in real time, a dynamic environmental model is established. The dynamic environmental model combines the fixed position of the static obstacles and the motion trajectory of the dynamic obstacles, estimates the future position of the dynamic obstacles through a prediction algorithm, and calculates the potential collision risk area through dynamic path planning;

[0012] S3. According to the dynamic environment perception data and the dynamic environment model, optimization is performed by adjusting the working parameters of the laser ranging, specifically including: adjusting the laser beam emission angle and frequency according to the environmental complexity to enhance the measurement accuracy, and when a dynamic obstacle approaches, giving priority to optimizing the ranging accuracy of the area to reduce the impact of the ranging dead zone, wherein the environmental complexity specifically includes the number of obstacles, the uncertainty of obstacle movement, and the amplitude of sea surface fluctuation;

[0013] S4. Feedback the optimized laser ranging data to the navigation control system of the unmanned ship to provide high-precision real-time navigation information. According to the current position and route planning of the unmanned ship, the path planning algorithm is used to adjust the heading to avoid collision with obstacles and optimize the navigation route in real time.

[0014] Furthermore, the environmental complexity ECP is calculated based on the number of obstacles, the complexity of dynamic object behavior and sea surface fluctuations, and a range adjustment coefficient RAC is introduced as a coefficient for adjusting the laser ranging accuracy according to the environmental perception result.

[0015] Second aspect:

[0016] The present invention provides an unmanned ship laser ranging optimization system based on dynamic environment perception, comprising:

[0017] processor;

[0018] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the unmanned ship laser ranging optimization method based on dynamic environment perception as described in the first aspect is implemented.

[0019] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0020] (1) In the present invention, by fusing multiple sensor data (laser ranging, vision, sonar and radar), the present invention can dynamically adjust the working parameters of laser ranging, such as the laser beam emission angle and frequency, so as to optimize the ranging accuracy according to the complexity of the environment. In particular, when dynamic obstacles are approaching, the ranging accuracy of these areas is optimized first, thereby reducing the impact of ranging dead zones. This measure significantly improves the ranging accuracy of unmanned ships in complex marine environments and ensures that the navigation system can obtain high-quality data in real time.

[0021] (2) In the present invention, by establishing a dynamic environment model, combining static and dynamic obstacle information, and using a prediction algorithm to estimate the future position of dynamic objects, potential collision risk areas can be effectively identified and path planning can be optimized. This real-time path adjustment mechanism based on dynamic environment perception can enable the unmanned ship to respond quickly in complex environments, avoid collisions with obstacles, and improve the unmanned ship's autonomous obstacle avoidance capability;

[0022] (3) In the present invention, on the basis of optimizing the laser ranging data, the present invention further feeds back the processed data to the navigation control system of the unmanned ship, and adjusts the heading in real time through the path planning algorithm. This adaptive optimization mechanism enables the unmanned ship to adjust the navigation route according to the real-time data, reduce energy consumption and navigation time, and enhance navigation safety, providing efficient and accurate navigation support under various environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic diagram of a flow chart of an unmanned ship laser ranging optimization method based on dynamic environment perception provided by an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of the structure of an unmanned ship laser ranging optimization system based on dynamic environment perception provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0027] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0028] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0029] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0030] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0031] Reference Manual Attached Figure 1 , showing a flow chart of an unmanned ship laser ranging optimization method based on dynamic environment perception provided by an embodiment of the present invention.

[0032] The embodiment of the present invention provides an unmanned ship laser ranging optimization method based on dynamic environment perception, which can be implemented by an unmanned ship laser ranging optimization device based on dynamic environment perception, which can be a terminal or a server. The processing flow of the unmanned ship laser ranging optimization method based on dynamic environment perception can include the following steps:

[0033] S1. The laser ranging sensors, visual sensors, sonar equipment and radar equipment carried by the unmanned ship collect the surrounding environment data in real time. The data includes sea surface fluctuation information, obstacle locations and motion trajectories of dynamic objects. All collected environmental data are processed by a multi-sensor fusion algorithm to remove noise and integrate them into unified environmental status information for subsequent dynamic model construction.

[0034] It should be noted that the unmanned ship collects data about the surrounding environment in real time through the laser ranging sensors, visual sensors, sonar equipment and radar equipment it carries. Different types of sensors can provide information about sea surface fluctuations, the location of static obstacles, and the movement trajectory of dynamic objects. The data provided by these various sensors have their own characteristics, but they are also affected by noise and environmental interference. Therefore, they need to be processed by multi-sensor fusion algorithms to remove noise and integrate them into unified environmental status information. Through data fusion, the system can obtain more accurate and consistent environmental perception results, which lays the foundation for the construction of dynamic models in subsequent steps, ensuring that the system can fully understand the current environmental conditions.

[0035] S2. A dynamic environment model is established based on the environmental data collected in real time. The dynamic environment model combines the fixed position of static obstacles and the motion trajectory of dynamic obstacles, estimates the future position of dynamic obstacles through a prediction algorithm, and calculates potential collision risk areas through dynamic path planning.

[0036] It should be noted that the system establishes a dynamic environment model using the real-time environmental data obtained from step S1. This model not only includes the fixed positions of static obstacles, but also combines the motion trajectories of dynamic obstacles. Through the prediction algorithm, the system can estimate the future positions of these dynamic obstacles and then predict possible collision risks. The core logic of this step is to model the motion patterns of dynamic objects, combine static obstacle information, predict future environmental conditions, and provide a basis for subsequent path planning and obstacle avoidance decisions. Through this model, potential collision risk areas can be identified in real time, enhancing the decision-making ability and safety of the unmanned ship.

[0037] S3. According to the dynamic environment perception data and the dynamic environment model, optimization is performed by adjusting the working parameters of the laser ranging, specifically including: adjusting the laser beam emission angle and frequency according to the environmental complexity to enhance the measurement accuracy, and when a dynamic obstacle approaches, giving priority to optimizing the ranging accuracy of the area to reduce the impact of the ranging dead zone. The environmental complexity specifically includes the number of obstacles, the uncertainty of obstacle movement, and the amplitude of sea surface fluctuations.

[0038] It should be noted that the system optimizes the working parameters of laser ranging according to the dynamic environment perception data and dynamic environment model to ensure the high accuracy of laser ranging results. According to the changes in environmental complexity (such as the number of obstacles, the uncertainty of obstacle movement, and the amplitude of sea surface fluctuations, etc.), the system dynamically adjusts the emission angle and frequency of the laser beam to improve the accuracy of the measurement. When a dynamic obstacle approaches, the ranging accuracy of the area is optimized first to reduce the impact of the ranging dead zone on navigation and path planning. By adjusting the laser ranging parameters in real time under different conditions of environmental changes, the system can ensure the accuracy of the ranging results and avoid ranging errors caused by changes in dynamic obstacles or complex sea surface environments, thereby providing more accurate data support for subsequent path planning.

[0039] S4. Feedback the optimized laser ranging data to the navigation control system of the unmanned ship to provide high-precision real-time navigation information. According to the current position and route planning of the unmanned ship, the path planning algorithm is used to adjust the heading to avoid collision with obstacles and optimize the navigation route in real time.

[0040] It should be noted that the optimized laser ranging data is fed back to the navigation control system of the unmanned ship and used to provide high-precision real-time navigation information. Combined with the current position and route planning of the unmanned ship, the system uses a path planning algorithm to adjust the heading to avoid collisions with obstacles. By dynamically adjusting the heading and optimizing the navigation route in real time, the system can cope with changing environmental conditions and ensure the safe navigation of the ship. The core logic of this step is to continuously adjust the heading based on the combination of real-time ranging data and path planning algorithms, so as to effectively avoid potential collision risks and optimize the navigation path, ultimately ensuring that the unmanned ship can complete its tasks efficiently and safely in complex environments.

[0041] Furthermore, the environmental complexity ECP is calculated based on the number of obstacles, the complexity of dynamic object behavior and sea surface fluctuations, and a range adjustment coefficient RAC is introduced as a coefficient for adjusting the laser ranging accuracy according to the environmental perception result.

[0042] Furthermore, the environmental perception stage adopts the fusion of laser radar and visual sensor data, uses the Kalman filter algorithm to estimate the position of dynamic obstacles and predict their future movement paths, and further optimizes the target area of ​​laser ranging.

[0043] It is understandable that during the environmental perception stage, LiDAR and visual sensors collect different data about the surrounding environment respectively. LiDAR provides high-precision distance information and can accurately detect the spatial position of objects, while visual sensors provide richer scene information, such as object shape, texture, and dynamic changes. The two complement each other. LiDAR can make up for the shortcomings of visual sensors in low light or complex backgrounds, while visual sensors can provide more object recognition and classification information. Therefore, by fusing the data of these two sensors, the system can obtain more comprehensive and accurate environmental perception information.

[0044] It is understandable that for real-time perception of dynamic obstacles, the Kalman filter algorithm is used for position estimation and motion trajectory prediction. The Kalman filter algorithm is a technology widely used in dynamic system state estimation, suitable for processing real-time data with noise and uncertainty. Here, it accurately estimates the position of dynamic obstacles by combining different information provided by lidar and visual sensors, and predicts their future motion path based on existing trajectory data. Kalman filtering can effectively balance the measurement errors of the two sensors, thereby providing more stable and accurate dynamic obstacle position estimation in noisy environments.

[0045] It is understandable that the system can predict the future movement path of the dynamic obstacle by using the current state (position, velocity, acceleration, etc.) estimated by the Kalman filter algorithm. This process calculates the possible position of the obstacle in the future time period by considering the motion model of the obstacle and the motion law in the environment. This step is crucial for dynamic obstacle avoidance because it can identify potential collision risks in advance when the unmanned ship approaches an obstacle, thereby providing a basis for dynamic path planning and ranging optimization.

[0046] It is understandable that after completing the real-time position estimation and future path prediction of dynamic obstacles, the system will optimize the target area of ​​laser ranging according to the prediction results. When obstacles are approaching or in motion, the system can give priority to accurate ranging of these target areas to ensure more accurate measurement results in these dynamic areas, thereby reducing the risks caused by ranging dead zones or ranging errors. By adjusting the focal length, sampling frequency, and emission angle of the laser ranging, the system can ensure that the ranging data is always highly accurate in complex dynamic environments.

[0047] Furthermore, in the dynamic model construction stage, a fusion model of a convolutional neural network (CNN) and a Kalman filter algorithm is used to detect and track dynamic obstacles, and a path prediction algorithm is used to optimize the risk area around the ship.

[0048] It is understandable that as a deep learning technology, convolutional neural network (CNN) is particularly good at processing image data. Through the image data obtained by the visual sensor, CNN can automatically extract and identify the features of objects in the image and identify dynamic obstacles in the surrounding environment. For example, CNN can identify floating objects or fast-moving targets on the sea surface, such as other ships, floating objects, etc. Through the trained CNN model, dynamic obstacles and static environments can be accurately distinguished, providing real-time obstacle detection information.

[0049] After CNN completes obstacle detection, the Kalman filter algorithm is used to track these dynamic obstacles. Kalman filtering is a recursive algorithm based on state estimation, which can estimate the motion state (position, speed, etc.) of obstacles in real time based on measurement data (such as the position and speed of obstacles) and prediction models, combined with noise and uncertainty information. It eliminates noise from sensors by updating and correcting the estimated values ​​multiple times, thereby achieving accurate tracking of dynamic obstacles. This enables the system to accurately grasp the position and speed of obstacles during their movement, and provide reliable data for subsequent path planning and obstacle avoidance decisions.

[0050] Based on the motion trajectory of dynamic obstacles obtained by Kalman filter tracking, the path prediction algorithm can predict the future position of these obstacles. The path prediction algorithm analyzes the movement pattern of the obstacle (such as speed, acceleration, heading, etc.) and combines environmental information to calculate the future trajectory of the obstacle. This process can help unmanned ships identify possible collision risk areas in advance and avoid accidents caused by sudden changes in obstacles.

[0051] Through the path prediction algorithm, the system can not only predict the future position of dynamic obstacles, but also optimize the risk areas of the surrounding environment based on these prediction results. Specifically, the system can dynamically calculate the safe distance between the ship and the obstacle, and adjust the size and shape of the risk area according to the predicted path. For example, when the movement trajectory of the obstacle is about to intersect the ship's path, the system can adjust the course or speed in advance to avoid a collision. In addition, the ranging accuracy can be dynamically optimized according to the movement speed and direction of the obstacle, improving the measurement accuracy of these areas and ensuring that the navigation system can make the safest decisions.

[0052] Furthermore, the calculation formula of the environmental complexity parameter ECP is as follows:

[0053] ECP=α·(N obs +β·D dyn +γ·H wave )

[0054] Among them, N obs is the number of obstacles in the environment, D dynis the motion complexity of dynamic obstacles in the environment, indicating the random motion characteristics of dynamic obstacles, H wave is the amplitude of sea surface fluctuation, α, β and γ are weight coefficients of the impact of environmental conditions on complexity, which are adaptively adjusted based on data training. The calculation method of the weight coefficients α, β and γ is as follows:

[0055]

[0056] Among them, W obs , W dyn , W wave are the preset weights of obstacle density, dynamic complexity, and sponge fluctuation, respectively. obs，i , D dyn，i , H wave，j is the measurement data for each obstacle, dynamic object and fluctuation, and n, m, and k are the number of obstacle, dynamic object and fluctuation data points in the environment, respectively.

[0057] Through the sensor system of the unmanned ship (such as lidar, visual sensor, sonar, etc.), obstacles, dynamic obstacles and sea surface fluctuation data in the sea environment are collected in real time. The data includes:

[0058] Number of obstacles (Nobs): Record and identify the number of obstacles in the surrounding environment.

[0059] Motion complexity of dynamic obstacles (Ddyn): The complexity of calculating the motion trajectory of dynamic obstacles (such as other ships or floating objects) by tracking them, usually based on dynamic characteristics such as velocity, acceleration, and uncertainty of motion.

[0060] Sea surface wave amplitude (Hwave): Obtain data on sea surface wave motion, which can be obtained through sonar or special meteorological equipment.

[0061] The collected data is applied to the ECP formula to calculate the complexity parameters in the environment. At this point, ECP can provide a comprehensive environmental complexity index, reflecting the impact of various factors in the current environment on the ship's navigation and ranging accuracy. For different environmental factors, the assigned weight coefficients (a, β, γ) will be adjusted according to the actual situation of the environment, making ECP more accurate.

[0062] According to the performance of the unmanned ship in different environments, the weight coefficients (a, β, γ) are dynamically adjusted based on data training. This is a critical step because the impact of environmental complexity varies depending on different ocean conditions. For example, when the sea surface fluctuates greatly, the weight of γ may be increased to emphasize the impact of fluctuations on ranging accuracy; when there are many obstacles and high motion uncertainty, the weight of β may be increased.

[0063] After ECP is calculated, it can be directly used to optimize path planning and ranging accuracy. Specifically, when the ECP value is high, it means that the environment is more complex, and the system can be adjusted according to the complexity value, such as adjusting the emission angle, frequency or sampling method of laser ranging to improve ranging accuracy;

[0064] In high-complexity areas, priority is given to improving the ranging accuracy of dynamic obstacles to reduce dead zones and errors;

[0065] Adjust the ship's heading and speed based on the predicted obstacle path to avoid potential collision risks.

[0066] Based on the calculation results of ECP, the navigation control system of the unmanned ship can adjust the heading or path planning in real time. For example, in a highly complex environment (such as dense obstacles, many dynamic obstacles and turbulent sea surface), the system may choose a safer obstacle avoidance path or increase the monitoring frequency of dynamic obstacles.

[0067] As an environmental complexity parameter, ECP plays an important role in the navigation and laser ranging optimization of unmanned ships. It comprehensively considers the number of obstacles, the movement complexity of dynamic obstacles and the amplitude of sea surface fluctuations, and adaptively adjusts the weight coefficient, so that the system can adjust the parameters of laser ranging according to different environmental conditions, thereby improving measurement accuracy, optimizing path planning, and ensuring the safe navigation of unmanned ships in complex environments.

[0068] Furthermore, the environmental complexity parameter ECP is further dynamically adjusted by the following formula:

[0069] ECP adjusted =δ1·ECP+δ2·V ship (t)·T sampling

[0070] Among them, δ1 and δ2 are dynamic adjustment factors, which represent the relationship between environmental complexity and ship motion, V ship (t) is the current sailing speed of the ship, T sampling is the ranging data sampling period, and the calculation method of the dynamic factors δ1 and δ2 is:

[0071]

[0072] Among them, V ship (t) is the current speed of the ship, max(V ship ) is the maximum speed of the ship, T sampling，i is the sampling period at different time points.

[0073] The dynamically adjusted ECP (i.e., ECPadjusted) can effectively reflect the impact of environmental complexity on ranging accuracy under the current navigation state. Its application method is as follows:

[0074] (1) Optimizing laser ranging accuracy

[0075] Through the dynamically adjusted ECP value, the ranging parameters can be adjusted in real time during the laser ranging process. Specifically, when the environment complexity is high (for example, when there are dense obstacles, complex dynamic obstacle movements, or drastic sea surface fluctuations), the adjusted ECP value will be larger, and the system will accordingly optimize the laser beam emission angle, frequency, and sampling method to improve the ranging accuracy. Conversely, when the environment complexity is low, the system may reduce the improvement of ranging accuracy and reduce the system's computational burden.

[0076] (2) Dynamic path planning

[0077] In highly complex environments, when the adjusted ECP value is large, the system will prioritize calculating safer obstacle avoidance paths. By combining with the path planning algorithm, the system can adjust the ship's navigation route according to the ECP to avoid potential collision risks. For example, when the ECP value is high, the system may choose to bypass complex areas or increase the frequency of obstacle monitoring.

[0078] (3) Adaptive environmental perception

[0079] By combining the dynamically adjusted ECP, the environmental perception system can more accurately assess the impact of the current environment on laser ranging. The system automatically adjusts the ranging accuracy, path planning and control strategy according to real-time environmental changes to improve overall navigation performance and safety.

[0080] The dynamic adjustment of ECP dynamically optimizes the environmental complexity by combining the ship's speed and the sampling period of the ranging data, so that the laser ranging accuracy and path planning can adapt to different navigation conditions. By adjusting factors δ1 and δ2, this method can not only enhance the adaptability to dynamic obstacles and complex environments, but also improve the accuracy of the ranging system in highly complex environments, thereby ensuring the safe and efficient navigation of the unmanned ship.

[0081] Furthermore, in S3, the RAC is calculated by the following formula:

[0082]

[0083] Among them, L max is the maximum ranging range of the laser ranging device, δ range is a correction factor related to the complexity of the environment and is used to adjust the ranging accuracy. The correction factor δ range The calculation method is:

[0084]

[0085] Among them, max(ECP) is the maximum value of environmental complexity, ECP i is the environmental complexity value of each measurement, and n is the number of measurements.

[0086] The role of RAC is reflected in the laser ranging optimization stage. According to the complexity of different environments, RAC dynamically adjusts the measurement range of the laser ranging system. The specific application method is as follows:

[0087] (1) Impact of environmental complexity on ranging accuracy

[0088] In highly complex environments (e.g., dense obstacles, turbulent sea surface, etc.), the RAC will be larger, which means the laser ranging range will be reduced. Through this adjustment, the system can improve the measurement accuracy of close-range obstacles and avoid mismeasurements.

[0089] In low environmental complexity, the RAC value is small and the laser ranging system will use a larger measurement range, thereby increasing the detection range and improving the accuracy of long-distance targets.

[0090] (2) Dynamically adapt to environmental changes

[0091] RAC is adjusted in real time. Whenever the complexity of the environment changes (such as encountering new obstacles or changes in sea conditions), RAC will recalculate and adjust the ranging range based on the new ECP value. This dynamic adaptability enables the unmanned ship to always maintain a high ranging accuracy in various complex environments.

[0092] (3) Navigation control optimization

[0093] The adjusted RAC further affects the navigation control of the unmanned vessel by affecting the laser ranging accuracy. In complex environments, the improved ranging accuracy makes path planning and navigation control more precise, thereby avoiding collision risks and optimizing navigation paths.

[0094] Through the above methods, RAC ensures that the unmanned ship can dynamically adjust the range of laser ranging according to different environmental conditions (such as the number of obstacles, dynamic objects, sea surface fluctuations, etc.) during actual navigation, thereby optimizing the ranging accuracy and improving navigation safety.

[0095] Furthermore, the adjustment process of the ranging accuracy is further optimized through an adaptive gain mechanism. When the ranging accuracy drops to a set threshold, the gain algorithm is started to automatically adjust the ranging accuracy and environmental perception parameters.

[0096] It should be noted that during the adjustment of ranging accuracy, when the accuracy of laser ranging drops to the set threshold, the system automatically triggers the gain algorithm for optimization. The gain algorithm automatically adjusts the environmental perception parameters to improve ranging performance by analyzing the difference between the current ranging accuracy and the target accuracy. The specific steps are as follows:

[0097] First, after the system detects that the ranging accuracy is lower than the set threshold, the gain algorithm begins to calculate the ranging error. The error is obtained by comparing the actual measurement value with the expected measurement value (such as the target distance predicted based on the environmental model). Then, the gain algorithm adjusts the gain parameters of the laser ranging system according to the error size, including the laser beam emission frequency, emission angle, and signal reception sensitivity.

[0098] Next, the gain algorithm will dynamically adjust the environmental perception parameters according to the current environmental complexity. These parameters may include the density of obstacles in the environment, the speed and uncertainty of moving objects, and sea surface fluctuations. By calculating the changes in environmental perception parameters in real time, the gain algorithm automatically adjusts the working mode of the laser ranging system. For example, when there are dense obstacles or many dynamic objects, the system will increase the ranging accuracy and reduce the ranging range; when the environmental complexity is low, the gain algorithm may relax the accuracy requirements and expand the ranging range.

[0099] The gain algorithm not only relies on the current ranging error during adjustment, but also considers historical data to ensure that the system can adaptively adjust in a dynamic environment and continuously maintain high ranging accuracy and environmental perception capabilities. Through this automatic adjustment mechanism, the system can optimize the laser ranging accuracy in various complex environments to ensure the navigation and obstacle avoidance capabilities of the unmanned ship.

[0100] Furthermore, the laser ranging data feedback in S4 includes the following steps:

[0101] S801, based on the real-time laser ranging data and obstacle positions, use a path planning algorithm based on a cost function to perform optimal path planning;

[0102] S802. The path planning result is used to adjust the heading and speed of the ship through a real-time feedback mechanism to avoid collision with obstacles.

[0103] It should be noted that the path planning algorithm based on the cost function evaluates the costs of different paths and selects the optimal path to ensure that the unmanned ship avoids obstacles and reaches the destination efficiently. The cost function usually includes multiple factors, such as path length, obstacle avoidance distance, navigation time, energy consumption, etc. The cost value of each potential path is calculated based on these factors, and the path with lower cost will be given priority. The path planning algorithm first generates multiple candidate paths based on the current environmental perception data (such as obstacle locations and motion trajectories of dynamic objects). Then, the cost function evaluates the overall cost of each path and selects the path with the lowest cost as the optimal path, avoiding the traditional path planning that only focuses on the single goal of the shortest distance, and enhancing the adaptability of the system in complex environments.

[0104] When the path planning results are generated, the unmanned ship will dynamically adjust the heading and speed according to the optimal path through the real-time feedback mechanism. The real-time feedback mechanism continuously updates the path planning results by continuously monitoring environmental changes (such as the appearance of new obstacles or changes in the position of dynamic objects) and the current state of the ship (such as speed, position deviation, etc.). If new risk areas or environmental changes are detected during path planning, the system will immediately recalculate the path and adjust the heading and speed to avoid new obstacles or adjust to a more appropriate navigation trajectory. The real-time feedback mechanism ensures that the path planning process is not only based on current environmental data, but can also be corrected in real time according to environmental changes, thereby continuously optimizing the navigation route of the unmanned ship, avoiding collisions and improving navigation efficiency.

[0105] The path planning algorithm based on the cost function is further optimized by the following formula:

[0106]

[0107] Among them, J path is the path cost, d i is the distance cost of the i-th node in the path, r i is the risk cost of the i-th node in the path, e turn (i) is the heading error cost of the i-th node in the path, and the calculation method of the weight coefficients ω1, ω2, and ω3 is:

[0108]

[0109] Among them, d max 、r max 、e max are the maximum distance, risk and heading error in the path, respectively.

[0110] Furthermore, in order to perform dynamic correction according to the heading error of the ship, the heading error adjustment coefficient HEAC is calculated by the following formula:

[0111] HEAC=δ3·|V ship ×Δt|

[0112] Among them, δ3 is the adjustment factor related to the ship heading error, V ship is the current speed of the ship, Δt is the time interval of laser ranging sampling, and the heading error adjustment factor

[0113] It should be noted that the main function of HEAC (Heading Error Adjustment Coefficient) in the application process is to adjust the accuracy of laser ranging according to the ship's speed and the time interval of ranging. As the speed changes, the heading error of the ship will affect the accuracy of laser ranging. The faster the speed, the greater the impact of the heading error on the ranging result. Therefore, dynamic adjustment through HEAC is required to ensure the ranging accuracy at high speed.

[0114] Specifically, HEAC evaluates the impact of heading error by considering the ship's current speed and the time interval of laser ranging. When the speed is fast, HEAC will increase to compensate for the ranging error caused by fast sailing; while when the speed is slow, HEAC will decrease, thereby unnecessarily increasing the computational burden of the system.

[0115] In this way, HEAC can dynamically adjust the ranging accuracy under different speed conditions. When the speed is high, the ranging system will be more sensitive to the heading error, and the adjustment coefficient will be appropriately increased to reduce the impact of the error on the ranging results; when the speed is low, the adjustment coefficient is reduced to maintain the stability and accuracy of the system. This adaptive adjustment mechanism ensures that the unmanned ship can maintain high-precision laser ranging under various speed conditions, providing reliable data support for path planning and navigation control.

[0116] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0117] (1) In the present invention, by fusing multiple sensor data (laser ranging, vision, sonar and radar), the present invention can dynamically adjust the working parameters of laser ranging, such as the laser beam emission angle and frequency, so as to optimize the ranging accuracy according to the complexity of the environment. In particular, when dynamic obstacles are approaching, the ranging accuracy of these areas is optimized first, thereby reducing the impact of ranging dead zones. This measure significantly improves the ranging accuracy of unmanned ships in complex marine environments and ensures that the navigation system can obtain high-quality data in real time.

[0118] (2) In the present invention, by establishing a dynamic environment model, combining static and dynamic obstacle information, and using a prediction algorithm to estimate the future position of dynamic objects, potential collision risk areas can be effectively identified and path planning can be optimized. This real-time path adjustment mechanism based on dynamic environment perception can enable the unmanned ship to respond quickly in complex environments, avoid collisions with obstacles, and improve the unmanned ship's autonomous obstacle avoidance capability;

[0119] (3) In the present invention, on the basis of optimizing the laser ranging data, the present invention further feeds back the processed data to the navigation control system of the unmanned ship, and adjusts the heading in real time through the path planning algorithm. This adaptive optimization mechanism enables the unmanned ship to adjust the navigation route according to the real-time data, reduce energy consumption and navigation time, and enhance navigation safety, providing efficient and accurate navigation support under various environmental conditions.

[0120] Reference Manual Attached Figure 2 , showing a structural schematic diagram of an unmanned ship laser ranging optimization system based on dynamic environment perception provided by an embodiment of the present invention.

[0121] The present invention also provides an unmanned ship laser ranging optimization system 20 based on dynamic environment perception, which is applied to the unmanned ship laser ranging optimization method based on dynamic environment perception, comprising:

[0122] Processor 201.

[0123] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the unmanned ship laser ranging optimization method based on dynamic environment perception as in the method embodiment is implemented.

[0124] The unmanned ship laser ranging optimization system based on dynamic environment perception provided by the present invention can execute the unmanned ship laser ranging optimization method based on dynamic environment perception and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0125] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0126] (1) In the present invention, by fusing multiple sensor data (laser ranging, vision, sonar and radar), the present invention can dynamically adjust the working parameters of laser ranging, such as the laser beam emission angle and frequency, so as to optimize the ranging accuracy according to the complexity of the environment. In particular, when dynamic obstacles are approaching, the ranging accuracy of these areas is optimized first, thereby reducing the impact of ranging dead zones. This measure significantly improves the ranging accuracy of unmanned ships in complex marine environments and ensures that the navigation system can obtain high-quality data in real time.

[0127] (2) In the present invention, by establishing a dynamic environment model, combining static and dynamic obstacle information, and using a prediction algorithm to estimate the future position of dynamic objects, potential collision risk areas can be effectively identified and path planning can be optimized. This real-time path adjustment mechanism based on dynamic environment perception can enable the unmanned ship to respond quickly in complex environments, avoid collisions with obstacles, and improve the unmanned ship's autonomous obstacle avoidance capability;

[0128] (3) In the present invention, on the basis of optimizing the laser ranging data, the present invention further feeds back the processed data to the navigation control system of the unmanned ship, and adjusts the heading in real time through the path planning algorithm. This adaptive optimization mechanism enables the unmanned ship to adjust the navigation route according to the real-time data, reduce energy consumption and navigation time, and enhance navigation safety, providing efficient and accurate navigation support under various environmental conditions.

[0129] The above contents are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0130] There are a few points to note:

[0131] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0132] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0133] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0134] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An unmanned ship laser ranging optimization method based on dynamic environment perception, characterized in that: include: S1. The laser rangefinder, visual sensor, sonar device and radar device carried by the unmanned ship collect the surrounding environment data in real time. The data includes sea surface fluctuation information, obstacle location and motion trajectory of dynamic objects. All collected environmental data are processed by multi-sensor fusion algorithm to remove noise and integrate them into unified environmental status information for subsequent dynamic model construction. S2. Based on the environmental data collected in real time, a dynamic environmental model is established. The dynamic environmental model combines the fixed position of the static obstacles and the motion trajectory of the dynamic obstacles, estimates the future position of the dynamic obstacles through a prediction algorithm, and calculates the potential collision risk area through dynamic path planning; S3. According to the dynamic environment perception data and the dynamic environment model, optimization is performed by adjusting the working parameters of the laser ranging, specifically including: adjusting the laser beam emission angle and frequency according to the environmental complexity to enhance the measurement accuracy, and when a dynamic obstacle approaches, giving priority to optimizing the ranging accuracy of the area to reduce the impact of the ranging dead zone, wherein the environmental complexity specifically includes the number of obstacles, the uncertainty of obstacle movement, and the amplitude of sea surface fluctuation; S4, feeds back the optimized laser ranging data to the navigation control system of the unmanned ship, provides high-precision real-time navigation information, uses the path planning algorithm to adjust the course according to the current position and route planning of the unmanned ship, avoids collision with obstacles, and optimizes the navigation route in real time; The environmental complexity ECP is calculated based on the number of obstacles, the complexity of dynamic object behavior and sea surface fluctuations, and the range adjustment coefficient RAC is introduced as a coefficient for adjusting the laser ranging accuracy according to the environmental perception result.

2. According to the unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 1, it is characterized in that: include: The environmental perception stage adopts the fusion of laser radar and visual sensor data, uses the Kalman filter algorithm to estimate the position of dynamic obstacles and predict their future movement paths, and further optimizes the target area of ​​laser ranging.

3. The unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 1 is characterized in that: include: In the dynamic model construction stage, a fusion model of a convolutional neural network (CNN) and a Kalman filter algorithm is used to detect and track dynamic obstacles, and a path prediction algorithm is used to optimize the risk area around the ship.

4. The unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 1 is characterized in that: include: The calculation formula of the environmental complexity parameter ECP is as follows: ECP=α·(N obs +β·D dyn +γ·H wave ) Among them, N obs is the number of obstacles in the environment, D dyn is the motion complexity of dynamic obstacles in the environment, indicating the random motion characteristics of dynamic obstacles, H wave is the amplitude of sea surface fluctuation, α, β and γ are weight coefficients of the impact of environmental conditions on complexity, which are adaptively adjusted based on data training. The calculation method of the weight coefficients α, β and γ is as follows: Among them, W obs , W dyn , W wave are the preset weights of obstacle density, dynamic complexity, and sponge fluctuation, respectively. obs，i , D dyn，i , H wave，j is the measurement data for each obstacle, dynamic object and fluctuation, and n, m, and k are the number of obstacle, dynamic object and fluctuation data points in the environment, respectively.

5. The unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 4 is characterized in that: include: The environmental complexity parameter ECP is further dynamically adjusted by the following formula: ECP adjusted =δ1·ECP+δ2·V ship (t)·T sampling Among them, δ1 and δ2 are dynamic adjustment factors, which represent the relationship between environmental complexity and ship motion, V ship (t) is the current sailing speed of the ship, T sampling is the ranging data sampling period, and the calculation method of the dynamic factors δ1 and δ2 is: Among them, V ship (t) is the current speed of the ship, max(V ship ) is the maximum speed of the ship, T sampling，i is the sampling period at different time points.

6. The unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 5 is characterized in that: The S3 specifically includes: The RAC is calculated by the following formula: Among them, L max is the maximum ranging range of the laser ranging device, δ range is a correction factor related to the complexity of the environment and is used to adjust the ranging accuracy. The correction factor δ range The calculation method is: Among them, max(ECP) is the maximum value of environmental complexity, ECP i is the environmental complexity value of each measurement, and n is the number of measurements.

7. The unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 6 is characterized in that: include: The adjustment process of the ranging accuracy is further optimized through an adaptive gain mechanism. When the ranging accuracy drops to a set threshold, the gain algorithm is started to automatically adjust the ranging accuracy and environmental perception parameters.

8. The unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 1 is characterized in that: The S4 further comprises: The laser ranging data feedback comprises the following steps: S801, based on the real-time laser ranging data and obstacle positions, use a path planning algorithm based on a cost function to perform optimal path planning; S802, the path planning result is used to adjust the heading and speed of the ship through a real-time feedback mechanism to avoid collision with obstacles; The path planning algorithm based on the cost function is further optimized by the following formula: Among them, J path is the path cost, d i is the distance cost of the i-th node in the path, r i is the risk cost of the i-th node in the path, e turn (i) is the heading error cost of the i-th node in the path, and the calculation method of the weight coefficients ω1, ω2, and ω3 is: Among them, d max 、r max 、e max are the maximum distance, risk and heading error in the path, respectively.

9. The unmanned ship laser ranging optimization method based on dynamic environment perception according to claim 1 is characterized in that: include: In order to perform dynamic correction according to the ship's heading error, the heading error adjustment coefficient HEAC is calculated by the following formula: HEAC=δ3·|V ship ×Δt| Among them, δ3 is the adjustment factor related to the ship heading error, V ship is the current speed of the ship, Δt is the time interval of laser ranging sampling, and the heading error adjustment factor 10. An unmanned ship laser ranging optimization system based on dynamic environment perception, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the unmanned ship laser ranging optimization method based on dynamic environment perception as described in any one of claims 1 to 9 is implemented.

Images