Material shoveling method and system of loading machine, loading machine and electronic equipment

Through the hierarchical decision-making mechanism of the parent and child agents, the loader's adaptive shovel operation is realized, which solves the problem of insufficient accuracy and universality of shovel points in the existing technology, and improves the full bucket rate and adaptability.

CN119083513AActive Publication Date: 2024-12-06NETEASE LINGDONG (HANGZHOU) TECHNOLOGY CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411067830.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-12-06
Estimated Expiration
2044-08-05

AI Technical Summary

Technical Problem

The existing loader automatic shoveling algorithm has defects in the accuracy and versatility of shoveling points, resulting in low full bucket rate, especially for materials with higher hardness, it is difficult to track the shoveling track for effective shoveling operations.

Method used

The hierarchical decision-making mechanism of the parent and child agents is adopted. By monitoring the real-time operation status of the loader, adaptive sub-agents are dynamically called to control sub-actions to realize the adaptive shovel operation process and avoid tracking the fixed shovel trajectory.

Benefits of technology

It achieves a high full-bucket rate for various materials, improves the versatility and adaptability of shovel operations, and reduces the dependence on shovel points and material hardness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119083513A_ABST
    Figure CN119083513A_ABST
Patent Text Reader

Abstract

The invention discloses a material shoveling method and system of a loading machine, the loading machine, electronic equipment and a computer readable storage medium. The method comprises the following steps: in response to a shoveling instruction, starting a parent agent corresponding to shoveling operation; in response to monitoring that the operation state of the loader meets the calling condition of the first sub-agent at the first operation moment, the parent agent calls the first sub-agent and issues the first operation task to the first sub-agent; the first sub-agent determines a first control quantity of the first sub-action at the first operation moment according to the first operation task and the operation state at the first operation moment; the first sub-agent controls the loader to execute a first sub-action at a first control amount at a first operation time. By means of the method, the technical problems that in the prior art, due to the fact that a loader tracks a fixed material shoveling track to complete automatic material shoveling, the fullness rate is low, and universality is poor are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a shoveling method and system for a loader, a loader, an electronic device, and a computer-readable storage medium. Background Art

[0002] As an indispensable equipment in construction and resource mining, loaders often face extreme operating conditions. Unmanned operation has received widespread attention because it can reduce the safety risks of operators.

[0003] Shoveling is a very critical part of the loader's operation. At present, the unmanned shoveling operation of the loader usually relies on the automatic shoveling algorithm. The automatic shoveling algorithm completes the automatic shoveling by making the loader track a fixed shoveling track. In the application process, the automatic shoveling algorithm has the following defects: first, it has high requirements for the accuracy of the shoveling point. Once the shoveling point is not suitable, it is difficult to achieve a high full bucket rate; second, it is not universal. For materials with higher hardness, it is difficult for the loader to track the shoveling track.

[0004] Therefore, how to achieve a high full bucket rate for different materials has become a technical problem that needs to be solved urgently during the unmanned operation of loaders. Summary of the invention

[0005] The present application provides a loader shoveling method, system, loader, electronic device, and computer-readable storage medium to solve the technical problems existing in the prior art of low full bucket rate and poor versatility caused by completing automatic shoveling by making the loader track a fixed shoveling trajectory.

[0006] In a first aspect, an embodiment of the present application provides a shoveling method for a loader, the method comprising: in response to a shoveling instruction, starting a parent agent corresponding to the shoveling operation; wherein the shoveling operation includes multiple sub-actions, the parent agent corresponds to multiple callable sub-agents, each of the sub-agents has a preset calling condition, and the sub-agent is used to control the execution of at least one of the sub-actions after being called by the parent agent; in response to monitoring that the operating state of the loader meets the calling condition of the first sub-agent at a first operating moment, the parent agent calls the first sub-agent and sends the first operating task to the first sub-agent, and the first sub-agent is the first sub-agent for the multiple sub-agents that can be called The calling condition of the called sub-agent is one that meets the working state, the first working task is determined by the parent agent according to the working state at the first working moment and the first sub-agent, and the first working moment is any working moment in the process of the loader performing the shoveling operation; the first sub-agent determines the first control amount of the first sub-action at the first working moment according to the first working task and the working state at the first working moment, and the first sub-action is at least one of the sub-actions controlled and executed by the first sub-agent; the first sub-agent controls the loader to perform the first sub-action with the first control amount at the first working moment.

[0007] In a second aspect, an embodiment of the present application provides a shoveling system for a loader, the system comprising: a positioning module, a sensor module, a parent agent module, a child agent module, and an actuator module; the positioning module comprises at least a first sensor and a positioning algorithm, the first sensor being configured on the loader and being used to collect scene data of a working scene in which the loader is located at a first working moment, the positioning algorithm being used to calculate scene status information of the working scene based on the scene data, the first working moment being any working moment in the process of the loader performing the shoveling operation; the sensor module comprises a plurality of second sensors, the second sensors being used to collect the self-state information of the loader at the first working moment; the parent agent module comprises a parent agent, the parent agent being used to determine the working state of the loader at the first working moment based on the self-state information and the scene state information; the parent agent being used to monitor whether the working state of the loader at the first working moment meets the calling condition of the first child agent; the parent agent being used to call the first child agent when it is determined that the working state of the loader at the first working moment meets the calling condition of the first child agent; the parent agent being used to Determine a first operating task for the first sub-agent according to the operating state of the loader at the first operating moment; also used to send the first operating task to the first sub-agent, the first sub-agent is one of the multiple sub-agents included in the sub-agent module whose calling condition is consistent with the operating state; the sub-agent module includes multiple sub-agents, the first sub-agent is used to determine the control amount of a first sub-action at the first operating moment according to the first operating task and the operating state of the loader at the first operating moment, the first sub-action is at least one of the multiple sub-actions included in the shoveling operation that is controlled by the first sub-agent; also used to control the loader to perform the first sub-action with the first control amount through a first actuator at the first operating moment, the first actuator is at least one of the multiple actuators included in the actuator module that corresponds to the first sub-action; the actuator module includes multiple actuators, the multiple actuators are configured on the loader, the first actuator is used to be controlled by the first sub-agent so that the loader performs the first sub-action with the first control amount at the first operating moment.

[0008] In a third aspect, an embodiment of the present application provides a loader, which is equipped with the above-mentioned shoveling system.

[0009] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor; the memory is used to store one or more computer instructions; the processor is used to execute the one or more computer instructions to implement the above method.

[0010] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having one or more computer instructions stored thereon, which, when executed by a processor, executes the above method.

[0011] Compared with the prior art, the loader shoveling method provided by the present application decomposes the shoveling operation into multiple sub-actions, and a parent agent monitors the real-time operation status of the loader, and calls the sub-agent according to the calling conditions of each sub-agent, and the called sub-agent determines the control amount of the sub-action controlled by the sub-agent to control the loader to perform the corresponding sub-action with the control amount. The method realizes hierarchical decision-making on the loader shoveling operation through the parent agent calling different sub-agents and the sub-agent's decision on the sub-action control amount. In this method, a fixed shoveling trajectory is not tracked. The parent agent can adjust the called sub-agent according to the real-time operation status of the loader, and the sub-agent can also adjust the control amount of the sub-action according to the real-time operation status of the loader. Therefore, this is an adaptive operation process, which is not affected by the shoveling point and the hardness of the material, and can achieve a high full bucket rate for various materials. The technical problem of low full bucket rate and poor versatility caused by making the loader track a fixed shoveling trajectory to complete automatic shoveling in the prior art is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a schematic diagram of a shoveling trajectory when a shoveling operation is performed based on an automated shoveling algorithm provided in an embodiment of the present application;

[0013] Figure 2 is an application system diagram of the shoveling method of a loader provided in an embodiment of the present application;

[0014] Figure 3 is a flow chart of a shoveling method of a loader provided in the first embodiment of the present application;

[0015] Figure 4 is a schematic diagram of a shoveling system of a loader provided in a second embodiment of the present application;

[0016] Figure 5 is a structural schematic diagram of a loader provided in a third embodiment of the present application;

[0017] Figure 6 It is a schematic diagram of the structure of an electronic device provided in the fourth embodiment of the present application. DETAILED DESCRIPTION

[0018] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0019] The loader is an indispensable engineering equipment in engineering construction, and plays an irreplaceable role in the fields of construction and resource mining. At present, most of the loader operations are still carried out by experienced operators on the loader. The operating environment of the loader is often more extreme, with a lot of dust and extreme temperatures. At the same time, there is a risk of disasters such as landslides and mudslides. If the operator is in this environment for a long time, it will not only seriously affect his health, but also pose a great threat to his personal safety. Therefore, the unmanned operation of intelligent loaders has received widespread attention.

[0020] The operating tasks of a loader include excavation, loading, unloading, and shoveling. Shoveling is a very critical part of the loader's operating tasks. A higher full bucket rate can improve operating efficiency and reduce operating costs. In the traditional operation process, the shoveling operation is completed by the operator through the combined control of the boom, bucket, throttle, and brake. This involves the interaction between the bucket and the material. To achieve a high full bucket rate, the operator needs to have superb skills and experience. At present, in the unmanned operation process, the loader's shoveling operation mainly relies on the automatic shoveling algorithm. The automatic shoveling algorithm enables the loader to track a fixed shoveling trajectory, and the boom and bucket perform fixed shoveling actions to complete the automatic shoveling.

[0021] Figure 1 It is a schematic diagram of the shoveling trajectory when performing a shoveling operation based on an automated shoveling algorithm provided in an embodiment of the present application.

[0022] like Figure 1 As shown in the figure, the gray part represents the material, and the black line part represents the shoveling trajectory (i.e., the moving trajectory of the bucket tip during the shoveling process). The shoveling process includes three stages: Stage 1, controlling the loader to move forward a distance L1, so that the bucket tip moves from point P0 to point P1 along the shoveling trajectory (black line); Stage 2, controlling the bucket to flip upward, and at the same time controlling the loader to continue to move forward a distance L2 in coordination with the bucket's flipping action, so that the bucket tip moves from point P1 to point P2 along the shoveling trajectory (black line), at this time, the bucket flips to a horizontal state; Stage 3, controlling the boom to lift upward, so that the bucket tip moves from point P2 along the shoveling trajectory (black line) to the outside of the material, and the shoveling process ends.

[0023] The automatic shoveling algorithm has the following defects: First, it requires a high accuracy of the shoveling point. Once the shoveling point is not appropriate, it is difficult to achieve a high full bucket rate. Figure 1As shown in the figure, when the sensed shoveling point is to the left of point P0 (such as P3), since the loader moves forward by a distance of L1 in stage 1, the tip of the bucket cannot reach point P1. In the subsequent stage 2, the amount of material that can enter the bucket through the bucket flip will decrease, and the full bucket rate will decrease. Second, it is not universal. For materials with higher hardness, it is difficult for the loader to track the shoveling trajectory. Figure 1 As shown in the figure, when the hardness of the material is high, the loader cannot be controlled to move forward by a distance L1 in stage 1, and the shoveling trajectory (black line) cannot be tracked, so the shoveling operation for the material cannot be completed. Therefore, there is an urgent need for an adaptable and robust shoveling method to achieve a high full bucket rate for different materials.

[0024] In view of this, the present application provides a loader shoveling method, which decomposes the shoveling operation into multiple sub-actions, and a parent agent monitors the real-time operation status of the loader, and calls the sub-agent according to the calling conditions of each sub-agent, and the called sub-agent decides the control amount of the sub-action controlled by the sub-agent to control the loader to perform the corresponding sub-action with the control amount. The method realizes hierarchical decision-making on the loader shoveling operation through the parent agent calling different sub-agents and the sub-agent's decision on the sub-action control amount. In this method, a fixed shoveling trajectory is not tracked. The parent agent can adjust the called sub-agent according to the real-time operation status of the loader, and the sub-agent can also adjust the control amount of the sub-action according to the real-time operation status of the loader. Therefore, this is an adaptive automatic operation process, which will not be affected by the shoveling point and the hardness of the material, and can achieve a high full bucket rate for various materials.

[0025] The loader shoveling method, system, device, electronic device, and computer-readable storage medium described in the present application are further described in detail below in conjunction with specific embodiments and drawings.

[0026] Figure 2 1 is an application system diagram of the shoveling method of the loader provided in the embodiment of the present application. Figure 2 As shown, the system includes a loader end 201 and a server end 202. The loader end 201 includes at least a loader and sensors deployed thereon. The sensors are used to capture scene status information of the operation scene and the loader's own status information. The server end 202 can be a processing device electrically connected to the loader end 201. The processing device can be deployed on the loader, or it can be a server connected to multiple loader ends 201 in communication, on which the loader shoveling method provided by the present application is deployed. When the server end 202 receives a shoveling instruction, it controls the loader to perform a shoveling action based on the method.

[0027] The first embodiment of the present application provides a shoveling method for a loader. The method realizes automatic adaptive shoveling of an unmanned loader based on the hierarchical decision-making principle, ensuring a high full bucket rate for various types of materials.

[0028] Figure 3 Flow chart of the shoveling method of the loader provided in this embodiment. Figure 3 The shoveling method of the loader provided in this embodiment is described in detail. The embodiments described below are used to explain the technical solution of this application and are not intended to be used as limitations for actual use.

[0029] like Figure 3 As shown, the shoveling method of a loader provided in this embodiment includes the following steps S310 to S340:

[0030] Step S310, in response to the shoveling instruction, start the parent agent corresponding to the shoveling operation; wherein the shoveling operation includes multiple sub-actions, the parent agent corresponds to multiple sub-agents that can be called, each sub-agent has a preset calling condition, and the sub-agent is used to control the execution of at least one sub-action after being called by the parent agent.

[0031] Step S320, in response to monitoring that the operating status of the loader meets the calling conditions of the first sub-agent at the first operating moment, the parent agent calls the first sub-agent and sends the first operating task to the first sub-agent. The first sub-agent is one of the multiple sub-agents that can be called whose calling conditions meet the operating status. The first operating task is determined by the parent agent based on the operating status at the first operating moment and the first sub-agent. The first operating moment is any operating moment during the loader's shoveling operation.

[0032] Step S330, the first sub-agent determines a first control amount of a first sub-action at the first working moment according to the first working task and the working status at the first working moment, wherein the first sub-action is at least one sub-action executed under the control of the first sub-agent.

[0033] Step S340: the first sub-agent controls the loader to perform a first sub-action with a first control amount at a first operation time.

[0034] In a specific implementation, the above method is performed by Figure 2The server 202 shown is executed, and the server 202 is deployed with the shoveling method of the loader provided in this embodiment, and also deployed with a parent agent and multiple child agents that can be called by the parent agent. The parent agent completes the shoveling operation by calling the child agents. Exemplarily, after the bucket of the loader touches the ground, the parent agent will first call the child agent A (responsible for straightening the loader) to ensure the safety of the shoveling action; to prevent the loader from being too close to the wall and causing safety problems, the parent agent monitors the distance between the vehicle and the wall in real time based on the acquired positioning information and map information, and when the distance is less than 0.5 meters, it will call the child agent B (responsible for suppressing the throttle output and adjusting the brake size according to the distance).

[0035] In a specific implementation, the parent agent can be an application program edited by a developer, which at least includes a method for monitoring the operating status of the loader, a method for calling the sub-agent, and the preset calling conditions of each sub-agent. Specifically, when the loader performs the shoveling operation, the parent agent monitors the operating status of the loader at each operating moment in real time, and judges whether the operating status of the loader meets the calling conditions of a certain sub-agent based on the calling conditions of each sub-agent. When it is determined that the operating status of the loader meets the calling conditions of a certain sub-agent, the parent agent will call the sub-agent according to the calling method. The sub-agent has multiple implementation methods, such as: neural network models obtained based on machine learning, traditional logic control methods, etc. Different sub-agents can set one or more implementation methods to realize their functions according to their operating tasks in the shoveling operation and the sub-actions of control execution. After the child agent is called by the parent agent, the sub-action control amount can be calculated according to its implementation method. For example, the mobile sub-agent includes a path planning model and a path tracking model. When the parent agent calls the mobile sub-agent, the mobile sub-agent can calculate the moving path of the loader to the shoveling point based on the path planning model, and based on the path tracking model, the loader's real-time operating status and moving path are used as input data to output the best throttle sub-action control amount, steering sub-action control amount, brake sub-action control amount, etc. in real time. The specific implementation methods of the parent agent and the child agent are not limited here.

[0036] The following is a detailed description of the above steps:

[0037] For step S310:

[0038] In this step, the server responds to the shoveling instruction and starts the parent agent corresponding to the shoveling operation.

[0039] The shoveling instruction can be understood as a kind of control information, which is used to convey to the server the need to control the loader to perform shoveling operations. The shoveling instruction can be sent by the operator to the server based on the remote control terminal, or generated and sent to the server by the client in response to the operator's triggering operation of the shoveling operation control, or automatically generated and sent to the server by the loader through the sensor to sense that a shoveling operation is to be performed, without specific restrictions. The shoveling instruction can include specific information related to the shoveling operation, such as: location information of the shoveling point, type information of the material, number of tasks for the shoveling operation, etc.

[0040] The shoveling operation refers to the process in which the loader moves to the shoveling point and shovels materials (such as soil, sand, coal, lime, ore, etc.) into the bucket, which includes a series of coherent actions, such as the vehicle body approaching the material, the bucket inserting the material, the bucket closing and loading the material, the arm raising and filling the bucket, etc. These actions are all achieved by the coordinated cooperation of several basic sub-actions. In this embodiment, the shoveling operation is divided into basic sub-actions so that the sub-agents called by the parent agent can directly control the execution of these sub-actions to achieve a more adaptable shoveling operation. Exemplarily, the shoveling operation includes throttle sub-actions, brake sub-actions, steering sub-actions, boom lifting sub-actions, bucket flipping sub-actions, etc.

[0041] In this embodiment, the sub-agent that can be called by the parent agent is determined by the specific work content included in the shoveling operation, and the increase or decrease of the work content can be achieved by adding or removing the sub-agent corresponding to the work content. Exemplarily, under normal circumstances, the work content of the shoveling operation includes moving the vehicle body and shoveling. The moving vehicle body can be achieved by the cooperation of the moving sub-agent and the safety sub-agent, and the shoveling can be achieved by the cooperation of the power sub-agent, the arm sub-agent, the bucket sub-agent, and the safety sub-agent. When the work content of shaking the material shoveled into the bucket is added in the shoveling operation, it is only necessary to add the bucket shaking sub-agent so that the bucket shaking sub-agent controls the execution of the bucket rotation sub-action. Therefore, the method provided in this embodiment can freely increase or decrease sub-agents according to the actual work content of the shoveling operation, and the deployment is more flexible. In an optional implementation method, adding a sub-agent needs to be registered with the parent agent. Specifically, the calling conditions of the added sub-agent are set in the parent agent.

[0042] The calling condition can be understood as the triggering condition for the parent agent to call the child agent, which can include the state condition of the loader itself, the scene state condition of the working scene where the loader is located, and the completion condition of the pre-action, etc., which needs to be determined according to the working content of the child agent and the sub-action controlled by the child agent. For example, the calling condition of the bucket sub-agent can be that the loader has moved to the vicinity of the shoveling point, for example, the distance between the loader and the shoveling point is less than 6 meters; the calling condition of the power sub-agent can be that the loader has reached the shoveling point and the bucket has been attached to the ground; the calling condition of the bucket shaking sub-agent can be that the bucket has flipped to a horizontal state and the throttle sub-action has ended.

[0043] In this embodiment, there is not a one-to-one correspondence between sub-agents and sub-actions. One sub-agent can control the execution of multiple sub-actions, and one sub-action can also be controlled by multiple sub-agents. For example, the sub-actions controlled by the mobile sub-agent may include throttle sub-actions, brake sub-actions, and steering sub-actions, and the throttle sub-action is also controlled by the power sub-agent, and the brake sub-action is also controlled by the safety sub-agent.

[0044] For step S320:

[0045] In this step, in response to monitoring that the operating status of the loader meets the calling conditions of the first sub-agent at the first operating moment, the parent agent calls the first sub-agent and sends the first operating task to the first sub-agent.

[0046] After the parent agent is started, it can monitor the operating status of the loader in real time, determine whether the operating status meets the calling conditions of a certain child agent, and if so, call the child agent and send the operating task to the child agent. In this embodiment, the first operating moment represents any operating moment in the process of the loader performing the shoveling operation, the first child agent represents a child agent whose calling conditions meet the operating status among multiple child agents that can be called by the parent agent, and the first operating task represents the operating task sent to the first child agent at the first operating moment. Specifically, when the parent agent detects that the operating status of the loader at the first operating moment meets the calling conditions of the first child agent, the first child agent is called and the first operating task is sent to the first child agent.

[0047] The operation time can be understood as the time node in the process of the loader performing the shoveling operation. The time node can be set manually, for example: taking 1 second as a time node, then a 10-minute shoveling operation will include 600 operation moments. In this embodiment, the time node is determined by the monitoring frequency of the parent agent, that is, each monitoring moment of the parent agent is taken as a time node. The higher the monitoring frequency of the parent agent, the denser the time nodes, and the shorter the time interval between the time nodes. Exemplarily, the monitoring frequency of the parent agent is 10 Hz, that is, the parent agent will monitor the operation status of the loader once every 0.1 second during the shoveling operation. Then, 1 second will include 10 time nodes, and a 10-minute shoveling operation will include 6000 operation moments.

[0048] The operation task is determined by the parent agent according to the called sub-agent and the operation status of the loader when the sub-agent is called. After the operation task is sent to the sub-agent, the sub-agent will make decisions on the sub-action control amount with the goal of completing the operation task until the sub-agent is stopped. For example, after the parent agent is started, it detects that the current position of the loader is point A, and the position of the shovel point is point B, then the mobile sub-agent is called, and the operation task (moving the loader from point A to point B) is sent to the mobile sub-agent.

[0049] For step S330:

[0050] In this step, the first sub-agent determines the first control amount of the first sub-action at the first working moment according to the first working task and the working status at the first working moment.

[0051] After the first sub-agent is called by the parent agent, it will decide the control amount of the sub-action controlled and executed by the first sub-agent based on the job task issued by the parent agent and the job status. In this embodiment, the sub-action controlled and executed by the first sub-agent is defined as the first sub-action, and the control amount of the first sub-action determined at the first job moment is defined as the first control amount.

[0052] The control amount of the sub-action is decided autonomously by each sub-agent. The implementation forms of the sub-agent are different, and the decision-making methods are also different. Exemplarily, the implementation form of the mobile sub-agent is a path planning model and a path tracking model. Both models are pre-trained neural network models. The path planning model can decide the movement path of the loader to the shoveling point based on the current position of the loader, the position of the shoveling point, and the map of the working scene. The path tracking model can use the loader's working state and moving path as input data to output the optimal control amount of the throttle sub-action, the control amount of the steering sub-action, and the control amount of the brake sub-action, that is, the mobile sub-agent decides the control amount of the sub-action based on the neural network model.

[0053] For step S340:

[0054] In this step, the first sub-agent controls the loader to perform the first sub-action with the first control amount at the first operation moment.

[0055] After the first sub-agent determines the first control amount of the first sub-action at the first operation moment, it will control the loader to perform the first sub-action with the first control amount. Specifically, the first sub-agent controls the loader to perform the first sub-action through an actuator configured on the loader. Exemplarily, the first sub-action is an accelerator sub-action, a brake sub-action, and a steering sub-action. Then, the first sub-agent controls the loader to perform the first sub-action through the accelerator pedal, brake pedal, and steering wheel of the loader.

[0056] In a specific implementation, the sub-agent outputs the control quantity of the sub-action decided in the form of a PWM (Pulse Width Modulation) signal to the actuator corresponding to the sub-action, so as to realize automatic and precise control of the sub-action.

[0057] Through the above steps, the loader is controlled to complete the work content at a certain working moment during the shoveling operation. Based on this method, the loader is controlled to complete the work content at each working moment, so that the shoveling operation can be completed.

[0058] In the method provided in this embodiment, after the first sub-agent determines the control amount of the first sub-action at the first operating moment (the operating moment when the first sub-agent is called), the decision-making process will not be stopped. Instead, the control amount of the first sub-action at each subsequent operating moment will be determined based on the real-time operating status of the loader until the first operating task is completed.

[0059] Based on this, in an optional implementation, the method provided in this embodiment may further include the following steps S351 to S352:

[0060] Step S351, the first sub-agent determines the second control amount of the first sub-action at the second working moment according to the first working task and the working status at the second working moment, and the second working moment includes every working moment after the first working moment.

[0061] Step S352: the first sub-agent controls the loader to perform the first sub-action with the second control amount at the second operation time.

[0062] In this embodiment, the second operating moment represents each operating moment after the first operating moment, and the second control amount represents the control amount of the first sub-action decided by the first sub-agent at the second operating moment. That is, after the first sub-agent determines the first control amount of the first sub-action at the first operating moment, and controls the loader to perform the first sub-action with the first control amount at the first operating moment, the first sub-agent will continue to determine the second control amount of the first sub-action at each subsequent operating moment according to the real-time operating status of the loader at each subsequent operating moment, and control the loader to perform the first sub-action with the corresponding second control amount at each subsequent operating moment.

[0063] Exemplarily, the mobile sub-agent decides the first control amount of the first sub-action according to the first working task and the working status at time T0 (the first working moment): throttle sub-action 50% (in this example, for ease of understanding, the control amount of the throttle sub-action / brake sub-action is represented by the pressing amplitude of the accelerator pedal / brake pedal), brake sub-action 0, steering sub-action 0 (in this example, for ease of understanding, the control amount of the steering sub-action is represented by the turning angle of the steering wheel). At time T0, the mobile sub-agent controls the loader to perform the first sub-action with the above-mentioned first control amount through the accelerator pedal, brake pedal, and steering wheel to accelerate and go straight. The mobile sub-agent decides the second control amount of the first sub-action according to the first working task and the working status at time T1 (the second working moment): throttle sub-action 0, The brake sub-action is 0, and the steering sub-action is to turn left 30 degrees. At time T1, the mobile sub-agent controls the loader through the accelerator pedal, brake pedal, and steering wheel to execute the first sub-action with the above-mentioned second control amount to achieve deceleration and turning; the mobile sub-agent decides the second control amount of the first sub-action according to the first operation task and the operation status at time T2 (the second operation moment): throttle sub-action 0, brake sub-action 50%, and steering sub-action 0 degrees. At time T2, the mobile sub-agent controls the loader through the accelerator pedal, brake pedal, and steering wheel to execute the first sub-action with the above-mentioned second control amount to achieve deceleration and straight driving; the mobile sub-agent continues to make decisions on the control amount of the first sub-action and control the loader at each subsequent operation moment until the loader reaches the shoveling point or the mobile sub-agent stops being called by the parent agent.

[0064] In the method provided in this embodiment, after the parent agent monitors the operating status of the loader at the first operating moment and calls the first child agent, it will not stop the monitoring process and the calling process. It will determine whether there is a child agent that can be called at each subsequent operating moment based on the real-time operating status of the loader. If so, the child agent will be called to enable the child agent to execute the operating task issued to the child agent by the parent agent while the first child agent executes the first operating task.

[0065] Based on this, in an optional implementation, the method provided in this embodiment may further include the following steps S361 to S364:

[0066] Step S361, in response to monitoring that the operating status of the loader meets the calling conditions of the second sub-agent at the third operating time, the parent agent calls the second sub-agent and sends the second operating task to the second sub-agent. The second sub-agent is any one of the multiple callable sub-agents that is in an uncalled state before the third operating time. The second operating task is determined by the parent agent based on the operating status at the third operating time and the second sub-agent. The third operating time is any operating time after the first operating time.

[0067] Step S362, the second sub-agent determines a third control amount of a second sub-action at a third working moment according to the second working task and the working state at a third working moment, wherein the second sub-action is at least one sub-action controlled by the second sub-agent;

[0068] Step S363, the first sub-agent determines a fourth control amount of the first sub-action at the third working moment according to the first working task and the working state at the third working moment;

[0069] Step S364, the second sub-agent controls the loader to perform the second sub-action with the third control amount at the third operating time; and / or, the first sub-agent controls the loader to perform the first sub-action with the fourth control amount at the third operating time.

[0070] In this embodiment, the third operation time represents any operation time of calling a sub-agent after the first operation time, and the second sub-agent represents the sub-agent called at the third operation time. The sub-agent can be any one of multiple sub-agents that can be called by the parent agent and is in an uncalled state before the third operation time.

[0071] When the parent agent detects that the current operating state of the loader meets the calling condition of the second sub-agent at the third operating moment, the second sub-agent will be called, and the operating task that needs to be completed by the second sub-agent will be sent to the second sub-agent. In this embodiment, the operating task sent to the second sub-agent is defined as the second operating task. After the second sub-agent is called by the parent agent, it will decide the control amount of the sub-action controlled and executed by the second sub-agent according to the second operating task issued by the parent agent and the operating state. In this embodiment, the sub-action controlled and executed by the second sub-agent is defined as the second sub-action, and the control amount of the second sub-action determined at the third operating moment is defined as the third control amount. Since the first sub-agent is in the called state at the third operating moment, the first sub-agent will also determine the control amount of the first sub-action at the third operating moment according to the first operating task and the operating state at the third operating moment. In this embodiment, the control amount of the first sub-action at the third operating moment is defined as the fourth control amount. After the first sub-agent and the second sub-agent respectively decide the control amount of the corresponding sub-action, they will control the loader to execute the corresponding sub-action.

[0072] In an optional implementation, the first sub-agent and the second sub-agent can synchronously control the loader to perform corresponding sub-actions, that is, the second sub-agent controls the loader to perform the second sub-action with the third control amount at the third operating moment, and the first sub-agent controls the loader to perform the first sub-action with the fourth control amount at the third operating moment. Specifically, when the first sub-action executed by the first sub-agent control and the second sub-action executed by the second sub-agent control are not repeated and do not conflict, the first sub-action and the second sub-action can be executed synchronously. Exemplarily, in the process of the parent agent calling the mobile sub-agent to control the loader to move to the shoveling point, when the distance between the loader and the shoveling point is less than 6 meters, the parent agent will call the upper arm sub-agent and the bucket sub-agent to control the bucket of the loader to fit the ground. Since the sub-actions controlled and executed by the mobile sub-agent are the throttle sub-action, the brake sub-action, and the steering sub-action, the sub-action controlled and executed by the boom sub-agent is the boom lifting and lowering sub-action, and the sub-action controlled and executed by the bucket sub-agent is the bucket flipping sub-action, therefore, when the mobile sub-agent decides the control amount A of the throttle sub-action, the control amount B of the brake sub-action, and the control amount C of the steering sub-action, the boom sub-agent decides the control amount D of the boom lifting and lowering sub-action, and the bucket sub-agent decides the control amount E of the bucket flipping sub-action, since there is no duplication or conflict between these sub-actions, the mobile sub-agent, the boom sub-agent, and the bucket sub-agent can simultaneously control the loader to execute the throttle sub-action with control amount A, the brake sub-action with control amount B, the steering sub-action with control amount C, the boom lifting and lowering sub-action with control amount D, and the bucket flipping sub-action with control amount E.

[0073] In another optional implementation, the first sub-agent and the second sub-agent can only choose to perform one of the control of the loader, that is, the second sub-agent controls the loader to perform the second sub-action with the third control amount at the third working moment, or the first sub-agent controls the loader to perform the first sub-action with the fourth control amount at the third working moment. How to determine whether to choose to control the loader by the first sub-agent or the second sub-agent at the third working moment is planned in advance by the parent agent, that is, the parent agent also deploys a screening method for sub-agent synchronization. Exemplarily, in the process of the parent agent calling the mobile sub-agent to control the loader to move to the shoveling point, in order to ensure the safety of the moving process, the safety sub-agent will also be called. The safety sub-agent senses whether there are obstacles in the working environment through the sensors set on the loader in real time, and judges whether it will hit the obstacle according to the moving direction, speed, and steering angle of the loader. When the safety sub-agent determines that there is a risk of hitting an obstacle, it will output the control amount of the throttle sub-action and the brake sub-action to reduce the moving speed of the loader or stop the movement of the loader. Assume that at the third operation moment, the safety sub-agent decides the control amount F of the throttle sub-action, the control amount G of the brake sub-action, and the mobile sub-agent decides the control amount A of the throttle sub-action, the control amount B of the brake sub-action, and the control amount C of the steering sub-action. Since the sub-actions controlled and executed by the safety sub-agent and the sub-actions controlled and executed by the mobile sub-agent are repeated, the safety sub-agent and the mobile sub-agent cannot control the loader to execute the above sub-actions at the same time. Based on the screening method when the mobile sub-agent and the safety sub-agent deployed in the parent agent are synchronized, it is determined that at the third operation moment, the safety sub-agent takes over the throttle sub-action and the brake sub-action, that is, the safety sub-agent controls the loader to execute the throttle sub-action with the control amount F and the brake sub-action with the control amount G.

[0074] In an optional implementation provided by this embodiment, after the step of the first sub-agent controlling the loader to perform the first sub-action with the first control amount, the method provided by this embodiment may further include the following steps S371 to S372:

[0075] Step S371, the first child agent reports the execution result of the loader performing the first child action to the parent agent.

[0076] Step S372, the parent agent adjusts the calling state of the first child agent according to the execution result.

[0077] In addition to making real-time decisions on the control amount of the first sub-action and controlling the loader to perform the first sub-action with the control amount in real time, the first sub-agent also reports in real time the execution result after the loader performs the first sub-action. The parent agent can adjust the call state of the first sub-agent according to the reported execution result. Exemplarily, the first sub-agent is a mobile sub-agent, which decides the control amount A of the throttle sub-action, the control amount B of the brake sub-action, and the control amount C of the steering sub-action at the first operation moment, controls the loader to perform the throttle sub-action with the control amount A, the brake sub-action with the control amount B, and the steering sub-action with the control amount C, and reports the distance between the loader and the shoveling point after the loader performs the above sub-actions to the parent agent. The parent agent adjusts the call state of the first sub-agent according to the distance between the loader and the shoveling point.

[0078] In a specific implementation, the parent agent adjusts the calling state of the first child agent according to the execution result, including: in response to the parent agent determining that the execution result has satisfied the first job task, stopping calling the first child agent.

[0079] The parent agent determines that the execution result reported by the first child agent has satisfied the first operation task based on the execution result reported by the first child agent, indicating that the first child agent has completed the first operation task issued by the parent agent, and then the parent agent can stop calling the first child agent. Exemplarily, the first child agent is a mobile child agent, and the mobile child agent reports the distance between the loader and the shoveling point to the parent agent. When the distance is 0, since the first operation task for the mobile child agent is to move the loader to the shoveling point, the distance between the loader and the shoveling point is 0, indicating that the execution result has satisfied the first operation task, the mobile child agent has completed the first operation task, and the parent agent can stop calling the first child agent.

[0080] Of course, in another implementation, after the first sub-agent completes the first job task, the first sub-agent can perform a self-stop operation and report to the parent agent to inform the parent agent that the first sub-agent has completed the first job task and has automatically stopped the call status.

[0081] In a specific implementation, the parent agent adjusts the calling state of the first child agent according to the execution result, including: in response to the parent agent judging that the execution result does not meet the first job task, issuing an adjustment instruction to the first child agent to adjust the first sub-action according to the job status at the fourth job moment, the fourth job moment being the next job moment of the first job moment.

[0082] The parent agent determines, based on the execution result reported by the first child agent, that the execution result has not yet satisfied the first job task, indicating that the first child agent has not yet completed the job task issued by the parent agent. The parent agent then needs to maintain the calling status of the first child agent.

[0083] After the first sub-agent reports the execution result to the parent agent, the first operation moment has been completed and the next operation moment of the first operation moment has entered. In this embodiment, the next operation moment of the first operation moment is defined as the fourth operation moment. The parent agent can issue an adjustment instruction to the first sub-agent to adjust the first sub-action according to the operation status of the loader at the fourth operation moment. Exemplarily, the first sub-agent is a mobile sub-agent, and the mobile sub-agent reports the distance between the loader and the shoveling point to the parent agent. When the distance is 2 meters, the parent agent determines that the execution result does not meet the first operation task (moving the loader to the shoveling point), and the parent agent maintains the calling state of the mobile sub-agent. The parent agent detects that the bucket of the loader is not in contact with the ground. Then, in order to ensure that the bucket of the loader can be in contact with the ground before the loader reaches the shoveling point, the parent agent will send an adjustment instruction to reduce the speed to the mobile sub-agent, so that when the mobile sub-agent determines the control amount of the throttle sub-action, the control amount of the brake sub-action, and the control amount of the steering sub-action at the next operating moment, it can reduce the control amount of the throttle sub-action or increase the control amount of the brake sub-action based on the decision amount according to the adjustment instruction.

[0084] An optional shoveling operation process is provided below based on the shoveling method described in this embodiment, which specifically includes the following steps S301 to S309:

[0085] Step S301, in response to the shoveling instruction, start the parent agent.

[0086] The shoveling instruction contains the location information of the shoveling point. The operation goal of the parent agent is to control the loader to go to the shoveling point to shovel materials and achieve a high full bucket rate.

[0087] Step S302, the parent agent calls the mobile sub-agent and the security sub-agent.

[0088] The mobile sub-agent controls the loader to move toward the shoveling point by controlling the execution of the throttle sub-action, brake sub-action, and steering sub-action. The safety sub-agent ensures that the loader will not collide with obstacles such as walls, other engineering vehicles, and people during movement by controlling the execution of the throttle sub-action and brake sub-action.

[0089] The mobile sub-agent includes a path planning module and a path tracking module. According to the real-time operating status of the loader, it outputs the control quantities of the throttle sub-action, brake sub-action, and steering sub-action, controls the loader to execute the above sub-actions with the output control quantities, and reports the execution results of the loader's execution of the above sub-actions (the distance between the loader and the shoveling point) to the parent agent in real time.

[0090] The safety sub-agent is a motion model based on a neural network. According to the real-time operating status of the loader, it determines whether the loader will collide with an obstacle in the subsequent operating time. When the safety sub-agent determines that the loader may collide with an obstacle, it will take over the throttle sub-action and the brake sub-action, and output the control amount of the throttle sub-action and the brake sub-action in real time according to the distance between the loader and the obstacle, and control the loader to perform the above sub-actions with the above control amounts.

[0091] Step S303, when the distance between the loader and the shoveling point is less than 6 meters, the parent agent calls the arm sub-agent and the bucket sub-agent to place the bucket in contact with the ground.

[0092] The boom sub-agent is responsible for controlling the boom to rise and fall to a preset angle. It adopts two control methods: one is position control based on PID, and the other is speed control based on speed feedback. The boom sub-agent will switch the appropriate control method according to the hydraulic pressure of the boom (collected by the pressure sensor).

[0093] The bucket sub-agent is responsible for controlling the bucket to flip to a preset angle, which uses PID-based position control.

[0094] Step S304, when the distance between the loader and the shoveling point is less than 2 meters, the parent agent monitors whether the bucket is in contact with the ground.

[0095] If there is no fit, an adjustment instruction to reduce the travel speed will be sent to the mobile sub-agent to ensure that the bucket can be lowered to fit the ground before the loader reaches the shoveling point.

[0096] Step S305, when the bucket is lowered to fit the ground and the loader reaches the shoveling point, the parent agent stops calling the mobile sub-agent and calls the power sub-agent.

[0097] The power sub-agent controls the execution of the throttle sub-action to make the loader's bucket continue to penetrate the material, during which the hydraulic pressure of the boom will continue to rise.

[0098] When the safety sub-agent determines that the bucket is too close to the wall, it will take over the throttle sub-action, output the control amount of the throttle sub-action and the brake sub-action in real time according to the distance between the loader and the wall, and control the loader to adjust the throttle and brake according to the above control amounts.

[0099] Step S306, when the hydraulic pressure of the boom reaches a preset value, the parent agent alternately calls the bucket sub-agent and the boom sub-agent to control the execution of the bucket flipping sub-action and the boom lifting sub-action.

[0100] During this period, the power sub-intelligence will coordinate the execution of the throttle sub-action to control as much material as possible into the bucket.

[0101] Step S307, when the bucket flips over and reaches a horizontal state, the parent agent stops calling the power sub-agent and calls the material shaking sub-agent.

[0102] The material shaking agent controls the execution of the bucket rotation sub-action to shake the material in the bucket and make the material evenly distributed in the bucket.

[0103] Step S308, the parent agent calls the mobile sub-agent, and the mobile sub-agent controls the execution of the throttle sub-action, the brake sub-action, and the steering sub-action to make the loader drive away from the shoveling point.

[0104] Step S309, completing the shoveling operation.

[0105] The above-mentioned first embodiment provides an optional shoveling method for a loader, which has the following advantages: first, the method does not rely on accurate perception of the shoveling point, and realizes automatic adaptive shoveling through the parent agent's call to different sub-agents and the sub-agent's decision on the sub-action control amount, thereby ensuring that each shoveling operation can achieve a high full bucket rate; second, the method does not rely on a fixed shoveling trajectory, can be applied to various materials, and is universal; third, the method is easy to deploy and can adapt to different business needs by adding or reducing sub-agents.

[0106] It should be noted that the example in the first embodiment is only for explaining the method described in this application and is not intended to be a limitation for actual use. The shoveling method of a loader provided in this application includes but is not limited to the method described in the first embodiment.

[0107] A second embodiment of the present application provides a shoveling system for a loader. Figure 4 It is a schematic diagram of the shoveling system of the loader provided in this embodiment.

[0108] like Figure 4 As shown, the loader shoveling system provided in this embodiment includes: a positioning module 401, a sensor module 402, a parent agent module 403, a child agent module 404, and an actuator module 405.

[0109] The positioning module 401 includes at least a first sensor and a positioning algorithm. The first sensor is configured on the loader and is used to collect scene data of the working scene in which the loader is located at a first working moment. The positioning algorithm is used to calculate scene status information of the working scene based on the scene data. The first working moment is any working moment in the process of the loader performing a shoveling operation.

[0110] The sensor module 402 includes a plurality of second sensors, and the second sensors are used to collect the state information of the loader itself at the first operation moment.

[0111] The parent agent module 403 includes a parent agent, which is used to determine the operating status of the loader at the first operating moment based on its own status information and scene status information; it is also used to monitor whether the operating status of the loader at the first operating moment meets the calling conditions of the first sub-agent; it is also used to call the first sub-agent when it is determined that the operating status of the loader at the first operating moment meets the calling conditions of the first sub-agent; it is also used to determine the first operating task for the first sub-agent based on the operating status of the loader at the first operating moment; it is also used to send the first operating task to the first sub-agent, and the first sub-agent is any one of the multiple sub-agents included in the sub-agent module whose calling conditions meet the operating status.

[0112] The sub-agent module 404 includes multiple sub-agents, and the first sub-agent is used to determine the control amount of the first sub-action at the first working moment according to the first working task and the working state of the loader at the first working moment, and the first sub-action is at least one sub-action controlled by the first sub-agent among the multiple sub-actions included in the shoveling operation; it is also used to control the loader to perform the first sub-action with the first control amount through the first actuator at the first working moment, and the first actuator is at least one actuator corresponding to the first sub-action among the multiple actuators included in the actuator module.

[0113] Optionally, the sub-agent module 404 includes at least the following sub-agents: a mobile sub-agent 4041, a power sub-agent 4042, a boom sub-agent 4043, a bucket sub-agent 4044, and a safety sub-agent 4045; wherein,

[0114] The mobile sub-agent 4041 controls the execution of the throttle sub-action, the brake sub-action, and the steering sub-action to enable the loader to move in the working scene;

[0115] The power sub-agent 4042 controls the execution of the throttle sub-action so that the bucket of the loader penetrates deeply into the material;

[0116] The arm sub-agent 4043 controls the execution of the arm lifting sub-action to raise or lower the arm of the loader;

[0117] The bucket sub-agent 4044 controls the execution of the bucket flipping sub-action to flip the bucket of the loader;

[0118] The safety sub-agent 4045 controls the execution of the throttle sub-action and the brake sub-action to keep the loader at a safe distance from obstacles in the working scene.

[0119] Optionally, the sub-agent module 404 further includes: a shaking material sub-agent 4046;

[0120] The material shaking sub-agent 4046 controls the execution of the bucket rotation sub-action to rotate the bucket of the loader.

[0121] The actuator module 405 includes a plurality of actuators, and the plurality of actuators are configured on the loader. The first actuator is used to be controlled by the first sub-agent so that the loader performs a first sub-action with a first control amount at a first operation moment.

[0122] The third embodiment of the present application provides a loader. Figure 5 It is a structural schematic diagram of the loader provided in this embodiment.

[0123] like Figure 5 As shown, the loader provided in this embodiment includes: a loader body 501 and a shoveling system 502 configured for the loader body 501 .

[0124] The shoveling system 502 includes: a positioning module 5021, a sensor module 5022, a parent agent module 5023, a child agent module 5024, and an actuator module 5025.

[0125] The positioning module 5021 includes at least a first sensor and a positioning algorithm. The first sensor is configured on the loader and is used to collect scene data of the working scene in which the loader is located at a first working moment. The positioning algorithm is used to calculate scene status information of the working scene based on the scene data. The first working moment is any working moment in the process of the loader performing a shoveling operation.

[0126] The sensor module 5022 includes a plurality of second sensors, and the second sensors are used to collect the loader's own state information at the first operation moment.

[0127] The parent agent module 5023 includes a parent agent, which is used to determine the operating status of the loader at the first operating moment based on its own status information and scene status information; it is also used to monitor whether the operating status of the loader at the first operating moment meets the calling conditions of the first sub-agent; it is also used to call the first sub-agent when it is determined that the operating status of the loader at the first operating moment meets the calling conditions of the first sub-agent; it is also used to determine the first operating task for the first sub-agent based on the operating status of the loader at the first operating moment; it is also used to send the first operating task to the first sub-agent, and the first sub-agent is any one of the multiple sub-agents included in the sub-agent module whose calling conditions meet the operating status.

[0128] The sub-agent module 5024 includes multiple sub-agents, and the first sub-agent is used to determine the control amount of the first sub-action at the first working moment according to the first working task and the working status of the loader at the first working moment, and the first sub-action is at least one sub-action controlled by the first sub-agent among the multiple sub-actions included in the shoveling operation; it is also used to control the loader to perform the first sub-action with the first control amount through the first actuator at the first working moment, and the first actuator is at least one actuator corresponding to the first sub-action among the multiple actuators included in the actuator module.

[0129] The actuator module 5025 includes a plurality of actuators, and the plurality of actuators are configured on the loader. The first actuator is used to be controlled by the first sub-agent so that the loader performs a first sub-action with a first control amount at a first operating moment.

[0130] A fourth embodiment of the present application provides an electronic device, Figure 6 It is a schematic diagram of the structure of the electronic device provided in this embodiment.

[0131] like Figure 6 As shown, the electronic device provided in this embodiment includes: a memory 601 and a processor 602;

[0132] The memory 601 is used to store computer instructions for executing the shoveling method of the loader;

[0133] The processor 602 is configured to execute computer instructions stored in the memory 601 to perform the following operations:

[0134] In response to a shoveling instruction, a parent agent corresponding to the shoveling operation is started; wherein the shoveling operation includes a plurality of sub-actions, the parent agent corresponds to a plurality of sub-agents that can be called, each of the sub-agents has a preset calling condition, and the sub-agent is used to control the execution of at least one of the sub-actions after being called by the parent agent;

[0135] In response to monitoring that the operating state of the loader meets the calling condition of the first sub-agent at the first operating moment, the parent agent calls the first sub-agent and issues a first operating task to the first sub-agent, the first sub-agent being one of the multiple callable sub-agents for which the calling condition meets the operating state, the first operating task is determined by the parent agent based on the operating state at the first operating moment and the first sub-agent, and the first operating moment is any operating moment during the loader performing the shoveling operation;

[0136] The first sub-agent determines a first control amount of a first sub-action at a first working moment according to the first working task and the working state at a first working moment, wherein the first sub-action is at least one sub-action executed under the control of the first sub-agent;

[0137] The first sub-agent controls the loader to perform the first sub-action with the first control amount at a first operation time.

[0138] Optionally, perform the following operations:

[0139] The first sub-agent determines a second control amount of the first sub-action at a second working moment according to the first working task and the working state at a second working moment, wherein the second working moment includes every working moment after the first working moment;

[0140] The first sub-agent controls the loader to perform the first sub-action with the second control amount at the second working time.

[0141] Optionally, perform the following operations:

[0142] In response to monitoring that the operating state of the loader meets the calling condition of the second sub-agent at the third operating time, the parent agent calls the second sub-agent and issues the second operating task to the second sub-agent, the second sub-agent is any one of the multiple sub-agents that can be called and is in an uncalled state before the third operating time, the second operating task is determined by the parent agent according to the operating state at the third operating time and the second sub-agent, and the third operating time is any operating time after the first operating time;

[0143] The second sub-agent determines a third control amount of a second sub-action at a third working moment according to the second working task and the working state at a third working moment, wherein the second sub-action is at least one sub-action controlled by the second sub-agent;

[0144] The first sub-agent determines a fourth control amount of the first sub-action at a third working moment according to the first working task and the working state at a third working moment;

[0145] The second sub-agent controls the loader to perform the second sub-action with the third control amount at a third operation time; and / or,

[0146] The first sub-agent controls the loader to perform the first sub-action with the fourth control amount at the third working moment.

[0147] Optionally, perform the following operations:

[0148] The first sub-agent reports the execution result of the loader executing the first sub-action to the parent agent;

[0149] The parent agent adjusts the calling state of the first child agent according to the execution result.

[0150] Optionally, the parent agent adjusts the calling state of the first child agent according to the execution result, including:

[0151] In response to the parent agent determining that the execution result has satisfied the first job task, the calling of the first child agent is stopped.

[0152] Optionally, the parent agent adjusts the calling state of the first child agent according to the execution result, including:

[0153] In response to the parent agent determining that the execution result does not meet the first job task, an adjustment instruction for adjusting the first sub-action is sent to the first child agent based on the job status at the fourth job moment, and the fourth job moment is the next job moment of the first job moment.

[0154] The fifth embodiment of the present application provides a computer-readable storage medium, which includes computer instructions. When the computer instructions are executed by a processor, they are used to implement the methods described in the embodiments of the present application.

[0155] It should be noted that the relational terms such as "first" and "second" in this article are only used to distinguish one entity or operation from another entity or operation, and do not require or imply any actual relationship or order between these entities or operations. In addition, the words "include", "have", "include" and "includes" and other similar forms are the same in meaning, and the end of any one or more items after any of the above words is open-ended, and any of the above nouns does not mean that the one or more items have been exhaustively listed or are limited to the one or more items listed.

[0156] As used herein, unless expressly stated otherwise, the term "or" includes all possible combinations, except those that are not feasible. For example, if it is expressed that a database may include A or B, then unless otherwise specifically stated or not feasible, it may include database A, or B, or A and B. As a second example, if it is expressed that a database may include A, B, or C, then unless otherwise specifically stated or not feasible, the database may include database A, or B, or C, or A and B, or A and C, or B and C, or A, B, and C.

[0157] It is worth noting that the above embodiments can be implemented by hardware or software (program code), or a combination of hardware and software. If implemented by software, it can be stored in the above-mentioned computer-readable medium. When the software is executed by a processor, it can execute the above-mentioned disclosed method. The computing unit and other functional units described in the present disclosure can be implemented by hardware or software, or a combination of hardware and software. Those of ordinary skill in the art will also understand that the above-mentioned multiple modules / units can be combined into one module / unit, and each of the above-mentioned modules / units can be further divided into multiple sub-modules / sub-units.

[0158] In the above detailed description, the embodiments have been described with reference to many specific details, which may vary from implementation to implementation. Certain adaptations and modifications may be made to the embodiments. For those skilled in the art, other embodiments may be readily apparent from the specific embodiments disclosed in the present application. This specification and examples are for exemplary purposes only, and the true scope and essence of the present application are described by the claims. The sequence of steps shown in the diagrams is also for the purpose of explanation only and is not intended to be limited to any particular steps or sequence. Therefore, those skilled in the art will appreciate that these steps may be performed in different orders when implementing the same method.

[0159] In the drawings and detailed description of the present application, exemplary embodiments are disclosed. However, many variations and modifications may be made to these embodiments. Accordingly, although specific terms are used, these terms are only general and descriptive and not for the purpose of limitation.

Claims

1. A shoveling method of a loader, It is characterized in that The method comprises: In response to a shoveling instruction, a parent agent corresponding to the shoveling operation is started; wherein the shoveling operation includes a plurality of sub-actions, the parent agent corresponds to a plurality of sub-agents that can be called, each of the sub-agents has a preset calling condition, and the sub-agent is used to control the execution of at least one of the sub-actions after being called by the parent agent; In response to monitoring that the operating state of the loader meets the calling condition of the first sub-agent at the first operating moment, the parent agent calls the first sub-agent and issues a first operating task to the first sub-agent, the first sub-agent being one of the multiple callable sub-agents for which the calling condition meets the operating state, the first operating task is determined by the parent agent based on the operating state at the first operating moment and the first sub-agent, and the first operating moment is any operating moment during the loader performing the shoveling operation; The first sub-agent determines a first control amount of a first sub-action at a first working moment according to the first working task and the working state at a first working moment, wherein the first sub-action is at least one sub-action executed under the control of the first sub-agent; The first sub-agent controls the loader to perform the first sub-action with the first control amount at a first operation time.

2. The method according to claim 1, It is characterized in that The method further comprises: The first sub-agent determines a second control amount of the first sub-action at a second working moment according to the first working task and the working state at a second working moment, wherein the second working moment includes every working moment after the first working moment; The first sub-agent controls the loader to perform the first sub-action with the second control amount at the second working time.

3. The method according to claim 1, It is characterized in that The method further comprises: In response to monitoring that the operating state of the loader meets the calling condition of the second sub-agent at the third operating time, the parent agent calls the second sub-agent and issues the second operating task to the second sub-agent, the second sub-agent is any one of the multiple sub-agents that can be called and is in an uncalled state before the third operating time, the second operating task is determined by the parent agent according to the operating state at the third operating time and the second sub-agent, and the third operating time is any operating time after the first operating time; The second sub-agent determines a third control amount of a second sub-action at a third working moment according to the second working task and the working state at a third working moment, wherein the second sub-action is at least one sub-action controlled by the second sub-agent; The first sub-agent determines a fourth control amount of the first sub-action at a third working moment according to the first working task and the working state at a third working moment; The second sub-agent controls the loader to perform the second sub-action with the third control amount at a third operation time; and / or, The first sub-agent controls the loader to perform the first sub-action with the fourth control amount at the third working moment.

4. The method according to claim 1, It is characterized in that The method further comprises: The first sub-agent reports the execution result of the loader executing the first sub-action to the parent agent; The parent agent adjusts the calling state of the first child agent according to the execution result.

5. The method according to claim 4, It is characterized in that The parent agent adjusts the calling state of the first child agent according to the execution result, including: In response to the parent agent determining that the execution result has satisfied the first job task, the calling of the first child agent is stopped.

6. The method according to claim 4, It is characterized in that The parent agent adjusts the calling state of the first child agent according to the execution result, including: In response to the parent agent determining that the execution result does not meet the first job task, an adjustment instruction for adjusting the first sub-action is sent to the first child agent based on the job status at the fourth job moment, and the fourth job moment is the next job moment of the first job moment.

7. A shoveling system for a loader, It is characterized in that The system comprises: a positioning module, a sensor module, a parent agent module, a child agent module, and an actuator module; The positioning module at least includes a first sensor and a positioning algorithm, wherein the first sensor is configured on the loader and is used to collect scene data of the working scene where the loader is located at a first working moment, and the positioning algorithm is used to calculate scene state information of the working scene according to the scene data, wherein the first working moment is any working moment during the loader performing the shoveling operation; The sensor module includes a plurality of second sensors, and the second sensors are used to collect the self state information of the loader at the first operation moment; The parent agent module includes a parent agent, and the parent agent is used to determine the operating state of the loader at the first operating moment according to the self-state information and the scene state information; it is also used to monitor whether the operating state of the loader at the first operating moment meets the calling condition of the first sub-agent; it is also used to call the first sub-agent when it is determined that the operating state of the loader at the first operating moment meets the calling condition of the first sub-agent; it is also used to determine the first operating task for the first sub-agent according to the operating state of the loader at the first operating moment; it is also used to send the first operating task to the first sub-agent, and the first sub-agent is one of the multiple sub-agents included in the sub-agent module whose calling condition meets the operating state; The sub-agent module includes a plurality of sub-agents, wherein the first sub-agent is used to determine the control amount of a first sub-action at a first operation moment according to the first operation task and the operation state of the loader at the first operation moment, wherein the first sub-action is at least one of the plurality of sub-actions included in the shoveling operation and controlled by the first sub-agent; and is also used to control the loader to perform the first sub-action with the first control amount through a first actuator at the first operation moment, wherein the first actuator is at least one of the plurality of actuators included in the actuator module and corresponding to the first sub-action; The actuator module includes a plurality of actuators, and the plurality of actuators are configured on the loader. The first actuator is used to be controlled by the first sub-agent so that the loader performs the first sub-action with the first control amount at a first operating moment.

8. The system according to claim 7, It is characterized in that The sub-agent module includes at least the following sub-agents: mobile sub-agent, power sub-agent, arm sub-agent, bucket sub-agent, and safety sub-agent; wherein, The mobile sub-agent controls the execution of the throttle sub-action, the brake sub-action, and the steering sub-action to enable the loader to move in the working scene; The power sub-agent controls the execution of the throttle sub-action so that the bucket of the loader penetrates deeply into the material; The arm sub-agent controls the execution of the arm lifting sub-action to lift or lower the arm of the loader; The bucket sub-agent controls the execution of the bucket flipping sub-action to flip the bucket of the loader; The safety sub-agent controls the execution of the throttle sub-action and the brake sub-action to keep the loader at a safe distance from obstacles in the working scene.

9. The system according to claim 8, It is characterized in that The sub-agent module also includes: a material shaking sub-agent; The material shaking sub-agent controls the execution of the bucket rotation sub-action to rotate the bucket of the loader.

10. A loader, It is characterized in that The loader is equipped with the shoveling system according to any one of claims 7-9.

11. An electronic device, It is characterized in that include: Memory, processor; The memory is used to store one or more computer instructions; The processor is used to execute the one or more computer instructions to implement the method according to any one of claims 1-6.

12. A computer-readable storage medium having stored thereon one or more computer instructions, It is characterized in that When the instruction is executed by a processor, the method according to any one of claims 1 to 6 is performed.

Citation Information

Patent Citations

  • System and method for truck loading assistance of work machine

    CN115341613A

  • Self-adaptive adjusting system and method for bucket of loading machine

    CN116623734A

  • Loader control method and device, computer equipment and storage medium

    CN117605106A

  • Shovel loading control method, device and equipment of loader and medium

    CN118207931A

  • Unmanned material shoveling device of intelligent loader and material shoveling method of unmanned material shoveling device

    CN118257306A