Control method, device and equipment for automatically driving mining truck, medium and product

By obtaining and integrating the status data of mining trucks, predicting driving trajectories and conflict situations, and generating pass strategies, it solves the problem of inefficient traffic efficiency of autonomous mining trucks at intersections, and achieves safe and efficient mining area transportation.

CN119088015APending Publication Date: 2024-12-06SINO TRUK JINAN POWER CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411202494.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The traffic efficiency of autonomous mining trucks at intersections is inefficient, and the existing technology is unable to flexibly adjust the traffic strategy based on rules and guidelines, resulting in insufficient safety spacing between vehicles and delays in traffic.

Method used

By obtaining the status data of multiple mining trucks, a graph neural network is constructed to identify and fuse the status data of target objects, predict driving trajectories and conflicts, and generate pass strategies to optimize the passage order, speed and trajectory of mining trucks to ensure safe passage .

Benefits of technology

It improves the traffic efficiency of autonomous mining trucks at complex intersections in the mining area, reduces waiting time, ensures safe distance between vehicles, and improves the overall transportation efficiency of the mining area.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088015A_ABST
    Figure CN119088015A_ABST
Patent Text Reader

Abstract

The invention provides a control method, device and equipment for automatically driving a mining truck, a medium and a product, and relates to the technical field of automatic driving. The method comprises the following steps: acquiring state data of a target object collected by a plurality of first mining trucks in a driving process; identifying one or more pieces of state data of the same target object from the plurality of pieces of state data, and fusing the one or more pieces of state data of the same target object to obtain fused state data of the same target object; predicting driving tracks of the plurality of mining trucks according to the fusion state data of the plurality of target objects; performing conflict prediction according to the driving tracks of the plurality of mining trucks to obtain a conflict prediction result; and generating passing strategies of the plurality of mining trucks according to the conflict prediction result, and issuing the passing strategies to the corresponding mining trucks to control the mining trucks to execute the passing strategies. According to the method, the passing efficiency of the automatic driving mining truck at the intersection can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a control method, device, equipment, medium and product for an autonomous driving mining truck. Background Art

[0002] With the continuous development of autonomous driving technology, autonomous mining trucks have become an important tool for transportation in mining areas.

[0003] In the existing technology, self-driving mining trucks can achieve autonomous navigation and transportation tasks in the mining area through sensors, artificial intelligence and communication technology. At the intersection of mining area roads, self-driving mining trucks are usually guided by rules, that is, they pass according to the rules of first come first served, uphill first or heavy load first.

[0004] However, the use of rule-based guidance to guide autonomous mining trucks through intersections has the disadvantage of low traffic efficiency. Summary of the invention

[0005] The present application provides a control method, device, equipment, medium and product for an autonomous driving mining truck, which are used to improve the traffic efficiency of the autonomous driving mining truck at intersections.

[0006] In a first aspect, the present application provides a control method for an autonomous driving mining truck, the method comprising:

[0007] Acquire state data of target objects collected by a plurality of first mining trucks during driving, wherein for each first mining truck, the target objects include: the first mining truck, obstacles around the first mining truck, and the obstacles include at least one of the following: a second mining truck other than the first mining truck, and other objects other than the mining truck, and the state data includes position, speed, and driving direction;

[0008] Identifying one or more state data of the same target object from the multiple state data, and fusing the one or more state data of the same target object to obtain fused state data of the same target object;

[0009] Predicting the trajectories of multiple mining trucks based on the fused state data of multiple target objects;

[0010] Conflict prediction is performed according to the driving trajectories of multiple mining trucks to obtain conflict prediction results;

[0011] If the conflict prediction result indicates that there is a conflict, a traffic strategy for multiple mining trucks is generated based on the conflict prediction result, and the traffic strategy is issued to the corresponding mining truck to control the mining truck to execute the traffic strategy. The traffic strategy includes: the traffic order of multiple mining trucks, the traffic speed of the mining truck, and the traffic trajectory of the mining truck.

[0012] In a possible design, identifying one or more state data of a same target object from a plurality of state data includes:

[0013] Take each state data as the state data of a target object, and take each target object as each node of the graph neural network to construct a graph neural network;

[0014] For any two nodes in the graph neural network, the similarity between the two nodes is determined based on the state data corresponding to the two nodes;

[0015] If the similarity is greater than or equal to a preset similarity threshold, it is determined that the two nodes correspond to the same target object, and a connecting edge is established between the two nodes.

[0016] In a possible design, the similarity between two nodes is determined based on the state data corresponding to the two nodes, including:

[0017] Calculate the distance between two nodes based on the positions in the state data corresponding to the two nodes;

[0018] If the distance between the two nodes is less than or equal to a preset threshold, the similarity between the two nodes is calculated based on the speed and direction in the state data corresponding to the two nodes.

[0019] In a possible design, one or more state data of the same target object are fused to obtain fused state data of the same target object, including:

[0020] For the same target object, the positions in one or more state data of the target object are averaged as the fusion position of the target object;

[0021] For the same target object, the speeds in one or more state data of the target object are averaged as the fusion speed of the target object;

[0022] For the same target object, the directions in one or more state data of the target object are averaged as the fusion direction of the target object;

[0023] Fusion status data is generated according to the fusion position, fusion speed and fusion direction.

[0024] In a possible design, conflict prediction is performed based on the driving trajectories of multiple mining trucks to obtain conflict prediction results, including:

[0025] Mark the driving tracks of multiple mining trucks on the map;

[0026] Determine whether there is an overlapping area between the driving tracks marked on the map;

[0027] If there is an overlapping area, the overlapping area is divided into multiple overlapping sub-areas, and the time it takes for the mining truck to reach each overlapping sub-area according to the driving trajectory is estimated;

[0028] For each overlapping sub-area, if at least two times corresponding to the overlapping sub-area overlap, it is determined that there is a conflict in the overlapping sub-area, and a conflict prediction result is generated according to the overlapping sub-area, the overlapping time, and the identification of the mining truck arriving at the overlapping sub-area.

[0029] In one possible design, multiple mine truck traffic strategies are generated based on conflict prediction results, including:

[0030] The conflict prediction results are input into a pre-trained traffic strategy prediction model to predict the traffic strategies of multiple mining trucks;

[0031] The training process of the traffic strategy prediction model includes:

[0032] Obtaining initial rules to generate an initial traffic strategy with conflicts according to the initial rules, and executing the initial traffic strategy to obtain conflict execution results, wherein the initial rules include: heavy load first, uphill first, and first come first;

[0033] Inputting the conflict execution result into the traffic strategy prediction model to obtain the predicted traffic strategy;

[0034] Execute the predicted traffic strategy and obtain the conflict resolution time corresponding to the predicted traffic strategy;

[0035] If the conflict resolution time does not meet the preset convergence condition, the traffic strategy prediction model is adjusted according to the conflict resolution time until the conflict resolution time meets the preset convergence condition.

[0036] In one possible design, the trajectories of multiple mining trucks are predicted based on the fused state data of multiple target objects, including:

[0037] The fused state data of multiple target objects are input into the pre-trained trajectory prediction model to predict the driving trajectory of each mining truck.

[0038] In a second aspect, the present application provides a control device for an autonomous driving mining truck, the device comprising:

[0039] An acquisition module is used to acquire state data of target objects collected by a plurality of first mining trucks during driving. For each first mining truck, the target object includes: the first mining truck, obstacles around the first mining truck, and obstacles include at least one of the following: a second mining truck other than the first mining truck, and other objects other than the mining truck. The state data includes position, speed, and driving direction.

[0040] A fusion module, used to identify one or more state data of the same target object from multiple state data, and fuse the one or more state data of the same target object to obtain fused state data of the same target object;

[0041] A trajectory prediction module, used to predict the driving trajectories of multiple mining trucks based on the fused state data of multiple target objects;

[0042] A conflict prediction module is used to perform conflict prediction based on the driving trajectories of multiple mining trucks to obtain conflict prediction results;

[0043] A generation module is used to generate a traffic strategy for multiple mining trucks according to the conflict prediction result if a conflict is indicated, and send the traffic strategy to the corresponding mining truck to control the mining truck to execute the traffic strategy. The traffic strategy includes: the traffic order of multiple mining trucks, the traffic speed of the mining truck, and the traffic trajectory of the mining truck.

[0044] In a possible design, the fusion module includes: a building module, a similarity module, and a connection edge module;

[0045] A construction module is used to take each state data as the state data of a target object, and take each target object as each node of the graph neural network to construct the graph neural network;

[0046] The similarity module is used to determine the similarity between any two nodes in the graph neural network according to the state data corresponding to the two nodes;

[0047] The connection edge module is used to determine that two nodes correspond to the same target object and establish a connection edge between the two nodes if the similarity is greater than or equal to a preset similarity threshold.

[0048] In one possible design, the similarity module includes: a distance module and a speed module;

[0049] The distance module is used to calculate the distance between two nodes according to the positions in the state data corresponding to the two nodes;

[0050] The speed module is used to calculate the similarity between the two nodes according to the speed and direction in the state data corresponding to the two nodes if the distance between the two nodes is less than or equal to a preset threshold.

[0051] In a possible design, the fusion module further includes: a fusion position module, a fusion speed module, a fusion direction module and a fusion state data module;

[0052] A fusion position module, used for averaging the positions of one or more state data of the same target object as the fusion position of the target object;

[0053] A fusion speed module is used to average the speeds in one or more state data of the same target object as the fusion speed of the target object;

[0054] A fusion direction module is used to average the directions in one or more state data of the same target object as the fusion direction of the target object;

[0055] The fusion state data module is used to generate fusion state data according to the fusion position, fusion speed and fusion direction.

[0056] In one possible design, the conflict prediction module includes a marking module, a judgment module, a division module, and a conflict prediction result module;

[0057] A marking module, used to mark the driving tracks of multiple mining trucks on a map;

[0058] A judgment module, used to judge whether there is an overlapping area between the driving tracks marked on the map;

[0059] A division module, for dividing the overlapping area into a plurality of overlapping sub-areas if there is an overlapping area, and estimating the time for the mining truck to reach each overlapping sub-area according to the driving trajectory;

[0060] The conflict prediction result module is used to determine that there is a conflict in each overlapping sub-area if at least two times corresponding to the overlapping sub-area have overlapping time, and generate a conflict prediction result based on the overlapping sub-area, overlapping time, and the identification of the mining truck arriving at the overlapping sub-area.

[0061] In a possible design, the generation module is further used to input the conflict prediction result into a pre-trained traffic strategy prediction model to predict the traffic strategies of multiple mining trucks;

[0062] The training device of the traffic strategy prediction model includes: an initial rule module, a traffic strategy prediction module, a conflict resolution time module and a convergence module;

[0063] The initial rule module is used to obtain the initial rules, generate the initial traffic strategy with conflicts according to the initial rules, and execute the initial traffic strategy to obtain the conflict execution result. The initial rules include: heavy load first, uphill first, and first come first.

[0064] A traffic strategy prediction module is used to input the conflict execution result into the traffic strategy prediction model to obtain a predicted traffic strategy;

[0065] The conflict resolution time module is used to execute the predicted traffic strategy and obtain the conflict resolution time corresponding to the predicted traffic strategy;

[0066] The convergence module is used to adjust the traffic strategy prediction model according to the conflict resolution time if the conflict resolution time does not meet the preset convergence condition until the conflict resolution time meets the preset convergence condition.

[0067] In a possible design, the trajectory prediction module is also used to input the fusion state data of multiple target objects into a pre-trained trajectory prediction model to predict the driving trajectory of each mining truck.

[0068] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0069] Memory stores computer-executable instructions;

[0070] The processor executes the computer execution instructions stored in the memory to implement a control method for an autonomous driving mining truck according to the first aspect of the invention.

[0071] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement a control method for an autonomous driving mining truck according to the invention content of the first aspect.

[0072] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement a control method for an autonomous driving mining truck according to the invention content of the first aspect.

[0073] The present application provides a control method, device, equipment, medium and product for an autonomous driving mining truck, the method comprising: obtaining state data of target objects collected by multiple first mining trucks during driving, for each first mining truck, the target objects include: the first mining truck, obstacles around the first mining truck, the obstacles include at least one of the following: a second mining truck other than the first mining truck, and other objects other than the mining truck, the state data includes position, speed and driving direction; identifying one or more state data of the same target object from multiple state data, and fusing the one or more state data of the same target object to obtain fused state data of the same target object; predicting driving trajectories of multiple mining trucks according to the fused state data of multiple target objects; performing conflict prediction according to the driving trajectories of multiple mining trucks to obtain conflict prediction results; if the conflict prediction results indicate that there is a conflict, generating a traffic strategy for multiple mining trucks according to the conflict prediction results, and issuing the traffic strategy to the corresponding mining trucks to control the mining trucks to execute the traffic strategy, the traffic strategy including: the traffic order of multiple mining trucks, the traffic speed of the mining trucks, and the traffic trajectory of the mining trucks. The following technical effects are achieved: through the on-board terminals carried by multiple first mining trucks, the status data such as the position, speed and travel direction of the vehicle, other mining trucks and other objects collected by each mining truck are obtained in real time, solving the problem of how to obtain the status data of each mining truck and other objects; the traffic strategies of multiple mining trucks are generated according to the conflict prediction results, and the traffic strategies are issued to the corresponding mining trucks to control the mining trucks to execute the traffic strategies and maintain a safe distance between vehicles, thereby avoiding collisions and ensuring the safe passage of mining trucks; by obtaining the status data such as the position, speed and travel direction of the vehicle, other mining trucks and other objects collected by each mining truck in real time, the traffic order, speed and trajectory of each mining truck are generated, so that the traffic strategies of multiple mining trucks can be flexibly adjusted according to the real-time traffic conditions, thereby reducing the waiting time of autonomous driving mining trucks at intersections, improving the traffic efficiency of autonomous driving mining trucks at complex intersections in mining areas, and thus improving the overall transportation efficiency of mining areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0075] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0076] Figure 1 A schematic diagram of an application scenario of a control method for an autonomous driving mining truck provided in an embodiment of the present application;

[0077] Figure 2 A flowchart of a control method for an autonomous driving mining truck provided in an embodiment of the present application Figure 1 ;

[0078] Figure 3 A flowchart of a control method for an autonomous driving mining truck provided in an embodiment of the present application Figure 2 ;

[0079] Figure 4 A schematic diagram of a graph neural network provided in an embodiment of the present application;

[0080] Figure 5 A schematic diagram of similarity determination of target objects provided in an embodiment of the present application;

[0081] Figure 6 A schematic diagram of the structure of a control device for an autonomous driving mining truck provided in an embodiment of the present application;

[0082] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0083] Reference numerals:

[0084] 110- cloud control system; 120- mining truck; 121- vehicle terminal; 130- other objects;

[0085] 410-First Mining Truck; 420-Obstacle;

[0086] 610-acquisition module; 620-fusion module; 630-trajectory prediction module; 640-conflict prediction module; 650-generation module;

[0087] 710 - processor; 720 - memory; 730 - communication component; 740 - bus. DETAILED DESCRIPTION

[0088] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0089] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will appreciate that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.

[0090] It should be noted that the "at..." in the embodiments of the present application can be the instant when a certain situation occurs, or it can be a period of time after a certain situation occurs, and the embodiments of the present application do not specifically limit this. In addition, the control method of an autonomous driving mining truck provided in the embodiments of the present application is only used as an example, and the control method of an autonomous driving mining truck can also include more or less content.

[0091] In order to clearly describe the technical solutions of the embodiments of the present application, some terms and technologies involved in the embodiments of the present application are briefly introduced below:

[0092] Cloud Control System: A control system based on cloud computing technology that can be used to manage and control remote devices or systems. In the application scenario of autonomous mining trucks, the cloud control system can serve as a centralized platform to collect data from each mining truck, analyze and process the data, and send instructions to each mining truck to achieve more efficient and safer operation.

[0093] On-board terminal: an electronic device installed on a vehicle that integrates multiple functions and is mainly used to collect and transmit vehicle data, and can receive external commands to control the vehicle.

[0094] With the continuous development of autonomous driving technology, more and more mines are beginning to use autonomous mining trucks for material transportation to improve production efficiency and reduce operating costs. These mining trucks are usually equipped with advanced sensors, positioning systems and communication equipment, which can achieve automatic driving and remote monitoring. In other words, autonomous mining trucks have become an important tool for transportation in mining areas.

[0095] In the prior art, the passage of autonomous mining trucks at intersections usually relies on preset rules, such as: first come, first served, that is, the vehicle that arrives at the intersection first has priority; uphill first, that is, at a slope intersection, vehicles going uphill have priority; heavy load first, that is, vehicles with heavier loads have priority to reduce energy consumption and mechanical losses caused by frequent starting and stopping of heavy-loaded vehicles; left turn first: that is, for vehicles that need to turn, left-turning vehicles can be given higher priority.

[0096] However, although these rules ensure the safe passage of mining trucks to a certain extent, the rule-guided approach lacks flexibility in dealing with complex traffic conditions and cannot be flexibly adjusted according to real-time traffic conditions, resulting in low traffic efficiency for mining trucks when passing through intersections.

[0097] Based on this, the embodiments of the present application propose a control method, device, equipment, medium and product for an autonomous driving mining truck, which can be used in the field of autonomous driving technology, and aims to solve the above technical problems of the prior art, so as to improve the traffic efficiency of autonomous driving mining trucks at complex intersections in mining areas, ensure a safe distance between vehicles, and reduce the waiting time of autonomous driving mining trucks at intersections, thereby improving the overall transportation efficiency of the mining area.

[0098] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0099] In order to facilitate understanding of the technical solution of the present application, the application scenario of the control method of the autonomous driving mining truck provided in the embodiment of the present application is first introduced. Figure 1 This is a schematic diagram of an application scenario of a control method for an autonomous driving mining truck provided in an embodiment of the present application. It should be noted that: Figure 1 What is shown are merely examples of application scenarios to which the embodiments of the present application can be applied, in order to help those skilled in the art understand the technical content of the present application, but it does not mean that the embodiments of the present application cannot be used in other devices, systems, environments or scenarios.

[0100] like Figure 1As shown, the application scenario includes: a cloud control system 110, multiple mining trucks 120 and other objects 130. Multiple mining trucks 120 each include a vehicle-mounted terminal 121 and multiple sensors. The multiple sensors include speed sensors, angle sensors, combined navigation systems, millimeter wave radars, laser radars, cameras and other equipment. Through multiple sensors, the mining truck 120 can not only obtain the status data such as the position, speed and direction of the mining truck itself, but also obtain the status data such as the position and speed of other mining trucks around the mining truck, as well as the remaining objects 130 outside the mining truck. The remaining objects 130 can be obstacles such as pedestrians or objects.

[0101] The cloud control system 110 can be implemented as one or more servers, which can be deployed in a cloud data center or a local data center in a mining area. The cloud control system 110 can be connected to the vehicle terminal 121 in the mining truck 120 through a wireless communication link, so as to obtain the position, speed, direction and other status data of the mining truck 120, other mining trucks and other objects 130 collected by each mining truck 120 in real time through the wireless communication network, and then process these status data to generate the passage sequence, passage speed and passage trajectory of each mining truck.

[0102] The cloud control system 110 is the executor of the control method of the autonomous driving mining truck. Through high-performance computing power and big data processing capabilities, the cloud control system can manage and control the autonomous driving mining trucks in the mining area in real time, thereby improving the traffic efficiency of the autonomous driving mining trucks at complex intersections in the mining area.

[0103] also, Figure 1 The application scenario of the method shown is an intersection, including two mining trucks 120, which is only an example. In other application scenarios, it can also be a T-junction, a curved road or a straight road, etc., and can also include a larger number of mining trucks 120. No specific limitation is made here.

[0104] The technical solution of the present application is described in detail below in conjunction with specific embodiments.

[0105] Optionally, Figure 2 A flowchart of a control method for an autonomous driving mining truck provided in an embodiment of the present application Figure 1 .like Figure 2 As shown, the method includes:

[0106] S201. Acquire state data of a plurality of target objects collected during the driving of a first mining truck.

[0107] In the embodiment of the present application, for each first mining truck, the target objects include: the first mining truck, obstacles around the first mining truck, obstacles include at least one of the following: the second mining truck other than the first mining truck, other objects other than the mining truck, and the status data includes position, speed and travel direction. Among them, the first mining truck refers to any mining truck that directly sends status data to the cloud control system, the second mining truck refers to other mining trucks other than the first mining truck; mining trucks include the first mining truck and the second mining truck.

[0108] Specifically, the cloud control system can obtain real-time status data such as the position, speed, and travel direction of the first mining truck, other mining trucks, and other objects collected by each mining truck through the on-board terminals carried by multiple first mining trucks.

[0109] S202: Identify one or more state data of the same target object from the multiple state data, and fuse the one or more state data of the same target object to obtain fused state data of the same target object.

[0110] Specifically, the cloud control system can first identify the status data belonging to the same mining truck or other objects from multiple status data, and then fuse the status data belonging to the same mining truck or other objects to obtain the fused status data belonging to the same mining truck or other objects.

[0111] S203. Predicting the driving trajectories of multiple mining trucks according to the fused state data of multiple target objects.

[0112] Specifically, the cloud control system can predict the driving trajectories of multiple mining trucks at intersections of mining roads based on the fusion state data of multiple mining trucks or other objects.

[0113] S204: Conflict prediction is performed according to the driving trajectories of the plurality of mining trucks to obtain a conflict prediction result.

[0114] In this embodiment, the cloud control system can further perform conflict prediction at the intersection of the mining area roads according to the driving trajectories of the multiple mining trucks to obtain conflict prediction results, that is, predict whether a collision will occur if the multiple mining trucks are not controlled and allowed to drive normally.

[0115] S205. If the conflict prediction result indicates that there is a conflict, a traffic strategy for multiple mining trucks is generated according to the conflict prediction result, and the traffic strategy is issued to the corresponding mining trucks to control the mining trucks to execute the traffic strategy.

[0116] In the embodiment of the present application, the passage strategy includes: the passage order of multiple mining trucks, the passage speed of the mining trucks, and the passage trajectory of the mining trucks.

[0117] Specifically, if the cloud control system predicts that if multiple mining trucks are not controlled and allowed to drive normally, they will collide, then the cloud control system can generate traffic strategies for multiple mining trucks based on the conflict prediction results, and send the traffic strategies to the corresponding mining trucks to control the mining trucks to execute the traffic strategies, thereby avoiding collisions and improving the traffic efficiency of autonomous driving mining trucks at intersections.

[0118] The present embodiment provides a control method for an autonomous driving mining truck, the method comprising: obtaining state data of target objects collected by multiple first mining trucks during driving, for each first mining truck, the target objects include: the first mining truck, obstacles around the first mining truck, the obstacles include at least one of the following: a second mining truck other than the first mining truck, and other objects other than the mining truck, the state data includes position, speed and driving direction; identifying one or more state data of the same target object from multiple state data, and fusing the one or more state data of the same target object to obtain fused state data of the same target object; predicting driving trajectories of multiple mining trucks according to the fused state data of the multiple target objects; performing conflict prediction according to the driving trajectories of the multiple mining trucks to obtain conflict prediction results; if the conflict prediction results indicate that there is a conflict, generating a traffic strategy for the multiple mining trucks according to the conflict prediction results, and issuing the traffic strategy to the corresponding mining trucks to control the mining trucks to execute the traffic strategy, the traffic strategy including: the traffic order of the multiple mining trucks, the traffic speed of the mining trucks, and the traffic trajectory of the mining trucks. The following technical effects are achieved: through the on-board terminals carried by multiple first mining trucks, the status data such as the position, speed and travel direction of the vehicle, other mining trucks and other objects collected by each mining truck are obtained in real time, solving the problem of how to obtain the status data of each mining truck and other objects; the traffic strategies of multiple mining trucks are generated according to the conflict prediction results, and the traffic strategies are issued to the corresponding mining trucks to control the mining trucks to execute the traffic strategies and maintain a safe distance between vehicles, thereby avoiding collisions and ensuring the safe passage of mining trucks; by obtaining the status data such as the position, speed and travel direction of the vehicle, other mining trucks and other objects collected by each mining truck in real time, the traffic order, speed and trajectory of each mining truck are generated, so that the traffic strategies of multiple mining trucks can be flexibly adjusted according to the real-time traffic conditions, thereby reducing the waiting time of autonomous driving mining trucks at intersections, improving the traffic efficiency of autonomous driving mining trucks at complex intersections in mining areas, and thus improving the overall transportation efficiency of mining areas.

[0119] Figure 3 A flowchart of a control method for an autonomous driving mining truck provided in an embodiment of the present application Figure 2 In one possible example, Figure 3 As shown, in this embodiment Figure 2 Based on the embodiment, how to generate a plurality of mine truck traffic strategies according to a plurality of status data is described in detail. Figure 3 As shown, the method includes:

[0120] S301. Acquire state data of target objects collected by a plurality of first mining trucks during driving.

[0121] S301 is similar to S201 and will not be described in detail in this embodiment.

[0122] S302. Take each state data as the state data of a target object, and take each target object as each node of the graph neural network to construct a graph neural network.

[0123] Specifically, after obtaining the status data collected by multiple first mining trucks, the cloud control system can first use each target object as a node in the graph neural network to construct a graph neural network, and use each status data as the status data of a target object.

[0124] Figure 4 A schematic diagram of a graph neural network provided in an embodiment of the present application. Figure 4 As shown, the first mining truck 410 can collect status data of multiple obstacles 420 around it through multiple sensors, and the following can be constructed based on the first mining truck 410 and the multiple obstacles 420 around it: Figure 4 The graph neural network shown in FIG. Among them, the first mining truck 410 and the multiple obstacles 420 around it are all nodes in the graph neural network. The cloud control system can build a large graph neural network based on multiple first mining trucks 410 and the multiple obstacles 420 around them. Figure 4 In the figure, only one first mining truck 410 is schematically illustrated.

[0125] S303: Calculate the distance between the two nodes according to the positions in the state data corresponding to the two nodes.

[0126] In an embodiment of the present application, since a graph neural network is constructed based on multiple first mining trucks and the surrounding obstacles they monitor as nodes in the graph neural network, the target objects corresponding to the nodes may be repeated. Therefore, it is first necessary to perform data fusion on the repeated target objects to obtain an updated graph neural network.

[0127] Specifically, for any two nodes in the graph neural network, the cloud control system can determine the similarity between the two nodes based on the status data corresponding to the two nodes, and then determine whether the two nodes are duplicate nodes and whether data fusion is required based on the similarity between the two nodes.

[0128] First, the distance between the two nodes can be calculated based on the positions in the state data corresponding to the two nodes. The distance calculation formula is as follows:

[0129]

[0130] Among them, d is the distance between two nodes. Among the two nodes, the coordinates of one node are (x1, y1, z1), and the coordinates of the other node are (x2, y2, z2).

[0131] S304: If the distance between the two nodes is less than or equal to a preset threshold, the similarity between the two nodes is calculated according to the speed and direction in the state data corresponding to the two nodes.

[0132] Specifically, the distance between any two nodes is compared with a preset threshold. If it is greater than the preset threshold, it indicates that the two nodes are not duplicate nodes and no data fusion is required. If it is less than or equal to the preset threshold, it indicates that the two nodes may be duplicate nodes. The similarity between the two nodes can be further calculated based on the speed and direction in the state data corresponding to the two nodes through the Hungarian matching (Kuhn-Munkres) algorithm to determine whether the two nodes need to be fused.

[0133] In one embodiment, if the speed difference between two nodes is less than or equal to a preset speed threshold, and the angle difference between the directions is less than or equal to a preset angle threshold, then the similarity between the two nodes meets the preset similarity threshold, which indicates that the two nodes are duplicate target objects and data fusion can be performed. Conversely, if the speed difference between the two nodes is greater than the preset speed threshold, or the angle difference between the directions is greater than the preset angle threshold, then it indicates that the two nodes are not duplicate target objects and data fusion is not required.

[0134] In one embodiment, the distance between two nodes, the speed difference, and the angle difference between directions may be weighted and then summed, and the sum result may be used as the similarity between the two nodes.

[0135] S305: If the similarity is greater than or equal to a preset similarity threshold, it is determined that the two nodes correspond to the same target object, and a connecting edge is established between the two nodes.

[0136] Specifically, if the calculated similarity between two nodes is greater than or equal to a preset similarity threshold, it is determined that the two nodes correspond to the same target object, and a connecting edge is established between the two nodes so as to subsequently perform data fusion on the two duplicate nodes.

[0137] Figure 5 This is a schematic diagram of similarity determination of target objects provided in the embodiment of the present application. Figure 5 As shown, mining truck A uses multiple sensors to identify surrounding obstacles including: obstacle A1, obstacle A2, obstacle A3; mining truck B uses multiple sensors to identify surrounding obstacles including: obstacle B1, obstacle B2, obstacle B3. After similarity calculation, if the similarity between obstacle A2 and obstacle B2 is greater than or equal to the preset similarity threshold, then obstacle A2 and obstacle B2 are the same target object and data fusion can be performed; if the similarity between obstacle A3 and obstacle B1 is also greater than or equal to the preset similarity threshold, then obstacle A3 and obstacle B1 are also the same target object and data fusion can also be performed.

[0138] S306: For the same target object, average the positions in one or more state data of the target object as the fusion position of the target object.

[0139] Specifically, one or more state data of the same target object are fused, including position fusion, that is, the positions in one or more state data of the target object are averaged as the fused position of the target object.

[0140] S307 . For the same target object, average the speeds in one or more state data of the target object to serve as the fusion speed of the target object.

[0141] Specifically, the fusion of one or more state data of the same target object also includes speed fusion, that is, averaging the speeds in the one or more state data of the target object as the fused speed of the target object.

[0142] S308: For the same target object, average the directions in one or more state data of the target object as the fusion direction of the target object.

[0143] Specifically, the fusion of one or more state data of the same target object also includes direction fusion, that is, averaging the directions in the one or more state data of the target object as the fusion direction of the target object.

[0144] S309: Generate fusion status data according to the fusion position, fusion speed and fusion direction.

[0145] Specifically, after obtaining the fusion position, fusion speed and fusion direction of the same target object, the fusion state data of the target object can be further generated according to the fusion position, fusion speed and fusion direction.

[0146] S310: Input the fusion state data of multiple target objects into a pre-trained trajectory prediction model to predict the driving trajectory of each mining truck.

[0147] In this embodiment, the cloud control system can predict the driving trajectory of each mining truck by inputting the fused state data of multiple target objects into the pre-trained trajectory prediction model. By predicting the driving trajectory of each mining truck through the fused state data, the prediction accuracy of the driving trajectory of each mining truck is improved.

[0148] S311. Mark the driving tracks of multiple mining trucks on a map.

[0149] In this embodiment, after predicting the driving trajectory of each mining truck, the cloud control system can mark the driving trajectory of each mining truck on the map.

[0150] S312: Determine whether there is any overlapping area between the driving tracks marked on the map.

[0151] In this embodiment, the cloud control system can further determine whether there is an overlapping area of ​​the driving tracks marked on the map.

[0152] S313: If there is an overlapping area, the overlapping area is divided into a plurality of overlapping sub-areas, and the time for the mining truck to reach each overlapping sub-area according to the driving trajectory is estimated.

[0153] In this embodiment, if there is no overlapping area, it indicates that the multiple mining trucks can travel normally and will not collide, and there is no need to intervene in the multiple mining trucks that are traveling normally.

[0154] If there is an overlapping area, the overlapping area can be further divided into multiple overlapping sub-areas, and the time it takes for the mining truck to reach each overlapping sub-area according to the driving trajectory can be estimated.

[0155] S314. For each overlapping sub-area, if at least two times corresponding to the overlapping sub-area overlap, it is determined that there is a conflict in the overlapping sub-area, and a conflict prediction result is generated according to the overlapping sub-area, the overlapping time, and the identification of the mining truck arriving at the overlapping sub-area.

[0156] In this embodiment, for each overlapping sub-area, if the times at which multiple mining trucks arrive at the overlapping sub-area are inconsistent, there is no overlapping time in the overlapping sub-area, indicating that the multiple mining trucks are traveling normally and will not collide, and there is no need to intervene in the multiple mining trucks that are traveling normally.

[0157] If at least two times overlap, it indicates that there is a conflict in the overlapping sub-area. If no intervention is made on the normally running mining trucks, at least two mining trucks will collide during the overlapping time corresponding to the overlapping sub-area.

[0158] Therefore, after determining the overlapping time when the overlapping sub-areas conflict, a conflict prediction result may be generated according to the overlapping sub-areas, the overlapping time, and the identification of the mining truck arriving at the overlapping sub-areas.

[0159] S315: Input the conflict prediction result into the pre-trained traffic strategy prediction model to predict the traffic strategies of multiple mining trucks.

[0160] In this embodiment, if the conflict prediction result indicates that a conflict exists, the cloud control system may further input the conflict prediction result into a pre-trained traffic strategy prediction model to predict the traffic strategies of multiple mining trucks.

[0161] The traffic strategy prediction model is obtained through pre-training. The training process of the traffic strategy prediction model includes:

[0162] First, initial rules such as heavy load first, uphill first, and first come first are obtained to generate an initial traffic strategy with conflicts based on these initial rules, and the initial traffic strategy is executed to obtain the conflict execution result; then, the conflict execution result is input into the traffic strategy prediction model to obtain the predicted traffic strategy; then, the predicted traffic strategy is executed, and the conflict resolution time corresponding to the predicted traffic strategy is obtained; finally, if the conflict resolution time does not meet the preset convergence condition, the traffic strategy prediction model is adjusted according to the conflict resolution time until the conflict resolution time meets the preset convergence condition.

[0163] S316. Send the traffic strategy to the corresponding mining truck to control the mining truck to execute the traffic strategy.

[0164] In this embodiment, the cloud control system can send the traffic strategy generated by the traffic strategy prediction model to the corresponding mining truck to control the mining truck to execute the corresponding traffic strategy.

[0165] A control method for an autonomous driving mining truck provided in an embodiment of the present application predicts the driving trajectory of each mining truck by fusing state data, thereby improving the prediction accuracy of the driving trajectory of each mining truck; after determining the overlapping time when a conflict exists in an overlapping sub-area, a conflict prediction result is generated according to the overlapping sub-area, the overlapping time, and the identification of the mining truck arriving at the overlapping sub-area, thereby improving the accuracy of the conflict prediction result, thereby improving the accuracy of the predicted communication strategy, and ultimately improving the traffic efficiency of the autonomous driving mining truck at the intersection.

[0166] The embodiment of the present invention can divide the electronic device or the main control device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0167] Figure 6 This is a schematic diagram of the structure of a control device for an autonomous driving mining truck provided in an embodiment of the present application. Figure 6 As shown, the control device of the autonomous driving mining truck includes: an acquisition module 610, a fusion module 620, a trajectory prediction module 630, a conflict prediction module 640 and a generation module 650;

[0168] The acquisition module 610 is used to acquire state data of target objects collected by the plurality of first mining trucks during driving. For each first mining truck, the target objects include: the first mining truck, obstacles around the first mining truck, and obstacles include at least one of the following: a second mining truck other than the first mining truck, and other objects other than the mining truck. The state data includes position, speed, and driving direction.

[0169] A fusion module 620 is used to identify one or more state data of the same target object from the multiple state data, and fuse the one or more state data of the same target object to obtain fused state data of the same target object;

[0170] A trajectory prediction module 630, for predicting the driving trajectories of multiple mining trucks according to the fusion state data of multiple target objects;

[0171] A conflict prediction module 640 is used to perform conflict prediction based on the driving trajectories of multiple mining trucks to obtain a conflict prediction result;

[0172] The generation module 650 is used to generate a traffic strategy for multiple mining trucks according to the conflict prediction result if the conflict prediction result indicates the existence of a conflict, and send the traffic strategy to the corresponding mining truck to control the mining truck to execute the traffic strategy. The traffic strategy includes: the traffic order of multiple mining trucks, the traffic speed of the mining truck, and the traffic trajectory of the mining truck.

[0173] In one possible design, the fusion module 620 includes: a construction module, a similarity module, and a connection edge module;

[0174] A construction module is used to take each state data as the state data of a target object, and take each target object as each node of the graph neural network to construct the graph neural network;

[0175] The similarity module is used to determine the similarity between any two nodes in the graph neural network according to the state data corresponding to the two nodes;

[0176] The connection edge module is used to determine that two nodes correspond to the same target object and establish a connection edge between the two nodes if the similarity is greater than or equal to a preset similarity threshold.

[0177] In one possible design, the similarity module includes: a distance module and a speed module;

[0178] The distance module is used to calculate the distance between two nodes according to the positions in the state data corresponding to the two nodes;

[0179] The speed module is used to calculate the similarity between the two nodes according to the speed and direction in the state data corresponding to the two nodes if the distance between the two nodes is less than or equal to a preset threshold.

[0180] In one possible design, the fusion module 620 further includes: a fusion position module, a fusion speed module, a fusion direction module, and a fusion state data module;

[0181] A fusion position module, used for averaging the positions of one or more state data of the same target object as the fusion position of the target object;

[0182] A fusion speed module is used to average the speeds in one or more state data of the same target object as the fusion speed of the target object;

[0183] A fusion direction module is used to average the directions in one or more state data of the same target object as the fusion direction of the target object;

[0184] The fusion state data module is used to generate fusion state data according to the fusion position, fusion speed and fusion direction.

[0185] In one possible design, the conflict prediction module 640 includes a marking module, a judgment module, a division module, and a conflict prediction result module;

[0186] A marking module, used to mark the driving tracks of multiple mining trucks on a map;

[0187] A judgment module, used to judge whether there is an overlapping area between the driving tracks marked on the map;

[0188] A division module, for dividing the overlapping area into a plurality of overlapping sub-areas if there is an overlapping area, and estimating the time for the mining truck to reach each overlapping sub-area according to the driving trajectory;

[0189] The conflict prediction result module is used to determine that there is a conflict in each overlapping sub-area if at least two times corresponding to the overlapping sub-area have overlapping time, and generate a conflict prediction result based on the overlapping sub-area, overlapping time, and the identification of the mining truck arriving at the overlapping sub-area.

[0190] In a possible design, the generation module 650 is further used to input the conflict prediction result into a pre-trained traffic strategy prediction model to predict the traffic strategies of multiple mining trucks;

[0191] The training device of the traffic strategy prediction model includes: an initial rule module, a traffic strategy prediction module, a conflict resolution time module and a convergence module;

[0192] The initial rule module is used to obtain the initial rules, generate the initial traffic strategy with conflicts according to the initial rules, and execute the initial traffic strategy to obtain the conflict execution result. The initial rules include: heavy load first, uphill first, and first come first.

[0193] A traffic strategy prediction module is used to input the conflict execution result into the traffic strategy prediction model to obtain a predicted traffic strategy;

[0194] The conflict resolution time module is used to execute the predicted traffic strategy and obtain the conflict resolution time corresponding to the predicted traffic strategy;

[0195] The convergence module is used to adjust the traffic strategy prediction model according to the conflict resolution time if the conflict resolution time does not meet the preset convergence condition until the conflict resolution time meets the preset convergence condition.

[0196] In a possible design, the trajectory prediction module 630 is further used to input the fusion state data of multiple target objects into a pre-trained trajectory prediction model to predict the driving trajectory of each mining truck.

[0197] The present embodiment provides a control device for an autonomous driving mining truck, which can execute a control method for an autonomous driving mining truck of the above-mentioned embodiment. The implementation principle and technical effects thereof are similar and will not be described in detail in the present embodiment.

[0198] In the specific implementation of the aforementioned control device for an autonomous driving mining truck, each module can be implemented as a processor, and the processor can execute computer execution instructions stored in the memory, so that the processor executes the aforementioned control method for an autonomous driving mining truck.

[0199] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 7 As shown, the electronic device includes: at least one processor 710 and a memory 720. The electronic device also includes a communication component 730. The processor 710, the memory 720 and the communication component 730 are connected via a bus 740.

[0200] In the specific implementation process, at least one processor 710 executes the computer execution instructions stored in the memory 720, so that at least one processor 710 executes a control method for an autonomous driving mining truck as executed by the electronic device side as above.

[0201] The specific implementation process of the processor 710 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0202] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0203] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk storage.

[0204] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0205] The above-mentioned functions implemented by the electronic device and the main control device introduce the scheme provided by the embodiment of the present invention. It can be understood that in order to implement the above-mentioned functions, the electronic device or the main control device includes a hardware structure and / or software module corresponding to the execution of each function. In combination with the units and algorithm steps of each example described in the embodiment disclosed in the embodiment of the present invention, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solution of the embodiment of the present invention.

[0206] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, it is used to implement the control method of an autonomous driving mining truck as described above.

[0207] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0208] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in an electronic device or a main control device.

[0209] The present application also provides a computer program product, which includes a computer program. The computer program is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium. At least one processor executes the computer program so that the electronic device executes the solution provided in any of the above embodiments.

[0210] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by hardware related to program instructions. The above program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above method embodiments are executed; and the above storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0211] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A control method for an automatic driving mining truck, characterized in that: include: Acquire state data of target objects collected by a plurality of first mining trucks during driving, wherein for each of the first mining trucks, the target objects include: the first mining truck, obstacles around the first mining truck, and the obstacles include at least one of the following: a second mining truck other than the first mining truck, and other objects other than the mining truck, and the state data includes position, speed, and driving direction; Identifying one or more state data of the same target object from the plurality of state data, and fusing the one or more state data of the same target object to obtain fused state data of the same target object; Predicting the driving trajectories of a plurality of the mining trucks according to the fused state data of a plurality of the target objects; Performing conflict prediction according to the driving trajectories of the plurality of mining trucks to obtain a conflict prediction result; If the conflict prediction result indicates that there is a conflict, a traffic strategy for multiple mining trucks is generated according to the conflict prediction result, and the traffic strategy is issued to the corresponding mining truck to control the mining truck to execute the traffic strategy, and the traffic strategy includes: the traffic order of multiple mining trucks, the traffic speed of the mining truck, and the traffic trajectory of the mining truck.

2. The method according to claim 1, characterized in that The step of identifying one or more state data of the same target object from the plurality of state data comprises: Taking each of the state data as the state data of a target object, and taking each of the target objects as each node of the graph neural network, so as to construct a graph neural network; For any two of the nodes in the graph neural network, determining the similarity between the two nodes according to the state data corresponding to the two nodes; If the similarity is greater than or equal to a preset similarity threshold, it is determined that the two nodes correspond to the same target object, and a connecting edge is established between the two nodes.

3. The method according to claim 2, characterized in that Determining the similarity between the two nodes according to the state data corresponding to the two nodes includes: Calculating the distance between the two nodes according to the positions in the state data corresponding to the two nodes; If the distance between the two nodes is less than or equal to a preset threshold, the similarity between the two nodes is calculated according to the speed and direction in the state data corresponding to the two nodes.

4. The method according to any one of claims 1 to 3, characterized in that The step of fusing one or more state data of the same target object to obtain the fused state data of the same target object includes: For the same target object, averaging the positions in one or more state data of the target object as the fused position of the target object; For the same target object, averaging the speeds in one or more state data of the target object as the fusion speed of the target object; For the same target object, averaging the directions in one or more state data of the target object as the fusion direction of the target object; The fusion state data is generated according to the fusion position, the fusion speed and the fusion direction.

5. The method according to claim 4, characterized in that The conflict prediction is performed according to the driving trajectories of the plurality of mining trucks to obtain the conflict prediction result, including: Marking the driving tracks of the plurality of mining trucks on a map; Determining whether there is an overlapping area between the driving tracks marked on the map; If there is an overlapping area, the overlapping area is divided into a plurality of overlapping sub-areas, and the time for the mining truck to reach each overlapping sub-area according to the driving trajectory is estimated; For each overlapping sub-area, if at least two times corresponding to the overlapping sub-area overlap, it is determined that there is a conflict in the overlapping sub-area, and the conflict prediction result is generated based on the overlapping sub-area, the overlapping time, and the identification of the mining truck arriving at the overlapping sub-area.

6. The method according to claim 5, characterized in that The generating of a plurality of passage strategies for the mining trucks according to the conflict prediction results comprises: Inputting the conflict prediction result into a pre-trained traffic strategy prediction model to predict the traffic strategies of the plurality of mining trucks; The training process of the traffic strategy prediction model includes: Acquire initial rules, generate an initial traffic strategy with conflicts according to the initial rules, and execute the initial traffic strategy to obtain conflict execution results, wherein the initial rules include: heavy load first, uphill first, and first come first; Inputting the conflict execution result into the traffic strategy prediction model to obtain a predicted traffic strategy; Executing the predicted traffic strategy and obtaining the conflict resolution time corresponding to the predicted traffic strategy; If the conflict resolution time does not meet the preset convergence condition, the traffic strategy prediction model is adjusted according to the conflict resolution time until the conflict resolution time meets the preset convergence condition.

7. The method according to claim 6, characterized in that The predicting the driving trajectories of the plurality of mining trucks according to the fused state data of the plurality of target objects comprises: The fused state data of the plurality of target objects are input into a pre-trained trajectory prediction model to predict the driving trajectory of each mining truck.

8. A control device for an automatic driving mining truck, characterized in that: include: an acquisition module, configured to acquire state data of target objects collected by a plurality of first mining trucks during driving, wherein for each of the first mining trucks, the target objects include: the first mining truck, obstacles around the first mining truck, the obstacles include at least one of the following: a second mining truck other than the first mining truck, and other objects other than the mining truck, and the state data includes position, speed, and driving direction; A fusion module, used for identifying one or more state data of the same target object from the plurality of state data, and fusing the one or more state data of the same target object to obtain fused state data of the same target object; A trajectory prediction module, used for predicting the driving trajectories of a plurality of the mining trucks according to the fused state data of a plurality of the target objects; A conflict prediction module, used for performing conflict prediction according to the driving trajectories of the plurality of mining trucks to obtain a conflict prediction result; A generation module is used to generate a plurality of traffic strategies for the mining trucks according to the conflict prediction result if the conflict prediction result indicates the existence of a conflict, and send the traffic strategy to the corresponding mining truck to control the mining truck to execute the traffic strategy, wherein the traffic strategy includes: the traffic order of the plurality of mining trucks, the traffic speed of the mining truck, and the traffic trajectory of the mining truck.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the control method of the autonomous driving mining truck according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the control method for an autonomous driving mining truck as described in any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the control method of the autonomous driving mining truck as described in any one of claims 1 to 7 is implemented.