A coal mine underground mechanical arm posture detection control method, device and equipment

Abstract

The present application provides a kind of coal mine underground mechanical arm posture detection control method, device and equipment, it is related to coal mine special robot and mechanical arm automation control technical field, comprising: when receiving mechanical arm movement instruction, obtain the current pose data and environment data of the mechanical arm;Current pose data and environment data of the mechanical arm are obtained;Mechanical arm dynamics calculation is carried out using the current pose data, and the digital model of mechanical arm posture is obtained;The working space of the mechanical arm is reconstructed in three dimensions using the environment data, and a three-dimensional environment model is obtained;Collision avoidance analysis is carried out based on the digital model of mechanical arm posture, the three-dimensional environment model, and the safe movement path of the mechanical arm at the current position is obtained.Improve control accuracy and work efficiency while reducing the risk of operation safety, realize the automation of coal mine underground heavy load mechanical arm pose detection and autonomous collision avoidance decision, effectively reduce the risk of equipment collision in use process, improve the intelligent level of coal mine mechanical equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal mine special robot and mechanical arm automatic control, and particularly relates to a coal mine underground mechanical arm posture detection control method, device, equipment and computer storage medium. BACKGROUND

[0002] China is the world's first coal producer, and coal production accounts for more than 50% of the world's total production. The coal industry has become an important foundation for the rapid development of the national economy. Underground mining is the main production method of coal mines, and most of the operations in the underground operation need to be completed by coal workers on the working surface. With the development of computer, automation and other fields, researchers have carried out a lot of research in the field of coal mine special robots in order to use robots to replace workers to complete complex tasks such as roadway excavation, drilling and dust flushing. Mechanical arm posture detection and control is an important basis for realizing the function of the robot, and the development of posture detection and control methods for coal mine underground heavy-duty mechanical arms is of great significance to the development of coal mine special robots.

[0003] At present, the existing mechanical arm still needs workers to obtain surrounding environment data and control, which greatly affects the work progress. Artificially obtaining environment data has problems such as difficult measurement and low efficiency, which directly affects the moving accuracy and work efficiency of the mechanical arm. Moreover, the existing mechanical arm control technology cannot effectively reduce the collision risk of the equipment during use, affecting the safety of underground workers.

[0004] From the above, it can be seen that how to design a coal mine underground mechanical arm posture detection control method with high precision, high efficiency and low collision risk is a problem to be solved at present. SUMMARY

[0005] The purpose of the present application is to provide a coal mine underground mechanical arm posture detection control method, device and application, to solve the problems of low efficiency, difficult measurement and inability to avoid collision of the existing mechanical arm.

[0006] To solve the above technical problems, the present application provides a coal mine underground mechanical arm posture detection control method, comprising:

[0007] When the mechanical arm motion instruction is received, the current pose data and environment data of the mechanical arm are obtained;

[0008] The current pose data is used for mechanical arm dynamics calculation to obtain a mechanical arm posture digital model;

[0009] The environment data is used for three-dimensional reconstruction of the working space of the mechanical arm to obtain a three-dimensional environment model;

[0010] Collision avoidance analysis is performed based on the digital model of the robotic arm's posture and the three-dimensional environment model to obtain the safe movement path of the robotic arm at the current position.

[0011] Preferably, the collision avoidance analysis based on the robotic arm's posture digital model and the three-dimensional environment model to obtain the safe movement path of the robotic arm at the current position includes:

[0012] The coordinate system transformation calculation is performed between the digital model of the robotic arm's posture and the three-dimensional environment model, and they are synchronized to the same coordinate system.

[0013] Based on the coordinates of each joint of the robotic arm and the end effector of the robotic arm, the distance between the robotic arm and other objects in the environment under the current posture is calculated, and a distance data set is generated.

[0014] Distance data below the safety threshold in the distance dataset are marked with collision risk to obtain risk-marked data;

[0015] The risk marker data is calculated to obtain new posture data in which all distance data sets meet the safety threshold, thus obtaining the safe movement path of the robotic arm at the current position.

[0016] Preferably, the current pose data of the robotic arm includes: joint angle values, joint angular acceleration, and joint movement trajectory; the environmental data includes: images, videos, and environmental point cloud data.

[0017] Preferably, the step of using the current pose data to perform robotic arm dynamics calculations to obtain a digital model of the robotic arm's pose includes:

[0018] Based on the joint angle values, joint angular acceleration, and joint movement trajectory of the robotic arm, the velocity and acceleration of each link of the robotic arm base are calculated sequentially using the Newton-Euler method, all the way to the end effector of the robotic arm. Then, starting from the external force on the end effector of the robotic arm, the torque of each joint is solved in reverse order to obtain the digital model of the robotic arm posture.

[0019] Preferably, the formula for calculating the digital model of the robotic arm's posture is:

[0020]

[0021] Where M(q) is the inertial force term, G(q) represents the centripetal force and Coriolis force, and τ represents the gravitational force. f This is the friction term.

[0022] Preferably, the step of using the environmental data to perform three-dimensional reconstruction of the robotic arm's workspace to obtain a three-dimensional environment model includes:

[0023] The noise interference of laser point cloud data in the environmental data is removed by using data analysis algorithms to obtain noise-free point cloud data;

[0024] Multi-view geometric reconstruction is performed on the image data in the environmental data to obtain a point cloud model with texture information;

[0025] The point cloud model is fused with the noise-reduced point cloud data to obtain a three-dimensional environment model.

[0026] Preferably, the three-dimensional environment model includes a dense three-dimensional spatial point cloud and accurate texture data.

[0027] The present invention also provides a posture detection and control device for a coal mine underground robotic arm, comprising:

[0028] The data acquisition module is used to acquire the current pose data of the robotic arm and environmental data when it receives a movement command from the robotic arm;

[0029] The robotic arm posture construction module uses the current posture data to perform robotic arm dynamics calculations to obtain a digital model of the robotic arm posture.

[0030] The three-dimensional environment construction module uses the environmental data to perform three-dimensional reconstruction of the working space of the robotic arm to obtain a three-dimensional environment model;

[0031] The collision avoidance analysis module performs collision avoidance analysis based on the digital model of the robotic arm's posture and the three-dimensional environment model to obtain the safe movement path of the robotic arm at the current position.

[0032] The present invention also provides a posture detection and control device for a coal mine underground robotic arm, comprising:

[0033] A camera is used to capture images and videos of the environment.

[0034] An inertial navigation unit is used to acquire the acceleration of the robotic arm;

[0035] LiDAR is used to acquire environmental point cloud data;

[0036] Memory, used to store computer programs;

[0037] A processor is used to execute the computer program to implement the steps of the above-described method for posture detection and control of a robotic arm in a coal mine.

[0038] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for posture detection and control of a robotic arm in a coal mine.

[0039] The present invention provides a posture detection and control method for a heavy-duty robotic arm in coal mines. By acquiring the current posture data and environmental data of the robotic arm, it achieves accurate posture detection of the heavy-duty robotic arm in coal mines, reconstructs a digital model of the robotic arm posture and a three-dimensional environment model, and performs collision avoidance analysis based on the digital model of the robotic arm posture and the three-dimensional environment model to obtain a safe movement path of the robotic arm at the current position. This improves control accuracy and work efficiency while reducing operational safety risks, realizing automated posture detection and autonomous collision avoidance decision-making for the heavy-duty robotic arm in coal mines, effectively reducing the risk of equipment collisions during use, and improving the intelligence level of coal mine machinery and equipment. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A flowchart of a first specific embodiment of the posture detection and control method for underground robotic arms in coal mines provided by the present invention;

[0042] Figure 2 A schematic diagram of a posture detection and control system for an underground robotic arm in a coal mine, provided by the present invention.

[0043] Figure 3 This is a structural block diagram of a posture detection and control device for an underground robotic arm in a coal mine, provided as an embodiment of the present invention. Detailed Implementation

[0044] The core of this invention is to provide a method, device, and application for posture detection and control of underground robotic arms in coal mines. This invention enables intelligent control of heavy-duty underground robotic arms beyond visual range, improving control accuracy and operational efficiency while reducing operational safety risks.

[0045] To enable those skilled in the art to better understand the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Please refer to Figure 1 , Figure 1 The flowchart illustrates a first specific embodiment of the posture detection and control method for underground robotic arms in coal mines provided by the present invention; the specific operation steps are as follows:

[0047] S101: Upon receiving a movement command from the robotic arm, acquire the current pose data of the robotic arm and environmental data;

[0048] The joint angle values, joint angular acceleration, joint movement trajectory, image and video data, and environmental point cloud data of the robotic arm are acquired.

[0049] S102: Calculate the dynamics of the robotic arm using the current pose data to obtain a digital model of the robotic arm's pose;

[0050] Based on the joint angle values, joint angular acceleration, and joint movement trajectory of the robotic arm, the velocity and acceleration of each link of the robotic arm base are calculated sequentially using the Newton-Euler method, all the way to the end mechanism of the robotic arm. Then, starting from the external force on the end mechanism of the robotic arm, the torque of each joint is solved in reverse order to obtain the digital model of the robotic arm posture.

[0051] The formula for calculating the digital model of the robotic arm's posture is:

[0052]

[0053] Where M(q) is the inertial force term, G(q) represents the centripetal force and Coriolis force, and τ represents the gravitational force. f This is the friction term.

[0054] S103: Using the environmental data, the working space of the robotic arm is reconstructed in three dimensions to obtain a three-dimensional environment model;

[0055] The noise interference of laser point cloud data in the environmental data is removed by using data analysis algorithms to obtain noise-free point cloud data;

[0056] Multi-view geometric reconstruction is performed on the image data in the environmental data to obtain a point cloud model with texture information;

[0057] The point cloud model is fused with the noise-reduced point cloud data to obtain a three-dimensional environment model.

[0058] The three-dimensional environment model includes a dense three-dimensional spatial point cloud and accurate texture data.

[0059] S104: Based on the digital model of the robotic arm's posture and the three-dimensional environment model, perform collision avoidance analysis to obtain the safe movement path of the robotic arm at the current position;

[0060] The coordinate system transformation calculation is performed between the digital model of the robotic arm's posture and the three-dimensional environment model, and they are synchronized to the same coordinate system.

[0061] Based on the coordinates of each joint of the robotic arm and the end effector of the robotic arm, the distance between the robotic arm and other objects in the environment under the current posture is calculated, and a distance data set is generated.

[0062] Distance data below the safety threshold in the distance dataset are marked with collision risk to obtain risk-marked data;

[0063] The risk marker data is calculated to obtain new posture data in which all distance data sets meet the safety threshold, thus obtaining the safe movement path of the robotic arm at the current position.

[0064] This invention provides a method for posture detection and control of a robotic arm in underground coal mines. By acquiring the current posture data and environmental data of the robotic arm, it achieves accurate posture detection of the heavy-duty robotic arm in underground coal mines, reconstructs a digital model of the robotic arm posture and a three-dimensional environment model, and performs collision avoidance analysis based on the digital model of the robotic arm posture and the three-dimensional environment model to obtain the safe movement path of the robotic arm at the current position. This improves control accuracy and work efficiency while reducing operational safety risks. By using automated posture detection and control technology to replace on-site visual operation, it realizes intelligent control of the heavy-duty robotic arm in underground coal mines and improves the working efficiency of the robotic arm.

[0065] Based on the above embodiments, this embodiment elaborates on the robotic arm posture detection and control method in detail, as follows:

[0066] S201: Collects environmental data, including images and videos, joint angle values, joint angular acceleration, joint movement trajectory, and environmental point cloud data. The data is transmitted to the autonomous decision control unit through the data transmission unit.

[0067] The system collects environmental data, including data on the robotic arm itself and its surrounding environment, such as the location information of target objects and obstacles, and enables the positioning of the robotic arm itself. The data transmission unit transmits the data acquired by the data acquisition unit and system control commands. The autonomous decision control unit performs data processing and motion analysis decisions to issue commands such as robotic arm movement, stopping, and emergency obstacle avoidance. The robotic arm motion unit executes the robotic arm's motion commands.

[0068] S202: Performs dynamic calculations on the robotic arm, determining its current pose, end-effector linear velocity, and linear acceleration, thus reconstructing a digital model of the robotic arm's motion. The dynamic model is established based on the Newton-Euler equations, which are as follows:

[0069]

[0070] Where M(q) is the inertial force term, G(q) represents the centripetal force and Coriolis force, and τ represents the gravitational force.f This is the friction term;

[0071] Furthermore, the dynamics calculation of the heavy-duty robotic arm adopts the "Newton-Euler" method, starting from the base of the heavy-duty robotic arm and calculating the velocity and acceleration of each link in sequence, all the way to the end mechanism of the robotic arm; then, starting from the external force on the end mechanism of the robotic arm, the torque of each joint is solved in reverse order, and finally the digital model of the robotic arm posture is obtained.

[0072] S203: Based on the image video and environmental point cloud, perform three-dimensional reconstruction of the robotic arm's environmental space and generate a three-dimensional environmental model. Perform coordinate system transformation calculations on the three-dimensional environmental model and the current robotic arm pose data, synchronize them to the same coordinate system for collision avoidance analysis, and select safe movement directions at the current position.

[0073] S204: Obtain the motion command of the robotic arm, perform dynamic calculations according to the motion command, re-execute the collision avoidance analysis, and after confirming that the motion trajectory of the command is risk-free, convert the command into specific values ​​and issue them to the robotic arm motion unit to start executing the corresponding motion command.

[0074] The method for solving the motion commands of the robotic arm is as follows: based on the digital model obtained by dynamic calculation, input the target position or trajectory coordinates that the end mechanism of the heavy-duty robotic arm needs to move, deduce how much torque the drive mechanism of each joint of the robotic arm needs to apply at each time point, and output electrical signals to the electro-hydraulic servo valve of the heavy-duty robotic arm to achieve precise control of the motion of the heavy-duty robotic arm.

[0075] This embodiment provides a method for posture detection and control of a robotic arm in underground coal mines. It elaborates on the construction methods of the robotic arm's posture digital model and three-dimensional environment model. Through a sensor array mounted on the robotic arm, it collects data such as images, videos, joint data, and environmental point cloud models. Based on this, it calculates the current motion state of the robotic arm and information about the working environment, achieving accurate posture detection of the heavy-duty robotic arm in underground coal mines. Simultaneously, by comparing the posture information with the environmental point cloud model, it analyzes the existence of collision risks and directly performs autonomous collision avoidance control, preventing positional interference between the robotic arm and other underground equipment during its movement. At the same time, the data transmission unit transmits the data information to the ground control terminal, enabling remote monitoring and remote operation commands to be issued to the robotic arm, giving the robotic arm both autonomous collision avoidance and remote control functions.

[0076] like Figure 2 As shown in the figure, this embodiment provides a posture detection and control system for an underground robotic arm in a coal mine, as detailed below:

[0077] The hardware mainly consists of a data acquisition unit, a data transmission unit, a control unit, and a robotic arm motion unit.

[0078] The data acquisition unit includes a camera, an inertial navigation unit, a lidar, an encoder, and a stress and strain sensor. During the use of the robotic arm, it acquires images and videos, joint angle values, joint angular acceleration, joint movement trajectories, and environmental point cloud data.

[0079] The data transmission unit includes a signal transceiver terminal, an intrinsically safe switch for mining, and underground communication optical cable equipment, which together form an underground data communication network.

[0080] The control unit is a main controller that includes a graphics computing unit, which is responsible for data processing and analysis decisions, and for issuing commands such as moving the robotic arm, stopping the machine, and emergency obstacle avoidance.

[0081] The robotic arm motor unit includes a hydraulic robotic arm body mechanism, an electro-hydraulic servo valve, and a hydraulic cylinder, which drives the movement of the heavy-duty robotic arm hydraulically.

[0082] Based on the above embodiments, this embodiment elaborates on collision avoidance analysis in detail, as follows:

[0083] S301: Perform 3D reconstruction based on data fusion using image and video data and environmental point cloud data to obtain a 3D environmental model of the area where the robotic arm is currently located;

[0084] S302: Perform coordinate system transformation calculations on the 3D environment model and the robotic arm posture digital model, and synchronize them to the same coordinate system;

[0085] S303: Using the coordinates of each joint of the robotic arm and the end effector of the robotic arm as a reference, calculate the distance between the robotic arm and other objects in the environment in the current posture, and generate a distance data set;

[0086] S304: Analyze whether there is any distance data in the distance dataset that is below the safety threshold, return the joint code corresponding to that part of the data, and mark the collision risk;

[0087] S305: The robot arm joints containing collision risk markers are re-input into the dynamic model for calculation, and new attitude data that meet the safety threshold are obtained from the distance data set. The collision avoidance motion command is then output.

[0088] Repeating steps S301 to S305 enables real-time collision avoidance analysis and autonomous collision avoidance control decisions during the use of underground robotic arms in coal mines.

[0089] This invention discloses a posture detection and control method for a robotic arm in underground coal mines. It collects data such as images, videos, joint data, and environmental point cloud models using sensors mounted on the robotic arm. Based on this data, it calculates the current motion state of the robotic arm and information about the working environment, achieving precise posture detection for the heavy-duty robotic arm in underground coal mines. Simultaneously, it uses the posture information and environmental point cloud model to analyze the existence of collision risks and directly implement autonomous collision avoidance control. This method enables remote monitoring and remote operation command issuance to the robotic arm, giving it both autonomous collision avoidance and remote control functions. This embodiment utilizes automated posture detection and control technology to replace on-site visual operation, achieving intelligent control of the heavy-duty robotic arm in underground coal mines and improving the robotic arm's operating efficiency.

[0090] Please refer to Figure 3 , Figure 3 A structural block diagram of a posture detection and control device for an underground robotic arm in a coal mine, provided in an embodiment of the present invention; the specific device may include:

[0091] The data acquisition module 100 is used to acquire the current pose data of the robotic arm and environmental data when it receives a motion command from the robotic arm.

[0092] The robotic arm posture construction module 200 uses the current posture data to perform robotic arm dynamics calculations to obtain a digital model of the robotic arm posture.

[0093] The three-dimensional environment construction module 300 uses the environmental data to perform three-dimensional reconstruction of the working space of the robotic arm to obtain a three-dimensional environment model;

[0094] The collision avoidance analysis module 400 performs collision avoidance analysis based on the digital model of the robotic arm's posture and the three-dimensional environment model to obtain the safe movement path of the robotic arm at the current position.

[0095] This embodiment of a coal mine underground robotic arm posture detection and control device is used to implement the aforementioned coal mine underground robotic arm posture detection and control method. Therefore, the specific implementation of the coal mine underground robotic arm posture detection and control device can be found in the embodiment section of the coal mine underground robotic arm posture detection and control method above. For example, the data acquisition module 100, the robotic arm posture construction module 200, the three-dimensional environment construction module 300, and the collision avoidance analysis module 400 are respectively used to implement steps S101, S102, S103, and S104 in the aforementioned coal mine underground robotic arm posture detection and control method. Therefore, its specific implementation can be referred to the description of the corresponding embodiments, which will not be repeated here.

[0096] To implement the above embodiments, the present invention also proposes a computer program product, which, when the instruction processor in the computer program product is executed, performs an artificial intelligence-based method, the method comprising:

[0097] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0098] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0099] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of the invention pertain.

[0100] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0101] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0102] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0103] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0104] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for posture detection and control of a robotic arm in an underground coal mine, characterized in that, include: Upon receiving a movement command from the robotic arm, the system acquires the current pose data of the robotic arm and environmental data. The current pose data of the robotic arm includes: joint angle values, joint angular acceleration, and joint movement trajectory. The environmental data includes: image video and environmental point cloud data. Using the current pose data, the dynamics of the robotic arm are calculated to obtain a digital model of the robotic arm's posture. This includes: based on the joint angle values, joint angular accelerations, and joint movement trajectories of the robotic arm, the velocity and acceleration of each link of the robotic arm base are calculated sequentially using the Newton-Euler method, all the way to the end effector of the robotic arm. Then, starting from the external force on the end effector of the robotic arm, the torque of each joint is solved in reverse order to obtain the digital model of the robotic arm's posture. The working space of the robotic arm is reconstructed in three dimensions using the environmental data to obtain a three-dimensional environment model; Collision avoidance analysis is performed based on the robotic arm posture digital model and the three-dimensional environment model to obtain a safe movement path for the robotic arm at the current position. This includes: performing coordinate system transformation calculations on the robotic arm posture digital model and the three-dimensional environment model to synchronize them to the same coordinate system; calculating the distances between the robotic arm and other objects in the environment at the current posture based on the coordinates of each joint point of the robotic arm and the end effector of the robotic arm, generating a distance data set; marking the distance data in the distance data set that are below the safety threshold as collision risk to obtain risk-marked data; calculating the risk-marked data to obtain new posture data where all distance data sets meet the safety threshold, thus obtaining a safe movement path for the robotic arm at the current position.

2. The method for posture detection and control of an underground robotic arm in coal mines as described in claim 1, characterized in that, The formula for calculating the digital model of the robotic arm's posture is: Where M(q) is the inertial force term, G(q) represents the centripetal force and Coriolis force, and τ represents the gravitational force. f This is the friction term.

3. The method for posture detection and control of an underground robotic arm in coal mines as described in claim 1, characterized in that, The step of using the environmental data to perform three-dimensional reconstruction of the robotic arm's workspace to obtain a three-dimensional environment model includes: The noise interference of laser point cloud data in the environmental data is removed by using data analysis algorithms to obtain noise-free point cloud data; Multi-view geometric reconstruction is performed on the image data in the environmental data to obtain a point cloud model with texture information; The point cloud model is fused with the noise-reduced point cloud data to obtain a three-dimensional environment model.

4. The method for posture detection and control of an underground robotic arm in coal mines as described in claim 3, characterized in that, The three-dimensional environment model includes a dense three-dimensional spatial point cloud and accurate texture data.

5. A posture detection and control device for an underground robotic arm in a coal mine, characterized in that, include: The data acquisition module is used to acquire the current pose data and environmental data of the robotic arm when it receives a motion command from the robotic arm. The current pose data of the robotic arm includes: joint angle values, joint angular acceleration, and joint movement trajectory; the environmental data includes: image video and environmental point cloud data. The robotic arm posture construction module uses the current pose data to perform robotic arm dynamics calculations to obtain a robotic arm posture digital model. This includes: based on the joint angle values, joint angular accelerations, and joint movement trajectories of the robotic arm, using the Newton-Euler method to sequentially calculate the velocity and acceleration of each link of the robotic arm base, all the way to the robotic arm end effector. Then, starting from the external force on the robotic arm end effector, the torque of each joint is solved in reverse order to obtain the robotic arm posture digital model. The three-dimensional environment construction module uses the environmental data to perform three-dimensional reconstruction of the working space of the robotic arm to obtain a three-dimensional environment model; The collision avoidance analysis module performs collision avoidance analysis based on the robotic arm posture digital model and the three-dimensional environment model to obtain a safe movement path for the robotic arm at the current position. This includes: performing coordinate system transformation calculations on the robotic arm posture digital model and the three-dimensional environment model to synchronize them to the same coordinate system; calculating the distances between the robotic arm and other objects in the environment at the current posture based on the coordinates of each joint point of the robotic arm and the end effector of the robotic arm; generating a distance data set; marking the distance data in the distance data set below a safety threshold as collision risk to obtain risk-marked data; and calculating the risk-marked data to obtain new posture data where all distance data in the set meet the safety threshold, thus obtaining a safe movement path for the robotic arm at the current position.

6. A posture detection and control device for an underground robotic arm in a coal mine, characterized in that, include: A camera is used to capture images and videos of the environment. An inertial navigation unit is used to acquire the acceleration of the robotic arm; LiDAR is used to acquire environmental point cloud data; Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the posture detection and control method for an underground robotic arm in a coal mine as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the posture detection and control method for an underground robotic arm in a coal mine as described in any one of claims 1 to 4.

Images