Carrying method and device for explosives and six-axis robot arm system

Abstract

The invention provides an explosive carrying method and device and a six-axis robot arm system. The method comprises the steps that the type of an object to be carried is obtained; and under the condition that the to-be-carried objects are explosive objects, the six-axis robot arm is controlled to carry the objects according to the target motion information, so that the objects are carried stably. According to the scheme, the problems that in the prior art, when an existing six-axis robot arm carries explosives, the explosives cannot be accurately and stably carried according to the application scene of the explosives, and accidents are likely to happen are solved.

Description

Technical Field

[0001] The present application relates to the field of robotic arm handling technology, and in particular, to a method, device, computer program product and six-axis robotic arm system for handling explosives. Background Art

[0002] A six-axis robot is a robotic arm with six degrees of freedom, commonly used in automation and robotic applications in industrial production. Each degree of freedom represents an independent dimension of motion of the robot in space, allowing it to move and rotate in six directions. This multi-degree-of-freedom design enables the six-axis robot to perform complex tasks such as assembly, handling, welding, etc. A six-axis robot usually consists of six joints, each of which is driven by an electric motor or hydraulic device to achieve precise motion control. These joints are usually designed as revolute joints, allowing the robot to rotate freely in multiple directions, thereby achieving a wider range of work and flexibility. In industrial applications, six-axis robots are often used in combination with sensors, control systems, and programming interfaces to achieve various tasks on automated production lines. Through programming, users can specify the robot's motion trajectory and action sequence to make it perform specific operations. This flexibility and programmability make six-axis robots an indispensable part of modern industrial production.

[0003] Six-axis robots are widely used in the field of handling robots. Their main advantages include flexibility, precision and programmability, making them suitable for a variety of different types of handling tasks. In the basic application of handling robots, six-axis robots can be used to carry materials from one location to another, such as moving parts from one workstation to another, or taking finished products off the production line and placing them in the packaging area. They can also be programmed to perform repetitive handling tasks, which can improve production efficiency and reduce labor costs. For example, in the logistics and warehousing industries, robots can be used to carry and stack goods. In particular, in dangerous environments, such as high temperature, high pressure or toxic gases, six-axis robots can also replace manual handling tasks to protect the safety of workers.

[0004] However, the current six-axis robot arms are unable to carry explosives accurately and stably according to the application scenario of explosives, which makes accidents prone to occur. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device, computer program product and six-axis robot system for transporting explosives, so as to at least solve the problem that the current six-axis robot in the prior art cannot accurately and stably transport explosives according to the application scenario of explosives, and is prone to accidents.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for transporting explosive items is provided, comprising: obtaining the type of items to be transported; when the type of the items to be transported is explosive items, controlling a six-axis robot to transport the items using target motion information so as to transport the items smoothly, wherein the target motion information includes one or more of path information, action posture information and force information, the path information is an optimal path for transporting the items to avoid obstacles, the action posture information is an optimal posture of rotation, bending and extension of the six-axis robot, the force information is a target force applied when grasping, transporting and placing the items, the target force is less than the force for transporting ordinary types of items, and the explosive items are one or more of dynamite, detonators, gunpowder, fireworks and flour.

[0007] Optionally, obtaining the type of the article to be transported includes: obtaining label information, wherein the label information is information of a barcode or RFID scan of the packaging of the article; and determining the type of the article according to the label information.

[0008] Optionally, before controlling the six-axis robot to move the item using the target motion information, the method further includes: acquiring relevant information, wherein the relevant information includes at least one or more of the position of the six-axis robot, the speed of the six-axis robot, the weight of the item, the size of the item, the position of the obstacle, a safety distance and the warehouse position; and determining the target motion information based on the relevant information.

[0009] Optionally, determining the target motion information based on the relevant information includes: constructing an action generation model, wherein the action generation model is trained using multiple sets of training data, each set of training data includes historical relevant information acquired within a historical time period, and historical target motion information corresponding to the historical relevant information; inputting the relevant information into the action generation model to obtain the target motion information corresponding to the relevant information.

[0010] Optionally, when the relevant information includes the weight of the item and the size of the item, after controlling the six-axis robot to move the item using the target motion information, the method further includes: when the items have been moved to the warehouse, stacking the items in order of weight from heavy to light and size from large to small; during the stacking process, acquiring image information of the stacking area; performing image recognition on the image information to determine whether the items are successfully stacked; and generating a first warning message when the stacking of the items fails.

[0011] Optionally, in the process of controlling the six-axis robot to carry the item using target motion information, the method also includes: obtaining a target distance, wherein the target distance is the distance between the six-axis robot and an obstacle; and controlling the six-axis robot to stop carrying when the target distance is less than a preset safety distance.

[0012] Optionally, in the process of controlling the six-axis robot to move the object using target motion information, the method also includes: obtaining the temperature of the six-axis robot; when the temperature is greater than a preset threshold, turning on the cooling system to cool the six-axis robot, wherein the cooling system includes one or more of a fan, a coolant and a heat sink; when the cooling system is turned on for a target duration, generating a second warning message and controlling the six-axis robot to stop moving.

[0013] According to another aspect of the present application, a device for transporting explosives is provided, comprising: a first acquisition unit, for acquiring the type of the item to be transported; and a first control unit, for controlling a six-axis robot to transport the item using target motion information when the type of the item to be transported is an explosive, so as to transport the item smoothly, wherein the target motion information comprises one or more of path information, action posture information and force information, the path information is an optimal path for transporting the item to avoid obstacles, the action posture information is an optimal posture of rotation, bending and extension of the six-axis robot, the force information is a target force applied when grasping, transporting and placing the item, the target force is smaller than the force for transporting ordinary types of items, and the explosive item is one or more of dynamite, detonator, gunpowder, fireworks and flour.

[0014] According to another aspect of the present application, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any one of the methods for transporting explosives are implemented.

[0015] According to another aspect of the present application, a six-axis robotic arm system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the methods for handling explosive items.

[0016] Applying the technical solution of the present application, the motion planning control of the existing six-axis robot is mostly a general control logic, which is not optimized for the application scenario of explosives. In the solution of the present application, if the transported item is an explosive, the path of the robot must be specifically limited to avoid collision between the explosive and other obstacles. The movement posture must also be specifically limited to ensure stability during the transportation process. The force can also be limited, and the explosives must be handled with care to improve safety, thereby avoiding accidents during the transportation of explosives. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a mobile terminal for executing a method for transporting explosives provided in an embodiment of the present application is shown;

[0019] Figure 2 A schematic flow chart of a method for transporting explosives provided in accordance with an embodiment of the present application is shown;

[0020] Figure 3 The structure diagram of the system of the six-axis robot is shown;

[0021] Figure 4 A schematic diagram of the structure of a neural network algorithm module is shown;

[0022] Figure 5 A structural block diagram of an explosive material transport device provided according to an embodiment of the present application is shown.

[0023] The above drawings include the following reference numerals:

[0024] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims 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 sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. 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.

[0028] The handling of explosives is also based on safety considerations. The current six-axis manipulators still have some urgent problems to overcome during their application. These are mainly reflected in: 1) The motion planning control of the existing six-axis manipulators is mostly general control logic, and has not been optimized for the application scenarios of explosives. This leads to the possibility of collisions with obstacles in the motion path, trajectory setting and posture control of the manipulator when multiple handling robots are working at the same time. For explosives, even a slight collision may lead to safety accidents; 2) The motion control of the existing six-axis manipulators is not sophisticated and intelligent enough when stacking, and is not safe for explosives that need to be handled with care; 3) When picking up explosives, the existing six-axis manipulators cannot automatically adjust the force / torque of the end effector according to the type of explosives, which may cause some explosives to explode or be damaged and leak under improper clamping force.

[0029] As introduced in the background technology, the current six-axis robot arm in the prior art is unable to accurately and stably carry explosives according to the application scenario of explosives, and accidents are prone to occur. To solve the above problems, the embodiments of the present application provide a method, device, computer program product and six-axis robot arm system for carrying explosives.

[0030] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0031] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a method for transporting explosives according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0032] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] In this embodiment, a method for transporting explosives running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 2 FIG. 1 is a flow chart of a method for transporting explosives according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0035] Step S201, obtaining the type of the object to be transported;

[0036] Specifically, the robot arm needs to be equipped with high-precision sensors, such as visual sensors, chemical sensors, or radio frequency identification (RFID) sensors, to identify and determine the specific attributes and types of objects. For example, visual sensors can be used to identify the shape, color, and label of an object; chemical sensors can detect the chemical composition of an object, which is particularly important for identifying explosives; and RFID sensors can determine the type and attributes of an object by reading the electronic tags on the object. The information obtained by the sensor is analyzed and identified by the data processing module of the robot arm or its control system to determine the type of the object.

[0037] Step S202, in the case that the above-mentioned type of the above-mentioned items to be transported is an explosive item, the six-axis robot is controlled to use target motion information to transport the above-mentioned items so as to transport the above-mentioned items smoothly, wherein the above-mentioned target motion information includes one or more of path information, action posture information and force information, the above-mentioned path information is the optimal path for transporting the above-mentioned items to avoid obstacles, the above-mentioned action posture information is the optimal posture of rotation, bending and extension of the above-mentioned six-axis robot, the above-mentioned force information is the target force applied when grasping, transporting and placing the above-mentioned items, and the above-mentioned target force is smaller than the force for transporting ordinary types of the above-mentioned items, and the above-mentioned explosive items are one or more of dynamite, detonators, gunpowder, fireworks and flour.

[0038] Specifically, when the six-axis robot arm identifies that the object to be transported is an explosive, it will generate specific target motion information based on the preset algorithm and strategy. This information includes path information, motion posture information and force information, which is used to guide the robot arm on how to safely transport the object.

[0039] Specifically, path information refers to the optimal path that the robot needs to follow during the handling process, which is designed to avoid obstacles and potential danger areas to reduce accidental impacts or collisions that explosive items may suffer during the handling process.

[0040] Specifically, the motion posture information refers to the optimal motion posture of each axis of the robot arm when carrying explosives, including rotation, bending and stretching movements, to ensure that the robot arm can grasp and place objects stably and accurately, and avoid additional force or vibration due to improper posture.

[0041] Specifically, force information refers to the amount of force applied when grabbing, carrying, and placing explosives. Due to the sensitivity of explosives, the force required is usually less than the force used to carry ordinary items to reduce the risk of damaging the items or triggering an explosion due to excessive force.

[0042] Specifically, when carrying explosives, the robot arm needs to adopt special handling strategies, such as using more stable and slow movements, and avoiding any rapid movements or high-force operations that may cause instability or reaction of the explosives.

[0043] Specifically, when grabbing, carrying and placing explosive items, the robot arm needs to be able to accurately control the force applied to ensure that the force is always lower than the operating force on ordinary objects, thereby reducing the risk of explosion.

[0044] Through this embodiment, the motion planning control of the existing six-axis robot is mostly a general control logic, which is not optimized for the application scenario of explosives. In the solution of the present application, if the transported item is an explosive, the path of the robot must be specifically limited to avoid collision between the explosive and other obstacles. The movement posture must also be specifically limited to ensure stability during the transportation process. The force can also be limited to ensure that the explosive is handled with care, thereby improving safety and avoiding accidents during the transportation of explosives.

[0045] Specifically, the solution of this application aims to develop and optimize a six-axis robot for handling explosives to improve the efficiency, safety and accuracy of handling operations. Through this research, a reliable robot system is designed that can better adapt to the application scenario of explosive handling in terms of motion and trajectory control, action and posture control, and force / torque control, and accurately and stably perform handling tasks, thereby reducing accident risks and improving operational efficiency to meet handling needs in high-risk environments.

[0046] Specifically, Figure 3 As shown, the system applied to the six-axis robot in this solution includes the following parts:

[0047] Intelligent warehouse management platform: The platform functions include but are not limited to task planning management, outbound management, inbound management, clearance management, access control, equipment management, alarm, statistical analysis, upload, personnel role authority management, auxiliary management and other modules, and can collect and display the temperature, humidity, quantity, stacking height, safety distance, type, etc. in the warehouse in real time. When the six-axis robot arm of the present invention is working, it needs to obtain task planning management information from the intelligent warehouse management platform, and at the same time obtain the type of explosives related to the task and the explosive packaging information.

[0048] Host computer: The host computer is the human-computer interaction interface, responsible for receiving user instructions and sending them to the control unit of the six-axis robot.

[0049] Safety system: The safety system is the original system of intelligent warehousing. The six-axis robot of the present invention can be equipped with a safety control unit to detect and respond to potential safety risks based on the robot's motion state and surrounding environment monitored by sensors. It includes safety equipment such as emergency stop buttons, safety sensors, protective covers, and safety logic and algorithms to ensure that the movement of the six-axis robot does not cause danger to personnel and equipment.

[0050] Robot arm: The robot arm is the actuator of the six-axis robot arm, which is composed of six joints, each of which can rotate around an axis, and an end effector is set at the end of the robot arm. The end effector is the end component of the six-axis robot arm, which can be customized according to the needs of different types of explosives, such as grippers, suction cups, etc. The machine structure of the six-axis robot arm is not specifically limited in the present invention, and can actually be specifically adjusted according to different types of explosives. The entire six-axis robot arm needs to include a control unit, a sensor, and an image acquisition unit.

[0051] The control unit specifically includes a neural network algorithm module, a safety control unit and a power control unit. The neural network algorithm module is responsible for: 1) motion planning and trajectory optimization: by learning and predicting the optimal motion path and trajectory of the robot when performing a specific explosive handling task. Then, according to different working environments and task requirements, a suitable motion planning strategy can be provided to improve the motion efficiency and flexibility of the robot. 2) Motion control and posture adjustment: used to realize the motion control and posture adjustment of the robot. By inputting sensor data into the neural network, the state of the robot and the working environment can be monitored in real time, and the movement of the robot can be adjusted as needed to achieve precise handling operations. 3) Force / torque control: used to realize the force and torque control of the robot. By training the neural network, the force and torque data measured by the sensor can be input into the network, and the movement of the robot can be adjusted as needed to adapt to different force and torque requirements, thereby achieving more precise handling operations. Based on this, the neural network algorithm module in the present invention at least includes a motion and trajectory control unit, a motion and posture control unit and a force / torque control unit.

[0052] In addition, the sensors in this solution include at least the following sensors:

[0053] Joint position sensor: Each robot joint is usually equipped with a position sensor to measure the angle or position of the joint as action and posture data. These sensors can be encoders, photoelectric encoders, or rotary transformers.

[0054] Joint force sensors: Joint force sensors are used to measure the force or torque applied by the joints of the robot. These sensors can help the robot achieve functions such as force control, torque control, and collision detection.

[0055] End effector force sensor: The end effector force sensor is installed on the end effector of the robot arm to measure the force or torque applied by the end effector on the workpiece or environment. These sensors are often used to achieve precise force control, force feedback, etc.

[0056] Force tactile sensors: These sensors measure the contact force and position between the robot arm and the workpiece or the environment. Force tactile sensors are used for force control, gripping tasks, and collision detection.

[0057] Inertial Measurement Unit (IMU): An IMU typically includes an accelerometer and a gyroscope to measure the acceleration and angular velocity of the robot arm for posture estimation and dynamic control.

[0058] Temperature sensor: The temperature sensor is used to measure the temperature of key components of the robot to ensure that it operates within a safe temperature range.

[0059] The control of the six-axis manipulator in the proposal of the present invention includes motion path, action and posture control, and force / torque control. The control of these three dimensions can be understood as three tasks, and these three tasks are uniformly controlled by the multi-task neural network algorithm model (i.e., action generation model) in the present invention. A common six-axis manipulator includes six joints, or six rotation axes, such as the main body rotation axis, the main arm forward and backward swing axis, the terminal rotation axis, etc. For each rotation axis, an inertial measurement unit, a joint position sensor, and a joint force sensor are provided, wherein the inertial measurement unit is used to detect the instantaneous acceleration and instantaneous angular velocity of the joint, and the joint position sensor is used to measure the angle or position of the joint as action and posture data.

[0060] Tactile force sensors and end-effector force sensors are both on the end-effector and are only used for force control and force feedback during grasping tasks. Similarly, temperature sensors are not included in the scope of motion path, motion and posture control and force / torque control.

[0061] Joint force sensors are used to detect force and torque. During actual detection, the instantaneous acceleration, instantaneous angular velocity, force, torque and joint angle at the six joints are stored as a 5*6 matrix and input into the neural network algorithm model.

[0062] In the specific implementation process, obtaining the type of the items to be transported can be achieved through the following steps: obtaining label information, wherein the label information is the barcode or RFID scan information of the packaging of the items; and determining the type of the items based on the label information.

[0063] In this solution, in automated handling scenarios, especially when dangerous goods such as explosives are involved, accurate identification of the type of items is essential for safe operation. By obtaining label information (such as barcodes or RFID tags) and analyzing this information, the six-axis robot can determine the specific type of items. By combining barcode and RFID technology, the robot can intelligently identify the type of items and take appropriate handling measures, greatly improving the efficiency and safety of handling.

[0064] Specifically, the six-axis robot is equipped with a barcode reader or RFID reader, which can scan the barcode or RFID tag on the surface of the object. The reader converts the signal on the tag into readable information, including but not limited to the name, type, manufacturer, production date, expiration date, and specific handling and transportation instructions of the object. Through the decoded tag information, the robot's control system can identify the type of object and call the corresponding handling strategy and parameters according to the type, such as handling speed, force control, and specific safety measures.

[0065] Specifically, in a warehouse for explosives, a six-axis robot is equipped with an RFID reader and a barcode scanner. When the robot is ready to carry a box containing explosives, its RFID reader first scans the RFID tag on the box to obtain the type of explosives, packaging information, and safe handling parameters. The barcode scanner reads the barcode to confirm the batch and expiration date of the explosives. Based on this information, the robot's control system adjusts the handling strategy, such as slowing down the handling speed, reducing the gripping force, and optimizing the handling path to avoid other objects and people to ensure safety during the handling process. In a chemical factory, the six-axis robot is tasked with carrying a series of barrels of raw materials that may contain explosives. Each barrel of raw materials is affixed with a barcode and RFID tag, which records the name of the chemical, the hazard level, and the handling requirements. Before grabbing each barrel, the robot first obtains this information through the barcode reader and RFID reader, and then adjusts its movement posture according to the hazard level of the chemical, such as using a more stable arm posture to carry chemicals with high hazard levels to ensure smooth and safe operation.

[0066] During the specific implementation process, before controlling the six-axis robot to use the target motion information to move the above-mentioned items, the above-mentioned method also includes the following steps: obtaining relevant information, wherein the above-mentioned relevant information at least includes one or more of the position of the above-mentioned six-axis robot, the speed of the above-mentioned six-axis robot, the weight of the above-mentioned items, the size of the above-mentioned items, the position of the obstacle, the safety distance and the warehouse position; determining the above-mentioned target motion information based on the above-mentioned relevant information.

[0067] In this solution, during the process of automated logistics or dangerous goods handling, the six-axis robot needs to obtain a series of relevant information to ensure that its handling action is both efficient and safe. This information includes but is not limited to the robot's own position and speed, the weight and size of the items to be handled, the location of obstacles in the surrounding environment, the safety distance, and the specific location of the warehouse or destination. By analyzing and integrating this information, the robot can determine its target motion information, that is, the path information, action posture information, and force information followed when handling items, ensuring that the handling process is both smooth and safe.

[0068] Specifically, the position and speed information of the robot can be obtained through the built-in position sensor and speed sensor to ensure the precise control of the robot during the handling process. The weight and size information of the item can be obtained through the weighing sensor and the dimension measurement sensor before handling. This information is essential for calculating the handling force and selecting the handling posture. Obstacle location information is obtained through environmental sensors (such as lidar, ultrasonic sensors, etc.), and the safe distance from the obstacle is measured through the distance sensor. This information is used to plan the handling path of the robot to avoid collisions and risks. The specific location of the warehouse or destination is obtained through GPS or indoor positioning system to determine the final goal of the handling.

[0069] Specifically, by analyzing the weight, size and type of the items, the robot's gripping point, gripping force and handling posture are determined to ensure the stability of the handling process. Based on the obstacle position and safety distance information obtained by the environmental perception sensor, a path planning algorithm (such as A* algorithm, RRT algorithm, etc.) is used to generate the optimal path for obstacle avoidance, while taking into account handling efficiency and safety. By communicating with the warehouse management system, the detailed layout of the warehouse and the destination location are obtained to ensure the optimization of the handling path and avoid unnecessary movement and collision.

[0070] Specifically, if a new obstacle is detected or the safe distance changes during the handling process, the robot arm should be able to adjust its path in real time to avoid risks. According to the dynamic changes of the objects during the handling process (such as slight differences in weight) and environmental changes (such as changes in ground friction), the robot arm should be able to adjust its strength and speed in real time to ensure the safety and stability of the handling process. The control system of the robot arm should have a feedback mechanism that can monitor various parameters in the handling process, such as speed, strength, and object position, in real time, and make necessary adjustments based on the feedback information to improve the accuracy and safety of the handling.

[0071] For example, in an industrial automated warehouse, a six-axis robot needs to carry a chemical raw material barrel weighing 50kg and measuring 60x40x30cm from one storage area to another. The robot first obtains its current position and speed to ensure smooth acceleration from the initial position; then, it confirms the weight of the raw material barrel through a weighing sensor and obtains its specific size through a dimension measurement sensor to determine the gripping point and handling posture; then, the robot uses a lidar sensor to scan the surrounding environment, identify and avoid other objects and obstacles, and determine a collision-free handling path; finally, the location of the destination warehouse is confirmed through the GPS positioning system. The entire handling process fully considers the weight, size and safety factors of the surrounding environment of the object, achieving efficient and safe handling.

[0072] During the specific implementation process, the above-mentioned target motion information is determined based on the above-mentioned relevant information, which can be achieved through the following steps: constructing an action generation model, wherein the above-mentioned action generation model is trained using multiple sets of training data, and each set of training data in the above-mentioned multiple sets of training data includes historical relevant information obtained within a historical time period and historical target motion information corresponding to the above-mentioned historical relevant information; inputting the above-mentioned relevant information into the above-mentioned action generation model to obtain the above-mentioned target motion information corresponding to the above-mentioned relevant information.

[0073] In this solution, the action generation model is trained through deep learning or machine learning algorithms, which can transform the complex decision-making process of robot operation and object handling into automatic analysis and response to input information. Specifically, the training data set consists of historical related information obtained in the historical time period and the corresponding historical target motion information. This information includes the position, speed, weight, size, location of obstacles, safety distance and warehouse location of the robot. Through the learning of a large amount of historical data, the model can identify the best actions that the robot should take in different scenarios. When a new handling task appears, the model uses the currently acquired relevant information as input and outputs the corresponding target motion information to guide the robot's handling operation. By building and applying the action generation model, the six-axis robot can realize intelligent and adaptive handling operations.

[0074] Specifically, the neural network model is a multi-task neural network model (i.e., an action generation model). The structure of the model has been described in Figure 4 As given in , its basic structure includes an input layer, a convolution layer, a pooling layer and a fully connected layer, wherein the input layer is a plurality of shared feature extraction tasks, corresponding to the input of motion and trajectory data, action and posture data and force / torque data respectively, and the convolution layer is the core part of the convolutional neural network. It uses convolution operation to extract image features. The convolution operation can be regarded as template matching: the convolution kernel slides on the image and calculates the sum of the product of the pixel value at each position and the weight in the convolution kernel. In the present invention, it specifically includes a motion and trajectory feature extraction unit, an action and posture feature extraction unit and a force / torque feature extraction unit. In the pooling layer, it is used to reduce the amount of calculation and the amount of parameters through the pooling operation. The pooling operation usually uses maximum pooling or average pooling, preferably maximum pooling. The fully connected layer is used to convert the features extracted by the convolution layer and the pooling layer into the final prediction result, which can specifically include the corresponding motion and trajectory prediction unit, action and posture prediction unit and force / torque prediction unit.

[0075] Specifically, in the neural network model (i.e., action generation model) of the present invention, the input layer learns the shared feature representations between the three tasks of motion and trajectory data, action and posture data, and force / torque data, and then extracts the shared features respectively through the convolution layer, and then performs pooling operations through the pooling layer, and then performs specific outputs for each task through the fully connected layer. Specifically, the data input by the input layer of the neural network model, i.e., learning motion and trajectory data, action and posture data, and force / torque data, needs to be provided by the sensor and image acquisition unit set on the six-axis sensor, wherein the image acquisition unit is one to two high-definition cameras for obtaining image information of the robot's surroundings to achieve functions such as target detection, object recognition, and posture estimation.

[0076] Specifically, in the technical solution of the six-axis robot arm of the present invention, the specific control process of the neural network algorithm model (i.e., the action generation model) in the motion planning and trajectory optimization control tasks of the six-axis robot arm can be summarized as follows:

[0077] First, collect training data. These data can be postures, trajectories, sensor measurements, etc. collected by the robot when performing a specific task. The data needs to be prepared in a format suitable for neural network training, usually in the form of input-output pairs. Next, it is necessary to design a neural network structure, and a multi-task convolutional neural network is used in this application. Then before the neural network training, the training data needs to be labeled. For motion planning and trajectory optimization tasks, the labeled data may include input states (current position of the robot, target position, etc.) and expected outputs (optimal motion trajectory). Then, the neural network is trained using the labeled data, and the neural network is enabled to learn the mapping relationship between input states and expected outputs by optimizing the loss function. After the training is completed, the trained neural network model needs to be evaluated. This includes using a validation set or a test set to evaluate the performance of the model, and tuning the model based on the evaluation results to improve its generalization ability and accuracy. When the neural network model is trained and passes the evaluation, it can be deployed in the actual six-axis robot control system. During operation, the current state of the robot (such as position, speed, etc.) is input into the neural network model to obtain the output result (such as the optimized motion trajectory), and then the output result is converted into control instructions and sent to the robot for execution.

[0078] In the technical solution of the six-axis robot arm of the present invention, the specific control process of the neural network algorithm model (i.e., the motion generation model) in the motion control and posture adjustment tasks of the six-axis robot arm can be summarized as follows:

[0079] Similarly, first, training data needs to be collected. This data can be the postures collected by the robot when performing various actions and adjusting postures, the measurement values ​​of force sensors, etc. Next, a multi-task convolutional neural network is used to learn the mapping relationship between input state and output action. Before training the neural network, the training data is labeled. For motion control and posture adjustment tasks, the labeled data may include input state (current robot posture, target posture, etc.) and expected output (action required to adjust the posture). Then, the neural network is trained using the labeled data to optimize the network parameters so that it can learn the mapping relationship between input state and expected output. After the training is completed, the trained neural network model needs to be evaluated. Use a validation set or a test set to evaluate the performance of the model, and tune the model based on the evaluation results to improve its generalization ability and accuracy. When the neural network model is trained and passes the evaluation, it can be deployed to the actual six-axis robot control system. At run time, the current state of the robot is input into the neural network model, the output result (action required to adjust the posture) is obtained, and then the output result is converted into a control instruction and sent to the robot for execution.

[0080] In the technical solution of the six-axis robot arm of the present invention, the specific control process of the neural network algorithm model (i.e., the action generation model) in the force and torque control task of the six-axis robot arm can be summarized as follows:

[0081] The first step is to collect training data, which includes the measurement values ​​of the force and torque sensors when the robot performs various actions, as well as the corresponding robot postures. Next, a multi-task convolutional neural network is used to learn the mapping relationship between the input state and the output control signal. Before training the neural network, the training data needs to be labeled. For force and torque control tasks, the labeled data may include input states (current posture of the robot, target force and torque, etc.) and expected outputs (control signals). Then, the neural network is trained using the labeled data to optimize the network parameters so that it can learn the mapping relationship between input states and expected outputs. After training, the trained neural network model needs to be evaluated. Use a validation set or a test set to evaluate the performance of the model, and tune the model based on the evaluation results to improve its generalization ability and accuracy. When the neural network model is trained and passes the evaluation, it can be deployed in the actual six-axis robot control system. At run time, the current state of the robot is input into the neural network model to obtain the output result (control signal), and then the output result is converted into a control instruction and sent to the robot to perform the force and torque control task.

[0082] Specifically, the process of building an action generation model involves the following key steps: data preprocessing, feature engineering, model selection and training, model evaluation and optimization, model deployment, and real-time application.

[0083] Data collection and preprocessing: Collect a large amount of historical operation data. This data should cover the scenarios of the robot moving different objects in various environments, including the position and speed of the robot, the weight and size of the objects, and the location of obstacles, safety distances, and warehouse locations in the environment. In the preprocessing stage, the data needs to be cleaned, normalized, and labeled to facilitate subsequent model training.

[0084] Feature engineering: Feature engineering is an important step in machine learning, which involves extracting features from raw data that are helpful for model training. In this scenario, the continuity and stability of the robot's operation, the efficiency and safety of object handling, and the accuracy and timeliness of environmental perception can be extracted as features for model training.

[0085] Model selection and training: Select a suitable machine learning or deep learning model, such as a neural network, decision tree, support vector machine (SVM), or reinforcement learning algorithm, for training. Model training is the process of adjusting model parameters to minimize prediction errors by taking historical relevant information as input and historical target motion information as output. During the training process, cross-validation, regularization, and other techniques can be used to prevent overfitting and ensure the generalization ability and prediction accuracy of the model.

[0086] Model evaluation and optimization: After the model training is completed, the model needs to be evaluated to check its performance on unseen data. If the model's prediction effect is not ideal, the performance of the model can be further improved by adjusting the model structure, adding training data, or optimizing the training algorithm.

[0087] Model deployment and real-time application: Deploy the trained model to the robot's control system. When a new handling task occurs, the robot obtains information about the current environment and objects, calculates the target motion information through the model, and performs the corresponding handling action. At the same time, the model should have online learning capabilities, and be able to continuously optimize and adjust itself according to the execution results of new tasks to improve the efficiency and safety of handling.

[0088] In some embodiments, when the above-mentioned relevant information includes the weight of the above-mentioned items and the size of the above-mentioned items, after controlling the six-axis robot arm to move the above-mentioned items using the target motion information, the above-mentioned method also includes the following steps: when the above-mentioned items have been transported to the warehouse, stacking the above-mentioned items in order from heavy to light weight and from large to small size; in the stacking process, acquiring image information of the stacking area; performing image recognition on the above-mentioned image information to determine whether the above-mentioned items are successfully stacked; in case the stacking of the above-mentioned items fails, generating a first warning information.

[0089] In this solution, after the six-axis robot completes the transportation of items to the designated warehouse, its next task is to stack the items in order of weight from heavy to light and size from large to small. If stacking fails, an early warning can be issued in time so that remedial measures can be taken to readjust the position of the items or restack them, thus achieving more efficient and safer warehouse management.

[0090] Specifically, the robot stacks the items in order according to their properties, such as weight and size. Heavier and larger items are stacked at the bottom first, and lighter and smaller items are placed at the top. This stacking order helps maintain the stability and safety of the stacking structure. During the stacking process, the robot's visual system will continue to obtain image information of the stacking area. This image information is processed by a dedicated image recognition algorithm to determine whether the items are successfully stacked in place. The image recognition algorithm analyzes the image of the stacking area, identifies the placement and stacking status of the items, and determines whether the items have been successfully stacked in the established order and position. If the recognition result shows that the item is successfully stacked, the robot will continue to carry and stack the next item. If the stacking of the item is found to fail during the image recognition process, such as the item is not placed in the correct position, the stacking structure is unstable, etc., the robot's control system will generate a first warning message to remind the operator or the control system to pay attention to the situation and take appropriate remedial measures, such as re-adjusting the position of the item or restacking it.

[0091] Specifically, the robot should be equipped with high-precision visual sensors, such as industrial cameras, to obtain image information of the stacking area in real time. The image recognition algorithm should be able to quickly and accurately identify the type, position and posture of the object, as well as the stability of the stacking structure. The robot needs to be able to process and memorize the attribute information such as weight and size of the object, as well as the order requirements when stacking, which is usually achieved through communication with the warehouse management system or other external databases. The stacking strategy should take into account the attributes of the object, the limitations of the stacking area, and the stability of the stacking structure. When stacking, the robot should be able to dynamically adjust the stacking order and placement method based on real-time object information and image feedback to ensure efficient and safe stacking. The early warning system should be able to monitor the stacking process in real time, and once a stacking failure is found, it will immediately generate early warning information and take corresponding countermeasures. The early warning information can be conveyed to the operator or central control system through visual, sound or wireless communication for rapid response and processing.

[0092] Specifically, the vision system of the six-axis robot, such as an industrial camera, continuously monitors the stacking area and collects images during the stacking process. These images may need to be preprocessed, including image enhancement, filtering, grayscale conversion, etc., to improve the clarity and contrast of the image for subsequent image recognition. Object detection algorithms (such as YOLO, Faster R-CNN, etc.) are used to locate the objects in the image and confirm the position and posture of the objects. Then, image recognition technology (such as convolutional neural network CNN in deep learning) is used to identify the type of object to ensure that each item can be correctly identified and classified. The results of object detection and recognition are compared with the expected attributes and stacking positions of the objects. For example, check whether the objects are stacked in order from heavy to light weight and from large to small size, and whether the objects are placed in the expected position and posture.

[0093] Specifically, the stability of the stacking structure is evaluated by analyzing the image of the stacking area. The alignment between stacking layers, the contact points between items, the tilt angle of items, etc. are detected to ensure that the stacking structure will not collapse due to factors such as gravity and friction. If the image analysis finds that the stacking of items has failed, such as the wrong placement of items, unstable stacking structure, etc., the control system of the robot arm should immediately stop the current operation and generate an early warning message. At the same time, the system should be able to propose adjustment plans based on the current stacking status, such as repositioning items, adjusting the stacking order, etc., to ensure successful stacking. After adjusting the stacking strategy, the robot arm should re-execute the stacking operation and verify the stacking results again through image recognition technology until it is confirmed that the items are successfully stacked.

[0094] For example, in a large automated warehouse, a six-axis robot is responsible for carrying and stacking different types of items in a designated area. During the stacking process, the robot's vision system continuously captures images of the stacking area and transmits the image information to the central control system in real time. The control system uses a deep learning algorithm to analyze the image and identify the stability of the stacking structure. For example, if after a certain stacking, the algorithm detects that the tilt angle of the upper object exceeds the safety threshold, or the object is not completely placed on the lower object, the stacking is judged to have failed. At this time, the system will immediately generate the first warning information, notifying the robot to stop the current operation, and send the warning information to the warehouse operator. The operator can view the specific stacking failure status on the central monitoring system and adjust the robot's stacking strategy in time, such as relocating the placement point or adjusting the order of the items to ensure the success of the stacking and the safety of the warehouse.

[0095] In some embodiments, in the process of controlling the six-axis robot to move the above-mentioned items using target motion information, the above-mentioned method also includes the following steps: obtaining a target distance, wherein the above-mentioned target distance is the distance between the above-mentioned six-axis robot and an obstacle; when the above-mentioned target distance is less than a preset safety distance, controlling the above-mentioned six-axis robot to stop moving.

[0096] In this solution, the safety control of the six-axis robot is crucial during the automated handling process. Among them, obtaining the target distance, that is, the distance between the six-axis robot and the surrounding obstacles, is a key link in ensuring the safety of handling. When the detected distance is less than the preset safety distance, the control system will immediately take measures to command the six-axis robot to stop handling to avoid possible collisions and damage, ensuring the safety of operators and equipment.

[0097] Specifically, advanced sensor technologies (such as LiDAR, ultrasonic sensors, etc.) are used to monitor the environment around the six-axis robot in real time to obtain distance information from obstacles. These sensors can provide high-precision measurement results and accurately identify obstacles even in complex environments. A safety distance threshold is preset in the control system. When the sensor detects that the distance to the obstacle is lower than this threshold, the control system triggers a safety response, which commands the robot to stop handling immediately until the obstacle is cleared or the robot is adjusted to a safe position.

[0098] Specifically, in addition to obtaining distance information, visual recognition technology or deep learning algorithms can also be used to detect and classify obstacles to identify their types and potential hazards. In this way, the robot can not only stop handling according to the distance information, but also adopt more specific obstacle avoidance strategies according to the characteristics of the obstacles. The preset safety distance can be fixed, but more advanced control strategies will adjust the safety distance in real time according to the size and weight of the objects being handled and the dynamic changes in the handling environment. For example, when carrying heavy objects or operating in a narrow space, the safety distance may need to be set smaller to ensure the safety and efficiency of the handling. Before approaching the preset safety distance, the control system of the robot can issue a safety warning in advance to notify the operator or adjust the handling path. In addition, path planning algorithms, such as the A* algorithm, the Dijkstra algorithm, etc., can be used to generate a safe path for the robot to avoid obstacles.

[0099] Specifically, a single sensor may be interfered or restricted in some cases. Therefore, multi-sensor fusion technology can be used to combine information from lidar, ultrasonic sensors, visual sensors, etc. to improve the accuracy and reliability of distance detection. By integrating a human-machine interaction interface into the robot control system, operators can monitor key parameters such as the robot's position, speed, distance to obstacles, and early warning information in real time. In this way, operators can intervene or adjust the robot's handling operation in a timely manner to improve the safety and controllability of the handling process.

[0100] For example, in an automated production line in an electronic component manufacturing plant, a six-axis robot is responsible for moving various components from one end of the production line to the other. To ensure the safety of the handling process, the robot is equipped with lidar and ultrasonic sensors for real-time monitoring of the surrounding environment. When the robot approaches the equipment on the production line or the handling pallet, the sensor continuously measures the distance between the robot and these obstacles. In the control system, a safety distance threshold is preset, such as 30 cm. Once the distance measured by the sensor is lower than this threshold, the control system will immediately trigger a safety response, commanding the robot to stop handling, and display a warning message on the human-computer interaction interface to alert the operator to potential collision risks. Based on the warning information, the operator can adjust the production line layout or the path of the robot to avoid collisions and ensure the continuity and safety of the production process.

[0101] In some embodiments, in the process of controlling the six-axis robot to move the above-mentioned items using target motion information, the above-mentioned method also includes the following steps: obtaining the temperature of the above-mentioned six-axis robot; when the above-mentioned temperature is greater than a preset threshold, turning on the cooling system to cool the above-mentioned six-axis robot, wherein the above-mentioned cooling system includes one or more of a fan, a coolant and a heat sink; when the turning-on time of the above-mentioned cooling system reaches the target duration, generating a second warning information, and controlling the above-mentioned six-axis robot to stop moving.

[0102] In this solution, during the operation of the six-axis robot, temperature management is a key link to ensure the performance and safe operation of the equipment. When the robot performs high-intensity or long-term handling tasks, its internal motors, drivers, electronic devices and other components may be damaged due to overheating, affecting the reliability and service life of the equipment. Therefore, it is a necessary preventive measure to monitor the temperature of the robot in real time and start the cooling system when the temperature exceeds the preset threshold. When the temperature monitoring system detects that the temperature of the six-axis robot exceeds the preset safety threshold, the cooling system will be activated to cool the robot through fans, coolant circulation or heat sinks, ensuring that when the risk of overheating occurs, the robot can quickly take measures to reduce the temperature and return to normal working state. In addition, in order to prevent the negative effects that may be caused by the long-term operation of the cooling system, such as coolant loss, fan wear, etc., when the cooling system is turned on for a target time, the control system will generate a second warning message and stop the handling operation of the six-axis robot until its temperature drops to a safe range. This mechanism not only protects the robot, but also avoids the waste of cooling resources and improves the overall management efficiency of the equipment.

[0103] Specifically, high-precision temperature sensors, such as thermocouples, infrared thermometers, etc., can be used to more accurately monitor the temperature of various parts of the robot. In addition, a temperature monitoring network can be designed to monitor the temperature of multiple key parts of the robot in real time to ensure comprehensive temperature management.

[0104] Specifically, the start and shut down of the cooling system can be linked with the temperature monitoring system to achieve intelligent control. For example, a PID (proportional-integral-differential) control algorithm can be used to adjust the cooling intensity of the cooling system according to temperature changes to control the temperature of the robot arm more efficiently and accurately.

[0105] Specifically, in addition to fans, coolant circulation and heat sinks, other cooling strategies such as heat pipes, phase change materials, etc. can also be considered to adapt to cooling requirements under different working environments and load conditions.

[0106] Specifically, the second warning information is not only used to stop the operation of the six-axis robot, but also can be used to notify maintenance personnel to check the status of the cooling system, such as whether the fan is blocked, whether the coolant needs to be replenished, etc., to prevent equipment failure.

[0107] Specifically, the temperature monitoring and cooling system is integrated with the robot's control system to achieve real-time monitoring and intelligent management of the equipment status. In addition, the robot's own thermal stability can be improved and the frequency of use of the cooling system can be reduced by optimizing the robot's structural design and material selection.

[0108] For example, in the paint shop of an automobile manufacturer, a six-axis robot is used to carry and paint car bodies. Since a lot of heat is emitted during the painting process, the robot is prone to overheating after a long period of operation. In order to ensure the safety of the equipment, the robot is equipped with a comprehensive thermal management system, including temperature sensors, cooling fans, coolant circulation systems and heat sinks. The control system presets a safety threshold for the operating temperature, such as 50°C. When the temperature sensor detects that the temperature of the robot exceeds this threshold, the cooling system automatically starts to cool the robot through the fan and coolant circulation. At the same time, the system sets a target cooling time. For example, after 30 minutes of continuous cooling, if the temperature still cannot be reduced to a safe range, the control system will generate a second warning message and stop the robot's handling operation until the temperature returns to normal. In this way, not only the safe operation of the robot in a high temperature environment is ensured, but also equipment damage and production interruption caused by overheating are avoided.

[0109] In summary, the existing algorithms are not optimized for the application scenarios of explosives, which leads to the possibility of collision with obstacles in the motion path, trajectory setting and posture control of the robot when multiple handling robots are working at the same time. Moreover, the motion control is not sophisticated and intelligent enough. For explosives that need to be handled with care, the safety is not high and there is no problem of automatically adjusting the force / torque of the end effector. Therefore, the solution adopted in this application is to share and separate specific task levels through a multi-task neural network to process multiple related tasks. The three tasks of trajectory data, motion and posture data, and force / torque data are then shared through the convolution layer. Feature extraction, and then after pooling through the pooling layer, the specific output of each task is performed through the fully connected layer and the result is converted into a control instruction.

[0110] The present application optimizes the motion and trajectory control, action and posture control, and force / torque control of the six-axis robot to prevent accidental collisions and scratches of the six-axis robot during operation, or safety issues that may be caused by excessive or insufficient clamping force of the end effector when picking up goods.

[0111] The embodiment of the present application also provides a device for transporting explosives. It should be noted that the device for transporting explosives in the embodiment of the present application can be used to execute the method for transporting explosives provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0112] The following is an introduction to the explosive material transporting device provided in the embodiments of the present application.

[0113] Figure 5 is a structural block diagram of an explosive material handling device according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0114] A first obtaining unit 10 is used to obtain the type of the object to be transported;

[0115] The first control unit 20 is used to control the six-axis robot to transport the above-mentioned items using target motion information when the above-mentioned type of the above-mentioned items to be transported is an explosive item, so as to transport the above-mentioned items smoothly, wherein the above-mentioned target motion information includes one or more of path information, action posture information and force information, the above-mentioned path information is the optimal path for transporting the above-mentioned items to avoid obstacles, the above-mentioned action posture information is the optimal posture of rotation, bending and extension of the above-mentioned six-axis robot, the above-mentioned force information is the target force applied when grasping, transporting and placing the above-mentioned items, and the above-mentioned target force is smaller than the force for transporting ordinary types of the above-mentioned items, and the above-mentioned explosive items are one or more of dynamite, detonators, gunpowder, fireworks and flour.

[0116] Through this embodiment, the motion planning control of the existing six-axis robot is mostly a general control logic, which is not optimized for the application scenario of explosives. In the solution of the present application, if the transported item is an explosive, the path of the robot must be specifically limited to avoid collision between the explosive and other obstacles. The movement posture must also be specifically limited to ensure stability during the transportation process. The force can also be limited to ensure that the explosive is handled with care, thereby improving safety and avoiding accidents during the transportation of explosives.

[0117] In the specific implementation process, the first acquisition unit includes an acquisition module and a determination module. The acquisition module is used to acquire label information, wherein the label information is the barcode or RFID scan information of the packaging of the above-mentioned item; the determination module is used to determine the above-mentioned type of the above-mentioned item based on the above-mentioned label information.

[0118] In this solution, in automated handling scenarios, especially when dangerous goods such as explosives are involved, accurate identification of the type of items is essential for safe operation. By obtaining label information (such as barcodes or RFID tags) and analyzing this information, the six-axis robot can determine the specific type of items. By combining barcode and RFID technology, the robot can intelligently identify the type of items and take appropriate handling measures, greatly improving the efficiency and safety of handling.

[0119] During the specific implementation process, the above-mentioned device also includes a second acquisition unit and a first determination unit. The second acquisition unit is used to acquire relevant information before controlling the six-axis robot to use the target motion information to move the above-mentioned items, wherein the above-mentioned relevant information at least includes one or more of the position of the above-mentioned six-axis robot, the speed of the above-mentioned six-axis robot, the weight of the above-mentioned items, the size of the above-mentioned items, the position of the obstacle, the safety distance and the warehouse position; the first determination unit is used to determine the above-mentioned target motion information based on the above-mentioned relevant information.

[0120] In this solution, during the process of automated logistics or dangerous goods handling, the six-axis robot needs to obtain a series of relevant information to ensure that its handling action is both efficient and safe. This information includes but is not limited to the robot's own position and speed, the weight and size of the items to be handled, the location of obstacles in the surrounding environment, the safety distance, and the specific location of the warehouse or destination. By analyzing and integrating this information, the robot can determine its target motion information, that is, the path information, action posture information, and force information followed when handling items, ensuring that the handling process is both smooth and safe.

[0121] During the specific implementation process, the first determination unit includes a construction module and a processing module. The construction module is used to construct an action generation model, wherein the above-mentioned action generation model is trained using multiple sets of training data, and each set of training data in the above-mentioned multiple sets of training data includes historical related information obtained within a historical time period and historical target motion information corresponding to the above-mentioned historical related information; the processing module is used to input the above-mentioned related information into the above-mentioned action generation model to obtain the above-mentioned target motion information corresponding to the above-mentioned related information.

[0122] In this solution, the action generation model is trained through deep learning or machine learning algorithms, which can transform the complex decision-making process of robot operation and object handling into automatic analysis and response to input information. Specifically, the training data set consists of historical related information obtained in the historical time period and the corresponding historical target motion information. This information includes the position, speed, weight, size, location of obstacles, safety distance and warehouse location of the robot. Through the learning of a large amount of historical data, the model can identify the best actions that the robot should take in different scenarios. When a new handling task appears, the model uses the currently acquired relevant information as input and outputs the corresponding target motion information to guide the robot's handling operation. By building and applying the action generation model, the six-axis robot can realize intelligent and adaptive handling operations.

[0123] In some embodiments, the above-mentioned device also includes a stacking unit, a third acquisition unit, a second determination unit and a generation unit. The stacking unit is used to stack the above-mentioned items in order of weight from heavy to light and size from large to small after controlling the six-axis robot arm to move the above-mentioned items using target motion information, when the above-mentioned relevant information includes the weight of the above-mentioned items and the size of the above-mentioned items, and when the above-mentioned items have been moved to the warehouse; the third acquisition unit is used to acquire image information of the stacking area during the stacking process; the second determination unit is used to perform image recognition on the above-mentioned image information to determine whether the above-mentioned items are stacked successfully; the generation unit is used to generate a first warning information when the stacking of the above-mentioned items fails.

[0124] In this solution, after the six-axis robot completes the transportation of items to the designated warehouse, its next task is to stack the items in order of weight from heavy to light and size from large to small. If stacking fails, an early warning can be issued in time so that remedial measures can be taken to readjust the position of the items or restack them, thus achieving more efficient and safer warehouse management.

[0125] In some embodiments, the above-mentioned device also includes a fourth acquisition unit and a second control unit, and the fourth acquisition unit is used to obtain the target distance in the process of controlling the six-axis robot to use the target motion information to move the above-mentioned items, wherein the above-mentioned target distance is the distance between the above-mentioned six-axis robot and the obstacle; the second control unit is used to control the above-mentioned six-axis robot to stop moving when the above-mentioned target distance is less than a preset safety distance.

[0126] In this solution, the safety control of the six-axis robot is crucial during the automated handling process. Among them, obtaining the target distance, that is, the distance between the six-axis robot and the surrounding obstacles, is a key link in ensuring the safety of handling. When the detected distance is less than the preset safety distance, the control system will immediately take measures to command the six-axis robot to stop handling to avoid possible collisions and damage, ensuring the safety of operators and equipment.

[0127] In some embodiments, the above-mentioned device also includes a fifth acquisition unit, a start unit and a third control unit. The fifth acquisition unit is used to obtain the temperature of the above-mentioned six-axis robot while controlling the six-axis robot to move the above-mentioned items using target motion information; the start unit is used to start the cooling system when the above-mentioned temperature is greater than a preset threshold value, so as to cool the above-mentioned six-axis robot, wherein the above-mentioned cooling system includes one or more of a fan, a coolant and a heat sink; the fifth acquisition unit is used to generate a second warning message when the start time of the above-mentioned cooling system reaches the target duration, and control the above-mentioned six-axis robot to stop moving.

[0128] In this solution, during the operation of the six-axis robot, temperature management is a key link to ensure the performance and safe operation of the equipment. When the robot performs high-intensity or long-term handling tasks, its internal motors, drivers, electronic devices and other components may be damaged due to overheating, affecting the reliability and service life of the equipment. Therefore, it is a necessary preventive measure to monitor the temperature of the robot in real time and start the cooling system when the temperature exceeds the preset threshold. When the temperature monitoring system detects that the temperature of the six-axis robot exceeds the preset safety threshold, the cooling system will be activated to cool the robot through fans, coolant circulation or heat sinks, ensuring that when the risk of overheating occurs, the robot can quickly take measures to reduce the temperature and return to normal working state. In addition, in order to prevent the negative effects that may be caused by the long-term operation of the cooling system, such as coolant loss, fan wear, etc., when the cooling system is turned on for a target time, the control system will generate a second warning message and stop the handling operation of the six-axis robot until its temperature drops to a safe range. This mechanism not only protects the robot, but also avoids the waste of cooling resources and improves the overall management efficiency of the equipment.

[0129] The explosive material handling device comprises a processor and a memory, wherein the first acquisition unit and the second control unit are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0130] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the kernel parameters can be adjusted to solve the problem that the current six-axis robot arm in the prior art cannot accurately and stably carry explosives according to the application scenario of explosives, which is prone to accidents.

[0131] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0132] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for transporting explosives.

[0133] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the program executes the method for transporting explosives when it is run.

[0134] The embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the steps of the method for transporting explosives are implemented. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0135] A computer program product includes a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for transporting explosives in each embodiment of the present application are implemented.

[0136] The present application also provides a six-axis robotic arm system, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the above-mentioned methods for handling explosives.

[0137] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0138] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0139] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0140] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0141] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0142] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0143] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0144] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0145] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0146] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0147] 1) The method for transporting explosives of the present application, the motion planning control of the existing six-axis robot arm is mostly a general control logic, and is not optimized for the application scenario of explosives. In the scheme of the present application, if the transported item is an explosive, the path of the robot arm must be specifically limited, so as to avoid collision between the explosive and other obstacles. The movement posture must also be specifically limited, so as to ensure stability during the transportation process. The force can also be limited, and the explosives must be handled with care to improve safety, thereby avoiding accidents during the transportation of explosives.

[0148] 2) The motion planning control of the existing six-axis robot for handling explosives in the present application is mostly a general control logic, which is not optimized for the application scenario of explosives. In the scheme of the present application, if the object being handled is an explosive, the path of the robot must be specifically limited to avoid collision between the explosive and other obstacles. The movement posture must also be specifically limited to ensure stability during the handling process. The force can also be limited to ensure that the explosive is handled with care, thereby improving safety and avoiding accidents during the handling of explosives.

[0149] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for transporting explosives, characterized in that: include: Get the type of items to be moved; In the case where the type of the item to be transported is an explosive item, the six-axis robot is controlled to transport the item using target motion information so that the item is transported smoothly, wherein the target motion information includes one or more of path information, motion posture information and force information, the path information is the optimal path for transporting the item to avoid obstacles, the motion posture information is the optimal posture of rotation, bending and extension of the six-axis robot, the force information is the target force applied when grasping, transporting and placing the item, and the target force is smaller than the force for transporting ordinary types of items, and the explosive item is one or more of dynamite, detonator, gunpowder, fireworks and flour.

2. The method according to claim 1, characterized in that Get the type of items to be moved, including: Acquiring label information, wherein the label information is information obtained by scanning a barcode or RFID on the packaging of the item; The type of the object is determined according to the tag information.

3. The method according to claim 1, characterized in that Before controlling the six-axis robot to carry the object using the target motion information, the method further includes: Acquiring relevant information, wherein the relevant information includes at least one or more of the position of the six-axis robot, the speed of the six-axis robot, the weight of the object, the size of the object, the position of the obstacle, the safety distance, and the warehouse position; The target motion information is determined according to the relevant information.

4. The method according to claim 3, characterized in that Determining the target motion information according to the relevant information includes: Constructing an action generation model, wherein the action generation model is trained using multiple sets of training data, each set of training data in the multiple sets of training data includes historical related information obtained within a historical time period and historical target motion information corresponding to the historical related information; The relevant information is input into the action generation model to obtain the target motion information corresponding to the relevant information.

5. The method according to claim 3, characterized in that: In a case where the relevant information includes the weight of the object and the size of the object, after controlling the six-axis robot to move the object using the target motion information, the method further includes: When the articles have been transported to the warehouse, the articles are stacked in order of weight from heavy to light and size from large to small; During the stacking process, image information of the stacking area is obtained; Performing image recognition on the image information to determine whether the objects are successfully stacked; In the case where the stacking of the objects fails, a first warning message is generated.

6. The method according to claim 1, characterized in that In the process of controlling the six-axis robot to carry the object using the target motion information, the method further includes: Acquire a target distance, wherein the target distance is the distance between the six-axis robot and an obstacle; When the target distance is less than the preset safety distance, the six-axis robot is controlled to stop carrying.

7. The method according to claim 1, characterized in that In the process of controlling the six-axis robot to carry the object using the target motion information, the method further includes: Obtaining the temperature of the six-axis robot; When the temperature is greater than a preset threshold, a cooling system is turned on to cool the six-axis robot, wherein the cooling system includes one or more of a fan, a coolant, and a heat sink; When the opening time of the cooling system reaches the target duration, a second warning message is generated, and the six-axis robot is controlled to stop carrying.

8. A device for transporting explosives, characterized in that: include: A first obtaining unit, used to obtain the type of the object to be transported; The first control unit is used to control the six-axis robot to carry the items using target motion information when the type of the items to be carried is an explosive item, so as to smoothly carry the items, wherein the target motion information includes one or more of path information, motion posture information and force information, the path information is an optimal path for carrying the items to avoid obstacles, the motion posture information is an optimal posture of rotation, bending and extension of the six-axis robot, the force information is a target force applied when grasping, carrying and placing the items, and the target force is less than the force for carrying ordinary types of items, and the explosive items are one or more of dynamite, detonators, gunpowder, fireworks and flour.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for transporting explosives according to any one of claims 1 to 7 are implemented.

10. A six-axis robot system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing the explosive material handling method described in any one of claims 1 to 7.

Images