Automatic operation method, device and equipment for underground transfer robot and medium
By obtaining multi-sensor data of the underground robot to draw and update the point cloud map in the well, combining multiple positioning methods, the problem of robot operation path planning under changes in the underground environment is solved, and the efficiency and safety of underground handling are improved.
Patent Information
- Application Number
- CN202410918546.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-08
AI Technical Summary
Existing underground handling robots cannot plan their operating paths in real time based on changes in the well environment, resulting in inefficiency and safety hazards.
By obtaining multiple sensor data of the robot, drawing a point cloud map in the well, and updating the map in real time according to environmental changes, combining various methods to obtain the robot's location information, drawing the job path, and finally controlling the robot to complete the handling operation.
Real-time planning of robot operation paths under changes in the well environment is realized, which improves handling efficiency and safety, and reduces the risk of positioning loss.
Smart Images

Figure CN118915720A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of underground robot control, and in particular to an automatic operation method, device, equipment and medium for an underground transport robot. Background Art
[0002] When working in a mine, the handling of various materials is arduous and dangerous due to the complexity and uncertainty of the underground environment. Traditional manual handling methods are not only inefficient, but also pose great safety risks. In recent years, although some underground handling robots have emerged, existing handling robots cannot plan the operation path in real time according to changes in the underground environment. Summary of the invention
[0003] The present application aims to at least solve the technical problems existing in the prior art. To this end, the present application proposes an automatic operation method, device, equipment and medium for an underground handling robot, which can plan the robot's operation path in real time according to the environment in the well.
[0004] A first aspect of an embodiment of the present application provides an automatic operation method of an underground transport robot, the method comprising:
[0005] Acquire operation data of the robot; wherein the operation data includes a plurality of sensor data of the robot;
[0006] Draw a point cloud map in the well according to the operation data;
[0007] Obtaining position information of the robot according to the operation data;
[0008] Drawing a working path of the robot in the point cloud map according to the position information;
[0009] According to the operation path, the robot is controlled to complete the handling operation.
[0010] The embodiment of the present application provides an automatic operation method for an underground handling robot. Different from the prior art, the method obtains the operation data of the robot, draws a point cloud map of the well according to the operation data, and can update the map of the well in real time according to changes in the environment in the well. Based on the operation data, the position information of the robot is obtained through a variety of methods to ensure that the robot can be positioned in different situations. According to the actual position information of the robot, the operation path of the robot is drawn in the point cloud map. The operation path of the robot can be planned in real time when the environment in the well changes. Finally, the robot is controlled according to the operation path to complete the handling operation.
[0011] In some embodiments of the present application, after drawing the well point cloud map according to the operation data, the method further includes:
[0012] Obtaining an initial position and posture of the robot;
[0013] Based on the initial pose, the point cloud map is expanded to obtain a new map;
[0014] Based on the initial pose, a transformation matrix is obtained;
[0015] The new map is integrated into the point cloud map through the transformation matrix to update the point cloud map.
[0016] In some embodiments of the present application, the plurality of sensor data includes lidar data, inertial measurement unit data, and odometer data;
[0017] The obtaining the position information of the robot according to the operation data comprises:
[0018] fusing the inertial measurement unit data and the odometer data through an unscented Kalman filter to obtain a first predicted position and posture of the robot;
[0019] Based on the laser radar data, obtaining a real-time point cloud of the robot;
[0020] Based on the first predicted posture and the real-time point cloud, the position information of the robot is obtained.
[0021] In some embodiments of the present application, obtaining the position information of the robot according to the operation data includes:
[0022] Based on the operation data, obtaining the historical position and posture of the robot;
[0023] Based on the historical posture, obtaining a second predicted posture of the robot;
[0024] The second predicted posture is input into the point cloud map to obtain the position information of the robot.
[0025] In some embodiments of the present application, the plurality of sensor data includes lidar data and historical operation trajectories;
[0026] The obtaining the position information of the robot according to the operation data comprises:
[0027] Based on the historical running trajectory, generating a global positioning point of the robot;
[0028] Based on the laser radar data, the position information of the robot is searched in the global positioning point.
[0029] In some embodiments of the present application, the operation path includes a global operation path;
[0030] Drawing the robot's operating path in the point cloud map according to the position information includes:
[0031] Based on the point cloud map, drawing the lane line for the robot to travel;
[0032] According to the location information and the preset destination, obtain a corresponding lane line set;
[0033] The center lines of the lane lines in the lane line set are connected to obtain a global operation path of the robot.
[0034] In some embodiments of the present application, the plurality of sensor data includes lidar data and well obstacle data;
[0035] The operation path includes a local operation path;
[0036] Drawing the robot's operating path in the point cloud map according to the position information includes:
[0037] Obtaining a real-time point cloud of the robot according to the laser radar data;
[0038] Filter out non-ground point clouds from the real-time point clouds;
[0039] fusing the well obstacle data into the non-ground point cloud;
[0040] Projecting the fused non-ground point cloud into a two-dimensional space to obtain a true value map;
[0041] According to the truth map, a local operation path of the robot is drawn in the point cloud map.
[0042] A second aspect of an embodiment of the present invention provides an automatic operation device of an underground transport robot, the device comprising:
[0043] An acquisition module, used to acquire operation data of the robot; wherein the operation data includes a plurality of sensor data of the robot;
[0044] A mapping module, used for drawing a point cloud map in the well according to the operation data;
[0045] A positioning module, used to obtain the position information of the robot according to the operation data;
[0046] A planning module, used for drawing a working path of the robot in the point cloud map according to the position information;
[0047] The control module is used to control the robot to complete the handling operation according to the operation path.
[0048] The third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the above-mentioned automatic operation method of the underground transport robot.
[0049] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned automatic operation method of an underground transport robot.
[0050] It can be understood that the beneficial effects of the second to fourth aspects compared with the related art are the same as the beneficial effects of the first aspect compared with the related art. Please refer to the relevant description in the first aspect, and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0052] Figure 1 It is a flowchart of an implementation method of the automatic operation method of the underground handling robot provided by the present application;
[0053] Figure 2 It is a structural schematic diagram of an implementation scheme of an automatic operation device of a downhole transport robot provided by the present application;
[0054] Figure 3 is a schematic structural diagram of an implementation scheme of an electronic device provided by the present application; DETAILED DESCRIPTION
[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0056] In underground mine operations, the handling of various materials is arduous and dangerous. Traditional manual handling methods are not only inefficient, but also pose great safety risks. First, the efficiency of manual handling is greatly limited, and miners need to engage in physical labor for a long time, which not only reduces the overall work efficiency, but also may cause physical injuries to workers. Secondly, the underground environment of mines is complex and there are many safety hazards, such as mine collapse, gas leakage, high temperature and high humidity, etc. Manual handling in this case poses great safety risks.
[0057] In recent years, with the development of science and technology, some underground handling robots have emerged; the existing underground handling robots have a certain degree of autonomous operation capabilities, which can reduce the labor intensity of miners to a certain extent; however, due to the complex and changeable underground environment, such as undulating terrain, dim light, and a wide variety of materials, the existing underground handling robots' autonomous operation capabilities are still limited and cannot fully meet the actual production needs.
[0058] For this purpose, refer to Figure 1 The embodiment of the present application provides an automatic operation method of an underground handling robot. The method is applied to a controller. The controller may be a server, an electronic device, or a mobile terminal, etc., which is not specifically limited here. The method includes the following steps S100 to S500:
[0059] Step S100: Acquire operation data of the robot; wherein the operation data includes a plurality of sensor data of the robot.
[0060] In this step, the data of multiple sensors equipped by the robot are used as operating data. The multiple sensors equipped on the handling robot include but are not limited to inertial measurement units, lidars, visual sensors, infrared sensors, ultrasonic sensors, accelerometers, gyroscopes, etc.; various sensors are used to collect information about the robot's surroundings, such as distance, speed, direction, temperature, humidity, etc., and the robot's real-time position, speed, posture and changes in the surrounding environment can be obtained.
[0061] Step S200: Draw a point cloud map of the well according to the operation data.
[0062] In this step, the acquired lidar data and inertial measurement unit data are preprocessed to ensure that all sensor data are in the same coordinate system. The preprocessed data are point cloud fused, and a point cloud map of the well is constructed based on the fused point cloud map.
[0063] Step S300: Obtain the position information of the robot according to the operation data.
[0064] In this step, multiple sensor data are acquired and fused to obtain the position information of the robot. In the event that some sensors fail, multiple methods are provided to obtain the position information of the robot. The specific methods will be described in detail in the subsequent implementation methods and are not specifically limited here.
[0065] Step S400: Draw the robot's operating path in the point cloud map according to the position information.
[0066] In this step, the operation path includes a global operation path and a local operation path, and different path planning methods are provided for different scenarios in the mine. The specific method will be described in detail in the subsequent implementation method and is not specifically limited here.
[0067] Step S500: Control the robot to complete the handling operation according to the operation path.
[0068] In this step, according to the operation path, the robot is controlled to navigate to the destination point. After reaching the destination point, the visual sensor at the end of the robotic arm is used to accurately identify the relative position and size information of the material, and then the robotic arm is controlled to grab the material. During the transportation process, the robot uses sensors to perceive changes in the surrounding environment in real time. If there are obstacles or abnormal conditions, the path and action are adjusted in time to ensure operation safety.
[0069] Different from the prior art, the implementation method of the present application obtains the operating data of the robot, draws a point cloud map of the well based on the operating data, and can update the map of the well in real time according to changes in the environment inside the well. Based on the operating data, the position information of the robot is obtained through a variety of methods to ensure that the robot can be positioned in different situations. According to the actual position information of the robot, the robot's working path is drawn in the point cloud map. The robot's working path can be planned in real time when the environment inside the well changes. Finally, the robot is controlled according to the working path to complete the handling operation.
[0070] After drawing the well point cloud map according to the operation data in step S200, the method further includes the following steps S201 to S204:
[0071] Step S201: Obtain the initial position and posture of the robot.
[0072] Step S202: Based on the initial pose, the point cloud map is expanded to obtain a new map.
[0073] Step S203: Obtain a transformation matrix based on the initial posture.
[0074] Step S204: Fusing the new map into the point cloud map through the transformation matrix to update the point cloud map.
[0075] In this embodiment, since the underground mine scenes are complex and changeable, the map needs to be updated and expanded regularly. However, the time cost of rebuilding the map is too high. Therefore, in response to the problem of updating the local map of the current working environment, the implementation method of the present application updates the map in real time while the robot is performing the transportation operation, reducing the time cost of updating the map to 0; and in response to the problem of expanding the local map of the current working environment, the implementation method of the present application incrementally expands the new map based on the original map, thereby avoiding a large amount of time cost incurred by rebuilding the map.
[0076] In this embodiment, when the robot starts to move and collect new sensor data, a new point cloud dataset is generated, which contains information about the environment around the robot's current position. Based on the robot's current initial position, the new point cloud dataset is added to the existing point cloud map, thereby expanding the point cloud map to obtain a new map.
[0077] In some embodiments, a transformation matrix is obtained based on the initial pose, and the newly collected point cloud data is aligned with the point cloud map to ensure that the new point cloud can be accurately placed at the corresponding position of the point cloud map; then, based on the transformation matrix, the new map is integrated into the point cloud map to update the point cloud map.
[0078] In some embodiments of the present application, the multiple sensor data of the robot include laser radar data, inertial measurement unit data and odometer data. In step S300, the position information of the robot is obtained according to the operation data, including steps S310 to S330:
[0079] Step S310: fusing the inertial measurement unit data and the odometer data through unscented Kalman filtering to obtain a first predicted position and posture of the robot.
[0080] Step S320: Acquire a real-time point cloud of the robot based on the laser radar data.
[0081] Step S330: Obtaining position information of the robot based on the first predicted posture and the real-time point cloud.
[0082] In this embodiment, a multi-sensor fusion positioning method is adopted. The inertial measurement unit data and the odometer data are fused through the unscented Kalman filter to obtain the first predicted posture of the robot, and the real-time point cloud of the collector is obtained through the lidar data; based on the first predicted posture and the real-time point cloud, the robot is positioned through the NDT (Normal Distributions Transform point cloud registration algorithm) to obtain the robot's position information, and when using the NDT algorithm, the calculation process is accelerated by the GPU (Graphics Processing Unit acceleration), which greatly improves the calculation efficiency, and can still provide stable and accurate equipment positioning information when the underground mine environment characteristics are degraded.
[0083] In some embodiments of the present application, obtaining the position information of the robot according to the operation data in step S300 includes steps S340 to S360:
[0084] Step S340: Obtain the historical position and posture of the robot based on the operation data.
[0085] Step S350: Based on the historical posture, obtain a second predicted posture of the robot.
[0086] Step S360: input the second predicted posture into the point cloud map to obtain the position information of the robot.
[0087] In this embodiment, when some sensors of the robot fail and the robot cannot be positioned by the multi-sensor fusion positioning method of steps S310 to S330, the coordinates, direction and other information of the robot at different points contained in the robot's past operation data are used to calculate the robot's historical posture, and the robot's posture is predicted by EKF (Extended Kalman Filter) based on the robot's historical posture to obtain a second predicted posture; the second predicted posture is input into the point cloud map, so that the robot can be quickly positioned to obtain the robot's position information.
[0088] In some embodiments of the present application, the multiple sensor data of the robot include laser radar data and historical operation trajectories. In step S300, the position information of the robot is obtained according to the operation data, including steps S370 to S380:
[0089] Step S370: Generate a global positioning point of the robot based on the historical running trajectory.
[0090] Step S380: Based on the laser radar data, search for the position information of the robot in the global positioning point.
[0091] In this embodiment, a series of global positioning points of the robot are generated by acquiring historical running trajectories; global positioning points are possible positions of the robot in the global coordinate system and can be regarded as key points on the robot's past movement path. Through the high-precision distance and angle information provided by the laser radar data, a point cloud map of the surrounding environment is constructed by emitting laser pulses and receiving reflected signals, and the point cloud obtained by the current laser radar scan is matched with the global positioning point through a variety of algorithms (such as the iterative closest point algorithm), thereby determining the exact position of the robot in the global positioning point.
[0092] In other embodiments, if the robot moves to a non-driving area after being powered off or the above method fails on the robot, the initial position of the robot can be manually set in the point cloud map, and the error with the actual position of the robot can be within 5m, and auxiliary positioning can be performed to obtain the robot's position information.
[0093] This implementation method firstly uses a multi-sensor fusion positioning algorithm to accurately position the robot, and can still provide accurate and stable robot positioning information even when the underground mining environment characteristics are degraded; secondly, when the robot loses its positioning, three repositioning methods are provided. The first is automatic repositioning based on historical posture, the second is to search for global positioning points to position the robot, and the last is manual assisted positioning. A variety of different positioning methods can ensure that the robot's position information is determined in time to position the robot.
[0094] In some embodiments of the present application, the operation path includes a global operation path. Drawing the operation path of the robot in the point cloud map according to the position information in step S400 includes the following steps S410 to S430:
[0095] Step S410: based on the point cloud map, draw the lane line for the robot to travel.
[0096] Step S420: Obtain a corresponding lane line set according to the location information and the preset destination.
[0097] Step S430: Connect the center lines of the lane lines in the lane line set to obtain a global operation path of the robot.
[0098] In this embodiment, features representing lane boundaries in the point cloud map are identified, corresponding lane lines are drawn based on the identified lane boundary features, all possible lane lines leading to the destination are found based on the robot's current position information and a preset work destination, a lane line collection is formed, the center lines of each lane line in the lane line collection are connected, and the global work path of the robot is obtained after curve smoothing.
[0099] In this embodiment, the global path can be automatically generated by simply setting different destinations, and the destination point can be flexibly changed, which is suitable for scenarios where the robot's transport position is not fixed.
[0100] In one embodiment, a remote-controlled robot walks along an operating route set by a technician. When the robot walks along the preset route, the sensors equipped on the robot continuously collect environmental data to synchronously complete the construction of a point cloud map. At the same time, the robot's walking trajectory is recorded, and the recorded walking trajectory is the global path of the robot's operation. This can achieve a simple and fast effect, with a safe and reliable path and low time cost.
[0101] In other embodiments, a technician manually draws a global path for the robot's operation on a point cloud map, which is simple and fast, and can quickly edit the path according to different destination points.
[0102] In some embodiments of the present application, the multi-sensor data of the robot includes laser radar data and well obstacle data, the operation path includes a local operation path, and the operation path of the robot is drawn in the point cloud map according to the position information in step S400, including the following steps S440 to S480:
[0103] Step S440: Obtain a real-time point cloud of the robot according to the laser radar data.
[0104] Step S450: Filter out non-ground point clouds from the real-time point clouds.
[0105] Step S460: Fusing the in-well obstacle data into the non-ground point cloud.
[0106] Step S470: project the fused non-ground point cloud into a two-dimensional space to obtain a true value map.
[0107] Step S480: Draw the local operation path of the robot in the point cloud map according to the truth map.
[0108] In this embodiment, the real-time point cloud of the robot is obtained through lidar data, and the real-time point cloud is screened to filter out point clouds that do not contain ground-related information to form a non-ground point cloud; the obstacle information obtained by the sensor is fused into the non-ground point cloud, and the fused non-ground point cloud is projected into a two-dimensional space to generate a dynamic truth map, wherein 0 in the truth map represents a feasible area and 1 represents an obstacle; finally, the hybrid A* algorithm is used to calculate the cost map and output the local operation path of the robot.
[0109] In this embodiment, the traditional hybrid A* method needs to rely on a 2D grid map to complete local path planning. This embodiment proposes a hybrid A* method without a grid map. It does not need to generate a grid map in real time through a point cloud map and obstacle information, but directly integrates real-time point cloud and obstacle information. It can efficiently and quickly generate a local path to complete obstacle avoidance, thereby improving the obstacle avoidance efficiency during robot operation.
[0110] Some embodiments of the present application, such as Figure 2 As shown, an automatic operation device of an underground handling robot is provided, the device includes an acquisition module 1100, a mapping module 1200, a positioning module 1300, a planning module 1400 and a control module 1500, specifically:
[0111] An acquisition module 1100 is used to acquire operation data of the robot; wherein the operation data includes a plurality of sensor data of the robot;
[0112] A mapping module 1200 is used to draw a point cloud map in the well according to the operation data;
[0113] A positioning module 1300, configured to obtain the position information of the robot according to the operation data;
[0114] A planning module 1400, configured to draw a working path of the robot in the point cloud map according to the position information;
[0115] The control module 1500 is used to control the robot to complete the handling operation according to the operation path.
[0116] It should be noted that the underground transport robot automatic operation device provided in this embodiment and the above-mentioned underground transport robot automatic operation method are based on the same inventive concept, so the relevant content of the above-mentioned underground transport robot automatic operation method is also applicable to the content of the underground transport robot automatic operation device, and therefore, it will not be repeated here.
[0117] like Figure 3 The present application also provides an electronic device, which includes:
[0118] at least one memory;
[0119] at least one processor;
[0120] at least one program;
[0121] The program is stored in the memory, and the processor executes at least one program to implement the automatic operation method of the underground transport robot implemented in the present disclosure.
[0122] The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a vehicle-mounted computer, etc.
[0123] The electronic device according to the embodiment of the present application is described in detail below.
[0124] The processor 1600 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.
[0125] The memory 1700 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1700 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the program code is stored in the memory 1700, and the processor 1600 calls and executes the automatic operation method of the underground handling robot in the embodiment of the present invention.
[0126] Input / output interface 1800, used to implement information input and output;
[0127] The communication interface 1900 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);
[0128] Bus 2000 , which transmits information between various components of the device (e.g., processor 1600 , memory 1700 , input / output interface 1800 , and communication interface 1900 );
[0129] The processor 1600 , the memory 1700 , the input / output interface 1800 , and the communication interface 1900 are connected to each other in communication within the device via the bus 2000 .
[0130] An embodiment of the present invention further provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned automatic operation method of the underground transport robot.
[0131] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed 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 combinations thereof.
[0132] The embodiments described in the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.
[0133] Those skilled in the art will appreciate that the technical solutions shown in the figures do not limit the embodiments of the present invention and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0134] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0135] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0136] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0137] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0138] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0139] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0140] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0141] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable an electronic device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store programs.
[0142] The above is a specific description of the preferred implementation of the embodiments of the present application, but the embodiments of the present application are not limited to the above embodiments. Technical personnel familiar with the field can also make various equivalent modifications or substitutions without violating the spirit of the embodiments of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the embodiments of the present application.
Claims
1. An automatic operation method of an underground handling robot, characterized in that: The method comprises: Acquire operation data of the robot; wherein the operation data includes a plurality of sensor data of the robot; Draw a point cloud map in the well according to the operation data; Obtaining position information of the robot according to the operation data; Drawing a working path of the robot in the point cloud map according to the position information; According to the operation path, the robot is controlled to complete the handling operation.
2. The automatic operation method of the underground handling robot according to claim 1, characterized in that: After drawing the well point cloud map according to the operation data, the method further includes: Obtaining an initial position and posture of the robot; Based on the initial pose, the point cloud map is expanded to obtain a new map; Based on the initial pose, a transformation matrix is obtained; The new map is integrated into the point cloud map through the transformation matrix to update the point cloud map.
3. The automatic operation method of the underground handling robot according to claim 1, characterized in that: The plurality of sensor data includes lidar data, inertial measurement unit data, and odometer data; The obtaining the position information of the robot according to the operation data comprises: fusing the inertial measurement unit data and the odometer data through an unscented Kalman filter to obtain a first predicted position and posture of the robot; Based on the laser radar data, obtaining a real-time point cloud of the robot; Based on the first predicted posture and the real-time point cloud, the position information of the robot is obtained.
4. The automatic operation method of the underground handling robot according to claim 1, characterized in that: The obtaining the position information of the robot according to the operation data comprises: Based on the operation data, obtaining the historical position and posture of the robot; Based on the historical posture, obtaining a second predicted posture of the robot; The second predicted posture is input into the point cloud map to obtain the position information of the robot.
5. The automatic operation method of the underground handling robot according to claim 1, characterized in that: The plurality of sensor data include lidar data and historical operation trajectories; The obtaining the position information of the robot according to the operation data comprises: Based on the historical running trajectory, generating a global positioning point of the robot; Based on the laser radar data, the position information of the robot is searched in the global positioning point.
6. The automatic operation method of the underground handling robot according to claim 1, characterized in that: The operation path includes a global operation path; Drawing the robot's operating path in the point cloud map according to the position information includes: Based on the point cloud map, drawing the lane line for the robot to travel; According to the location information and the preset destination, obtain a corresponding lane line set; The center lines of the lane lines in the lane line set are connected to obtain a global operation path of the robot.
7. The automatic operation method of the underground handling robot according to claim 1, characterized in that: The plurality of sensor data include lidar data and well obstacle data; The operation path includes a local operation path; Drawing the robot's operating path in the point cloud map according to the position information includes: Obtaining a real-time point cloud of the robot according to the laser radar data; Filter out non-ground point clouds from the real-time point clouds; fusing the well obstacle data into the non-ground point cloud; Projecting the fused non-ground point cloud into a two-dimensional space to obtain a true value map; According to the truth map, a local operation path of the robot is drawn in the point cloud map.
8. An automatic operation device for underground transport robots, characterized in that: The device comprises: An acquisition module, used to acquire operation data of the robot; wherein the operation data includes a plurality of sensor data of the robot; A mapping module, used for drawing a point cloud map in the well according to the operation data; A positioning module, used to obtain the position information of the robot according to the operation data; A planning module, used for drawing a working path of the robot in the point cloud map according to the position information; The control module is used to control the robot to complete the handling operation according to the operation path.
9. An electronic device, characterized in that: It includes at least one controller and a memory for communicating with the controller; the memory stores instructions that can be executed by the at least one controller, and the instructions are executed by at least one controller to enable at least one controller to execute the automatic operation method of an underground transport robot as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the automatic operation method of the underground transport robot as described in any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Intelligent navigation system for safe operation
CN119146974A
Drilling machine moving planning method, device and equipment, medium and drilling machine
CN119411941A
Planning method, device, equipment, medium and drilling rig for drilling rig relocation
CN119411941B
