Autonomous underwater vehicle seabed pipeline tracking method and device based on side scan sonar

Abstract

The application provides a kind of autonomous underwater vehicle seabed pipeline tracking method and device based on side scan sonar, it is related to underwater pipeline tracking technical field, the method comprises: during the control underwater robot is in pipeline investigation area and carries out comb search, utilize side scan sonar to continuously obtain seabed acoustic image;Pipeline track is detected based on seabed acoustic image, and the initial trajectory of pipeline is determined based on pipeline track;The state estimation of the pipeline is carried out based on the initial trajectory using Kalman filter;Based on state estimation result, the spatial length, confidence and continuity of initial trajectory are determined using trajectory quality evaluation method, and trajectory score is generated;In response to trajectory score meets preset requirement, the initial trajectory is determined as the target tracking trajectory of underwater robot;The front view distance and heading of the underwater robot are dynamically adjusted based on the target tracking trajectory.

Description

Technical Field

[0001] This invention relates to the field of multifunctional underwater robot pipeline tracking technology, and in particular to an autonomous underwater robot method and apparatus for tracking seabed pipelines based on side-scan sonar. Background Technology

[0002] With the increasing development of marine resource exploration and marine engineering construction, the inspection and maintenance of subsea pipelines (such as submarine cables, oil / gas pipelines, and communication optical cables) has become crucial. Currently, such tasks mainly rely on towed side-scan sonar performed by mother ships, which is inefficient, costly, and limited by the maneuverability of the mother ship, making it difficult to conduct precise and continuous tracking and inspection of pipelines in complex sea conditions. Autonomous underwater vehicles (AUVs), due to their high degree of autonomy, flexibility, and low-cost operation, have become an important platform for performing such seabed surveys. Side-scan sonar, as the core detection sensor carried by AUVs, can efficiently acquire large-area, high-resolution acoustic images of the seabed, providing a data foundation for pipeline identification. However, achieving stable and smooth autonomous tracking of subsea pipelines by AUVs still faces a series of technical challenges.

[0003] At the target detection level, acoustic image feature recognition of pipelines is a key challenge. In 2010, Isaacs and Goroshin proposed an improved Hough transform method, defining the cable as a straight line segment with a coherent structure. Some researchers use gradient model-based filtering algorithms combined with Hough transform to locate pipelines. Others connect piecewise linear segments using self-organizing maps to form pipeline trajectories. Still others propose using the YOLOv5 model to extract cable linear features from sonar sub-images. At the tracking and control level, transforming unstable detection information into smooth, look-ahead AUV motion is another major challenge. One researcher treats the pipeline tracking problem as a target interception problem, combining proportional navigation guidance (PNG) and model predictive control (MPC). Others propose controlling the pipeline to be perpendicular to and centered within the sonar field of view; still others explore reinforcement learning-based action selection strategies to keep the pipeline within the optimal observation area of ​​the AUV sensor. Alternatively, magnetic line-of-sight guidance is used to estimate the horizontal lateral offset relative to the cable. However, the above strategy has two common drawbacks: 1. It does not fully consider the measurement error in the detection process, resulting in control input jitter and an uneven pipeline tracking path; 2. The guidance law lacks forward-looking prediction of the pipeline direction and is a "reactive" control. When the pipeline direction changes abruptly or the detection is briefly lost, it is very easy to cause tracking failure.

[0004] In summary, current technologies for autonomous tracking of subsea pipelines suffer from systemic defects: In the detection stage, both traditional image processing and deep learning models focus on identifying static and weak target features in sonar images, which are severely affected by complex seabed backgrounds and noise interference, leading to uncertainties, discontinuities, and even temporary loss of detection results; In the tracking and control stage, guidance laws are mostly "reactive" designs, which have inherent lag that easily leads to AUV motion oscillations, and generally lack forward-looking prediction of target trajectory and fault tolerance mechanisms for temporary loss of detection. Even when advanced control methods are introduced, they are difficult to effectively utilize the spatiotemporal continuity of pipelines due to the lack of deep integration with unstable detection signals, ultimately resulting in insufficient tracking reliability in complex scenarios. Summary of the Invention

[0005] To address the aforementioned technical problems, embodiments of the present invention provide a method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar, comprising: During the comb-like search of the target survey area by the control of the underwater robot, side-scan sonar is used to continuously acquire seabed acoustic images; Based on the underwater acoustic image, pipeline traces are detected, and the initial trajectory of the pipeline is determined based on the pipeline traces. The initial trajectory is related to the pipeline's layout trajectory. The state of the pipeline is estimated based on the initial trajectory using a Kalman filter. Based on the state estimation results, the spatial length, confidence level, and continuity of the initial trajectory are determined using a trajectory quality assessment method, and a trajectory score is generated. In response to the trajectory score meeting the preset requirements, the initial trajectory is determined to be the target tracking trajectory of the underwater robot; The underwater robot's forward-looking distance and heading are dynamically adjusted based on the target tracking trajectory.

[0006] In one embodiment, the target survey area is a rectangular area, including a short side and a long side; Controlling the underwater robot to perform a comb-like search within the target survey area includes: Multiple survey lines parallel to the first side are generated using the first side of the target survey area as a reference. Based on the first side and the survey line, a comb-shaped survey line is generated, and the underwater robot is controlled to search for pipelines based on the comb-shaped survey line.

[0007] In one embodiment, generating a comb-shaped survey line based on the first edge and the survey line includes: The comb-shaped survey lines are generated based on the first side and the survey line spacing between the survey lines, wherein the survey line spacing w = 2Rcov - δ Rcov represents the effective range of a side-scan sonar on one side. δ The set overlap amount; Determine the waypoint sequence based on the comb-shaped survey lines; Continuous acquisition of seabed acoustic images using side-scan sonar, including: During the underwater robot's search along the waypoint sequence, the side-scan sonar sequentially acquires the seabed acoustic images of each waypoint.

[0008] In one embodiment, determining the initial trajectory of the pipeline based on the pipeline traces includes: The pipeline points are associated with the goal of minimizing the global association cost to determine the initial trajectory of the pipeline.

[0009] In one embodiment, associating the pipeline points with the goal of minimizing the global association cost includes: The pipeline points are associated using the following association cost function, with the goal of minimizing the global association cost:

[0010] For the association cost function, The spatial distance between the target point and the initial trajectory. The weighting coefficient represents the angle difference between the target point and the initial trajectory. and These measures the importance of spatial distance and angular differences in the association cost function. express t The target point at any given time, express t The initial trajectory at time -1 i Indicates the first i A dot mark, j Indicates the first j A trajectory point; The method further includes: A global optimization algorithm is used to determine the optimal match between the target point and the initial trajectory, and the initial trajectory is optimized based on the optimal matching result; The global optimization algorithm includes:

[0011] x For spatial coordinates, m For the number of dots, n The number of trajectory points is denoted by , and the spatial coordinates of the points matched with the trajectory points are denoted by . .

[0012] In one embodiment, the trajectory quality assessment method includes:

[0013] in, for t time trajectory score, For the initial trajectory in t At the time of j The spatial length at each point for t The initial trajectory at time 1 i Confidence level at each point for t The initial trajectory at time 1 j Trajectory continuity of points, weighting coefficients , , These are used to measure the lifetime of a trajectory. Confidence of dot marks Related costs In trajectory quality evaluation function The relative importance of [the subject / method].

[0014] In one embodiment, , and For the initial trajectory The Middle n , n -1 spatial coordinates of a point, where express t Time Track The total number of dots already included in the data;

[0015] It is a binary indicator function. For trajectory points j The weighting coefficients.

[0016] In one embodiment, the step of using a Kalman filter to estimate the state of the pipeline based on the initial trajectory includes: The state of the pipeline is estimated based on the following observation equation and state equation:

[0017] x k , y k This indicates that the pipeline is in k Location at any given moment φ k For the pipeline in k The direction angle at that moment, , , These are the rates of change of the position and orientation angle of the pipeline, respectively; The state equations include: The observation equations include: Z k = H k X k + V k , X k for k The predicted pipeline state vector at time 10:00. X k-1 for k- Predicted pipeline state vector at time 1, Z k for k Pipeline observation vector at time 10:00 Z k for k Pipeline observation vector at time 10:00 for k The state transition matrix at time t, H k for k The observation matrix at time, W k-1 and V k These are system noise and observation noise, respectively. for k The control input matrix at time -1.

[0018] In one embodiment, dynamically adjusting the forward-looking distance and heading of the underwater robot based on the target tracking trajectory includes: An adaptive line-of-sight guidance law is used in conjunction with the target tracking trajectory to dynamically adjust the forward-looking distance and desired heading angle of the underwater robot; The desired heading angle include:

[0019] For the estimated direction angle of the pipeline, y e This is the vertical distance from the underwater robot to the nearest point on the pipeline; The forward sight distance include:

[0020] As a fixed reference value, As a regulating factor, For the initial trajectory in t Curvature of time, q is the exponent of the curvature.

[0021] Another embodiment of the present invention also provides an autonomous underwater robot subsea pipeline tracking device based on side-scan sonar, comprising: The acquisition module is used to continuously acquire seabed acoustic images using side-scan sonar while controlling the underwater robot to perform a comb search in the target survey area; The first determining module is used to detect pipeline traces based on the underwater acoustic image and determine the initial trajectory of the pipeline based on the pipeline traces, wherein the initial trajectory is related to the pipeline's layout trajectory. An estimation module is used to estimate the state of the pipeline based on the initial trajectory using a Kalman filter; The second determination module is used to determine the spatial length, confidence level, and continuity of the initial trajectory based on the state estimation results and using a trajectory quality assessment method, and to generate a trajectory score. The third determining module is used to determine the initial trajectory as the target tracking trajectory of the underwater robot in response to the trajectory score meeting the preset requirements. The adjustment module is used to dynamically adjust the forward-looking distance and heading of the underwater robot based on the target tracking trajectory.

[0022] Other features and advantages of this application will be set forth in the following description. The objectives and other advantages of this application can be realized and obtained through the structures particularly pointed out in the written description and drawings.

[0023] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0024] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating the method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar in an embodiment of the present invention.

[0026] Figure 2 This is a flowchart illustrating the method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar in an application embodiment of the present invention.

[0027] Figure 3 This is a schematic diagram of the survey line structure in an embodiment of the present invention.

[0028] Figure 4 This is a structural block diagram of an autonomous underwater robot subsea pipeline tracking device based on side-scan sonar in an embodiment of the present invention. Detailed Implementation

[0029] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but these are not intended to limit the scope of the invention.

[0030] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the following description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope of this disclosure will be apparent to those skilled in the art.

[0031] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present disclosure and, together with the general description of the disclosure given above and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.

[0032] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0033] It should also be understood that although the invention has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of the invention.

[0034] The above and other aspects, features and advantages of this disclosure will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0035] Specific embodiments of the present disclosure are described thereafter with reference to the accompanying drawings; however, it should be understood that the disclosed embodiments are merely examples of the present disclosure and can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the present disclosure. Therefore, the specific structural and functional details disclosed herein are not intended to be limiting, but are merely representative of the present disclosure and are intended to teach those skilled in the art to use the present disclosure in a variety of substantially any suitable detailed structures.

[0036] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0037] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0038] like Figure 1 and Figure 2 As shown, this embodiment of the invention provides a method for tracking seabed pipelines using an autonomous underwater robot based on side-scan sonar, including: S1: During the comb search of the target survey area, the underwater robot continuously acquires seabed acoustic images using side-scan sonar. S2: Detect pipeline traces based on the underwater acoustic image, and determine the initial trajectory of the pipeline based on the pipeline traces, wherein the initial trajectory is related to the pipeline's layout trajectory; S3: Use a Kalman filter to estimate the state of the pipeline based on the initial trajectory; S4: Based on the state estimation results, the spatial length, confidence level and continuity of the initial trajectory are determined using the trajectory quality assessment method, and a trajectory score is generated; S5: In response to the trajectory score meeting the preset requirements, the initial trajectory is determined to be the target tracking trajectory of the underwater robot; S6: Dynamically adjust the forward-looking distance and heading of the underwater robot based on the target tracking trajectory.

[0039] In this embodiment, the optimal estimation of the target state is achieved through a Kalman filter, and the forward-looking distance and heading of the underwater robot are dynamically adjusted in conjunction with the target tracking trajectory. This ensures that the underwater robot maintains the optimal observation distance and angle along the pipeline, thereby significantly improving the tracking accuracy and stability of the underwater robot. Furthermore, this embodiment utilizes a pipeline point search mechanism to form an initial trajectory and perform trajectory quality assessment based on the initial trajectory. This effectively suppresses false alarms caused by environmental interference and noise, improving the reliability of target detection.

[0040] In this embodiment, the underwater robot acquires acoustic images of the subsea pipeline in real time, uses target detection and association mechanisms to filter targets, and then tracks them. During tracking, the robot dynamically adjusts its forward-looking distance based on calculated target tracking trajectories to ensure stable tracking of curved or buried targets. Then, a Kalman filter is used to optimally estimate the target state, thereby improving the underwater robot's tracking accuracy and stability of the pipeline.

[0041] As can be seen from the above, the method in this embodiment supports modular division, thus it can be flexibly adjusted according to task requirements to adapt to tracking tasks of different underwater targets, and has strong versatility and adaptability. For example, the method in this embodiment can be widely used for autonomous inspection, positioning and long-term monitoring of linear infrastructure such as submarine cables, pipelines, and optical cables, and has good prospects for engineering promotion.

[0042] In one embodiment, such as Figure 3As shown, the target survey area is a rectangular area, including a short side and a long side. An underwater robot (e.g., an AUV) performs pipeline detection and tracking within this rectangular area. The specific size of this rectangular area is variable and can be determined based on actual conditions. To ensure that detection and tracking can cover the entire target survey area, this embodiment proposes dividing the target survey area into several survey lines parallel to one side of the area (line segments with arrows in the figure). Specifically, the underwater robot is controlled to perform a comb-like search within the target survey area, including: S101: Generate multiple survey lines parallel to the first side using the first side of the target survey area as a reference; S102: Generate a comb-shaped survey line based on the first side and the survey line, and control the underwater robot to search for pipelines based on the comb-shaped survey line.

[0043] In this embodiment, the first side can be any side of the rectangular region, such as a long side or a short side, the specifics are not fixed.

[0044] Based on the first side and the survey line, a comb-shaped survey line is generated, including: S103: Generate the comb-shaped survey lines based on the first side and the survey line spacing between the survey lines, wherein the survey line spacing w = 2Rcov - δ Rcov represents the effective range of a side-scan sonar on one side. δ The set overlap amount; S104: Determine the waypoint sequence based on the comb-shaped survey lines; Continuous acquisition of seabed acoustic images using side-scan sonar, including: S105: During the underwater robot's search along the waypoint sequence, the side-scan sonar is used to sequentially acquire the seabed acoustic images of each waypoint.

[0045] In this embodiment, the spacing w between each measuring line is 2Rcov- δ Where Rcov is the effective range of the side-scan sonar on one side. δ This is the set overlap amount. The spacing of the survey lines is calculated using this formula, and the resulting comb-shaped survey lines ensure appropriate overlap between them, thus guaranteeing comprehensive detection. During the search process, the AUV will sequentially search along the waypoint sequence determined by the comb-shaped survey lines, that is, sequentially search along the determined pathpoint sequence {pi|i= 1,2,......N}. Each time the AUV passes a survey line, the side-scan sonar will acquire the corresponding seabed acoustic image in real time. The system will then detect and identify potential pipelines in the images. For example, based on image processing algorithms, the system will detect potential pipeline traces in the seabed acoustic image and form the initial trajectory of the pipeline based on the target traces.

[0046] In this embodiment, determining the initial trajectory of the pipeline based on the pipeline points includes: S201: Associate the pipeline points with the goal of minimizing the global association cost to determine the initial trajectory of the pipeline.

[0047] Furthermore, the association of the pipeline points with the goal of minimizing the global association cost includes: S202: The following association cost function is used to associate the pipeline points with the goal of minimizing the global association cost:

[0048] For the association cost function, The spatial distance between the target point and the initial trajectory. The weighting coefficient represents the angle difference between the target point and the initial trajectory. and These measures the importance of spatial distance and angular differences in the association cost function. express t The target point at any given time, express t The initial trajectory at time -1 i Indicates the first i A dot mark, j Indicates the first j A trajectory point.

[0049] That is, using the global correlation cost function to calculate the current time step ( t The target point at time (in this embodiment) is associated with the trajectory generated at the previous time (initial trajectory), meaning the initial trajectory is generated progressively. The cost function in this embodiment is based on the nearest Euclidean distance between the point and the trajectory. and direction angle difference composition.

[0050] The method further includes: S203: Use a global optimization algorithm to determine the optimal match between the target point and the initial trajectory, and optimize the initial trajectory based on the optimal matching result; The global optimization algorithm includes:

[0051] x For spatial coordinates, m For the number of dots, n The number of trajectory points. The spatial coordinates of the point and the trajectory point are matched. For example, by minimizing the association cost, simulated annealing is used to sequentially associate each target point to form a trajectory, and finally the initial trajectory, which is the initial target tracking trajectory, is generated.

[0052] After determining the initial trajectory, the system uses a filtering method to estimate the pipeline's state based on the initial trajectory. This process of using a Kalman filter to estimate the pipeline's state based on the initial trajectory includes: S301: Estimate the state of the pipeline based on the initial trajectory using the following observation equation and state equation:

[0053] X k Let this be the state vector of the pipeline. x k , y k This indicates that the pipeline is in k Location at any given moment φ k For the pipeline in k The direction angle at that moment, , , These are the rates of change of the position and orientation angle of the pipeline, respectively; The state equations include: The observation equations include: Z k = H k X k + V k , X k for k The predicted pipeline state vector at time 10:00. X k-1 for k- Predicted pipeline state vector at time 1, Z k for k Pipeline observation vector at time 10:00 Z k for k Pipeline observation vector at time 10:00 for k The state transition matrix at time t, H k for k The observation matrix at time, W k-1 and V k These are system noise and observation noise, respectively.

[0054] For example, to further improve tracking accuracy and reduce the impact of noise, a Kalman motion process can be used to describe the time step using a uniform motion model. t Pipeline status State compared to the previous moment The relationship between them is specifically represented by the state transition matrix, and the state equation is: . for k The control input matrix at time -1. The observation equation is obtained through the observation matrix. H k The relationship between the observed state and the target state, obtained by correlating the pipeline's state with actual measurements, is also known as the observation equation, and is expressed as follows: Z k = H k X k + V k .in Z k These are actual observed values. V k To account for observation noise, the target state and error covariance at the current time are predicted based on the target's dynamic model and the state at the previous time step. Then, the target state is updated based on the target state, error covariance, and the observation data at the current time step. The Kalman gain is used to balance the difference between the predicted and observed values. The updated state estimate is:

[0055]

[0056] The updated error covariance is The Kalman filter continuously updates the target state estimate based on new observation data through recursive calculation. This allows the estimation error of the target trajectory to decrease continuously with each addition of measurement data.

[0057] To further improve the reliability and accuracy of target tracking, a trajectory quality assessment method is introduced to filter and optimize the generated trajectories, ensuring the accuracy and stability of the tracking results. The purpose of trajectory quality assessment is to comprehensively score each target trajectory to help further determine its reliability. The quality assessment score is also known as the trajectory rating. Calculated using the following formula:

[0058] in, for t Initial trajectory at time trajectory score, For the initial trajectory in t At the time of j The spatial length at each trajectory point is used to measure the persistence of the trajectory, representing the actual path length of the target in space. The larger the trajectory length, the longer the target's movement path, and the higher the tracking stability. for t The initial trajectory at time 1 i The confidence level of each point is used to evaluate the reliability of the target point track. Each point track has a confidence level associated with it. The higher the confidence level, the better the quality of the track. for t The initial trajectory at time 1 j The continuity of the trajectory at each point. By calculating the update frequency of the target trajectory points, the stability of the trajectory over time can be measured. A trajectory with high continuity indicates that the pipeline's state changes relatively smoothly and the update frequency is high. Weighting coefficients , , These are used to measure the lifetime of a trajectory. Confidence of dot marks Related costs In trajectory quality evaluation function The system calculates a trajectory score by comprehensively considering the above factors, providing a comprehensive quality score for each trajectory so that the system can further filter and optimize trajectories. High-quality trajectories will be retained for further target tracking, while low-quality trajectories may be discarded or re-evaluated. Specifically, a score threshold can be set to filter trajectories based on the score threshold, thus obtaining the target tracking trajectory.

[0059] When solving the above equation, the stated , and For the initial trajectory The Middle n , n -1 spatial coordinates of a point, where express t Time Track The total number of dots already included in the data;

[0060] It is a binary indicator function. For trajectory points j The weighting coefficients.

[0061] Furthermore, after obtaining the target tracking trajectory, the system dynamically adjusts the underwater robot's forward-looking distance and heading based on the target tracking trajectory, including: S601: The underwater robot's forward-looking distance and desired heading angle are dynamically adjusted by combining an adaptive line-of-sight guidance law with the target tracking trajectory. The desired heading angle include:

[0062] For the estimated direction angle of the pipeline, y e This is the vertical distance from the underwater robot to the nearest point on the pipeline; The forward sight distance include:

[0063] As a fixed reference value, As a regulating factor, For the initial trajectory in t Curvature of time, q is the exponent of the curvature.

[0064] The system generates real-time heading control commands based on the desired heading angle, and then adjusts the underwater robot's heading and forward sight distance in real time through a closed-loop control system. It makes corrections based on the current state and expected goals to ensure that the underwater robot tracks the pipeline smoothly and accurately.

[0065] like Figure 4 As shown, another embodiment of the present invention also provides an autonomous underwater robot subsea pipeline tracking device based on side-scan sonar, comprising: The acquisition module is used to continuously acquire seabed acoustic images using side-scan sonar while controlling the underwater robot to perform a comb search in the target survey area; The first determining module is used to detect pipeline traces based on the underwater acoustic image and determine the initial trajectory of the pipeline based on the pipeline traces, wherein the initial trajectory is related to the pipeline's layout trajectory. An estimation module is used to estimate the state of the pipeline based on the initial trajectory using a Kalman filter; The second determination module is used to determine the spatial length, confidence level, and continuity of the initial trajectory based on the state estimation results and using a trajectory quality assessment method, and to generate a trajectory score. The third determining module is used to determine the initial trajectory as the target tracking trajectory of the underwater robot in response to the trajectory score meeting the preset requirements. The adjustment module is used to dynamically adjust the forward-looking distance and heading of the underwater robot based on the target tracking trajectory.

[0066] In one embodiment, the target survey area is a rectangular area, including a short side and a long side; Controlling the underwater robot to perform a comb-like search within the target survey area includes: Multiple survey lines parallel to the first side are generated using the first side of the target survey area as a reference. Based on the first side and the survey line, a comb-shaped survey line is generated, and the underwater robot is controlled to search for pipelines based on the comb-shaped survey line.

[0067] In one embodiment, generating a comb-shaped survey line based on the first edge and the survey line includes: The comb-shaped survey lines are generated based on the first side and the survey line spacing between the survey lines, wherein the survey line spacing w = 2Rcov - δ Rcov represents the effective range of a side-scan sonar on one side. δ The set overlap amount; Determine the waypoint sequence based on the comb-shaped survey lines; Continuous acquisition of seabed acoustic images using side-scan sonar, including: During the underwater robot's search along the waypoint sequence, the side-scan sonar sequentially acquires the seabed acoustic images of each waypoint.

[0068] In one embodiment, determining the initial trajectory of the pipeline based on the pipeline traces includes: The pipeline points are associated with the goal of minimizing the global association cost to determine the initial trajectory of the pipeline.

[0069] In one embodiment, associating the pipeline points with the goal of minimizing the global association cost includes: The pipeline points are associated using the following association cost function, with the goal of minimizing the global association cost:

[0070] For the association cost function, The spatial distance between the target point and the initial trajectory. The weighting coefficient represents the angle difference between the target point and the initial trajectory. and These measures the importance of spatial distance and angular differences in the association cost function. express t The target point at any given time, express tThe initial trajectory at time -1 i Indicates the first i A dot mark, j Indicates the first j A trajectory point; The device further includes: An optimization module is used to determine the optimal match between the target point and the initial trajectory using a global optimization algorithm, and to optimize the initial trajectory based on the optimal matching result; The global optimization algorithm includes:

[0071] x For spatial coordinates, m For the number of dots, n The number of trajectory points is denoted by , and the spatial coordinates of the points matched with the trajectory points are denoted by . .

[0072] In one embodiment, the trajectory quality assessment method includes:

[0073] in, for t Initial trajectory at time trajectory score, For the initial trajectory in t At the time of j The spatial length at each point for t The initial trajectory at time 1 i Confidence level at each point for t The initial trajectory at time 1 j Trajectory continuity of points, weighting coefficients , , These are used to measure the lifetime of a trajectory. Confidence of dot marks Related costs In trajectory quality evaluation function The relative importance of [the subject / method].

[0074] In one embodiment, , and For the initial trajectory The Middle n , n -1 spatial coordinates of a point, where express t Time Track The total number of dots already included in the data;

[0075] It is a binary indicator function. For trajectory points j The weighting coefficients.

[0076] In one embodiment, the step of using a Kalman filter to estimate the state of the pipeline based on the initial trajectory includes: The state of the pipeline is estimated based on the following observation equation and state equation:

[0077] x k , y k This indicates that the pipeline is in k Location at any given moment φ k For the pipeline in k The direction angle at that moment, , , These are the rates of change of the position and orientation angle of the pipeline, respectively; The state equations include: The observation equations include: Z k = H k X k + V k , X k for k The predicted pipeline state vector at time 10:00. X k-1 for k- Predicted pipeline state vector at time 1, Z k for k Pipeline observation vector at time 10:00 Z k for k Pipeline observation vector at time 10:00 for k The state transition matrix at time t, H k for k The observation matrix at time, W k-1 and V k These are system noise and observation noise, respectively. for k The control input matrix at time -1.

[0078] In one embodiment, dynamically adjusting the forward-looking distance and heading of the underwater robot based on the target tracking trajectory includes: An adaptive line-of-sight guidance law is used in conjunction with the target tracking trajectory to dynamically adjust the forward-looking distance and desired heading angle of the underwater robot; The desired heading angle include:

[0079] For the estimated direction angle of the pipeline, y e This is the vertical distance from the underwater robot to the nearest point on the pipeline; The forward sight distance include:

[0080] As a fixed reference value, As a regulating factor, For the initial trajectory in t Curvature of time, q is the exponent of the curvature.

[0081] Another embodiment of the present invention also provides an electronic device, comprising: One or more processors; Memory, configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for tracking subsea pipelines by an autonomous underwater robot based on side-scan sonar as described in any one of the above descriptions.

[0082] Furthermore, one embodiment of the present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the above-described method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar. It should be understood that the various solutions in this embodiment have the corresponding technical effects described in the above-described method embodiments, and will not be repeated here.

[0083] Furthermore, embodiments of the present invention also provide a computer program product, which is tangibly stored on a computer-readable medium and includes computer-readable instructions that, when executed, cause at least one processor to perform a method for tracking subsea pipelines by an autonomous underwater robot based on side-scan sonar, as described in the embodiments above.

[0084] It should be noted that the computer storage medium of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access storage medium (RAM), a read-only storage medium (ROM), an erasable programmable read-only storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only storage medium (CD-ROM), an optical storage medium, a magnetic storage medium, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program configured for use by or in connection with an instruction execution system, system, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, antenna, optical fiber, RF, etc., or any suitable combination thereof.

[0085] Furthermore, those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0086] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0087] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0088] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of protection of this application is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.

Claims

1. A method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar, characterized in that, include: During the comb-like search of the target survey area by the control of the underwater robot, side-scan sonar is used to continuously acquire seabed acoustic images; Based on the underwater acoustic image, pipeline traces are detected, and the initial trajectory of the pipeline is determined based on the pipeline traces. The initial trajectory is related to the pipeline's layout trajectory. The state of the pipeline is estimated based on the initial trajectory using a Kalman filter. Based on the state estimation results, the spatial length, confidence level, and continuity of the initial trajectory are determined using a trajectory quality assessment method, and a trajectory score is generated. In response to the trajectory score meeting the preset requirements, the initial trajectory is determined to be the target tracking trajectory of the underwater robot; The underwater robot's forward-looking distance and heading are dynamically adjusted based on the target tracking trajectory.

2. The method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar according to claim 1, characterized in that, The target survey area is a rectangular area, including the short side and the long side; Controlling the underwater robot to perform a comb-like search within the target survey area includes: Multiple survey lines parallel to the first side are generated using the first side of the target survey area as a reference. Based on the first side and the survey line, a comb-shaped survey line is generated, and the underwater robot is controlled to search for pipelines based on the comb-shaped survey line.

3. The method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar according to claim 2, characterized in that, Based on the first side and the survey line, a comb-shaped survey line is generated, including: The comb-shaped survey lines are generated based on the first side and the survey line spacing between the survey lines, wherein the survey line spacing w = 2Rcov - δ Rcov represents the effective range of a side-scan sonar on one side. δ The set overlap amount; Determine the waypoint sequence based on the comb-shaped survey lines; Continuous acquisition of seabed acoustic images using side-scan sonar, including: During the underwater robot's search along the waypoint sequence, the side-scan sonar sequentially acquires the seabed acoustic images of each waypoint.

4. The method for tracking subsea pipelines using an autonomous underwater robot based on side-scan sonar according to claim 1, characterized in that, Determining the initial trajectory of the pipeline based on the pipeline points includes: The pipeline points are associated with the goal of minimizing the global association cost to determine the initial trajectory of the pipeline.

5. The method for tracking subsea pipelines by an autonomous underwater robot based on side-scan sonar according to claim 4, characterized in that, The association of the pipeline points with the goal of minimizing the global association cost includes: The pipeline points are associated using the following association cost function, with the goal of minimizing the global association cost: For the association cost function, The spatial distance between the target point and the initial trajectory. The weighting coefficient represents the angle difference between the target point and the initial trajectory. and These measures the importance of spatial distance and angular differences in the association cost function. express t The target point at any given time, express t The initial trajectory at time -1 i Represents the first point in the dot pattern i One point, j Indicates the first j A trajectory point; The method further includes: A global optimization algorithm is used to determine the optimal match between the target point and the initial trajectory, and the initial trajectory is optimized based on the optimal matching result; The global optimization algorithm includes: x For spatial coordinates, m For the number of dots, n The number of trajectory points. The spatial coordinates of the matching point trace and trajectory point.

6. The method for tracking subsea pipelines by an autonomous underwater robot based on side-scan sonar according to claim 1, characterized in that, The trajectory quality assessment method includes: in, for t Initial trajectory at time trajectory score, For the initial trajectory in t At the time of j The spatial length at each point for t The initial trajectory at time 1 i Confidence level at each point for t The initial trajectory at time 1 j Trajectory continuity of points, weighting coefficients , , These are used to measure the lifetime of a trajectory. Confidence of dot marks Related costs In trajectory quality evaluation function The relative importance of [the subject / method].

7. The method for tracking subsea pipelines by an autonomous underwater robot based on side-scan sonar according to claim 6, characterized in that, , and For the initial trajectory The Middle n , n -1 spatial coordinates of a point, where express t Time Track The total number of dots already included in the data; It is a binary indicator function. For trajectory points j The weighting coefficients.

8. The method for tracking subsea pipelines by an autonomous underwater robot based on side-scan sonar according to claim 1, characterized in that, The process of using a Kalman filter to estimate the pipeline's state based on the initial trajectory includes: The state of the pipeline is estimated based on the following observation equation and state equation: x k , y k This indicates that the pipeline is in k Location at any given moment φ k For the pipeline in k The direction angle at that moment, , , These are the rates of change of the position and orientation angle of the pipeline, respectively; The state equations include: The observation equations include: Z k = H k X k + V k , X k for k The predicted pipeline state vector at time 10:

00. X k-1 for k- Predicted pipeline state vector at time 1, Z k for k Pipeline observation vector at time 10:00 for k The state transition matrix at time t, H k for k The observation matrix at time, W k-1 and V k These are system noise and observation noise, respectively. for k The control input matrix at time -1.

9. The method for tracking subsea pipelines by an autonomous underwater robot based on side-scan sonar according to claim 1, characterized in that, The dynamic adjustment of the underwater robot's forward-looking distance and heading based on the target tracking trajectory includes: An adaptive line-of-sight guidance law is used in conjunction with the target tracking trajectory to dynamically adjust the forward-looking distance and desired heading angle of the underwater robot; The desired heading angle include: For the estimated direction angle of the pipeline, y e This is the vertical distance from the underwater robot to the nearest point on the pipeline; The forward sight distance include: As a fixed reference value, As a regulating factor, For the initial trajectory in t Curvature of time, q is the exponent of the curvature.

10. A side-scan sonar-based autonomous underwater robot subsea pipeline tracking device, characterized in that, include: The acquisition module is used to continuously acquire seabed acoustic images using side-scan sonar while controlling the underwater robot to perform a comb search in the target survey area; The first determining module is used to detect pipeline traces based on the underwater acoustic image and determine the initial trajectory of the pipeline based on the pipeline traces, wherein the initial trajectory is related to the pipeline's layout trajectory. An estimation module is used to estimate the state of the pipeline based on the initial trajectory using a Kalman filter; The second determination module is used to determine the spatial length, confidence level, and continuity of the initial trajectory based on the state estimation results and using a trajectory quality assessment method, and to generate a trajectory score. The third determining module is used to determine the initial trajectory as the target tracking trajectory of the underwater robot in response to the trajectory score meeting the preset requirements. The adjustment module is used to dynamically adjust the forward-looking distance and heading of the underwater robot based on the target tracking trajectory.

Images