An autonomous working robot for a surface of a ship and a control method and control system thereof

Abstract

The application provides a ship surface autonomous operation robot and a control method and system thereof, comprising: an adsorption system, a rust removal system, a motor control system, a sensing system and a communication system; the adsorption system is used for adsorbing the robot on the ship surface; the rust removal system is used for removing stains and rust on the ship surface through a high-pressure water pump; the motor control system is used for controlling the robot to move and walk on the ship surface; the sensing system is used for collecting position and attitude information of the robot; and the communication system is used for transmitting and receiving control instructions and the position and attitude information of the robot. The application solves the problems of high cost and great difficulty of existing dock surface cleaning operation.

Description

Technical Field

[0001] This invention relates to the field of ship maintenance technology, and in particular to an autonomous ship surface operation robot and its control method and control system. Background Technology

[0002] During the construction or maintenance of a ship, the hull surface may be affected by oxidation, rust, and other deposits, requiring rust removal treatment in a dry dock. This process improves the adhesion of paint to the ship's surface during painting, thereby maximizing the paint's anti-corrosion capabilities and extending the ship's service life.

[0003] The traditional method involves workers using handheld rust removal equipment, while the workers work in conjunction with an elevated vehicle to remove rust. In addition to manual labor, modified elevated vehicles are also used for rust removal. The top of the elevated vehicle's boom is equipped with a rust removal device, which eliminates the need for manual handling of the rust removal equipment.

[0004] Some rust removal operations also utilize remotely controlled rust removal robots. These wheeled mobile robots equipped with rust removal devices can adhere to the ship's hull surface, and workers can control their movement within a certain working distance using a remote control handle to remove rust from partial or all areas of the hull. Existing manual operations are costly, primarily due to high personnel costs and training costs. Traditional manual rust removal solutions require at least one rust removal worker and one operator of an aerial work platform. Even modified aerial work platforms and remotely controlled rust removal robots still require at least one worker, and considering worker shifts, the actual number of workers needed is very large.

[0005] On the other hand, worker training is demanding; all machines require specialized operation training and practical experience to achieve the desired operational results. Furthermore, shipyards are mostly outdoor environments, where the working conditions, in addition to discomfort caused by various natural weather conditions, include significant noise pollution and potential harm from dust and chemicals. The entire working environment is extremely harsh, greatly increasing the risk of personal injury accidents. The operational efficiency of the aforementioned methods is limited by multiple factors, primarily including: the number of workers and machines, time lost during machine scheduling, and time lost due to machine malfunctions. Summary of the Invention

[0006] This invention provides an autonomous ship surface cleaning robot and its control method and control system to solve the problems of high cost and difficulty in existing dock surface cleaning operations.

[0007] This invention provides an autonomous operation robot for ship surfaces, comprising:

[0008] Adsorption system, rust removal system, motor control system, sensing system, and communication system;

[0009] The adsorption system is used to adsorb the robot onto the surface of the ship. The adsorption system uses magnets to adsorb the entire robot onto the surface of the ship. The magnets are installed on the side of the robot's rollers and are in contact with the surface of the ship.

[0010] The rust removal system is used to remove stains and rust from the surface of the ship. The rust removal system includes a high-pressure water pump and a rust removal grinding wheel. The high-pressure water pump washes away dirt, and the rust removal grinding wheel grinds away rust.

[0011] The motor control system is used to control the robot to move and walk on the surface of the ship. The motor control system includes a motor, a steering gear and a controller. The controller receives control commands and controls the motor to rotate, driving the robot's rollers to rotate and move the robot's position. The steering gear changes the direction of the robot's rollers to control the direction of the robot's movement.

[0012] The sensing system is used to collect the robot's position and attitude information;

[0013] The communication system is used for sending and receiving control commands and robot position and attitude information.

[0014] According to the present invention, an autonomous ship surface operation robot is provided, wherein the sensing system includes:

[0015] Odometers and inertial measurement units;

[0016] The odometer is installed on the robot's wheels and is used to calculate relative positioning data.

[0017] The inertial measurement unit is mounted on the connecting frame between the rollers and measures the direction of gravitational acceleration in the robot coordinate system.

[0018] According to the present invention, an autonomous operation robot for ship surface is provided, wherein the sensing system further includes a monitoring station, and the monitoring station includes: a lidar and a camera;

[0019] The point cloud data collected by the lidar is used to establish a model of the ship's surface and to make a rough estimate of the robot's real-time position.

[0020] The camera is used to acquire visual images, and the robot's position is accurately located based on visual features after a rough estimate of the robot's position using laser point clouds.

[0021] The present invention also provides a control method for an autonomous operating robot on a ship surface, the method comprising:

[0022] Acquire point cloud data collected by lidar and establish a coordinate system on the ship's surface;

[0023] The robot's precise position is determined in the coordinate system based on the robot's point cloud data and visual image.

[0024] Generate the robot's real-time movement path based on the robot's precise location;

[0025] The robot's real-time movement path is compared with a preset designated movement path to generate a deviation.

[0026] Control commands are generated based on the deviation, and the robot's movement path is adjusted using these commands.

[0027] According to the present invention, a control method for an autonomous ship surface operation robot determines the robot's accurate position in the coordinate system based on the robot's point cloud data and visual image, specifically including:

[0028] Based on the acquired robot point cloud data, the approximate position of the robot in the coordinate system is determined;

[0029] Based on visual images, image features are extracted to determine the robot's precise position from a rough estimate of its location.

[0030] According to the control method of an autonomous ship surface operation robot provided by the present invention, the real-time movement path of the robot is compared with a preset designated movement path to generate a deviation, specifically including:

[0031] Based on the robot's precise location information, obtain the robot's real-time movement direction and position, and draw the robot's real-time movement path;

[0032] The robot's real-time movement path is compared with a preset designated path to generate coordinate deviation values ​​and thus deviation information.

[0033] The present invention also provides a control system for an autonomous operation robot on a ship surface, the system comprising:

[0034] The coordinate system establishment module is used to acquire point cloud data collected by lidar and establish a coordinate system on the ship's surface;

[0035] The positioning module is used to determine the robot's accurate position in the coordinate system based on the robot's point cloud data and visual images.

[0036] The movement path drawing module is used to generate the robot's real-time movement path based on the robot's accurate position.

[0037] The comparison module is used to compare the robot's real-time movement path with a preset specified movement path and generate a deviation amount.

[0038] The adjustment module is used to generate control commands based on the deviation amount, and adjust the robot's movement path through the control commands.

[0039] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the control method of any of the above-described autonomous ship surface operation robots.

[0040] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the control method for an autonomous ship surface operation robot as described above.

[0041] This invention provides an autonomous ship surface operation robot and its control method and control system. Operators can remotely issue work instructions to the robot via wireless communication technology. The robot can autonomously execute tasks without real-time manual operation, enabling one operator to manage multiple robots, thus saving labor costs. It also reduces the probability of personal injury and accidents to workers in the working environment. Autonomous robot operation can improve work efficiency. Through certain software and communication technologies, one operator can manage multiple robots to perform operations, and multiple robots can work in parallel, ultimately improving work efficiency. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is a top view of an autonomous ship surface operation robot provided by the present invention;

[0044] Figure 2 This is a bottom view structural diagram of an autonomous ship surface operation robot provided by the present invention.

[0045] Figure 3 This is a schematic diagram showing the positional relationship between the monitoring station and the ship hull provided by the present invention;

[0046] Figure 4 This is a schematic diagram of the internal structure of the monitoring station provided by the present invention;

[0047] Figure 5 This is a schematic diagram of the roller correction according to a preset path provided by the present invention;

[0048] Figure 6This is one of the flowcharts illustrating a control method for an autonomous operation robot on a ship surface provided by the present invention;

[0049] Figure 7 This is the second flowchart illustrating a control method for an autonomous operation robot on a ship surface provided by the present invention;

[0050] Figure 8 This is the third flowchart illustrating a control method for an autonomous ship surface operation robot provided by the present invention;

[0051] Figure 9 This is a schematic diagram of the module connection of the control system of an autonomous operation robot on the ship surface provided by the present invention;

[0052] Figure 10 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0053] Figure label:

[0054] 1: Roller; 2: Protective housing; 3: Rust removal system; 4: Motor control system; 5: Communication system; 6: Inertial measurement unit; 7: Adsorption system; 8: Odometer; 9: Hull; 10: Monitoring station; 11: Mounting frame; 12: LiDAR; 13: Camera; 14: Power supply equipment;

[0055] 110: Coordinate system establishment module; 120: Positioning module; 130: Movement path drawing module; 140: Comparison module; 150: Adjustment module;

[0056] 1010: Processor; 1020: Communication interface; 1030: Memory; 1040: Communication bus. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0058] The following is combined Figures 1-2 The present invention describes an autonomous ship surface operation robot, comprising:

[0059] 7. Adsorption system; 3. Rust removal system; 4. Motor control system; 5. Sensing system and communication system;

[0060] The adsorption system 7 is used to adsorb the robot onto the surface of the ship. The adsorption system uses magnets to adsorb the entire robot onto the surface of the ship. The magnets are installed on the side of the robot's rollers and are in contact with the surface of the ship.

[0061] The rust removal system 3 is used to remove stains and rust from the surface of the ship. The rust removal system includes a high-pressure water pump and a rust removal grinding wheel. The high-pressure water pump is used to rinse away dirt, and the rust removal grinding wheel is used to grind away rust.

[0062] The motor control system 4 is used to control the robot to move and walk on the surface of the ship. The motor control system includes a motor, a steering gear and a controller. The controller receives control commands and controls the motor to rotate, driving the robot's rollers to rotate and move the robot's position. The steering gear changes the direction of the robot's rollers to control the direction of the robot's movement.

[0063] The sensing system is used to collect the robot's position and attitude information;

[0064] The communication system 5 is used for sending and receiving control commands and robot position and attitude information.

[0065] In this invention, a robot is used to clean the surface of a ship according to a set path, which reduces labor costs and operational difficulty, and avoids the dangers of manual operation.

[0066] The sensing system includes:

[0067] Odometer 8 and inertial measurement unit 6;

[0068] The odometer 8 is installed on the robot's roller 1, and a protective shell 2 is installed on the outside of the roller 1. The relative positioning data is calculated through the odometer 8.

[0069] The inertial measurement unit 6 is mounted on the connecting frame between the rollers 1, and measures the direction of gravitational acceleration in the robot coordinate system.

[0070] The robot's rollers 1 are divided into two sides, each with an independently controllable servo motor. The robot's linear motion speed is 0.05–0.2 m / s.

[0071] The odometer 8, mounted on the roller 1, can accurately calculate the distance the robot moves and extrapolate relative positioning data. The inertial measurement unit 6 is used to measure the direction of gravitational acceleration in the robot's coordinate system and to measure the robot's current orientation relative to gravity in real time. Since the orientation of gravity is always vertically downward, this determines the robot's orientation on the surface of the hull 9.

[0072] refer to Figure 4The sensing system also includes a monitoring station 10, which includes a lidar 12 and a camera 13.

[0073] The point cloud data collected by the lidar 12 is used to establish the surface model of the hull 9 and to make a rough estimate of the robot's real-time position.

[0074] The camera 13 is used to acquire visual images and to accurately locate the robot's position based on visual features, which are used to roughly estimate the robot's position using laser point clouds.

[0075] In this invention, the lidar 12 and camera 13 are fixed on the mounting bracket 11 and powered by a power supply device 14. The lidar 12 is a Livox or a conventional mechanical multi-line lidar 12. The collected point cloud data is used to establish a surface model of the hull 9, forming a coordinate system and providing a coarse estimate of the robot's real-time position. The camera 13 is used to acquire visual images, further refining the robot's position based on the lidar point cloud estimation using visual features. (Reference) Figure 3 The monitoring station 10 can be set up at intervals of 20 meters according to the field of view of the sensor (generally about 45°) and the distance between the monitoring station 10 and the ship (generally 20 meters) to achieve complete coverage of the surface of the ship 9.

[0076] Inertial measurement unit (IMU) data includes: [linear_acceleration.x, linear_acceleration.y, linear_acceleration.z] --- 3-axis acceleration values; [roll, pitch, yaw] --- roll, pitch, and yaw angles.

[0077] Since the robot lies vertically on the surface of hull 9 during operation, the angle between the robot and the direction of gravity is determined by pitch. Since the Euler angle pitch ranges from [-90°, 90°], while the range of the angle between the robot's orientation and gravity should be [-180°, 180°], the quadrant of the robot's orientation is determined by judging [linear_acceleration.x, linear_acceleration.z]. Based on the determined quadrant, the pitch range is adjusted to [-180°, 180°].

[0078] The method for determining the quadrant is to refer to Table 1.

[0079] Table 1 Quadrant Judgment Table

[0080]

[0081]

[0082] Pitch angle adjustment follows the formula

[0083] pitch = -(pitch + 180) in the fourth quadrant; pitch = 180 - pitch in the third quadrant

[0084] According to the robot's odometer 8 speed Odometer Vx t The angle pitch with respect to gravity can be used to calculate the change in robot motion.

[0085] DeltaX t =OdometerVx t *cos(pitch)

[0086] DeltaY t =OdometerVx t *sin(pitch)

[0087] The robot's position at time t+1 can be predicted from its position at time t. The prediction formula is as follows:

[0088] OdometerPositionX t+1 =OdometerPositionX t +DeltaXt

[0089] OdometerPositionYt+1=OdometerPositionYt+DeltaYt.

[0090] refer to Figures 6-8 The present invention also discloses a control method for an autonomous operating robot on a ship surface, the method comprising:

[0091] S100: Acquire point cloud data collected by lidar 12 and establish a coordinate system on the surface of the ship;

[0092] S200. Determine the robot's accurate position in the coordinate system based on the robot's point cloud data and visual image.

[0093] S300: Generate a real-time movement path for the robot based on its accurate position.

[0094] S400: Compare the real-time movement path of the robot with the preset designated movement path to generate a deviation amount;

[0095] S500: Generate control commands based on the deviation amount, and adjust the robot's movement path using the control commands.

[0096] Determining the robot's precise position in the coordinate system based on the robot's point cloud data and visual image specifically includes:

[0097] S201. Based on the acquired robot point cloud data, determine the approximate position of the robot in the coordinate system;

[0098] S202. Based on the visual image, extract image features to determine the robot's precise position from the rough position of the robot.

[0099] Before the robot starts its work, a laser point cloud data acquisition is performed on the surface of the hull 9. Multiple frames of laser data can be collected and merged into the same dataset, which is called CloudDataReference. Each data point in the dataset consists of [x,y,z]. The XZ axis is the horizontal plane of the lidar 12, and the Y axis is vertically upward, forming a coordinate system with the XZ axis.

[0100] Laser point cloud data is rasterized on the XY coordinate plane according to a certain size (typically 0.1 meters). 2 Since the surface of hull 9 is approximately a smooth surface, it can be fitted locally by plane fitting.

[0101] The grid range is defined by discretizing 400 grid cells along the x-axis from [-20, 20] at 0.1 meters intervals. The z-axis is discretized in the same way as the y-axis. Each point in the CloudDataReference can be used to calculate its corresponding grid cell. For the i-th point [x... i ,yi,z i The corresponding raster coordinates are Row. i = Take the integer (yi / 0.1), Col j = Take the integer (xi / 0.1).

[0102] For those falling in [Row] i Col j The laser point cloud within the grid is fitted with a planar model as follows:

[0103] a ij x+b ij y+c ij z+d ij =0

[0104] The root mean square error of the fit is sigma ij Sigma represents the planar uniformity and noise evaluation of the laser points within the grid. ij The smaller the value, the lower the noise. [a] ij ,b ij ,c ij ,d ij sigma ij] represents the parameters of the fitted surface of the point cloud in the raster. The fitting can be calculated using the least squares algorithm to calculate the parameters and the root mean square of the fitting error.

[0105] The more laser frames included in the collected CloudDataReference, the better it is for the accuracy and numerical stability of the fitted plane parameters.

[0106] Point cloud data collected in real time during the robot's operation (CloudData) t First, use the same method as CloudDataReference to analyze CloudData. t Discretize data into raster [Row] i Col j ].

[0107] For the first frame of data, i.e., time t=0, it is necessary to traverse all grids to determine the candidate grid where the robot is located at time t=0. The method for determining the candidate grid is to traverse all CloudData... t The raster and calculate [Row] i Col j Model a of fitting a plane to a point cloud within a grid ij x+b ij y+c ij z+d ij =0, calculate the center point of the grid.

[0108] x_center=Col j *0.1+0.05

[0109] y_center = Row i *0.1+0.05

[0110] Calculate the projection points [x_center, y_center, z_center] of the grid center point onto the grid plane model, where z_center = (-d ij -a ij x_center-b ij y_center) / c ij

[0111] Calculate the [Row] of the projection point to the CloudDataReference i Col j ]Grid plane model[a ij ,b ij ,c ij ,d ij sigma ij The distance is calculated using the formula Dist = |a|. ijx_center+b ij y_center+c ij z_center+d ij | / sqrt(a ij 2 +b ij 2 +c ij 2 ).

[0112] If Dist > 3*sigma ij Then the [Row] i Col j The raster is marked as a candidate raster.

[0113] For time t>0, the candidate grid [Row] that the robot will fall into can be determined based on the robot's predicted position [OdometerPositionXt+1, OdometerPositionYt+1]. i Col j Row i = Round to the nearest integer (OdometerPositionYt+1 / 0.1), Col j = Round to the nearest integer (OdometerPositionXt+1 / 0.1).

[0114] CloudData within candidate grid t The distance from each data point to the plane is calculated using the formula:

[0115] Dist = |a ij x+b ij y+c ij z+d ij | / sqrt(a ij 2 +b ij 2 +c ij 2 )

[0116] Set Dist thresh Threshold, Dist>Dist thresh The laser point cloud points are candidate points for the robot, Dist thresh The value is typically taken as 0.3 meters of the robot's half height. For all conditions satisfying Dist > Dist threshThe laser point calculation coordinate center [RobotPositionXt+1, RobotPositionYt+1, RobotPositionZt+1] is the robot's coarse positioning position in the laser point cloud computing. Among them, [RobotPositionXt+1, RobotPositionYt+1, RobotPositionZt+1] are the robot's coordinates on the surface of the hull 9, and RobotPositionZt+1 is the depth value of the robot from the camera 13, which is used in the visual precision positioning step.

[0117] The computing unit pre-stores a visible light image of the robot's top view, as well as the robot's image feature vector. Generally, feature operators such as SIFT (Scale-invariant feature transform), SURF (Speeded Up Robust Features), ORB (Oriented Fast and Rotated BRIEF), and AKAZE (Accelerated-KAZE) can be used. This invention uses the AKAZE feature operator, a fast multi-scale feature detection and feature vector description algorithm with scaling and rotation invariance. The pre-stored image feature vector is a DescriptorTemplate.

[0118] The current frame image is captured by camera 13, and the location is coarsely determined based on the laser data [RobotPositionX]. t+1 RobotPositionY t+1 RobotPositionZ t+1] Identify the regions of interest (ROIs) in the image and calculate the AKAZE feature vector.

[0119] The purpose of determining the Region of Interest (ROI) is to narrow down the image matching area, reducing computational complexity. Narrowing the matching area also minimizes the loss of matching accuracy due to false matches. The ROI is calculated as follows:

[0120] The camera's intrinsic and extrinsic parameters are obtained using existing mature camera calibration algorithms, and the world coordinate system coordinates are transformed into image pixel coordinates using the camera model. The ROI is [RobotPositionX]. t+1 RobotPositionY t+1 The area corresponding to the pixel coordinates of [RobotPositionZt+1] is expanded by a certain number of pixels. The formula for converting world coordinates to pixel coordinates using camera intrinsic and extrinsic parameters is:

[0121]

[0122] The feature vector of the current image to be matched is DescriptorCandidate.

[0123] The Brute-Force Matcher (BF) algorithm is used to match two sets of feature vectors, DescriptorTemplate and DescriptorCandidate. Based on the matched feature point pairs, the pixel coordinates [PixelPositionX] of the robot's position in the current frame image are calculated. t+1 ,PixelPositionY t+1 ].

[0124] Based on the camera's internal and external parameters and depth values, RobotPositionZ t+1 , set pixel coordinates [PixelPositionX t+1 ,PixelPositionY t+1 Convert to physical coordinates: [VisualPositionX] t+1 VisualPositionY t+1 ].

[0125] The robot's real-time movement path is compared with a preset designated movement path to generate a deviation, specifically including:

[0126] S401. Obtain the robot's real-time movement direction and position based on the robot's precise position information, and draw the robot's real-time movement path;

[0127] S402. Compare the real-time movement path of the robot with the preset designated path to generate coordinate deviation values ​​and generate deviation information.

[0128] The preset path consists of a sequence of straight line segments, where the expression for the tangent direction of the i-th preset path segment is:

[0129] a i x+b i y+c i =0

[0130] [a i ,b i ,c i ] represents the parameters of the preset path for this segment.

[0131] refer to Figure 5 Calculate the error e of the robot deviating from the current path. offset Let φ be the vertical distance from the robot's current position to the preset path, and phi be the deviation angle between the robot's current orientation and the tangent of the preset path. The calculation formula is as follows:

[0132] eoffset =|a i *VisualPositionX t+1 +b i *VisualPositionY t+1 +c i | / sqrt(a i 2 +b i 2 )

[0133] phi = pitch-tan -1 (-a / b)

[0134] Set the robot's forward speed V robo Calculate the robot's rotational control quantity W, given a speed of 0.1 m / s. robo The calculation formula is as follows:

[0135] W robo =phi + tan -1 (k*e offset / V robo )

[0136] Where k is a proportionality coefficient determined empirically, and its range here is approximately 0.5 to 1.5. W is limited based on the physical execution capabilities of the machine design. robo The value ranges from [-0.5, 0.5] radians per second.

[0137] refer to Figure 9 The present invention also discloses a control system for an autonomous operation robot on a ship surface, the system comprising:

[0138] The coordinate system establishment module 110 is used to acquire point cloud data collected by the lidar 12 and establish a coordinate system on the surface of the ship.

[0139] The positioning module 120 is used to determine the precise position of the robot in the coordinate system based on the robot's point cloud data and visual image.

[0140] The movement path drawing module 130 is used to generate the robot's real-time movement path based on the robot's accurate position.

[0141] The comparison module 140 is used to compare the real-time movement path of the robot with a preset specified movement path and generate a deviation amount.

[0142] The adjustment module 150 is used to generate control commands based on the deviation amount, and adjust the robot's movement path through the control commands.

[0143] This invention provides a control system for an autonomous robot operating on a ship's surface. Operators can remotely issue work instructions to the robot via wireless communication technology. The robot can autonomously execute tasks without real-time manual operation, enabling one operator to manage multiple robots, thus saving labor costs. It also reduces the probability of personal injury and accidents to workers in the working environment. Autonomous robot operation can improve work efficiency. Through certain software and communication technologies, one operator can manage multiple robots to perform operations, and multiple robots can work in parallel, ultimately improving work efficiency.

[0144] Figure 10 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 10 As shown, the electronic device may include a processor 1010, a communication interface 1020, a memory 1030, and a communication bus 1040. The processor 1010, communication interface 1020, and memory 1030 communicate with each other via the communication bus 1040. The processor 1010 can call logical instructions from the memory 1030 to execute a control method for an autonomous ship surface operation robot. This method includes: acquiring point cloud data collected by the lidar 12 and establishing a coordinate system on the ship surface.

[0145] The robot's precise position is determined in the coordinate system based on the robot's point cloud data and visual image.

[0146] Generate the robot's real-time movement path based on the robot's precise location;

[0147] The robot's real-time movement path is compared with a preset designated movement path to generate a deviation.

[0148] Control commands are generated based on the deviation, and the robot's movement path is adjusted using these commands.

[0149] Furthermore, the logical instructions in the aforementioned memory 1030 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0150] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being able to be stored on a non-transitory computer-readable storage medium, the computer program being executed by a processor, the computer being able to execute a control method for an autonomous operation robot on the ship surface provided by the above methods, the method including: acquiring point cloud data collected by lidar 12, and establishing a coordinate system on the ship surface;

[0151] The robot's precise position is determined in the coordinate system based on the robot's point cloud data and visual image.

[0152] Generate the robot's real-time movement path based on the robot's precise location;

[0153] The robot's real-time movement path is compared with a preset designated movement path to generate a deviation.

[0154] Control commands are generated based on the deviation, and the robot's movement path is adjusted using these commands.

[0155] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a control method for an autonomous operating robot on a ship surface provided by the methods described above, the method comprising: acquiring point cloud data collected by a lidar 12 and establishing a coordinate system on the ship surface;

[0156] The robot's precise position is determined in the coordinate system based on the robot's point cloud data and visual image.

[0157] Generate the robot's real-time movement path based on the robot's precise location;

[0158] The robot's real-time movement path is compared with a preset designated movement path to generate a deviation.

[0159] Control commands are generated based on the deviation, and the robot's movement path is adjusted using these commands.

[0160] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0161] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A control method for an autonomous operating robot on a ship's surface, comprising a robot, characterized in that, The control method for the autonomous ship surface operation robot includes: Acquire point cloud data collected by lidar and establish a coordinate system on the ship's surface; The robot's precise position is determined in the coordinate system based on the robot's point cloud data and visual image. Generate the robot's real-time movement path based on the robot's precise location; The robot's real-time movement path is compared with a preset designated movement path to generate a deviation. Control commands are generated based on the deviation, and the robot's movement path is adjusted using these control commands. The robot includes: Adsorption system, rust removal system, motor control system, sensing system, and communication system; The adsorption system is used to adsorb the robot onto the surface of the ship. The adsorption system uses magnets to adsorb the entire robot onto the surface of the ship. The magnets are installed on the side of the robot's rollers and are in contact with the surface of the ship. The rust removal system is used to remove stains and rust from the surface of the ship. The rust removal system includes a high-pressure water pump and a rust removal grinding wheel. The high-pressure water pump washes away dirt, and the rust removal grinding wheel grinds away rust. The motor control system is used to control the robot to move and walk on the surface of the ship. The motor control system includes a motor, a steering gear and a controller. The controller receives control commands and controls the motor to rotate, driving the robot's rollers to rotate and move the robot's position. The steering gear changes the direction of the robot's rollers to control the direction of the robot's movement. The sensing system is used to collect the robot's position and attitude information; The communication system is used for sending and receiving control commands and robot position and attitude information.

2. The control method for the autonomous ship surface operation robot according to claim 1, characterized in that, The sensing system includes: Odometers and inertial measurement units; The odometer is installed on the robot's wheels and is used to calculate relative positioning data. The inertial measurement unit is mounted on the connecting frame between the rollers and measures the direction of gravitational acceleration in the robot coordinate system.

3. The control method for the autonomous ship surface operation robot according to claim 2, characterized in that, The sensing system also includes a monitoring station, which includes a lidar and a camera. The point cloud data collected by the lidar is used to establish a model of the ship's surface and to make a rough estimate of the robot's real-time position. The camera is used to acquire visual images, and the robot's position is accurately located based on visual features after a rough estimate of the robot's position using laser point clouds.

4. The control method for the autonomous ship surface operation robot according to claim 1, characterized in that, Determining the robot's precise position in the coordinate system based on the robot's point cloud data and visual image specifically includes: Based on the acquired robot point cloud data, the approximate position of the robot in the coordinate system is determined; Based on visual images, image features are extracted to determine the robot's precise position from a rough estimate of its location.

5. The control method for the autonomous ship surface operation robot according to claim 1, characterized in that, The step of comparing the robot's real-time movement path with a preset designated movement path to generate a deviation specifically includes: Based on the robot's precise location information, obtain the robot's real-time movement direction and position, and draw the robot's real-time movement path; The robot's real-time movement path is compared with a preset designated path to generate coordinate deviation values ​​and thus deviation information.

6. A control system for an autonomous ship surface operation robot applied to the control method of any one of claims 1 to 5, characterized in that, The control system of the autonomous ship surface operation robot includes: The coordinate system establishment module is used to acquire point cloud data collected by lidar and establish a coordinate system on the ship's surface; The positioning module is used to determine the robot's accurate position in the coordinate system based on the robot's point cloud data and visual images. The movement path drawing module is used to generate the robot's real-time movement path based on the robot's accurate position. The comparison module is used to compare the robot's real-time movement path with a preset specified movement path and generate a deviation amount. The adjustment module is used to generate control commands based on the deviation amount, and adjust the robot's movement path through the control commands.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the control method for the autonomous ship surface operation robot as described in any one of claims 1 to 5.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the control method for the autonomous ship surface operation robot as described in any one of claims 1 to 5.

Images