Method and device for determining inspection path of unmanned ship, equipment and medium

Abstract

The embodiment of the invention discloses a method, a device, equipment and a medium for determining an inspection path of an unmanned ship, and the method comprises the steps: generating a digital twin model of an inspection region according to the sensor data of a preset sensor of the unmanned ship; generating a plurality of candidate inspection paths based on the digital twin model and a preset inspection sequence; updating the plurality of candidate inspection paths based on the obstacle information and the position information of the preset operation part to obtain a plurality of updated inspection paths; and determining a target driving path based on the path indexes of the plurality of updated routing inspection paths, the path indexes including routing inspection coverage rate, routing inspection task time consumption and routing inspection task energy consumption. According to the technical scheme provided by the invention, the accuracy of path determination can be improved, and the inspection efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of navigation, and more particularly to a method, apparatus, equipment, and medium for determining the inspection path of an unmanned surface vessel. Background Technology

[0002] With the booming development of the global marine economy, the demands for maritime facility safety, marine ecological protection, and maritime supervision are increasing. Traditional manual inspections face bottlenecks such as low efficiency, high risk, and limited coverage. Unmanned surface vessel (USV) technology has emerged to address this challenge, becoming a key force driving change in the field of maritime inspection due to its efficient autonomous navigation, precise sensor detection, and real-time data transmission capabilities. The widespread application of USV maritime inspection technology not only promotes the intelligent transformation of marine resource development but also provides core technological support for building a safe and green marine environment, contributing to the modernization and upgrading of the global ocean governance system.

[0003] However, the inspection paths of unmanned surface vessels (USVs) are generally planned manually. Manually planned paths cannot adapt to the ever-changing marine environment, resulting in low inspection efficiency and affecting the safety of USVs. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for determining the inspection path of an unmanned surface vessel (USV). The technical solution of this invention can improve the intelligence and accuracy of inspection path planning, increase the inspection efficiency of USVs, and ensure safety.

[0005] In a first aspect, embodiments of the present invention provide a method for determining an unmanned surface vessel (USV) inspection path, comprising:

[0006] Based on sensor data from the unmanned surface vessel's preset sensors, a digital twin model of the inspection area is generated. The inspection area is the region formed by the initial position of the unmanned surface vessel and the positions of each object to be inspected. The digital twin model includes detection point information of the objects to be inspected, ocean current information, and obstacle information within the inspection area.

[0007] Multiple candidate inspection paths are generated based on the digital twin model and the preset inspection order, wherein the preset inspection order represents the inspection order of the object to be inspected;

[0008] Based on the obstacle information and the location information of the preset working components, the multiple candidate inspection paths are updated to obtain multiple updated inspection paths;

[0009] The target driving route is determined based on the path indicators of the multiple updated inspection routes, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption.

[0010] Secondly, embodiments of the present invention provide a device for determining the inspection path of an unmanned surface vessel, comprising:

[0011] The generation module is used to generate a digital twin model of the inspection area based on the sensor data of the preset sensors of the unmanned surface vessel (USV). The inspection area is the area formed by the initial position of the USV and the positions of each object to be inspected. The digital twin model includes the detection point information of the objects to be inspected, ocean current information and obstacle information within the inspection area.

[0012] The candidate inspection path determination module is used to generate multiple candidate inspection paths based on the digital twin model and the preset inspection order, wherein the preset inspection order represents the inspection order of the object to be inspected;

[0013] The inspection path determination module is used to update the multiple candidate inspection paths based on the obstacle information and the location information of the preset working components, so as to obtain multiple updated inspection paths.

[0014] The target driving route determination module is used to determine the target driving route based on the path indicators of the multiple updated inspection routes, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption.

[0015] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0016] At least one processor; and,

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the method for determining the unmanned surface vessel inspection path as described in any one of the embodiments of the present invention.

[0019] Fourthly, according to an embodiment of the present invention, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium stores computer instructions, which are used to cause a processor to execute the method for determining the inspection path of an unmanned surface vessel as described in any embodiment of the present invention.

[0020] This invention provides a method, apparatus, device, and medium for determining an unmanned surface vessel (USV) inspection path. The method includes: generating a digital twin model of an inspection area based on sensor data from preset sensors of the USV, wherein the inspection area is a region formed by the initial position of the USV and the positions of each object to be inspected; the digital twin model includes detection point information of the objects to be inspected, ocean current information, and obstacle information within the inspection area; generating multiple candidate inspection paths based on the digital twin model and a preset inspection sequence, wherein the preset inspection sequence represents the inspection sequence of the objects to be inspected; updating the multiple candidate inspection paths based on the obstacle information and the position information of preset operating components, resulting in multiple updated inspection paths; and determining a target travel path based on path indicators of the multiple updated inspection paths, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption. This embodiment of the invention models the inspection area using sensor data, facilitating the generation of multiple candidate inspection paths based on the digital twin model of the inspection area. Based on obstacle information and the location information of preset operating components, candidate inspection paths can be optimized to avoid collisions between unmanned surface vessels (USVs) or preset operating components and obstacles at sea. By updating the path indicators of multiple inspection paths, the target travel path can be determined, thereby ensuring that the inspection coverage, inspection time, and inspection energy consumption of the target travel path are relatively optimal. The method of this invention can improve the intelligence and accuracy of inspection path determination, increase inspection efficiency, and ensure the safety of USVs. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a method for determining an unmanned surface vessel (USV) inspection path according to Embodiment 1 of the present invention;

[0023] Figure 2 This is a flowchart of a method for determining an unmanned surface vessel inspection path according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of an unmanned surface vessel path planning system provided in Embodiment 3 of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of a device for determining the inspection path of an unmanned surface vessel according to Embodiment 4 of the present invention;

[0026] Figure 5This is a schematic diagram of the structure of an electronic device not provided in the embodiments of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] It should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a method for determining the inspection path of an unmanned surface vessel (USV) according to Embodiment 1 of the present invention. This method is specifically applicable to the planning of inspection paths for USVs at sea. This method can be executed by a USV inspection path determination device, which can be composed of software and / or hardware and configured in the control system of the USV.

[0032] like Figure 1 As shown, it includes:

[0033] Step 110: Generate a digital twin model of the inspection area based on the sensor data of the unmanned surface vessel's preset sensors. The inspection area is the region formed by the initial position of the unmanned surface vessel and the positions of each object to be inspected. The digital twin model includes the detection point information of the objects to be inspected, ocean current information, and obstacle information within the inspection area.

[0034] Specifically, the unmanned surface vessel (USV) is equipped with various heterogeneous sensors to collect various sensor data within the inspection area, and then uses the sensor data to generate a digital twin model of the inspection area. The inspection area is the region formed by the initial position of the USV and the positions of each object to be inspected. Specifically, it can be the area enclosed by the initial position of the USV and the positions of each object to be inspected. Furthermore, due to the special nature of the marine environment, the inspection area can also include underwater structures below the ocean.

[0035] Furthermore, a digital model corresponding to the actual physical entity is created in virtual space. This digital twin model includes the coordinates of each spatial point within the inspection area, the detection point information of the object to be inspected, ocean current information, and obstacle information within the inspection area. The detection points of the object to be inspected can be preset target components or damaged defect areas. Detection point information includes the location of the detection point, component type, and damage type, and may also include the estimated repair time corresponding to the detection point type, the distribution information of the detection points, and the risk level. Ocean current information can include the current velocity, pressure, and direction. Obstacle information can include the location, type, and predicted movement trajectory of marine obstacles.

[0036] Optionally, generating a digital twin model of the inspection area based on sensor data from the unmanned surface vessel's preset sensors includes:

[0037] Acquire sonar data, ocean current Doppler data, point cloud data, and image data sent by the preset sensors of the unmanned surface vessel; determine the detection point information of the object to be inspected and the coordinates of obstacles within the inspection area based on the image data.

[0038] A point cloud model of the inspection area is generated based on the sonar data and point cloud data; ocean current information of the inspection area is determined based on the ocean current Doppler data; a digital twin model of the inspection area is generated based on the point cloud model, the ocean current information of the inspection area, the coordinates of obstacles, and the detection point information of the object to be inspected.

[0039] Specifically, the sensors include underwater sonar, three-dimensional lidar, and multispectral imager.

[0040] Underwater sonar is used to collect sonar data and ocean current Doppler data of the inspection area, three-dimensional lidar is used to collect point cloud data, and multispectral imager is used to collect image data of the inspection area.

[0041] Specifically, the point cloud model includes the three-dimensional coordinates of each spatial point in the inspection area. By labeling the corresponding ocean current information, obstacle coordinates, and detection point information of the object to be inspected on these spatial points, a digital twin model of the inspection area can be generated. Image data can include surface defects of the object to be inspected and ocean images of the inspection area. Specifically, locations with surface defects can be identified as detection points, and the corresponding surface defect information can be used to define these detection point information.

[0042] For example, the underwater sonar employs broadband synthetic aperture sonar technology with a transmission frequency range of f. min =50kHz to f max A frequency-modulated signal of 200kHz is used to generate millimeter-resolution three-dimensional point cloud data of the object to be inspected and the underwater structure through the echo signal.

[0043] For example, the ocean current velocity V can be directly calculated from the collected ocean current Doppler data using echo frequency shift. current .

[0044] For example, sonar data can also be used to determine surface defects of the object to be inspected, specifically: the acoustic scattering model of the surface defects is as follows:

[0045]

[0046] Where p is the position of the unmanned surface vessel, S(p k ) represents the location p of the surface defect. k Acoustic scattering intensity at point A; k Let be the reflection coefficient of the k-th surface defect, which is proportional to the size of the surface defect; δ(pp) represents the round-trip time delay of the sound wave, and c represents the speed of sound in water; k ) is the Dirac function, which characterizes the discrete distribution characteristics of the defect, and f is the sound wave frequency.

[0047] For example, the current velocity is calculated from ocean current Doppler data as follows:

[0048]

[0049] Where Δf is the ocean current Doppler frequency shift; c is the speed of sound; f0 is the sonar transmission frequency; and cosθ is the angle between the sound beam and the ocean current direction.

[0050] 3D LiDAR: Utilizing the Time-of-Flight (ToF) principle, it emits pulsed laser light with a wavelength of 1550nm. Through point cloud registration algorithms, it constructs a geometric model of the surface of the object to be inspected and surrounding water obstacles (such as buoys and ship wreckage) with centimeter-level accuracy. The point cloud registration error function is defined as:

[0051]

[0052] Where R is the rotation matrix and t is the translation vector; x i ,y i ω represents the coordinates of the matching point pair in the point cloud of adjacent frames; i The weighting coefficients are calculated based on point cloud density and curvature, where N is the number of coordinates.

[0053] Multispectral imagers are used to cover the visible light (400-700nm) and near-infrared (700-1000nm) bands, and detect surface corrosion, biofouling, coating peeling, and marine surface conditions of objects to be inspected through spectral feature fusion.

[0054] Furthermore, a digital twin model is obtained by weighted fusion of continuous sensor data using the covariance matrix:

[0055]

[0056] Among them, M fused For the inspection area environmental model (digital twin model), M s scan The original data matrix of the s-th type of sensor can be obtained from the sensor data of the aforementioned types of sensors; M4 tactile This is the raw data matrix of a tactile sensor; W s η is the dynamic weight matrix; η(t) is the tactile data decay function. Tactile sensors can be installed at specific positions on the robotic arm of the unmanned surface vessel.

[0057] Step 120: Generate multiple candidate inspection paths based on the digital twin model and the preset inspection order, wherein the preset inspection order represents the inspection order of the object to be inspected.

[0058] Among them, the objects to be inspected can be the offshore wind farm base.

[0059] Specifically, since there are multiple objects to be inspected, there are also multiple preset inspection sequences. For example, if there are three objects to be inspected, A, B, and C, the preset inspection sequences can be ABC, ACB, BAC, BCA, CAB, and CBA. Furthermore, multiple candidate inspection paths can be generated by combining the detection point information of the objects to be inspected from the digital twin model, the ocean current information and obstacle information within the inspection area, and the preset inspection sequence. It is understandable that the candidate inspection paths corresponding to different preset inspection sequences differ in terms of required time, energy consumption, and inspection efficiency. Therefore, the method of this embodiment of the invention needs to optimize multiple candidate inspection paths multiple times to determine the target inspection path.

[0060] Step 130: Update the multiple candidate inspection paths based on the obstacle information and the location information of the preset working components to obtain multiple updated inspection paths.

[0061] Specifically, the pre-set operational components are those configured on the unmanned surface vessel (USV) for inspection and maintenance, such as a robotic arm. Due to the size and installation limitations of the robotic arm itself, it's crucial to avoid collisions with obstacles during USV operation to prevent damage. Furthermore, obstacles in the ocean are typically in a dynamic, moving state. Therefore, it's necessary to update the candidate inspection path based on obstacle information and the location information of the pre-set operational components to obtain an updated inspection path, ensuring the USV can safely reach the inspection location.

[0062] Step 140: Determine the target driving route based on the path indicators of the multiple updated inspection routes, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption.

[0063] Specifically, after obtaining the updated inspection path, the various path indicators of the updated inspection path can be determined. Since the path indicators of different updated inspection paths differ, a new target driving path can be generated based on the path indicators of multiple updated inspection paths, thereby making the various path indicators of the target driving path relatively optimal.

[0064] Optionally, the detection point information includes the detection location, and after the unmanned surface vessel arrives at the location of the object to be inspected, it also includes:

[0065] Based on the position information and detection position of the preset working component, the rotation angle of each sub-component of the preset working component is adjusted so that the sub-component used for maintenance operation reaches the detection position; based on the contact pressure fed back by the tactile sensor of the sub-component used for maintenance operation, the worn parts at the detection position are repaired.

[0066] Specifically, once the unmanned surface vessel (USV) reaches the location of the object to be inspected, the position information of the preset working components can be determined based on the connection relationship between the USV and the preset working components. Furthermore, the preset working components can adjust the rotation angle of their preset sub-components to bring the sub-components used for maintenance operations to the detection position. Simultaneously, the maintenance sub-components are equipped with tactile sensors, which can collect contact pressure through contact. Based on the contact pressure feedback from the tactile sensors of the maintenance sub-components, the worn parts at the detection position can be repaired.

[0067] For example, the preset working component can be a robotic arm, and the sub-components include working parts for maintenance operations and joints of the robotic arm.

[0068] For each robotic arm, an inverse kinematics solution model is constructed, and the objective function for the robotic arm end-effector pose is defined:

[0069]

[0070] Among them, T base Let θ be the coordinate system of the robotic arm base; i S is the rotation angle of the i-th joint; i The helical motion generators corresponding to the joint axis are used; the joint angle θ is solved by the gradient descent method. i This allows the end effector (a sub-component used for maintenance operations) to accurately reach the detection location.

[0071] Multi-robotic arm task allocation: A dynamic auction algorithm is used to allocate detection tasks, and a task value function is defined.

[0072]

[0073] Among them, D priority,j The priority of the j-th detection location (based on confidence level and risk level); t estimate,j The estimated time for the robotic arm to complete the j-position detection task; ω1, ω2, and ω3 are weighting coefficients; the task allocation results are synchronized to each robotic arm control unit via a distributed communication protocol; p USV P represents the current position of the robotic arm. target,j For the j-th detection position, t estimate,j Let be the estimated completion time for the j-th detection location.

[0074] Contact scanning force control strategy: Based on tactile sensor feedback, an impedance control algorithm is used to adjust the contact force at the end effector of the robotic arm (the sub-component used for maintenance operations).

[0075]

[0076] Among them, K p K d Here are the stiffness and damping matrices; x desired For preset contact trajectory; x actual This is the actual contact trajectory. and These are the derivatives of the preset contact trajectory and the actual contact trajectory, respectively.

[0077] This invention provides a method for determining an unmanned surface vessel (USV) inspection path. The method includes: generating a digital twin model of the inspection area based on sensor data from preset sensors of the USV, wherein the inspection area is a region formed by the initial position of the USV and the positions of each object to be inspected; the digital twin model includes detection point information of the objects to be inspected, ocean current information, and obstacle information within the inspection area; generating multiple candidate inspection paths based on the digital twin model and a preset inspection sequence, wherein the preset inspection sequence represents the inspection sequence of the objects to be inspected; updating the multiple candidate inspection paths based on the obstacle information and the position information of preset operating components to obtain multiple updated inspection paths; and determining a target travel path based on path indicators of the multiple updated inspection paths, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption. Specifically, candidate inspection paths can be optimized based on obstacle information to avoid collisions with obstacles at sea. Simultaneously, by updating the path indicators of multiple inspection paths, the target travel path can be determined, thereby ensuring that the inspection coverage, inspection time, and energy consumption of the target travel path are relatively optimal. The method of this invention can improve the accuracy of inspection path determination, increase inspection efficiency, and ensure the safety of unmanned surface vessels.

[0078] Example 2

[0079] Figure 2 This is a flowchart of a method for determining an unmanned surface vessel (USV) inspection path according to Embodiment 2 of the present invention. Based on the above embodiment, this method further specifies the methods for determining candidate inspection paths, updated inspection paths, and target travel paths.

[0080] like Figure 2 As shown, it includes:

[0081] Step 201: Generate a digital twin model of the inspection area based on the sensor data of the unmanned surface vessel's preset sensors. The inspection area is the region formed by the initial position of the unmanned surface vessel and the positions of each object to be inspected. The digital twin model includes the detection point information of the objects to be inspected, ocean current information, and obstacle information within the inspection area.

[0082] Step 202: Based on the position of the unmanned surface vessel, the coordinates of the obstacles, the positions of each object to be inspected, the ocean current information, and each preset inspection sequence, determine the potential energy field distribution information corresponding to each preset inspection sequence.

[0083] Step 203: For any potential energy field distribution information, determine the potential energy decrease direction based on the potential energy field distribution information, and determine the candidate inspection path based on the potential energy decrease direction.

[0084] Specifically, different preset inspection sequences correspond to different potential energy field distribution information, which is used to characterize the potential energy distribution at each location point within the inspection area. This includes, for example, the potential energy magnitude, equipotential lines, and potential energy gradient at each coordinate point. Furthermore, since the unmanned surface vessel (USV) must reach the locations of each object to be inspected according to the preset inspection sequence, and given that ocean current information differs at different locations, and obstacles exist at some points, all of these factors affect the potential energy field distribution information of the inspection area. Specifically, the detection location of the object to be inspected can be considered the point of lowest potential energy, and the current location as the point of highest potential energy. By controlling the USV to travel along the direction of decreasing potential energy, it can be ensured that the USV reaches the detection location.

[0085] Optionally, step 202 includes:

[0086] Based on the position of the unmanned surface vessel (USV) and the coordinates of obstacles within the inspection area, the potential energy parameters of the obstacles are determined; based on the ocean current information, the potential energy parameters of the ocean currents are determined; for any preset inspection sequence, the position potential energy parameters corresponding to the preset inspection sequence are determined based on the position of the USV and the position of each object to be inspected; based on the obstacle potential energy parameters, the position potential energy parameters corresponding to the preset inspection sequence, and the ocean current potential energy parameters, the potential energy field distribution information corresponding to the preset inspection sequence is determined.

[0087] Specifically, factors such as obstacle coordinates, ocean current information, and the positions of each object to be inspected in the preset inspection sequence all affect the potential energy field distribution information. Therefore, it is necessary to comprehensively consider these influencing factors to determine accurate potential energy field distribution information, thereby improving the accuracy of candidate inspection paths.

[0088] Optionally, step 203 includes:

[0089] The potential energy gradient corresponding to the current position of the unmanned surface vessel is determined based on the potential energy field distribution information; the next position of the unmanned surface vessel is determined based on the current position of the unmanned surface vessel and the potential energy gradient.

[0090] Specifically, the unmanned surface vessel will move in the direction of the fastest decrease in potential energy, that is, in the direction of the fastest decrease in gradient between two adjacent potential energy gradients.

[0091] For example, the potential energy field distribution information can be determined using the following formula:

[0092] U(p)=α·U goal (p)+β·U obs (p)+γ·U current (p)

[0093] Where p = (x, y, z) are the three-dimensional position coordinates of the unmanned surface vessel; U goal (p)=||pp target || 2The gravitational potential field (position potential energy parameter) attracts the unmanned surface vessel to move towards the location of the object to be inspected. target For detection location; The obstacle potential energy parameter, p, repels the unmanned surface vessel away from the obstacle. obs,i U represents the position of the i-th obstacle. current (p)=||V current (p)||·cosθ is the ocean current potential energy parameter, resisting the ocean current V. current Lateral drift of (p), V current (p) represents the real-time ocean current velocity at position p, θ represents the angle between the unmanned surface vessel's heading and the ocean current, and α, β, γ represent weighting coefficients.

[0094] For example, the gradient descent algorithm is as follows:

[0095]

[0096] Where, p k Current position It is a potential energy field in p k The gradient at point p, where η is the step size coefficient; its termination condition is when ||p|| k -p target Iteration stops when || < δ (δ is the position tolerance), p target To detect the location, iteratively generate a discrete path point sequence {p0, p1, ..., p...}. n}, where p0 is the starting position, p n The target detection location.

[0097] Step 204: For any candidate inspection path, determine the end position of the preset operating component of the unmanned surface vessel on the current inspection path.

[0098] Specifically, the end position of the preset working component can be determined by the current position of the unmanned surface vessel (USV) and its connection relationship with the preset working component.

[0099] Step 205: Determine the spatiotemporal conflict information corresponding to the current inspection path based on the end position of the preset operation component corresponding to the current inspection path, the obstacle coordinates of each obstacle in the inspection area, and the current position of the unmanned surface vessel.

[0100] Spatiotemporal conflict information can characterize whether the unmanned surface vessel and its pre-set operating components overlap with obstacles at any given moment. For example, spatiotemporal conflict information includes a spatiotemporal conflict penalty item.

[0101] Specifically, the pre-installed operating components are generally installed on the side of the unmanned surface vessel (USV). Therefore, during operation, it is necessary to ensure that the USV and the pre-installed operating components do not collide with obstacles on the ocean.

[0102] Step 206: Determine the optimized inspection path corresponding to the current inspection path based on the spatiotemporal conflict information.

[0103] Specifically, the current inspection path can be optimized using spatiotemporal conflict information to ensure the safety of the unmanned surface vessel.

[0104] For example, path optimization can be performed using the following formula:

[0105] f(n)=g(n)+h(n)+λ·T collision (n)

[0106] Where g(n) is the actual cost from the starting point to position n; h(n) is the heuristically estimated cost; p is a penalty term for spatiotemporal conflict. arm,j (t) represents the position of the j-th robotic arm (preset working component) at the end of time t. If the robotic arm is located at p at time t... arm,j (t), then the unmanned surface vessel path point p n Must satisfy ||p n -p arm,j (t)||>σ, where σ is the safety distance threshold; λ is the conflict penalty weight; p obs,d (t) represents the coordinates of the dynamic obstacle, which are detected in real time by sonar and lidar.

[0107] Step 207: Smooth the optimized inspection paths corresponding to each candidate inspection path to obtain the updated inspection paths corresponding to each candidate inspection path.

[0108] Specifically, the optimized inspection path consists of a series of discrete coordinate points. To ensure the smooth movement of the unmanned surface vessel, the optimized inspection path needs to be smoothed.

[0109] For example, the updated inspection path can be determined using the following formula:

[0110]

[0111] T(s) is the parameterized form of the updated inspection path, T0 is the initial pose matrix, and G... k For the 6 generators of the SE(3) Lie algebra (corresponding to 3 translation directions + 3 rotation axes), a k Here, is the trajectory parameter, and s is the normalized path parameter, which changes continuously from the starting point to the ending point to ensure that the pose trajectory of T(s) has no abrupt changes.

[0112] Optionally, based on the ocean current information corresponding to the current position of the unmanned surface vessel (USV), the ocean current resistance to the USV is determined; based on the ocean current resistance, the supplementary power for the USV is determined; and based on the supplementary power, the USV is controlled to travel along the updated inspection path.

[0113] Specifically, since ocean currents can impact unmanned surface vessels (USVs), ocean current information can be used to determine ocean current resistance. Based on this resistance, additional power can be determined to counteract the current resistance, ensuring that the USV travels along the updated inspection path.

[0114] For example, the unmanned surface vessel includes a magnetohydrodynamic (MHD) vector thruster: employing a multi-channel MHD propulsion unit, the thrust direction and magnitude are controlled by Lorentz force, and the single-channel thrust output equation is:

[0115] F i =k·B i ·I i ·L i

[0116] Among them, B i Let I be the magnetic field strength of the i-th channel; i L represents the current intensity. i is the electrode spacing; k is the magnetohydrodynamic constant; the thruster response time is ≤10ms, and it supports 360° omnidirectional vector thrust output.

[0117] For example, the unmanned surface vessel (USV) has a biomimetic articulated hull: the hull consists of three articulated modules, which dynamically adjust the bending angle φ∈[0-45] degrees via hydraulic drive to adapt to the narrow gap of the base; the bending angle control equation is:

[0118]

[0119] Where φ0 is the initial angle; e(t) = φ target -φ actual For angular error; K p This is the proportional gain coefficient.

[0120] Compensation power F comp Real-time ocean current velocity V based on digital twin model current Calculate the thrust compensation of the thruster: Where m is the mass of the unmanned surface vessel (USV) and ω is the angular velocity of the USV.

[0121] Step 208: Determine the target velocity and target acceleration of each path point on the updated inspection path.

[0122] Specifically, to ensure smooth driving and to determine the estimated energy consumption and estimated task duration, it is necessary to determine the target speed and target acceleration of each path point on the updated inspection path.

[0123] For example, curvature and acceleration can be jointly optimized: construct an objective function that minimizes the integral of trajectory curvature and the rate of change of acceleration:

[0124]

[0125] Where J is the objective function, ||T″(s)|| is the second derivative of the updated inspection path, representing acceleration; T′(s) is the first derivative of the updated inspection path, representing velocity; ω1 and ω2 are weighting coefficients, controlling smoothness and energy consumption respectively.

[0126] Furthermore, the target velocity and target acceleration must still be guaranteed to not exceed the maximum constraint velocity. ||ω(s)||≤θ max ||a(s)||≤a max ω(s) is the angular velocity vector corresponding to the target velocity, and a(s) is the linear acceleration vector corresponding to the target acceleration.

[0127] Step 209: Determine the estimated maintenance time and risk level of each inspection point of each object to be inspected based on the inspection point information of each object to be inspected.

[0128] Specifically, different types of inspection points have different estimated maintenance times and risk levels.

[0129] Step 210: Determine the inspection task time based on the target speed, target acceleration and estimated maintenance time of each object to be inspected in the updated inspection path, and determine the inspection task energy consumption based on the inspection task time.

[0130] For any update inspection path, the inspection task time is the total time taken to execute the inspection task through the update inspection path, and the energy consumption for executing the inspection task through the update inspection path is the total energy consumption of the inspection task.

[0131] Specifically, the travel time can be determined by updating the target speed and target acceleration of the waypoints in the inspection path. Then, based on the travel time and the estimated maintenance time of each object to be inspected, the inspection task time can be determined. Furthermore, the energy consumption of this inspection task can be calculated based on the inspection task time of the unmanned surface vessel.

[0132] Step 211: Determine the inspection coverage rate based on the distribution information of the detection points; determine the remaining task duration based on the current time and the time consumed by the inspection task.

[0133] Among them, the distribution information of the detection points is the location of the detection points, and the inspection coverage rate is the proportion of detection points covered by the inspection when the inspection path is updated.

[0134] Step 212: Based on the inspection coverage rate, inspection task time, inspection task energy consumption, remaining task duration, risk level, and ocean current velocity, determine the energy consumption index, duration index, and coverage rate index for updating the inspection path.

[0135] Optionally, risk weights can be determined based on risk level and highest risk level; time weights can be determined based on current time and remaining mission duration; ocean current weights can be determined based on ocean current velocity and preset maximum compensable velocity; coverage indicators can be determined based on risk weights and inspection coverage rate; duration indicators can be determined based on time weights and inspection mission duration; and energy consumption indicators can be determined based on ocean current weights and inspection mission energy consumption.

[0136] For example, the energy consumption index, duration index, and coverage index of the updated inspection path are determined by the following formula;

[0137] Define a comprehensive objective function J to quantify the global merits of different path options:

[0138]

[0139] Wherein, ω1·C coverage The coverage rate is calculated using the defect distribution from a digital twin model. For duration indicators; ω1, ω2, and ω3 are energy consumption indicators; ω1, ω2, and ω3 are dynamic weighting coefficients that satisfy ω1 + ω2 + ω3 = 1.

[0140]

[0141] Among them, DefectRisk represents the risk level of undetected defects; t remain For the remaining tasks

[0142] Length, t0,k are adjustment parameters; ||V current || represents the current ocean current velocity, V max The maximum compensable flow rate.

[0143] Step 213: Adjust the updated inspection path according to the energy consumption index, duration index and coverage index of each updated inspection path to obtain the target driving path.

[0144] For example, a multi-objective optimization problem can be modeled as a non-cooperative game, where each objective corresponds to a virtual "player," and the Pareto optimal path is obtained by iteratively solving for the Nash equilibrium. The equilibrium condition is:

[0145]

[0146] Among them, P * For a balanced path scheme, P i To optimize only the update inspection path for the i-th objective (e.g., P1 is the path that maximizes coverage); P -i *Let J be the path optimized according to the equilibrium scheme for all objectives except the i-th objective. For example, consider path A (high coverage but high energy consumption) and path B (low time consumption but high false negative rate). A game theory model is constructed, and the three objectives (coverage, time, and energy consumption) are modeled as virtual "players," each attempting to optimize J. Simultaneously, each "player" takes turns adjusting their path scheme until convergence to the equilibrium point P. * Finally, the Pareto optimal path (target driving path) J is obtained. i (P * ).

[0147] It should be noted that, since the digital twin model of the unmanned surface vessel is updated in real time according to a preset update rate during operation, the candidate inspection path, the updated inspection path, and the target driving path are also constantly being updated.

[0148] This invention provides a method for determining the inspection path of an unmanned surface vessel (USV). This method optimizes candidate inspection paths using obstacle information and the position information of preset operational components, preventing damage to these components from obstacles during operation. Furthermore, by performing game theory calculations based on the path indicators of each updated inspection path, a target travel path with relatively optimal path indicators can be obtained. Controlling the USV along the target travel path improves inspection efficiency and ensures the safety of the USV.

[0149] Example 3

[0150] Figure 3 This is a schematic diagram of the unmanned surface vessel path planning system provided in Embodiment 3 of the present invention.

[0151] like Figure 3 As shown, the unmanned surface vessel includes a multi-source heterogeneous sensor array, a digital twin model module, a dynamic hierarchical path planning module, a three-dimensional motion trajectory optimizer, an environment adaptive execution module, a multi-objective decision center, and a multi-robotic arm control center.

[0152] The multi-source heterogeneous sensor array serves as the core of the system's front-end perception, integrating underwater high-resolution sonar, 3D lidar, multispectral imager, and miniature tactile sensors. It collects real-time data on the surface geometry of the base (the object to be inspected), structural defects (such as crack width ≥ 0.5 mm, corrosion area thickness loss > 10%), biological attachment status, and surrounding ocean current parameters. The data update frequency reaches 10 Hz, providing high-precision raw input for subsequent modeling and planning.

[0153] The digital twin model module, based on various sensor data collected from multiple sources, constructs a base surface model with centimeter-level accuracy (error ≤2mm) through unstructured mesh modeling technology. It integrates machine learning algorithms to automatically identify and quantify base defects (cracks, corrosion areas, etc.), and simultaneously establishes a material degradation prediction model. It dynamically updates key data such as base geometric curvature, defect location, and ocean current interference, realizing real-time mapping between the physical base and the virtual model, and providing accurate environmental semantic support for path planning.

[0154] The dynamic hierarchical path planning module adopts a three-level collaborative architecture of "global situation field - local spatiotemporal optimization - execution smoothing": The global situation field layer combines the 3D point cloud data of the base to generate an adaptive potential energy field, driving the unmanned surface vessel to approach the target area along the direction of potential energy decrease. The local spatiotemporal optimization layer introduces a spatiotemporal constraint A* algorithm coupled with the kinematic constraints of the robotic arm (joint angular velocity ≤ π / 4 rad / s), and optimizes the obstacle avoidance trajectory by sliding through a time window (Δt = 0.5s) to avoid conflicts between obstacles and robotic arm movements. The execution layer trajectory smoothing uses Lie group manifold theory for differential geometry optimization to ensure the continuity index of path curvature (K). 2 ≤0.01), improving the passability of unmanned surface vessels in narrow base gaps.

[0155] The 3D motion trajectory optimizer optimizes the curvature and acceleration of the path generated by the hierarchical planning, taking into account the dynamic characteristics of the unmanned surface vessel. It eliminates abrupt changes in the path through differential geometry methods, ensuring that the trajectory meets the kinematic constraints of the robotic arm (such as joint angular velocity limits) and the dynamic requirements of the hull (such as a maximum turning angle of 60°). This avoids propeller overload or hull instability caused by uneven trajectory, and provides continuous and controllable motion commands for subsequent execution.

[0156] The environment-adaptive execution module integrates a magnetohydrodynamic vector thruster and a biomimetic articulated hull design. It adjusts course and speed through real-time compensation algorithms to adapt to complex sea conditions (such as turbulence and tidal changes). It supports real-time hull shape transformation and can autonomously move between base support structures, significantly improving the maneuverability and operational efficiency of unmanned surface vessels in complex marine environments.

[0157] The multi-objective decision center, based on real-time determined multi-source data (coverage, energy consumption, timeliness, etc.) of each updated inspection path, adopts a dynamic weight allocation strategy and a multi-objective game decision model to dynamically balance objectives such as maximizing detection coverage, minimizing operation time, and optimizing energy consumption. Based on the Nash equilibrium principle, it generates Pareto optimal path schemes, adjusts path planning weights, and optimizes task execution performance.

[0158] The multi-arm control center controls the motion parameters of the robotic arms (such as joint angular velocity and end-effector pose) to ensure that the trajectory of the unmanned surface vessel (USV) is synchronized with the detection actions of the robotic arms. This meets the requirements for motion coordination in refined tasks (such as base topology detection, bolt loosening identification, and anti-corrosion layer evaluation) and avoids detection errors or collision risks caused by asynchronous movements between the USV and the robotic arms.

[0159] The unmanned surface vessel (USV) path planning system provided in this invention can improve the accuracy of USV path planning, avoid collisions with obstacles, dynamically balance detection coverage, operation time and energy consumption, and improve inspection efficiency.

[0160] Example 4

[0161] Figure 4 This is a schematic diagram of a device for determining the inspection path of an unmanned surface vessel (USV) according to Embodiment 4 of the present invention. Figure 4 As shown, the device includes:

[0162] The generation module 310 is used to generate a digital twin model of the inspection area based on the sensor data of the preset sensors of the unmanned surface vessel. The inspection area is the area formed by the initial position of the unmanned surface vessel and the positions of each object to be inspected. The digital twin model includes the detection point information of the object to be inspected, ocean current information and obstacle information within the inspection area.

[0163] The candidate inspection path determination module 320 is used to generate multiple candidate inspection paths based on the digital twin model and the preset inspection order, wherein the preset inspection order represents the inspection order of the object to be inspected;

[0164] The inspection path determination module 330 is used to update the multiple candidate inspection paths based on the obstacle information and the position information of the preset working components, so as to obtain multiple updated inspection paths.

[0165] The target driving path determination module 340 is used to determine the target driving path based on the path indicators of the multiple updated inspection paths, wherein the path indicators include inspection coverage, inspection task time and inspection task energy consumption.

[0166] This invention provides an apparatus for determining the inspection path of an unmanned surface vessel (USV). The apparatus comprises: generating a digital twin model of the inspection area based on sensor data from preset sensors of the USV, wherein the inspection area is the region formed by the initial position of the USV and the positions of each object to be inspected; the digital twin model includes detection point information of the objects to be inspected, ocean current information, and obstacle information within the inspection area; generating multiple candidate inspection paths based on the digital twin model and a preset inspection sequence, wherein the preset inspection sequence represents the inspection sequence of the objects to be inspected; updating the multiple candidate inspection paths based on the obstacle information and the position information of preset operating components, resulting in multiple updated inspection paths; and determining a target travel path based on path indicators of the multiple updated inspection paths, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption. Specifically, candidate inspection paths can be optimized based on obstacle information to avoid collisions with obstacles at sea. Simultaneously, by updating the path indicators of multiple inspection paths, the target travel path can be determined, thereby ensuring that the inspection coverage, inspection time, and energy consumption of the target travel path are relatively optimal. The method of this invention can improve the accuracy of inspection path determination, increase inspection efficiency, and ensure the safety of unmanned surface vessels.

[0167] Optionally, the generation module 310 includes:

[0168] The acquisition unit is used to acquire sonar data, ocean current Doppler data, point cloud data, and image data sent by the preset sensors of the unmanned surface vessel;

[0169] An image unit is used to determine the detection point information of the object to be inspected and the coordinates of obstacles within the inspection area based on the image data.

[0170] Point cloud unit, used to generate a point cloud model of the inspection area based on the sonar data and point cloud data;

[0171] The ocean current unit is used to determine the ocean current information of the inspection area based on the ocean current Doppler data.

[0172] The generation unit is used to generate a digital twin model of the inspection area based on the point cloud model, ocean current information of the inspection area, obstacle coordinates, and detection point information of the object to be inspected.

[0173] Optionally, the candidate inspection path determination module 320 includes:

[0174] The potential field determination unit is used to determine the potential field distribution information corresponding to each preset inspection sequence based on the position of the unmanned surface vessel, the coordinates of the obstacles, the positions of each object to be inspected, the ocean current information, and each preset inspection sequence.

[0175] The path determination unit is used to determine the direction of potential energy decrease based on any potential energy field distribution information, and to determine a candidate inspection path based on the direction of potential energy decrease.

[0176] Optionally, the potential field determination unit includes:

[0177] The first determining subunit is used to determine the obstacle potential energy parameters based on the position of the unmanned surface vessel and the coordinates of the obstacles in the inspection area.

[0178] The second determining subunit is used to determine the ocean current potential energy parameters based on the ocean current information;

[0179] The third determining subunit is used to determine the position potential energy parameters corresponding to the preset inspection sequence based on the position of the unmanned surface vessel and the position of each object to be inspected, for any preset inspection sequence.

[0180] The fusion subunit is used to determine the potential energy field distribution information corresponding to the preset inspection sequence based on the obstacle potential energy parameters, the position potential energy parameters corresponding to the preset inspection sequence, and the ocean current potential energy parameters.

[0181] Optionally, the path determination unit includes:

[0182] The gradient determination unit is used to determine the potential energy gradient corresponding to the current position of the unmanned surface vessel based on the potential energy field distribution information.

[0183] The position determination unit is used to determine the next position of the unmanned surface vessel (USV) based on its current position and the potential energy gradient.

[0184] Optionally, the updated inspection path determination module 330 includes:

[0185] The position determination unit is used to determine the end position of the preset operating component of the unmanned surface vessel on any candidate inspection path.

[0186] The spatiotemporal conflict information determination unit is used to determine the spatiotemporal conflict information corresponding to the current inspection path based on the end position corresponding to the current inspection path, the obstacle coordinates of each obstacle in the inspection area, and the current position of the unmanned surface vessel.

[0187] An optimized inspection path determination unit is used to determine an optimized inspection path corresponding to the current inspection path based on the spatiotemporal conflict information.

[0188] The smoothing unit is used to smooth the optimized inspection path corresponding to each candidate inspection path to obtain the updated inspection path corresponding to each candidate inspection path.

[0189] Optionally, the updated inspection path determination module 330 further includes: a power unit, used to determine the ocean current resistance of the unmanned surface vessel (USV) based on the ocean current information corresponding to the current position of the USV; determine the supplementary power of the USV based on the ocean current resistance; and control the USV to travel along the updated inspection path based on the supplementary power.

[0190] Optionally, the target driving path determination module 340 includes:

[0191] The calculation unit is used to determine the target velocity and target acceleration of each path point on the updated inspection path;

[0192] The detection point unit is used to determine the estimated maintenance time and risk level of each detection point of each object to be inspected based on the detection point information of each object to be inspected.

[0193] The time and energy consumption calculation unit is used to determine the inspection task time based on the target speed, target acceleration and estimated maintenance time of each object to be inspected in the updated inspection path, and to determine the inspection task energy consumption based on the inspection task time.

[0194] The coverage and remaining time determination unit is used to determine the inspection coverage based on the distribution information of the detection points, and to determine the remaining task time based on the current time and the inspection task duration.

[0195] The integrated unit is used to determine the energy consumption index, duration index and coverage index of the updated inspection path based on the inspection coverage rate, inspection task time, inspection task energy consumption, remaining task time, risk level and ocean current velocity.

[0196] The optimization unit is used to adjust the updated inspection path according to the energy consumption index, duration index and coverage index of each updated inspection path to obtain the target driving path.

[0197] Optional, the integration unit includes:

[0198] The risk weight calculation subunit is used to determine the risk weight based on the risk level and the highest risk level.

[0199] The time weight calculation subunit is used to determine the time weight based on the current time and the remaining task duration.

[0200] The ocean current weight calculation subunit is used to determine the ocean current weight based on the ocean current velocity and the preset maximum compensable velocity.

[0201] The integrated subunit is used to determine the coverage index based on risk weight and inspection coverage rate, the duration index based on time weight and inspection task duration, and the energy consumption index based on ocean current weight and inspection task energy consumption.

[0202] Optionally, the unmanned surface vessel (USV) inspection path determination device further includes: a maintenance module, used to adjust the rotation angle of each sub-component of the preset working component according to the position information and detection position of the preset working component, so that the sub-component used for maintenance operations reaches the detection position; and to repair the worn parts at the detection position according to the contact pressure fed back by the tactile sensor of the sub-component used for maintenance operations.

[0203] The unmanned surface vessel (USV) inspection path determination device provided in this embodiment of the invention can execute the USV inspection path determination method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0204] Example 5

[0205] Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various types of unmanned surface vessels. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0206] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0207] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as a multi-source heterogeneous sensor array; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as a disk, optical disk, etc.; and communication unit 19, such as a network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0208] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining the inspection path of an unmanned surface vessel.

[0209] In some embodiments, the method for determining the unmanned surface vessel (USV) inspection path can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the USV inspection path described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method for determining the USV inspection path by any other suitable means (e.g., by means of firmware).

[0210] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0211] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0212] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0213] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0214] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0215] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0216] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0217] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining the inspection path of an unmanned surface vessel, characterized in that, include: Based on sensor data from the unmanned surface vessel's preset sensors, a digital twin model of the inspection area is generated. The inspection area is the region formed by the initial position of the unmanned surface vessel and the positions of each object to be inspected. The digital twin model includes detection point information of the objects to be inspected, ocean current information, and obstacle information within the inspection area. Multiple candidate inspection paths are generated based on the digital twin model and the preset inspection order, wherein the preset inspection order represents the inspection order of the object to be inspected; Based on the obstacle information and the location information of the preset working components, the multiple candidate inspection paths are updated to obtain multiple updated inspection paths; The target driving route is determined based on the path indicators of the multiple updated inspection routes, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption.

2. The method according to claim 1, characterized in that, The step of generating a digital twin model of the inspection area based on sensor data from preset sensors of the unmanned surface vessel includes: Acquire sonar data, ocean current Doppler data, point cloud data, and image data transmitted by the preset sensors of the unmanned surface vessel; The detection point information of the object to be inspected and the coordinates of obstacles within the inspection area are determined based on the image data. A point cloud model of the inspection area is generated based on the sonar data and point cloud data. The ocean current information of the inspection area is determined based on the ocean current Doppler data. Based on the point cloud model, ocean current information of the inspection area, obstacle coordinates, and detection point information of the object to be inspected, a digital twin model of the inspection area is generated.

3. The method according to claim 1, characterized in that, The generation of multiple candidate inspection paths based on the digital twin model and the preset inspection order includes: Based on the position of the unmanned vessel, the coordinates of the obstacles, the positions of each object to be inspected, the ocean current information, and each preset inspection sequence, the potential energy field distribution information corresponding to each preset inspection sequence is determined. For any potential energy field distribution information, the direction of potential energy decrease is determined based on the potential energy field distribution information, and a candidate inspection path is determined based on the direction of potential energy decrease.

4. The method according to claim 3, characterized in that, The step of determining the potential field distribution information corresponding to each preset inspection sequence based on the position of the unmanned surface vessel, the coordinates of obstacles, the positions of each object to be inspected, ocean current information, and each preset inspection sequence includes: Based on the location of the unmanned surface vessel and the coordinates of obstacles within the inspection area, the potential energy parameters of the obstacles are determined. Based on the ocean current information, determine the ocean current potential energy parameters; For any preset inspection sequence, the position potential energy parameters corresponding to the preset inspection sequence are determined based on the position of the unmanned surface vessel and the position of each object to be inspected. Based on the obstacle potential energy parameters, the position potential energy parameters corresponding to the preset inspection sequence, and the ocean current potential energy parameters, the potential energy field distribution information corresponding to the preset inspection sequence is determined.

5. The method according to claim 3, characterized in that, The step of determining the potential energy decrease direction based on the potential energy field distribution information, and determining the candidate inspection path based on the potential energy decrease direction, includes: The potential energy gradient corresponding to the current position of the unmanned surface vessel is determined based on the potential energy field distribution information. The next position of the unmanned surface vessel is determined based on its current position and the potential energy gradient.

6. The method according to claim 1, characterized in that, The process of updating the multiple candidate inspection paths based on the obstacle information and the location information of the preset operating components yields multiple updated inspection paths, including: For any candidate inspection path, determine the end position of the preset operating component of the unmanned surface vessel on the current inspection path; Based on the end position of the preset operating component corresponding to the current inspection path, the obstacle coordinates of each obstacle in the inspection area, and the current position of the unmanned surface vessel, determine the spatiotemporal conflict information corresponding to the current inspection path; Determine the optimized inspection path corresponding to the current inspection path based on the spatiotemporal conflict information; The optimized inspection paths corresponding to each candidate inspection path are smoothed to obtain the updated inspection paths corresponding to each candidate inspection path.

7. The method according to claim 6, characterized in that, Also includes: Based on the ocean current information corresponding to the current position of the unmanned surface vessel, determine the ocean current resistance to the unmanned surface vessel; The supplementary power of the unmanned surface vessel is determined based on the ocean current resistance, and the unmanned surface vessel is controlled to travel along the updated inspection path based on the supplementary power.

8. The method according to claim 6, characterized in that, The inspection point information of the object to be inspected includes the type of inspection point, the estimated maintenance time corresponding to the type of inspection point, the distribution information of the inspection points and the risk level; The determination of the target driving route based on the path indicators of the multiple updated inspection routes includes: Determine the target velocity and target acceleration of each path point on the updated inspection path; Based on the inspection point information of each object to be inspected, determine the estimated maintenance time and risk level of each inspection point of each object to be inspected. Based on the target speed, target acceleration and estimated maintenance time of each object to be inspected in the updated inspection path, the inspection task time is determined, and the inspection task energy consumption is determined based on the inspection task time. The inspection coverage rate is determined based on the distribution information of the detection points; the remaining task duration is determined based on the current time and the time consumed by the inspection task. Based on the inspection coverage rate, inspection task time, inspection task energy consumption, remaining task time, risk level and ocean current velocity, determine the energy consumption index, time index and coverage index for updating the inspection path. The updated inspection paths are adjusted based on their energy consumption, duration, and coverage indicators to obtain the target driving path.

9. The method according to claim 8, characterized in that, The process of determining the energy consumption, duration, and coverage indicators for updating the inspection path based on the inspection coverage rate, inspection task time, inspection task energy consumption, remaining task duration, risk level, and ocean current velocity includes: Risk weights are determined based on risk levels and the highest risk level. The time weight is determined based on the current time and the remaining task duration; The ocean current weight is determined based on the ocean current velocity and the preset maximum compensable velocity. The coverage rate indicator is determined based on risk weight and inspection coverage rate; the duration indicator is determined based on time weight and inspection task time; and the energy consumption indicator is determined based on ocean current weight and inspection task energy consumption.

10. The method according to claim 1, characterized in that, The detection point information includes the detection location, and after the unmanned surface vessel arrives at the location of the object to be inspected, it also includes: Based on the position information and detection position of the preset working component, adjust the rotation angle of each sub-component of the preset working component so that the sub-component used for maintenance operation reaches the detection position; Repair is performed on worn parts at the detection location based on the contact pressure fed back by the tactile sensor of the sub-component of the maintenance operation.

11. A device for determining the inspection path of an unmanned surface vessel, characterized in that, include: The generation module is used to generate a digital twin model of the inspection area based on the sensor data of the preset sensors of the unmanned surface vessel (USV). The inspection area is the area formed by the initial position of the USV and the positions of each object to be inspected. The digital twin model includes the detection point information of the objects to be inspected, ocean current information and obstacle information within the inspection area. The candidate inspection path determination module is used to generate multiple candidate inspection paths based on the digital twin model and the preset inspection order, wherein the preset inspection order represents the inspection order of the object to be inspected; The inspection path determination module is used to update the multiple candidate inspection paths based on the obstacle information and the location information of the preset working components, so as to obtain multiple updated inspection paths. The target driving route determination module is used to determine the target driving route based on the path indicators of the multiple updated inspection routes, wherein the path indicators include inspection coverage, inspection task time, and inspection task energy consumption.

12. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the unmanned surface vessel inspection path according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the inspection path of the unmanned surface vessel as described in any one of claims 1-10.

Images