Train carriage excess material cleaning method, computer program product and system

Abstract

The invention provides a train carriage excess material cleaning method, a computer program product and a system. The method comprises the following steps: collecting point cloud data of a carriage by using a visual module; according to the point cloud data, planning a movement path of the cleaning robot for cleaning the carriage; the cleaning robot is started and precisely cleans the carriage according to the movement path; the contact force data between the cleaning robot and the carriage are obtained in real time, whether the movement path has deviation or not is judged according to the contact force data, if deviation exists, the path deviation is corrected according to the contact force data, and the cleaning precision is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent robots, and particularly to a method for cleaning residual materials in a train carriage, a computer program product, and a system. Background Art

[0002] The long-distance transportation of bulk materials such as coal and ore mainly relies on railway transportation. After the train carriage completes unloading, there are often still some residual materials inside, which need to be cleaned in a timely manner. The traditional manual cleaning method requires workers to climb into the carriage for operation, which not only has a large labor intensity and low efficiency, but also has safety hazards such as climbing and falling, and dust inhalation.

[0003] There is a current solution that uses a cleaning robot to replace manual labor. However, such robots usually rely on a preset movement path for cleaning operations, which requires extremely high accuracy in the docking position of the carriage. During the actual operation process, due to factors such as track settlement and vehicle inertia, the docking position of the train carriage often deviates, which causes the robot to operate according to the preset movement path and it is difficult to accurately cover the cleaning area, resulting in cleaning blind spots and affecting the cleaning effect. In addition, the position deviation may also cause the robot to idle or repeat cleaning, reducing the cleaning efficiency. Summary of the Invention

[0004] The technical problem to be solved by the present invention is how to improve the accuracy of the cleaning robot in cleaning the residual materials in the carriage.

[0005] To solve the above technical problem, the present invention provides a method for cleaning residual materials in a train carriage, including the following steps:

[0006] S1. Using a vision module to collect the point cloud data of the carriage;

[0007] S2. Planning the movement path of the cleaning robot to clean the carriage according to the point cloud data;

[0008] S3. Starting the cleaning robot and cleaning the carriage according to the movement path;

[0009] S4. Real-time obtaining the contact force data between the cleaning robot and the carriage, and judging whether there is a deviation in the movement path based on this. If there is a deviation, correcting the path deviation according to the contact force data.

[0010] Further, in step S1, an initial image of the remaining materials in the carriage is also obtained by using a vision module; step S5 which is executed after the cleaning is completed is also included. An image of the remaining materials in the carriage after cleaning is obtained by using the vision module, and the remaining material residue rate after cleaning is analyzed according to the initial image of the remaining materials and the image of the remaining materials after cleaning. If the remaining material residue rate is greater than a preset value, the movement path for the cleaning robot to clean the carriage is re-planned according to the image of the remaining materials after cleaning, and the cleaning robot is made to clean the carriage according to the re-planned movement path.

[0011] Further, step S6 which is executed after the cleaning is completed is also included. The cleaning robot is made to discharge the remaining materials swept down into a remaining material collection bucket.

[0012] Further, in step S2, specifically, the point cloud data is imported into offline programming software, and the movement path for the cleaning robot to clean the carriage is planned through the offline programming software.

[0013] Further, in step S4, specifically, a force control sensor is used to detect and obtain the contact force data between the cleaning robot and the carriage.

[0014] Further, specifically for determining whether there is a deviation in the movement path: if the contact force data detected by each force control sensor on the cleaning robot is not greater than a safety threshold, it is determined that there is no deviation in the movement path; if the contact force data detected by a force control sensor in a certain direction of the cleaning robot is greater than the safety threshold, it is determined that the movement path deviates in that direction.

[0015] Further, the safety threshold of the contact force data is specifically Fmax = k * m_tool * a_max, where k is a safety factor, m_tool is the mass of the cleaning device of the cleaning robot, and a_max is the maximum acceleration of the robotic arm of the cleaning robot.

[0016] The present invention also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0017] The present invention also provides a system for cleaning remaining materials in a train carriage, including a cleaning robot, a vision module, and a controller. The controller is respectively connected to the cleaning robot and the vision module. The controller includes a memory and a processor connected to each other, and the above computer program product is stored in the memory.

[0018] Further, it also includes a gantry truss, a carriage track and a waste material collection bucket. A moving crossbeam driven by a motor and a linear module is provided on the gantry truss, and the controller is connected to the motor. The carriage track and the waste material collection bucket are arranged inside the gantry truss, below the moving crossbeam. The carriage track is arranged along the moving direction of the moving crossbeam. The cleaning robot and the vision module are installed on the moving crossbeam.

[0019] The present invention has the following beneficial effects: When cleaning the carriage, the vision module is used to collect the point cloud data of the carriage, and the motion path for the cleaning robot to clean the carriage is generated according to the point cloud data. Then, the cleaning robot can accurately clean the carriage according to the motion path. During the cleaning process, the contact force data between the cleaning robot and the carriage is obtained in real time. If there is a deviation in the motion path, the path deviation is corrected according to the contact force data, further improving the cleaning accuracy. Description of the Drawings

[0020] Figure 1 is a schematic structural diagram of a train carriage waste material cleaning system.

[0021] Figure 2 is a schematic flow diagram of a train carriage waste material cleaning method.

[0022] Description of the reference numerals: 1, gantry truss; 2, carriage track; 3, cleaning robot; 4, vision module; 5, waste material collection bucket; 6, outlet end of the adsorption pipeline; 11, moving crossbeam. Detailed Embodiments

[0023] The following further elaborates on the present invention in detail in combination with the specific embodiments.

[0024] This embodiment provides a train carriage waste material cleaning system, as Figure 1 shown, including a gantry truss 1, a carriage track 2, a cleaning robot 3, a vision module 4, a waste material collection bucket 5 and a controller (not shown in the figure). A moving crossbeam 11 driven by a motor and a linear module is provided on the gantry truss 1, and the controller is connected to the motor. The carriage track 2 and the waste material collection bucket 5 are arranged inside the gantry truss 1, below the moving crossbeam 11. The carriage track 2 is arranged along the moving direction of the moving crossbeam 11. The cleaning robot 3 and the vision module 4 are installed on the moving crossbeam 11, and the controller is respectively connected to the cleaning robot 3 and the vision module 4.

[0025] There are two cleaning robots 3, and each cleaning robot 3 includes a six-axis robotic arm, a cleaning device, and a suction device. Specifically, the cleaning robot 3 is installed on the moving crossbeam 11 of the gantry truss 1 through the six-axis robotic arm. The cleaning device includes a side wall roller brush and a bottom sweeping brush installed at the end of the six-axis robotic arm, and the suction device includes a vacuum pump and a suction pipeline installed at the end of the six-axis robotic arm. During the process of the cleaning robot 3 following the moving crossbeam 11, the outlet end 6 of the suction pipeline will pass above the surplus material collection bucket 5. A force control sensor connected to the controller is also provided at the installation position of the cleaning device of the cleaning robot 3. The controller can detect and obtain the contact force data between the cleaning robot and the carriage through the force control sensor.

[0026] The vision module 4 is a 3D vision sensor, such as a lidar, a structured light camera, a binocular stereo vision camera, etc. It is an intelligent sensing device that can obtain three-dimensional spatial information of an object (such as depth, shape, size, etc.) and generate point cloud data, and is widely used in fields such as industrial automation, robot navigation, autonomous driving, medical imaging, and augmented reality (AR).

[0027] The controller includes a memory and a processor connected to each other. A computer program product is stored in the memory, which includes a computer program. When the computer program is executed by the processor, it implements the Figure 2 shown method for cleaning surplus materials in a train carriage, specifically including the following steps S1, S2, S3, S4, S5, and S6.

[0028] S1. Use the vision module 4 to collect the point cloud data of the carriage.

[0029] When cleaning the train carriage, the staff first initialize the system. Then the controller commands the moving crossbeam 11 to move the cleaning robot 3 and the vision module 4 to the carriage entrance. Then the staff drive the train carriage into the area below the moving crossbeam 11 along the carriage track 2 from the entrance. During the driving process, the controller commands the vision module 4 to start collecting the point cloud data of the carriage. After the carriage is completely driven in, the vision module 4 also completes the collection of the point cloud data of the carriage and reconstructs the three-dimensional model of the carriage based on this. During this process, the controller also uses the vision module 4 to obtain the initial image of the surplus materials in the carriage.

[0030] S2. Plan the movement path of the cleaning robot 3 to clean the carriage according to the point cloud data.

[0031] After the controller uses the vision module 4 to collect the point cloud data of the carriage, it imports the point cloud data into offline programming software (such as KUKA.Sim, Meiqin Simulation, MELSOFT Gemini). The offline programming software plans the movement path of the cleaning robot 3 to clean the carriage according to the point cloud data.

[0032] S3. Start the cleaning robot 3 and clean the carriage according to the movement path.

[0033] After the motion path planning is completed, the controller obtains the motion path from the offline programming software, and then starts the cleaning robot 3, and its cleaning device and adsorption device start working. Then the controller controls the movement of the moving beam 11, and controls the movement of the robotic arm of the cleaning robot 3 during the movement, so that the cleaning robot 3 moves according to the motion path to clean the carriage. The cleaning robot 3 specifically cleans the residual materials in the carriage through the cleaning device, and absorbs the cleaned residual materials through the adsorption device, so as to achieve precise cleaning of the carriage.

[0034] S4. Acquire the contact force data between the cleaning robot 3 and the vehicle compartment in real time, and judge whether there is a deviation in the motion path based on it. If there is a deviation, correct the path deviation according to the contact force data.

[0035] During the process of cleaning the carriage by the cleaning robot 3, the controller obtains the contact force data between the cleaning robot 3 and the carriage in real time through the force control sensor on the cleaning robot 3, and judges whether there is any deviation in the movement path of the cleaning robot 3 for cleaning the carriage. Specifically, if the contact force data detected by each force control sensor on the cleaning robot 3 is not greater than the safety threshold, it is judged that there is no deviation in the movement path of the cleaning robot 3 for cleaning the carriage; if the contact force data detected by the force control sensor in a certain direction of the cleaning robot 3 is greater than the safety threshold, it is judged that the movement path of the cleaning robot 3 for cleaning the carriage is biased in that direction. Therefore, the controller corrects the path deviation according to the larger contact force data, so that the movement path of the cleaning robot 3 for cleaning the carriage deviates from the direction of the force control sensor with the larger contact force data, thereby further improving the cleaning accuracy.

[0036] In this embodiment, the safety threshold of the contact force data is specifically Fmax=k*m_tool*a_max, where k is the safety factor, which is 1.5, m_tool is the mass of the cleaning device of the cleaning robot 3, and a_max is the maximum acceleration of the robotic arm.

[0037] S5. Use the visual module 4 to obtain the residual image of the residual material in the car, and analyze the residual material residual rate after cleaning based on the initial residual material image and the residual material residual image. If the residual material residual rate is greater than the preset value, the movement path of the cleaning robot 3 for cleaning the car is re-planned according to the residual material residual image, and the cleaning robot 3 is ordered to clean the car according to the re-planned movement path.

[0038] After the cleaning is completed, the controller uses the vision module 4 to obtain the residual image of the remaining materials in the carriage, and then compares the initial image of the remaining materials with the residual image of the remaining materials, so as to analyze the residual rate of the remaining materials after cleaning. The residual rate of the remaining materials is specifically the ratio of the amount of the remaining materials in the residual image of the remaining materials to the amount of the remaining materials in the initial image of the remaining materials. If the residual rate of the remaining materials is greater than the preset value (for example, 5%), it means that the cleaning is not clean. Therefore, the controller analyzes the residual position of the remaining materials according to the residual image of the remaining materials, re-plans the movement path of the cleaning robot 3 to clean the carriage accordingly, and commands the cleaning robot 3 to clean the carriage according to the re-planned movement path. If the residual rate of the remaining materials is not greater than the preset value, it means that the cleaning is clean, so there is no need to clean the carriage again.

[0039] S6. Command the cleaning robot 3 to discharge the remaining materials swept down into the remaining material collection bucket 5.

[0040] After the cleaning is completed and it is ensured that the residual rate of the remaining materials is not greater than the preset value, the controller controls the moving crossbeam 11 to move so that the outlet end 6 of the adsorption pipeline of the adsorption device of the cleaning robot 3 is located above the remaining material collection bucket 5, and then controls the adsorption device to discharge the remaining materials swept down from the outlet end 6 of the adsorption pipeline into the remaining material collection bucket 5, which is convenient for collecting and transporting away the remaining materials swept down.

[0041] As described above, it is only the implementation mode of the present invention, and does not limit the scope of patent protection. Those skilled in the art make non-substantive changes or substitutions on the basis of the present invention, and still fall within the scope of patent protection.

Claims

1. A method for cleaning the remaining materials in a train carriage, characterized in that It includes the following steps: S1. Use the vision module to collect the point cloud data of the carriage; S2. Plan the movement path for the cleaning robot to clean the carriage according to the point cloud data; S3. Start the cleaning robot and let it clean the carriage according to the movement path; S4. Real-time obtain the contact force data between the cleaning robot and the carriage, and judge whether there is a deviation in the movement path based on this. If there is a deviation, correct the path deviation according to the contact force data.

2. The method for cleaning the remaining materials in a train carriage according to claim 1, characterized in that, In step S1, the vision module is also used to obtain the initial image of the remaining materials in the carriage; it also includes step S5 executed after the cleaning is completed. Use the vision module to obtain the remaining material residual image in the carriage, and analyze the remaining material residual rate after cleaning according to the initial image of the remaining materials and the remaining material residual image. If the remaining material residual rate is greater than the preset value, re-plan the movement path for the cleaning robot to clean the carriage according to the remaining material residual image, and let the cleaning robot clean the carriage according to the re-planned movement path.

3. The method for cleaning the remaining materials in a train carriage according to claim 1, characterized in that, It also includes step S6 executed after the cleaning is completed. Let the cleaning robot discharge the remaining materials cleaned down into the remaining material collection bucket.

4. The method for cleaning the remaining materials in a train carriage according to claim 1, characterized in that, In step S2, specifically import the point cloud data into the offline programming software, and plan the movement path for the cleaning robot to clean the carriage through the offline programming software.

5. The method for cleaning the remaining materials in a train carriage according to claim 1, characterized in that, In step S4, specifically use the force control sensor to detect and obtain the contact force data between the cleaning robot and the carriage.

6. The method for cleaning the remaining materials in a train carriage according to claim 5, characterized in that, Specifically judge whether there is a deviation in the movement path: If the contact force data detected by each force control sensor on the cleaning robot is not greater than the safety threshold, it is judged that the movement path has no deviation; if the contact force data detected by the force control sensor in a certain direction of the cleaning robot is greater than the safety threshold, it is judged that the movement path deviates in that direction.

7. The method for cleaning the remaining materials in a train carriage according to claim 1, characterized in that, The safety threshold of the contact force data is specifically Fmax = k * m_tool * a_max, where k is the safety factor, m_tool is the mass of the cleaning device of the cleaning robot, and a_max is the maximum acceleration of the robotic arm of the cleaning robot.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 7.

9. A cleaning system for the leftover materials in a train carriage, characterized in that, It includes a cleaning robot, a vision module and a controller. The controller is respectively connected to the cleaning robot and the vision module. The controller includes a memory and a processor connected to each other, and the computer program product according to claim 8 is stored in the memory.

10. The train carriage waste cleaning system according to claim 9, characterized in that, It also includes a gantry truss, a carriage track and a remaining material collection bucket. A moving crossbeam driven by a motor and a linear module is provided on the gantry truss. The controller is connected to the motor. The carriage track and the remaining material collection bucket are arranged inside the gantry truss, below the moving crossbeam. The carriage track is arranged along the moving direction of the moving crossbeam. The cleaning robot and the vision module are installed on the moving crossbeam.

Images