Belt conveyor cleaning robot navigation method, device and equipment and storage medium

Abstract

The invention relates to a belt conveyor cleaning robot navigation method, device and equipment and a storage medium, and is applied to the technical field of robot navigation, and the method comprises the steps: scanning a to-be-cleaned area through a laser radar, and generating a point cloud map of the to-be-cleaned area; controlling the belt conveyor cleaning robot to operate according to a preset to-be-cleaned point, and determining an operation path of the belt conveyor cleaning robot in the to-be-cleaned area in the point cloud map; the GPS receiver and the laser radar are used for determining the position of the belt conveyor cleaning robot in the point cloud map, and the belt conveyor cleaning robot is controlled to advance according to the operation path; and identifying and sweeping materials to be swept, wherein the materials to be swept are materials needing to be swept on the lower side of the belt conveyor. The device has the technical effects that non-stop operation of the device is realized, manual material cleaning operation is replaced, and the production efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of robot navigation technology, and in particular to a belt conveyor cleaning robot navigation method, device, equipment and storage medium. Background Art

[0002] Belt conveyors have the characteristics of long distance, large transport capacity, energy saving and reliability, and play an important role in iron ore transportation. During the material transportation process, due to the adhesiveness, the existing belt cleaning measures cannot completely clean the materials attached to the belt, and the materials may be scattered along the return belt; in addition, during the material transmission process, the materials may be thrown along the line due to the sudden stop or deviation of the belt.

[0003] There are many types of cleaning robots on the market. However, due to the small space at the bottom of the belt conveyor, the cleaning robots currently on the market find it difficult to operate and clean materials in the narrow space under the belt, which may affect production continuity and reduce production efficiency. Summary of the invention

[0004] In order to help solve the problem that cleaning robots currently on the market have difficulty operating and cleaning materials in the narrow space under the belt, thereby affecting production continuity and reducing production efficiency, the present application provides a belt conveyor cleaning robot navigation method, device, equipment and storage medium.

[0005] In the first aspect, the present application provides a belt conveyor cleaning robot navigation method, which adopts the following technical solution: the method is applied to a belt conveyor cleaning robot control system, the belt conveyor cleaning robot control system includes a laser radar and a GPS receiver, and the method includes:

[0006] Scanning the area to be cleaned by the laser radar and generating a point cloud map of the area to be cleaned;

[0007] Controlling the conveyor belt cleaning robot to run according to the preset points to be cleaned, and determining the running path of the conveyor belt cleaning robot in the area to be cleaned in the point cloud map;

[0008] Determine the position of the belt conveyor cleaning robot in the point cloud map by using the GPS receiver and the laser radar, and control the belt conveyor cleaning robot to move forward along the running path;

[0009] Identify and clean the material to be cleaned, where the material to be cleaned is the material that needs to be cleaned on the lower side of the belt conveyor.

[0010] In a specific implementation scheme, the use of the GPS receiver and the laser radar to determine the position of the belt conveyor cleaning robot in the point cloud map includes:

[0011] Utilizing the GPS receiver to receive the GPS positioning signal of the belt conveyor cleaning robot;

[0012] Communicate with a reference receiver at a preset reference position, calibrate the GPS positioning signal of the belt conveyor cleaning robot, and generate a GPS calibration signal;

[0013] Scanning the point cloud signal of the location of the belt conveyor cleaning robot by the laser radar, and comparing the point cloud signal of the location with the point cloud map to generate a radar positioning signal;

[0014] Fusing the GPS calibration signal and the radar signal to generate a fused positioning signal;

[0015] The position of the belt conveyor cleaning robot in the point cloud map is determined according to the fused positioning signal.

[0016] In a specific implementation scheme, the belt conveyor cleaning robot control system further includes an image acquisition unit, and the identifying and cleaning of the material to be cleaned includes:

[0017] Acquire image information of the current viewing angle through the image acquisition unit, and input the image information of the current viewing angle into the trained material recognition model;

[0018] Determining whether the result output by the material identification model is the material to be cleaned;

[0019] If the result output by the material identification model is the material to be cleaned, the belt conveyor cleaning robot is controlled to push the material to be cleaned forward.

[0020] In a specific implementation scheme, the training method of the material recognition model includes:

[0021] Acquire an image set of the material to be cleaned by the image acquisition unit;

[0022] The image set of the material to be cleaned is input into a preset image recognition model for training, and the material recognition model is generated.

[0023] In a specific embodiment, before identifying and cleaning the material to be cleaned, the method further includes:

[0024] According to the position of the obstacle in the area to be cleaned, marking the obstacle point in the point cloud map;

[0025] According to the point cloud map, the distance between the belt conveyor cleaning robot and all obstacle points is calculated, and the minimum distance between the belt conveyor cleaning robot and all obstacle points is determined;

[0026] Comparing the calculated minimum distance value with a preset threshold;

[0027] If the minimum distance is less than a preset threshold, the belt conveyor cleaning robot is controlled to stop moving forward.

[0028] In a specific embodiment, the method further comprises:

[0029] In response to the charging instruction, locate and proceed to the location of the charging pile for charging.

[0030] In a specific implementation scheme, the belt conveyor cleaning robot moves forward in a crawler manner.

[0031] In the second aspect, the present application provides a belt conveyor cleaning robot navigation device, which adopts the following technical solution: the device is applied to a belt conveyor cleaning robot control system, the belt conveyor cleaning robot control system includes a laser radar and a GPS receiver, and the device includes:

[0032] A point cloud map generation module, used to scan the area to be cleaned by the laser radar and generate a point cloud map of the area to be cleaned;

[0033] An operation path determination module is used to control the belt conveyor cleaning robot to operate according to preset points to be cleaned, and determine the operation path of the belt conveyor cleaning robot in the area to be cleaned in the point cloud map;

[0034] A position determination module, used for determining the position of the belt conveyor cleaning robot in the point cloud map by using the GPS receiver and the laser radar, and controlling the belt conveyor cleaning robot to move forward along the running path;

[0035] The material identification and cleaning module is used to identify and clean the material to be cleaned, and the material to be cleaned is the material that needs to be cleaned on the lower side of the belt conveyor.

[0036] In a third aspect, the present application provides a computer device, which adopts the following technical solution: it includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and executed by any of the above-mentioned belt conveyor cleaning robot navigation methods.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: a computer program that can be loaded by a processor and execute any of the above-mentioned belt conveyor cleaning robot navigation methods is stored.

[0038] In summary, this application has the following beneficial technical effects:

[0039] The robot's movement path is planned by presetting points. During the robot's forward movement, GPS positioning and radar laser positioning are integrated to realize the accurate position of the belt conveyor cleaning robot in the three-dimensional point cloud map, so that it can accurately move forward according to the set running trajectory to realize the material cleaning under the belt conveyor. By intelligently cleaning the accumulated materials under the belt conveyor, the robot can realize non-stop operation of the equipment, replace the manual material cleaning operation method, ensure personnel safety, save labor costs, and improve production efficiency. The robot bucket can automatically retract when encountering a bump on the ground, so that the robot will not be stuck on the ground and difficult to move forward, ensuring that the robot can carry out the cleaning operation smoothly. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of a belt conveyor cleaning robot navigation method in an embodiment of the present application;

[0041] Figure 2 is a schematic diagram of a belt conveyor cleaning robot in an embodiment of the present application;

[0042] Figure 3 is a schematic diagram of a belt conveyor cleaning robot navigation device in an embodiment of the present application;

[0043] Figure 4 It is a schematic diagram used to embody a computer device in an embodiment of the present application.

[0044] Attached figure numbers: 301, point cloud map generation module; 302, operation path determination module; 303, position determination module; 304, material identification and cleaning module. DETAILED DESCRIPTION

[0045] The following combination Figure 1-Figure 4 This application is described in further detail.

[0046] An embodiment of the present application discloses a belt conveyor cleaning robot navigation method, which is applied to a belt conveyor cleaning robot control system. Through this method, the belt conveyor cleaning robot can be controlled to clean materials in a narrow space at the bottom of the belt conveyor.

[0047] Belt conveyors play an important role in the transportation of coal and iron ore. In practical applications, long belt conveyors, for example, 1,000-meter-long belt conveyors, can quickly and efficiently transport coal and iron ore to their destinations, thereby improving production efficiency and reducing the waste of manpower and material resources. However, in the process of using belts to transport materials such as coal and iron ore, belt conveyors may experience problems such as shaking, emergency stops, and deviations, causing the materials transported on the belt to spill, or the materials to adhere to the belt and fall on the lower side of the belt during the return journey. There are now some cleaning robots designed specifically for outdoor cleaning work, which can effectively remove dust, leaves, pebbles and other debris on the ground. The materials that fall around the belt conveyor can be cleaned by the cleaning robot. However, the existing robots are large in size and cannot drill into the low, narrow and poorly visible areas under the belt conveyor for automatic navigation operations; in addition, most of the current cleaning robots are wheel-driven and can only be used on relatively flat ground. They are easily stuck in harsh industrial environments and cannot move forward.

[0048] Therefore, there is currently no suitable robot for cleaning materials on the lower side of the belt conveyor, and workers are usually required to clean them manually. Since the belt conveyor rotates at high speed during transportation, manual cleaning usually requires the equipment to be shut down before manual cleaning. Manual cleaning not only affects production continuity and reduces production efficiency, but is also time-consuming and labor-intensive, and poses a safety hazard. In order to facilitate the cleaning of materials on the lower side of the belt conveyor, the present application provides a belt conveyor cleaning robot navigation method.

[0049] Reference Figure 1 , the method comprises the following steps:

[0050] S10, scanning the area to be cleaned by using a laser radar, and generating a point cloud map of the area to be cleaned.

[0051] Specifically, in the embodiment of the present application, the schematic diagram of the designed belt conveyor cleaning robot is as follows Figure 2 As shown, the belt conveyor cleaning robot is equipped with a laser radar. The laser radar used can be three-dimensional or two-dimensional. The specific selection can be based on the actual application. In the embodiment of the present application, a three-dimensional laser radar is used for illustration. By controlling the three-dimensional laser radar to scan the area to be cleaned, a point cloud map of the area to be cleaned can be generated. Since a three-dimensional laser radar is used in the embodiment of the present application, the generated point cloud map is a three-dimensional point cloud map in the embodiment of the present application. The generated three-dimensional point cloud map is recorded and stored inside the control system of the belt conveyor cleaning robot.

[0052] S20, controlling the belt conveyor cleaning robot to run according to the preset points to be cleaned, and determining the running path of the belt conveyor cleaning robot in the area to be cleaned in the point cloud map.

[0053] Specifically, the user will set the material cleaning points of the belt conveyor cleaning robot in advance, and control the belt conveyor cleaning robot to run once according to the pre-set points to be cleaned by manual remote control, forming the cleaning operation trajectory of the belt conveyor cleaning robot, thereby determining the operation path of the belt conveyor cleaning robot in the area to be cleaned, and recording and storing the operation path in the robot control system. In the actual application of coal mines and iron ore transportation, long belt conveyors are generally used, such as long belt conveyors of hundreds or thousands of meters. Due to the narrow space under the belt conveyor, poor vision, and dim and complex environment, determining the robot's operation path in advance can prevent the robot from running off in a dim and complex environment, thereby affecting the material cleaning work.

[0054] S30, using a GPS receiver and a laser radar to determine the position of the belt conveyor cleaning robot in the point cloud map, and controlling the belt conveyor cleaning robot to move forward along the running path.

[0055] Specifically, the user manually remotely controls the robot to determine the path of the robot's cleaning operation in advance and records and stores it. After that, the robot can move forward according to the set operation path. During the robot's advancement, it is necessary to first determine the robot's specific position in the entire cleaning area. The robot determines its position in the cleaning area by combining GPS positioning and laser radar positioning. A GPS receiver and a laser radar are installed on the belt conveyor cleaning robot. The GPS receiver can receive the robot's GPS positioning, and the laser radar can scan the environment of the robot's current position and compare it with the pre-generated three-dimensional point cloud map to determine the robot's position in the map. By combining the two positioning methods, the robot's accurate position in the three-dimensional point cloud map is determined to determine the next point the robot needs to go to. Among them, it should be noted that the robot moves forward by means of crawlers. In the application of industrial scenes such as coal mines and iron ore, due to the mining process of coal mines and iron ore, the road surface is generally rugged and not flat. The general wheel drive method is easy to get stuck in harsh industrial environments such as coal mining, and it is difficult to move forward smoothly.

[0056] S40, identifying and cleaning the materials to be cleaned, where the materials to be cleaned are the materials that need to be cleaned on the lower side of the belt conveyor.

[0057] Specifically, an image acquisition unit is installed on the belt conveyor cleaning robot. The image acquisition unit is specifically used to acquire image information in front of the robot. The image acquisition unit can be a camera, etc. The specific method of acquiring the image is not limited here. The camera is used as an example to illustrate the embodiment of the present application. The camera continuously shoots videos and photos, extracts features from the image information and compares them with the features of the material acquired in advance. If the features are consistent, it is determined to be material, and the robot performs cleaning operations on the material. Figure 2 A bucket is set at the front end of the belt conveyor cleaning robot. When the robot is running in the cleaning area, the bucket is in a falling state. When the control system determines that there is material in front that needs to be cleaned, the robot pushes the material forward through the bucket at the front end, pushes the material to the outside of the belt conveyor, and then uses a large cleaning machine to clean up the material.

[0058] It should be noted that the bucket is installed in front of the belt conveyor cleaning robot. When the robot does not need to clean materials, the bucket is in a normal slightly raised state, and the bucket does not touch the ground to avoid the robot getting stuck; when the robot enters the cleaning area, the robot control system will control the bucket to fall and touch the ground, and move forward according to the set running path. When it is recognized that there is material that needs to be cleaned, the bucket will push the material from the bottom of the belt conveyor to the outside of the belt conveyor. After the robot uses the bucket to push the material to the outside of the belt conveyor, the internal system of the robot will control the bucket to lift up and place the material outside the belt conveyor, waiting for other machines to continue cleaning the material. In addition, when the bucket encounters a bump on the ground, the bucket will automatically retract, allowing the bucket and the robot to cross the bump so as not to get stuck and unable to move forward.

[0059] In this application, the robot's movement path is planned by presetting points. During the robot's forward movement, GPS positioning and radar laser positioning are integrated to realize the accurate position of the belt conveyor cleaning robot in the three-dimensional point cloud map, so that it can accurately move forward according to the set running trajectory to realize the material cleaning under the belt conveyor. By having the robot intelligently clean the accumulated materials under the belt conveyor, the equipment can be operated without stopping, replacing the manual material cleaning operation method, ensuring personnel safety, saving labor costs, and improving production efficiency.

[0060] In one embodiment, the step of using a GPS receiver and a laser radar to determine the position of the belt conveyor cleaning robot in the point cloud map can be specifically performed as follows:

[0061] First, a GPS receiver is used to receive the GPS positioning signal of the belt conveyor cleaning robot; specifically, a GPS receiver is installed on the robot for receiving the GPS positioning signal, which is also a specific latitude and longitude coordinate signal. The robot will receive the GPS positioning signal in real time during the normal operation of the cleaning area, and locate in real time to determine its own accurate position. Considering that the received GPS positioning signal may have deviations, it communicates with the reference receiver at the preset reference position, and calibrates the GPS positioning signal of the belt conveyor cleaning robot to generate a GPS calibration signal; specifically, the preset reference position is also a known accurate coordinate point, and a similar GPS receiver is set at the preset reference position, and the deviation between the position coordinate signal received by the GPS receiver and the actual position coordinate signal is recorded, and the deviation value is calculated. The GPS receiver of the belt conveyor cleaning robot communicates with the receiver set at the preset reference position to obtain the deviation value. The belt conveyor cleaning robot control system calculates the accurate position of the robot itself based on the received GPS positioning signal and the deviation value, that is, the GPS positioning signal is calibrated to obtain the GPS calibration signal.

[0062] Afterwards, the laser radar is used to scan the point cloud signal of the location of the belt conveyor cleaning robot, and the point cloud signal of the location is compared with the point cloud map to generate a radar positioning signal; it can also be understood that the point cloud data of the current location of the robot is scanned by the laser radar, and the point cloud data of the current location is compared with the three-dimensional point cloud map generated in advance, so as to obtain a radar positioning signal. By fusing the GPS calibration signal and the radar signal, a fused positioning signal is generated; the specific method of fusing the positioning signal can be implemented by existing technologies, for example, the fused positioning signal can be obtained by fusion calculation in a weighted manner to improve the accuracy of positioning; or by judging the confidence of the GPS positioning signal and the radar positioning signal in the fused positioning signal, the positioning signal with high confidence is selected as the accurate positioning signal. Finally, the position of the belt conveyor cleaning robot in the point cloud map is determined according to the fused positioning signal.

[0063] In the present application, taking into account the narrow space and dark and complex environment under the belt conveyor, a positioning method combining GPS positioning and radar positioning is adopted to determine the specific position of the robot in the cleaning area and improve the positioning accuracy, so that the robot can automatically navigate and operate under the belt conveyor.

[0064] In one embodiment, the belt conveyor cleaning robot control system further includes an image acquisition unit, and the steps of identifying and cleaning the material to be cleaned can be specifically performed as follows:

[0065] First, the image information of the current viewing angle is obtained through the image acquisition unit, and the image information of the current viewing angle is input into the trained material recognition model; for example, the video or photo under the current viewing angle can be continuously obtained through the camera, and the captured video or photo can be input into the material recognition model to extract the feature information in the image. Afterwards, it is determined whether the result output by the material recognition model is the material to be cleaned. Specifically, the feature information in the extracted image can be compared with the features of the pre-extracted and determined material to determine whether they match, and the corresponding recognition result is output; if the result output by the material recognition model is the material to be cleaned, the belt conveyor cleaning robot is controlled to push the material to be cleaned forward. If the result of the model recognition is not the material to be cleaned, it may be the steel frame structure of the belt conveyor itself. The robot can regard it as an obstacle and automatically avoid it, and then move forward according to the pre-planned path.

[0066] The material recognition model can be trained by: acquiring an image set of the material to be cleaned through an image acquisition unit, such as a camera, a camera, etc., which can be an image set of materials such as coal mines and iron ore on the lower side of the belt conveyor. Considering that the space on the lower side of the belt conveyor is small and the environment is relatively dim and complex, the characteristics of the material in an open environment and in a dim environment will be different. The image set of the material on the lower side of the belt conveyor is selected, and the image set of the material to be cleaned is input into the preset image recognition model for training, and a material recognition model is generated, so that the trained image set is more targeted, thereby improving the accuracy of model recognition. The preset image recognition model can be an existing model implementation, such as a YOLO model, etc., which is not limited here, and the user can determine it according to the computing power resources of the actual system.

[0067] In addition, when collecting images to train the image recognition model, the image set of materials on the lower side of the belt conveyor and the image set of the steel frame structure of the belt conveyor can be used for training and recognition; on the lower side of the belt conveyor, in addition to the materials to be cleaned, the main thing is the steel frame structure of the belt conveyor. By identifying the characteristic information of the two objects, in actual application, the steel frame structure of the belt conveyor and the materials can be better distinguished, so as to improve the accuracy of material recognition, thereby realizing intelligent cleaning of materials.

[0068] In the present application, images are captured and the information in the images is identified to achieve the purpose of cleaning materials. In the model training process, the image set of the belt conveyor steel frame structure and the materials under the belt conveyor is used for training, which can improve the accuracy of model recognition, so that the materials can be more accurately identified and cleaned in actual applications, thereby realizing the intelligent cleaning operation of accumulated materials.

[0069] In one embodiment, before identifying and cleaning the material to be cleaned, the following steps may be performed:

[0070] First, according to the position of the obstacle in the area to be cleaned, the obstacle points are marked in the point cloud map; specifically, in the process of generating the robot motion trajectory by manually remote-controlling the robot for the first time, the internal memory of the robot will record each point to be cleaned, and the places where obstacles are encountered will also be recorded. After generating a complete three-dimensional point cloud map, the position of the obstacles encountered will be marked. After that, during the automatic navigation operation of the robot, according to the position of the obstacles marked in the point cloud map, the distance between the belt conveyor cleaning robot and all obstacle points is calculated, and the minimum distance between all obstacle points is determined; that is, the position of the robot itself is determined by positioning, and the distance between the current position of the robot and each obstacle is calculated, the minimum distance between the obstacles with the smallest distance is determined, and the calculated minimum distance is compared with the preset threshold; if the minimum distance is less than the preset threshold, the belt conveyor cleaning robot is controlled to stop moving forward, and the robot can avoid obstacles, determine the next point to be cleaned and move forward again, or send a reminder to the user, and the user determines the robot's running trajectory again. If the minimum distance is not less than the preset threshold, the vehicle continues to move forward along the pre-planned path until the materials on the path are cleared to the outside of the belt conveyor.

[0071] It should be noted that the robot can also automatically identify obstacles and avoid them during operation. For example, in the non-cleaning area, if the robot encounters obstacles such as people and objects, the robot can automatically avoid them. In the cleaning area, mainly in the narrow, dim and complex environment under the belt conveyor, marking obstacles can better help the robot avoid obstacles and help the robot to successfully clean out the accumulated materials under the belt conveyor.

[0072] In the present application, by marking obstacle points and calculating the distance between the robot and the obstacle, the robot can be better assisted in obstacle avoidance, which helps the robot to smoothly clean the accumulated materials on the lower side of the belt conveyor and realize the cleaning of accumulated materials without stopping the equipment.

[0073] In one embodiment, considering that the robot needs power to maintain the entire movement process and cleaning work of the robot, it is difficult to perform the cleaning operation of accumulated materials when the robot is out of power. Therefore, the navigation method of the belt conveyor cleaning robot also includes:

[0074] In response to the charging instruction, the robot locates and moves to the location of the charging pile for charging; specifically, during the normal operation of the robot, if the user finds that the robot is low on power, a command to return to the charging pile can be sent to the control system. After receiving the command, the robot responds to the charging instruction, automatically runs to the charging pile and connects to the power supply for automatic charging.

[0075] In the present application scheme, considering that the robot needs power to maintain the entire movement process and cleaning work of the robot, it is difficult to complete the accumulated material cleaning operation when the robot is out of power. Therefore, when the robot is low on power, the user can send a charging command to the system. After the robot receives the command and returns to the charging pile to charge, it continues to perform the cleaning operation to ensure that the cleaning operation can proceed smoothly.

[0076] Figure 1 FIG. 1 is a flow chart of a belt conveyor cleaning robot navigation method in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows; unless otherwise specified in this document, there is no strict order restriction for the execution of the steps, and the steps may be executed in other orders; and Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0077] Based on the above method, an embodiment of the present application also discloses a belt conveyor cleaning robot navigation device.

[0078] Reference Figure 3 , the device includes the following modules:

[0079] The point cloud map generation module 301 is used to scan the area to be cleaned by using a laser radar and generate a point cloud map of the area to be cleaned;

[0080] The running path determination module 302 is used to control the belt conveyor cleaning robot to run according to the preset points to be cleaned, and determine the running path of the belt conveyor cleaning robot in the area to be cleaned in the point cloud map;

[0081] The position determination module 303 is used to determine the position of the belt conveyor cleaning robot in the point cloud map using a GPS receiver and a laser radar, and control the belt conveyor cleaning robot to move forward according to the running path;

[0082] The material identification and cleaning module 304 is used to identify and clean the materials to be cleaned, and the materials to be cleaned are the materials that need to be cleaned on the lower side of the belt conveyor.

[0083] In one embodiment, the position determination module 303 is specifically used to use a GPS receiver to receive the GPS positioning signal of the belt conveyor cleaning robot; communicate with a reference receiver at a preset reference position, and calibrate the GPS positioning signal of the belt conveyor cleaning robot to generate a GPS calibration signal; scan the point cloud signal of the belt conveyor cleaning robot at the location through a laser radar, and compare the point cloud signal at the location with the point cloud map to generate a radar positioning signal; fuse the GPS calibration signal and the radar signal to generate a fused positioning signal; determine the position of the belt conveyor cleaning robot in the point cloud map according to the fused positioning signal.

[0084] In one embodiment, the material identification and cleaning module 304 is specifically used to obtain image information of the current perspective through an image acquisition unit, and input the image information of the current perspective into a trained material identification model; determine whether the result output by the material identification model is the material to be cleaned; if the result output by the material identification model is the material to be cleaned, control the belt conveyor cleaning robot to push the material to be cleaned forward.

[0085] In one embodiment, the material recognition and cleaning module 304 is further used to obtain an image set of the material to be cleaned through an image acquisition unit; input the image set of the material to be cleaned into a preset image recognition model for training, and generate a material recognition model.

[0086] In one embodiment, the material identification and cleaning module 304 is also used to mark obstacle points in the point cloud map according to the positions of obstacles in the area to be cleaned; according to the point cloud map, the distance between the belt conveyor cleaning robot and all obstacle points is calculated, and the minimum distance between all obstacle points is determined; the calculated minimum distance value is compared with a preset threshold; if the minimum distance value is less than the preset threshold, the belt conveyor cleaning robot is controlled to stop moving.

[0087] In one embodiment, the belt conveyor cleaning robot navigation device is also used to respond to charging instructions, locate and advance to the location of the charging pile for charging.

[0088] In one embodiment, in the position determination module 303, the belt conveyor cleaning robot moves forward in a crawler manner.

[0089] The belt conveyor cleaning robot navigation device provided in the embodiment of the present application can be applied to the belt conveyor cleaning robot navigation method provided in the above embodiment. Relevant details refer to the above method embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0090] It should be noted that: the belt conveyor cleaning robot navigation device provided in the embodiment of the present application only uses the division of the above-mentioned functional modules / functional units as an example when performing belt conveyor cleaning robot navigation. In actual applications, the above-mentioned functions can be assigned to different functional modules / functional units as needed, that is, the internal structure of the belt conveyor cleaning robot navigation device is divided into different functional modules / functional units to complete all or part of the functions described above. In addition, the implementation method of the belt conveyor cleaning robot navigation method provided in the above method embodiment and the implementation method of the belt conveyor cleaning robot navigation device provided in this embodiment belong to the same concept. The specific implementation process of the belt conveyor cleaning robot navigation device provided in this embodiment is detailed in the above method embodiment, which will not be repeated here.

[0091] The embodiment of the present application also discloses a computer device.

[0092] Specifically, if Figure 4 As shown, the computer device can be a computer device such as a desktop computer, a laptop computer, a PDA, and a cloud server. The computer device may include, but is not limited to, a processor and a memory. The processor and the memory may be connected via a bus or otherwise. The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, graphics processors (GPU), embedded neural network processors (NPU) or other dedicated deep learning coprocessors, discrete gates or transistor logic devices, discrete hardware components and other chips, or a combination of the above-mentioned various chips.

[0093] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the methods in the above-mentioned embodiments of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the method in the above-mentioned method implementation is realized. The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0094] The embodiment of the present application also discloses a computer-readable storage medium.

[0095] Specifically, a computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in the above-mentioned method implementation is implemented. Those skilled in the art will understand that the implementation of all or part of the process in the above-mentioned implementation method of the present application can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and the program, when executed, may include the process of the implementation of the above-mentioned methods. Among them, the storage medium may be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memory.

[0096] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

Claims

1. A belt conveyor cleaning robot navigation method, characterized in that: The method is applied to a belt conveyor cleaning robot control system, wherein the belt conveyor cleaning robot control system includes a laser radar and a GPS receiver, and the method includes: Scanning the area to be cleaned by the laser radar and generating a point cloud map of the area to be cleaned; Controlling the conveyor belt cleaning robot to run according to the preset points to be cleaned, and determining the running path of the conveyor belt cleaning robot in the area to be cleaned in the point cloud map; Determine the position of the belt conveyor cleaning robot in the point cloud map by using the GPS receiver and the laser radar, and control the belt conveyor cleaning robot to move forward along the running path; Identify and clean the material to be cleaned, where the material to be cleaned is the material that needs to be cleaned on the lower side of the belt conveyor.

2. The method according to claim 1, characterized in that: Determining the position of the belt conveyor cleaning robot in the point cloud map by using the GPS receiver and the laser radar includes: Utilizing the GPS receiver to receive the GPS positioning signal of the belt conveyor cleaning robot; Communicate with a reference receiver at a preset reference position, calibrate the GPS positioning signal of the belt conveyor cleaning robot, and generate a GPS calibration signal; Scanning the point cloud signal of the location of the belt conveyor cleaning robot by the laser radar, and comparing the point cloud signal of the location with the point cloud map to generate a radar positioning signal; Fusing the GPS calibration signal and the radar signal to generate a fused positioning signal; The position of the belt conveyor cleaning robot in the point cloud map is determined according to the fused positioning signal.

3. The method according to claim 1, characterized in that: The belt conveyor cleaning robot control system further includes an image acquisition unit, and the identifying and cleaning of the material to be cleaned includes: Acquire image information of the current viewing angle through the image acquisition unit, and input the image information of the current viewing angle into the trained material recognition model; Determining whether the result output by the material identification model is the material to be cleaned; If the result output by the material identification model is the material to be cleaned, the belt conveyor cleaning robot is controlled to push the material to be cleaned forward.

4. The method according to claim 3, characterized in that: The training method of the material recognition model includes: Acquire an image set of the material to be cleaned by the image acquisition unit; The image set of the material to be cleaned is input into a preset image recognition model for training, and the material recognition model is generated.

5. The method according to claim 1, characterized in that: Before identifying and cleaning the material to be cleaned, the method further includes: According to the position of the obstacle in the area to be cleaned, marking the obstacle point in the point cloud map; According to the point cloud map, the distance between the belt conveyor cleaning robot and all obstacle points is calculated, and the minimum distance between the belt conveyor cleaning robot and all obstacle points is determined; Comparing the calculated minimum distance value with a preset threshold; If the minimum distance is less than a preset threshold, the belt conveyor cleaning robot is controlled to stop moving forward.

6. The method according to claim 1, characterized in that: The method further comprises: In response to the charging instruction, locate and proceed to the location of the charging pile for charging.

7. The method according to claim 1, characterized in that: The belt conveyor cleaning robot moves forward in a crawler manner.

8. A belt conveyor cleaning robot navigation device, characterized in that: The device is applied to a belt conveyor cleaning robot control system, the belt conveyor cleaning robot control system includes a laser radar and a GPS receiver, and the device includes: A point cloud map generation module (301), used for scanning the area to be cleaned by using the laser radar, and generating a point cloud map of the area to be cleaned; An operation path determination module (302) is used to control the belt conveyor cleaning robot to operate according to a preset point to be cleaned, and determine the operation path of the belt conveyor cleaning robot in the area to be cleaned in the point cloud map; A position determination module (303), used for determining the position of the belt conveyor cleaning robot in the point cloud map using the GPS receiver and the laser radar, and controlling the belt conveyor cleaning robot to move forward along the running path; The material identification and cleaning module (304) is used to identify and clean the material to be cleaned, wherein the material to be cleaned is the material that needs to be cleaned on the lower side of the belt conveyor.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images