A method and system for unloading a ship by an automatic grab ship unloader at a bulk cargo terminal

Abstract

The present invention discloses a ship unloading method and system for an automatic grab ship unloader at a bulk cargo terminal, which relates to the technical field of automatic ship unloading at a bulk cargo terminal. The method includes: using a lidar, a camera, and an ultrasonic sensor to collect data on the cabin structure and bulk cargo distribution; generating a three-dimensional grid model by fusing the data collected by the lidar, the camera, and the ultrasonic sensor; based on a blockchain platform, assigning tasks to the ship unloader; generating a unloading path based on the three-dimensional grid model and the assigned tasks; updating the unloading path according to the change in the state of the bulk cargo in the cargo ship during the operation process; and coordinating the unloading paths of each ship unloader in real time according to different positions and states of the ship unloader. The present invention realizes the collaborative operation of multiple ship unloaders, avoids conflicts and collisions, and further improves the overall unloading efficiency and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of automated ship unloading at bulk cargo terminals, and particularly to a method and system for automatically unloading ships using a grab ship unloader at a bulk cargo terminal. Background Art

[0002] Automated ship unloading operations at bulk cargo terminals are an important part of the port logistics field. With the growth of global trade and the increasing requirements for efficiency and safety, traditional manual operations are gradually being replaced by automated systems.

[0003] Early automated ship unloaders mainly relied on preset path planning and fixed operation modes, which were suitable for situations where the cargo distribution was relatively uniform and changed little. However, with the increase in ship size and the diversification of cargo types, traditional automated systems have proven inadequate in dealing with complex and changing cabin environments. When multiple ship unloaders operate in the same area, there is a lack of an effective coordination mechanism, which easily leads to collisions or conflicts, affecting the safety and continuity of operations. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for automatically unloading ships using a grab ship unloader at a bulk cargo terminal to solve the problem of coordinating the synchronous operation of multiple ship unloaders in the same area.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for automatically unloading ships using a grab ship unloader at a bulk cargo terminal, which includes:

[0008] Using lidar, cameras, and ultrasonic sensors to collect data on the cabin structure and bulk cargo distribution;

[0009] Generating a three-dimensional grid model by fusing the data collected by the lidar, cameras, and ultrasonic sensors;

[0010] Based on a blockchain platform, assigning tasks to the ship unloaders;

[0011] Generating a unloading path based on the three-dimensional grid model and the assigned tasks;

[0012] Updating the unloading path according to the change in the state of the bulk cargo in the cargo ship during the operation;

[0013] According to the positions and states of different ship unloaders, coordinating the unloading paths of each ship unloader in real time.

[0014] As a preferred solution of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal of the present invention, wherein: a lidar, a camera and an ultrasonic sensor are used to collect data on the cabin structure and bulk cargo distribution, and the specific steps are as follows,

[0015] Use a checkerboard calibration board to collect lidar and camera data simultaneously for joint calibration;

[0016] Calculate the external parameter matrix between the lidar and the camera through a calibration algorithm;

[0017] Scan a standard object with a known distance through the ultrasonic sensor for distance calibration;

[0018] The lidar scans the cabin at a fixed frequency in all directions to collect point cloud data;

[0019] Adopt a voxel filtering method to filter the collected point cloud data to remove noise points and outliers;

[0020] While the lidar is scanning, the camera synchronously collects image data of the cabin, and uses a deep learning algorithm to segment the image to identify bulk cargo, cabin walls and other obstacles;

[0021] The ultrasonic sensor monitors the position of obstacles around the ship unloader by collecting the distance data between the cabin and the ultrasonic sensor, and uses moving average filtering to smooth the distance data.

[0022] As a preferred solution of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal of the present invention, wherein: the data collected by the lidar, the camera and the ultrasonic sensor are fused to generate a three-dimensional grid model, and the specific steps are as follows,

[0023] Use the hardware synchronization method to align the timestamps of the processed point cloud data, image data and distance data;

[0024] Based on the external parameter matrix, align the image data collected by the camera with the point cloud data of the lidar, and each pixel in the image corresponds to a point cloud data to obtain point cloud data with image information;

[0025] Convert the position of the obstacles around the ship unloader monitored by the ultrasonic sensor into three-dimensional points and synchronize them into the point cloud data with image information to obtain fused point cloud data;

[0026] Perform rasterization processing on the fused point cloud data and divide the entire three-dimensional space into several voxels;

[0027] Form triangular patches by connecting the representative points in the voxels to generate a three-dimensional grid model;

[0028] Optimize the generated three-dimensional grid model using the QEM algorithm;

[0029] Continuously collect new fused point cloud data, fuse it with the existing three-dimensional grid model, update the three-dimensional grid model in real time, and upload it to the blockchain platform;

[0030] The ship unloader uploads the real-time updated three-dimensional grid model and working status to the blockchain platform in real time through the control center.

[0031] As a preferred solution of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal described in the present invention, wherein: based on the blockchain platform, task allocation is performed on the ship unloader, and the specific steps are as follows.

[0032] The port scheduling center uploads the ship arrival plan and the bulk cargo list of the cargo ship to the blockchain platform;

[0033] The blockchain platform allocates ship unloading tasks to each ship unloader according to the real-time three-dimensional grid model and real-time working status uploaded by the ship unloader;

[0034] It is sent to the ship unloader control center through a secure channel, and the ship unloader automatically unloads the ship according to the received ship unloading task.

[0035] As a preferred solution of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal described in the present invention, wherein: based on the three-dimensional grid model and the allocated tasks, a unloading path is generated, and the specific steps are as follows.

[0036] Mark the non-passable voxels according to the cargo distribution, cabin structure and obstacle positions in the three-dimensional grid model;

[0037] According to the ship unloading tasks issued by the blockchain platform to the ship unloader, use a hybrid path planning algorithm combining A-Star and deep reinforcement learning to plan the unloading path;

[0038] The hybrid path planning algorithm uses the Euclidean distance as the heuristic function to estimate the cost from the initial position of the ship unloader grab to the target position;

[0039] According to the voxel division in the three-dimensional grid model, starting from the voxel where the ship unloader grab is located, gradually expand the adjacent voxels and bypass the non-passable voxels until reaching the voxel where the target position is located;

[0040] Based on the principle of minimum cost, select the voxel with the minimum cost for expansion in the target direction;

[0041] When the target position is found, trace back the route from the target position to the initial position of the ship unloader grab in reverse to generate an initial path.

[0042] As a preferred solution of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal of the present invention, the update of the unloading path according to the change of the bulk cargo state in the cargo ship during the operation process is as follows:

[0043] Based on the real-time updated three-dimensional grid model, each time the grab of the ship unloader grabs a bulk cargo, the non-passable voxels are re-marked;

[0044] According to the height coordinates of the bulk cargo in the three-dimensional grid model, judge the bulk cargo accumulation state, and preferentially set the position with the highest height coordinate as the target position of the grab of the ship unloader.

[0045] Estimate the cost from the initial position of the grab of the ship unloader to the target position, update the initial path, and generate a new unloading path.

[0046] As a preferred solution of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal of the present invention, the real-time coordination of the unloading paths of each ship unloader according to different positions and states of the ship unloader is as follows:

[0047] The ship unloader control center uploads the real-time unloading path information to the port scheduling center at a fixed frequency;

[0048] According to the maximum opening radius of the grabs of adjacent ship unloaders, set the safety distance threshold between the grabs of the ship unloaders;

[0049] According to the rotation speed of the ship unloader and the charging speed of the grab of the ship unloader, set the safety time threshold;

[0050] Summarize the real-time unloading path information, and cross-compare the real-time unloading paths of adjacent ship unloaders. When the distance between the grabs of adjacent ship unloaders is less than the safety distance threshold, it is determined that there is a collision risk, otherwise there is no collision risk;

[0051] Conduct a time cross-comparison on the two unloading paths with a collision risk. When the time difference between the grabs of adjacent ship unloaders reaching the position with a collision risk is less than the safety time threshold, it is confirmed that there is a collision risk, otherwise there is no collision risk;

[0052] The port scheduling center issues a safety warning notice to the ship unloader control center with a collision risk. One ship unloader pauses moving and restarts after the other ship unloader passes the position with a collision risk;

[0053] And when updating the unloading path, mark the voxels where the position with a collision risk is located as non-passable voxels.

[0054] In a second aspect, the present invention provides a ship unloading system for a bulk cargo terminal automatic grab ship unloader, including a data acquisition module, a model construction module, a task allocation module, a path generation module, a path update module, and a path coordination module.

[0055] The data acquisition module is used to collect data on the cabin structure and bulk cargo distribution using lidar, cameras, and ultrasonic sensors.

[0056] The model construction module is used to fuse the data collected by the lidar, cameras, and ultrasonic sensors to generate a three-dimensional grid model.

[0057] The task allocation module is used to allocate tasks to the ship unloader based on a blockchain platform.

[0058] The path generation module is used to generate a unloading path based on the three-dimensional grid model and the allocated tasks.

[0059] The path update module is used to update the unloading path according to the change of the bulk cargo state in the cargo ship during the operation process.

[0060] The path coordination module is used to coordinate the unloading paths of each ship unloader in real time according to the positions and states of different ship unloaders.

[0061] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the ship unloading method for a bulk cargo terminal automatic grab ship unloader as described in the first aspect of the present invention is implemented.

[0062] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the ship unloading method for a bulk cargo terminal automatic grab ship unloader as described in the first aspect of the present invention is implemented.

[0063] The beneficial effects of the present invention are as follows: Through the fusion of lidar, cameras, and ultrasonic sensors, the system achieves high-precision environmental perception, ensures the accuracy of the three-dimensional grid model, and provides reliable basic data for subsequent path planning. The task allocation system based on blockchain avoids human intervention and operation errors, improves the fairness and traceability of task allocation. The hybrid path planning algorithm automatically generates unloading paths in static and dynamic environments, adapts to changes in cargo distribution, and avoids operation delays caused by path failures. The real-time path update mechanism dynamically adjusts the path according to the latest cargo distribution, avoids repeated grabs and unnecessary movements, and significantly improves the unloading efficiency. Through the global coordination of the port scheduling center, the cooperative operation of multiple ship unloaders is achieved, avoiding conflicts and collisions, and further improving the overall unloading efficiency and safety. Brief Description of the Drawings

[0064] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0065] Figure 1 It is a flowchart of the ship unloading method for the automatic grab ship unloader at the bulk cargo terminal in Embodiment 1.

[0066] Figure 2 It is a module diagram of the ship unloading system for the automatic grab ship unloader at the bulk cargo terminal in Embodiment 1. Detailed Embodiments

[0067] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the drawings in the specification.

[0068] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0069] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that mutually excludes other embodiments.

[0070] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides a ship unloading method for an automatic grab ship unloader at a bulk cargo terminal, including the following steps:

[0071] S1. Use lidar, cameras, and ultrasonic sensors to collect data on the cabin structure and bulk cargo distribution.

[0072] Install the lidar and cameras on the top of the ship unloader to facilitate scanning the cargo ship cabin and bulk cargo. The installation positions of the ultrasonic sensors should cover the front, rear, left, and right directions of the ship unloader to ensure that the cargo ship approaching the ship unloader can be detected;

[0073] Use a checkerboard calibration board to collect data from the lidar and cameras simultaneously for joint calibration;

[0074] Through a calibration algorithm (such as Zhang Zhengyou calibration method), calculate the external parameter matrix (i.e., rotation matrix and translation vector) between the lidar and the camera to ensure the consistency of the coordinate systems of the two;

[0075] Scan a standard object with a known distance through an ultrasonic sensor for distance calibration;

[0076] Specifically, based on the known geometric structure of the calibration board and combining the data collected by the lidar and the camera, calculate the external parameter matrix (i.e., rotation matrix and translation vector) between the two;

[0077] Select a number of feature points with known positions (such as the corner points of the calibration board) on the calibration board, and measure the three-dimensional coordinates of these points through the lidar and the camera respectively. Compare the measurement results of the two, calculate the error value. If the error is within the allowable range (such as ±1 cm), the calibration is successful; otherwise, the calibration needs to be performed again;

[0078] The lidar scans the cabin at a fixed frequency in all directions to collect point cloud data. The point cloud data generated by each scan contains XYZ coordinates and intensity values;

[0079] Use the voxel filtering method to filter the collected point cloud data to remove noise points and outliers;

[0080] While the lidar is scanning, the camera synchronously collects image data of the cabin, and uses a deep learning algorithm (such as Mask R-CNN) to segment the image to identify bulk cargo, cabin walls and other obstacles;

[0081] Among them, other obstacles include lighting equipment, cables and wires, and safety signs, etc.;

[0082] The ultrasonic sensor monitors the position of obstacles around the ship unloader in real time by collecting the distance data between the cabin and the ultrasonic sensor, and uses moving average filtering to smooth the distance data to reduce the fluctuations caused by environmental noise.

[0083] S2. Generate a three-dimensional grid model by fusing the data collected by the lidar, the camera and the ultrasonic sensor.

[0084] Use the hardware synchronization method to align the timestamps of the processed point cloud data, image data and distance data;

[0085] Based on the external parameter matrix, align the image data collected by the camera with the point cloud data of the lidar. Each pixel in the image corresponds to a point cloud data to obtain point cloud data with image information;

[0086] Convert the positions of obstacles around the ship unloader monitored by the ultrasonic sensor into three-dimensional points and synchronize them into the point cloud data with image information to obtain the fused point cloud data;

[0087] Perform rasterization processing on the fused point cloud data and divide the entire three-dimensional space into several voxels;

[0088] Form triangular patches by connecting the representative points in the voxels to generate a three-dimensional mesh model;

[0089] Use the QEM algorithm to optimize the generated three-dimensional mesh model and reduce the complexity of the three-dimensional mesh model;

[0090] As the ship unloader operates, the bulk cargo in the cabin gradually decreases. By continuously collecting new fused point cloud data and fusing it with the existing three-dimensional mesh model, the three-dimensional mesh model is updated in real time and uploaded to the blockchain platform;

[0091] Specifically, according to the size of the cabin and the distribution range of the point cloud data, determine the boundaries of the voxel grid, divide the entire three-dimensional space into uniform voxels, and effectively reduce the redundancy of the point cloud data through the voxel grid while maintaining the details of the three-dimensional mesh model;

[0092] Assign the fused point cloud data to the voxels. Each voxel contains multiple point cloud data, and take the average value of all the point clouds in the voxel as the representative point;

[0093] Use the triangulation method (such as Delaunay triangulation) to form triangular patches by connecting the representative points in the voxels to generate a three-dimensional mesh model;

[0094] Use the QEM algorithm to optimize the three-dimensional mesh model by minimizing the error after vertex merging. Calculate the quadratic error matrix for each vertex of the triangular patch to describe the geometric relationship between the vertex and its neighboring vertices;

[0095] Traverse all vertex pairs, calculate the error value after merging each pair of vertices, select the vertex pair with the minimum error for merging, and update the error matrix of the adjacent vertices;

[0096] It should be noted that the QEM algorithm can maximize the retention of geometric features while simplifying the model;

[0097] Adopt incremental fusion to fuse the newly collected data, and use the ICP (Iterative Closest Point) algorithm to register the newly fused point cloud data with the existing three-dimensional mesh model;

[0098] Add the registered new fused point cloud data to the voxel grid. By calculating the point cloud density and point cloud geometric features within each voxel, detect the voxels with changes in density and geometric features. For example, if the point cloud density within a certain voxel significantly decreases, it indicates that the bulk cargo in this area has been removed;

[0099] Give priority to updating the detected changed voxels, and do not process the voxels that have not changed;

[0100] The ship unloader uploads the real-time updated 3D grid model and working status to the blockchain platform in real time through the control center, which serves as an important basis for the blockchain platform to assign tasks.

[0101] S3. Based on the blockchain platform, assign tasks to the ship unloader.

[0102] The port scheduling center uploads the cargo ship arrival plan and bulk cargo list to the blockchain platform;

[0103] The blockchain platform assigns unloading tasks to each ship unloader according to the real-time 3D grid model and real-time working status uploaded by the ship unloader;

[0104] Among them, the unloading tasks include unloading priority, ship name, bulk cargo type (such as coal, ore, grain, etc.), unloading volume, estimated operation time, and ship unloader ID and quantity;

[0105] The generated unloading tasks will be checked through a series of verification rules to ensure that all fields meet the predefined standards. For example, the unloading volume cannot exceed the maximum load capacity of the ship, and the operation time window cannot conflict with other tasks, etc.;

[0106] Send them to the ship unloader control center through a secure channel (such as TLS / SSL), and the ship unloader automatically unloads the ship according to the received unloading tasks.

[0107] S4. Based on the 3D grid model and the assigned tasks, generate an unloading path.

[0108] Mark the non-passable voxels according to the cargo distribution, cabin structure, and obstacle positions in the 3D grid model;

[0109] According to the unloading tasks issued by the blockchain platform to the ship unloader, use a hybrid path planning algorithm combining A-Star and deep reinforcement learning (DRL) to plan the unloading path;

[0110] The hybrid path planning algorithm uses the Euclidean distance as the heuristic function to estimate the cost from the initial position of the ship unloader grab to the target position. The calculation formula is as follows:

[0111] ;

[0112] Among them, is the Euclidean distance from the grab of the ship unloader to the target position, are the three-dimensional coordinate values of the grab of the ship unloader in the three-dimensional grid model, are the three-dimensional coordinate values of the target position in the three-dimensional grid model;

[0113] According to the voxel division in the three-dimensional grid model, starting from the voxel where the grab of the ship unloader is located, gradually expand the adjacent voxels and bypass the impassable voxels until reaching the voxel where the target position is located;

[0114] Based on the principle of minimum cost, select the voxel with the minimum cost for expansion along the target direction;

[0115] After finding the target position, trace back the route from the target position to the initial position of the grab of the ship unloader in reverse to generate the initial path.

[0116] S5. Update the unloading path according to the change of the bulk cargo state in the cargo ship during the operation process.

[0117] Based on the real-time updated three-dimensional grid model, each time the grab of the ship unloader grabs a bulk cargo, re-label the impassable voxels;

[0118] When the cargo ship just arrives at the port, the bulk cargo in the cabin is piled up relatively evenly, and the grab of the ship unloader can grab randomly. After grabbing, the surface of the bulk cargo pile shows undulations. If it has been concentrated on a certain place for grabbing, there are risks such as affecting the center of gravity of the cargo ship and causing it to capsize. At the same time, it is not conducive to the unloading efficiency;

[0119] According to the height coordinates of the bulk cargo in the three-dimensional grid model, judge the state of the bulk cargo pile, and give priority to setting the position with the highest height coordinate as the target position of the grab of the ship unloader

[0120] Estimate the cost from the initial position of the grab of the ship unloader to the target position, update the initial path, and generate a new unloading path.

[0121] S6. According to the positions and states of different ship unloaders, coordinate the unloading paths of each ship unloader in real time.

[0122] The ship unloader control center uploads the real-time unloading path information to the port dispatching center at a fixed frequency (such as once per second);

[0123] Among them, the unloading path information includes the current position, target position, unloading path, unloading path activation time, and estimated arrival and return times of the ship unloader;

[0124] According to the maximum opening radius of the grabs of adjacent ship unloaders, set the safety spacing threshold between the grabs of the ship unloaders to twice the maximum radius of the grab;

[0125] Set a safety time threshold according to the rotation speed of the ship unloader and the charging speed of the ship unloader's grab bucket;

[0126] Furthermore, summarize the real-time unloading path information, cross-compare the real-time unloading paths of adjacent ship unloaders. When the distance between the grabs of adjacent ship unloaders is less than the safety distance threshold, it is determined that there is a collision risk; otherwise, there is no collision risk;

[0127] Conduct a time cross-comparison of the two unloading paths with collision risks. When the time difference between the grabs of adjacent ship unloaders reaching the position with collision risk is less than the safety time threshold, it is confirmed that there is a collision risk; otherwise, there is no collision risk;

[0128] The port dispatching center issues a safety warning notice to the ship unloader control center with collision risks. One ship unloader pauses to move and restarts after the other ship unloader passes the position with collision risk;

[0129] Specifically, by comparing the path lengths of the grabs of the two ship unloaders to the position with collision risk, pause the ship unloader with the longer path and let it pass after the grab of the ship unloader with the shorter path passes, to ensure safety and efficiency;

[0130] And when updating the unloading path, mark the voxel where the position with collision risk is located as an impassable voxel.

[0131] This embodiment also provides a ship unloader system for bulk cargo terminals with automatic grab buckets, including: a data acquisition module, a model construction module, a task assignment module, a path generation module, a path update module, and a path coordination module,

[0132] The data acquisition module is used to collect data on the cabin structure and bulk cargo distribution using lidar, cameras, and ultrasonic sensors;

[0133] The model construction module is used to fuse the data collected by lidar, cameras, and ultrasonic sensors to generate a three-dimensional grid model;

[0134] The task assignment module is used to assign tasks to the ship unloaders based on the blockchain platform;

[0135] The path generation module is used to generate an unloading path based on the three-dimensional grid model and the assigned tasks;

[0136] The path update module is used to update the unloading path according to the change of the bulk cargo state in the cargo ship during the operation process;

[0137] The path coordination module is used to coordinate the unloading paths of each ship unloader in real time according to the positions and states of different ship unloaders.

[0138] This embodiment also provides a computer device, which is applicable to the case of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the ship unloading method of the automatic grab ship unloader proposed in the above embodiment.

[0139] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, a trackball or a touchpad provided on the outer shell of the computer device, or an external keyboard, a touchpad or a mouse, etc.

[0140] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the ship unloading method of the automatic grab ship unloader proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read Only Memory (EPROM for short), Programmable Red-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk or an optical disc.

[0141] In summary, through the fusion of lidar, cameras, and ultrasonic sensors, the system achieves high-precision environmental perception, ensures the accuracy of the 3D grid model, and provides reliable basic data for subsequent path planning. The blockchain-based task assignment system avoids human intervention and operational errors, improving the fairness and traceability of task assignment. The hybrid path planning algorithm automatically generates unloading paths in static and dynamic environments, adapts to changes in cargo distribution, and avoids operation delays caused by path failures. The real-time path update mechanism dynamically adjusts paths according to the latest cargo distribution, avoiding repeated grasping and unnecessary movements, and significantly improving unloading efficiency. Through the global coordination of the port scheduling center, the collaborative operation of multiple ship unloaders is achieved, avoiding conflicts and collisions, and further improving the overall unloading efficiency and safety.

[0142] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for unloading a ship by an automatic grab ship unloader at a bulk cargo terminal, characterized in that: including Using lidar, cameras, and ultrasonic sensors to collect data on the cabin structure and bulk cargo distribution. The specific steps are as follows Using a checkerboard calibration board to collect data from the lidar and cameras simultaneously for joint calibration Calculating the external parameter matrix between the lidar and the camera through a calibration algorithm Scanning a standard object with a known distance using the ultrasonic sensor for distance calibration The lidar scans the cabin at a fixed frequency over a full angle to collect point cloud data Using a voxel filtering method to filter the collected point cloud data to remove noise points and outliers While the lidar is scanning, the camera synchronously collects image data of the cabin. Using deep learning algorithms to segment the images to identify bulk cargo, cabin walls, and other obstacles The ultrasonic sensor monitors the position of obstacles around the ship unloader by collecting distance data between the cabin and the ultrasonic sensor, and uses moving average filtering to smooth the distance data Generating a three-dimensional grid model by fusing the data collected from the lidar, cameras, and ultrasonic sensors Based on the blockchain platform, task allocation for the ship unloader is performed Based on the three-dimensional grid model and the assigned tasks, a unloading path is generated Updating the unloading path according to the change in the state of the bulk cargo in the cargo ship during the operation process According to the positions and states of different ship unloaders, the unloading paths of each ship unloader are coordinated in real time 2. The ship unloading method of the bulk cargo terminal automatic grab ship unloader according to claim 1, characterized in that: The specific steps for generating a three-dimensional grid model by fusing the data collected from the lidar, cameras, and ultrasonic sensors are as follows Using a hardware synchronization method to align the timestamps of the processed point cloud data, image data, and distance data Based on the external parameter matrix, aligning the image data collected by the camera with the point cloud data of the lidar Each pixel in the image corresponds to a point cloud data, obtaining point cloud data with image information Converting the position of obstacles around the ship unloader monitored by the ultrasonic sensor into three-dimensional points and synchronizing them into the point cloud data with image information to obtain fused point cloud data Performing voxelization on the fused point cloud data and dividing the entire three-dimensional space into several voxels Forming triangular patches by connecting the representative points in the voxels to generate a three-dimensional grid model Using the QEM algorithm to optimize the generated three-dimensional grid model By continuously collecting new fused point cloud data and fusing it with the existing three-dimensional grid model, the three-dimensional grid model is updated in real time and uploaded to the blockchain platform The ship unloader uploads the real-time updated three-dimensional grid model and working status to the blockchain platform through the control center in real time 3. The ship unloading method of the bulk cargo terminal automatic grab ship unloader according to claim 1, characterized in that: The specific steps for performing task allocation for the ship unloader based on the blockchain platform are as follows The port scheduling center uploads the arrival plan of the cargo ship and the bulk cargo list to the blockchain platform The blockchain platform assigns unloading tasks to each ship unloader according to the real-time three-dimensional grid model and real-time working status uploaded by the ship unloader Issuing them to the ship unloader control center through a secure channel, and the ship unloader automatically unloads the ship according to the received unloading tasks 4. The ship unloading method of the bulk cargo terminal automatic grab ship unloader according to claim 1, characterized in that: The specific steps for generating a unloading path based on the three-dimensional grid model and the assigned tasks are as follows Mark the impassable voxels according to the cargo distribution, cabin structure, and obstacle positions in the three-dimensional grid model; According to the unloading tasks sent by the blockchain platform to the ship unloader, use a hybrid path planning algorithm that combines A-Star and deep reinforcement learning to plan the unloading path; The hybrid path planning algorithm uses the Euclidean distance as the heuristic function to estimate the cost from the initial position of the ship unloader's grab to the target position; According to the voxel division in the three-dimensional grid model, starting from the voxel where the ship unloader's grab is located, gradually expand the adjacent voxels and bypass the impassable voxels until reaching the voxel where the target position is located; Based on the principle of minimum cost, select the voxel with the minimum cost for expansion in the target direction; When the target position is found, trace back the route from the target position to the initial position of the ship unloader's grab in reverse to generate the initial path.

5. The ship unloading method of the automatic grab ship unloader at the bulk cargo terminal according to claim 1, wherein: The unloading path is updated by the change of the bulk cargo state in the cargo ship during the operation process. The specific steps are as follows. Based on the real-time updated three-dimensional grid model, every time the ship unloader's grab grabs a bulk cargo, re-mark the impassable voxels; According to the height coordinates of the bulk cargo in the three-dimensional grid model, judge the bulk cargo accumulation state, and preferentially set the position with the highest height coordinate as the target position of the ship unloader's grab. Estimate the cost from the initial position of the ship unloader's grab to the target position, update the initial path, and generate a new unloading path.

6. The ship unloading method of the bulk cargo terminal automatic grab ship unloader according to claim 1, characterized in that: The unloading paths of each ship unloader are coordinated in real time according to different ship unloader positions and states. The specific steps are as follows. The ship unloader control center uploads the real-time unloading path information to the port scheduling center at a fixed frequency; Set the safety distance threshold between the ship unloader's grabs according to the maximum opening radius of the grabs of adjacent ship unloaders; Set the safety time threshold according to the rotation speed of the ship unloader and the receiving speed of the ship unloader's grab; Summarize the real-time unloading path information, cross-compare the real-time unloading paths of adjacent ship unloaders. When the distance between the grabs of adjacent ship unloaders is less than the safety distance threshold, it is determined that there is a collision risk, otherwise there is no collision risk; Conduct a time cross-comparison on the two unloading paths with collision risks. When the time difference between the grabs of adjacent ship unloaders reaching the position with collision risk is less than the safety time threshold, it is confirmed that there is a collision risk, otherwise there is no collision risk; The port scheduling center issues a safety warning notice to the ship unloader control center with collision risks. One ship unloader pauses moving and restarts after the other ship unloader passes the position with collision risk; And when updating the unloading path, mark the voxels where the position with collision risk is located as impassable voxels.

7. A ship unloading system for an automatic grab ship unloader at a bulk cargo terminal, based on the ship unloading method for an automatic grab ship unloader at a bulk cargo terminal according to any one of claims 1 to 6, characterized in that: Including a data acquisition module, a model construction module, a task assignment module, a path generation module, a path update module, and a path coordination module. The data acquisition module is used to collect data on the cabin structure and bulk cargo distribution using lidar, cameras, and ultrasonic sensors; The model construction module is used to fuse the data collected by the lidar, cameras, and ultrasonic sensors to generate a three-dimensional grid model; The task assignment module is used to assign tasks to the ship unloader based on the blockchain platform. The path generation module is configured to generate a discharging path based on the three-dimensional grid model and the assigned tasks; The path update module is configured to update the discharging path according to the change of the bulk cargo state in the cargo ship during the operation process; The path coordination module is configured to coordinate the discharging paths of each ship unloader in real time according to the positions and states of different ship unloaders.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the ship unloading method of the automatic grab ship unloader at the bulk cargo terminal according to any one of claims 1 to 6 are implemented.

Images