A control method, device, equipment and medium for engineering vehicles based on AI algorithm

Abstract

The present application relates to the field of vehicle control, and in particular to a method, device, equipment and medium for engineering vehicle control based on AI algorithm. The method includes: the present application obtains the work plan of the vehicle to be controlled that has not been carried out in the current cycle, and generates the corresponding work instructions for each moment based on these plans, so as to ensure that the engineering vehicle works according to the preset driving trajectory and operation sequence, thereby reducing the labor cost during the work of the engineering vehicle. Furthermore, it not only relies on the pre-set work plan, but also monitors its working status by obtaining the working image of the vehicle to be controlled in real time. Based on the analysis of the working image, it can intelligently judge whether the work instructions need to be adjusted to adapt to the changes in the actual situation, which not only ensures that the engineering vehicle can work in the optimal state, but also can respond quickly when encountering emergencies to avoid potential safety hazards and efficiency losses.

Description

Technical Field

[0001] The present application relates to the field of vehicle control, and in particular to an engineering vehicle control method, device, equipment and medium based on an AI algorithm. Background Art

[0002] Engineering vehicles are the backbone of a construction project. They are mainly used for transportation, excavation, and emergency repairs. They are one of the indispensable tools on the construction site, including excavators and loaders. With the continuous development of artificial intelligence technology, intelligence has become an important trend in the field of vehicle control.

[0003] Engineering vehicles such as excavators and loaders are usually operated by drivers on site. With the advancement of technology, the concept of remote intelligent control of excavators and other engineering vehicles has emerged, allowing operators to use handles or controllers to control them when they are close to the mechanical equipment. However, when the operator uses the handle or controller to control the engineering vehicle, he still needs to operate near the engineering vehicle and monitor the working status of the engineering vehicle, which does not reduce the labor cost during the operation of the engineering vehicle. Summary of the invention

[0004] In order to reduce the labor cost during the operation of an engineering vehicle, the present application provides an engineering vehicle control method, device, equipment and medium based on an AI algorithm.

[0005] In the first aspect, the present application provides an engineering vehicle control method based on an AI algorithm, which adopts the following technical solutions:

[0006] A control method for an engineering vehicle based on an AI algorithm, comprising:

[0007] Obtaining a work plan of the vehicle to be controlled that has not been performed in the current cycle, wherein the work plan includes a vehicle driving plan and a vehicle operation plan, wherein the vehicle driving plan is a preset driving trajectory of the vehicle, and the vehicle operation plan is an operation performed by the vehicle in chronological order;

[0008] Based on the work plan, generate work instructions corresponding to each moment in the current cycle;

[0009] According to the time corresponding to each work instruction, the work instruction is sent to the terminal of the vehicle to be controlled in sequence, and the work image of the vehicle to be controlled is acquired in real time;

[0010] Based on the working image of the vehicle to be controlled, it is determined whether to adjust the working instruction.

[0011] By adopting the above technical solution, by obtaining the work plans that the vehicle to be controlled has not performed in the current cycle, and generating the corresponding work instructions for each moment based on these plans, it is possible to ensure that the engineering vehicle works according to the preset driving trajectory and operation sequence, thereby reducing the labor cost during the work of the engineering vehicle. Furthermore, it not only relies on the pre-set work plan, but also monitors its working status by obtaining the working image of the vehicle to be controlled in real time. Based on the analysis of the working image, it can intelligently determine whether the work instructions need to be adjusted to adapt to changes in the actual situation, which not only ensures that the engineering vehicle can work in the optimal state, but also can respond quickly when encountering emergencies to avoid potential safety hazards and efficiency losses. In addition, by continuously collecting and analyzing work image data, it is also possible to continuously optimize future work plans and instruction generation strategies, further improving the operating efficiency and intelligence level of engineering vehicles.

[0012] In a possible implementation, generating a work instruction corresponding to each moment in the current cycle based on the work plan includes:

[0013] Based on the vehicle driving plan and the vehicle operation plan, generating a first work instruction and a second work instruction corresponding to each moment in the current cycle;

[0014] Based on the first working instruction and the second working instruction, a working instruction corresponding to each moment in the current cycle is obtained.

[0015] By adopting the above technical solution, by breaking down the work plan into the first work instruction and the second work instruction corresponding to each moment, refined management of vehicle driving and work tasks is achieved. This refined management method not only ensures that the vehicle can accurately execute according to the preset driving trajectory and work sequence, but also can accurately control the behavior of the vehicle at each critical moment, thereby helping to reduce errors and delays in the task execution process, improve the overall operation efficiency of engineering vehicles, and at the same time, enable the vehicle to more flexibly respond to complex working environments and changing task requirements.

[0016] In a possible implementation, the vehicle operation plan includes an operation position, and generating the first work instruction and the second work instruction corresponding to each moment in the current cycle based on the vehicle driving plan and the vehicle operation plan includes:

[0017] Predicting the operation duration corresponding to each operation in the vehicle operation plan, and determining the planned duration of the current cycle from the current moment to the end moment;

[0018] Based on the vehicle operation plan, dividing the vehicle travel plan into a plurality of vehicle travel sub-plans;

[0019] Determine the vehicle driving duration corresponding to each vehicle driving sub-plan based on the operation duration corresponding to each of the work operations and the planned duration;

[0020] Based on the vehicle driving sub-plan and the vehicle driving time corresponding to each vehicle driving sub-plan, a first work instruction corresponding to each moment in the current cycle is generated, and based on the vehicle driving time corresponding to each vehicle driving sub-plan, a second work instruction corresponding to each moment in the current cycle is determined.

[0021] By adopting the above technical solution, by predicting the operation time corresponding to each operation and dividing the vehicle driving plan into multiple sub-plans accordingly, it can ensure that the vehicle has enough time to make necessary preparations and perform operations at each operation location. At the same time, since each vehicle driving sub-plan corresponds to a specific driving time and operation, the first work instruction (controlling vehicle driving) and the second work instruction (operation) can be matched more accurately, reducing operation delays or errors caused by time mismatch. Further, the vehicle driving plan is divided into multiple sub-plans, and the driving time is determined based on the operation time of each operation, so that the plan has higher flexibility. In the actual operation process, if there are changes in the operating environment, equipment failures, or task priority adjustments, the driving time or operation of a sub-plan can be quickly adjusted or reallocated without large-scale modifications to the entire plan. It not only helps to respond quickly to emergencies, but also optimizes the operation process according to real-time conditions and improves the adaptability of the plan.

[0022] In a possible implementation, based on the vehicle operation plan, the vehicle driving plan is divided into a plurality of vehicle driving sub-plans, including:

[0023] Sorting each operation position in the vehicle operation plan in chronological order to obtain an operation position sequence;

[0024] Each work position in the work position sequence is taken as a division point, so as to divide the vehicle driving plan into a plurality of vehicle driving sub-plans based on the division points.

[0025] By adopting the above technical solution, each work position in the vehicle operation plan is sorted in chronological order, ensuring the consistency between the logical order of the work positions and the actual operation process. On this basis, each work position is used as a dividing point to divide the vehicle driving plan, making the operation process clearer, easier for drivers and dispatchers to grasp and understand, and reducing operational errors and communication costs. By dividing the vehicle driving plan into multiple sub-plans, each sub-plan corresponds to one or several specific work positions and corresponding driving time periods, so that dispatchers can arrange vehicle driving and operations more flexibly and adjust the order or content of sub-plans according to actual needs.

[0026] In a possible implementation, determining the vehicle driving duration corresponding to each vehicle driving sub-plan based on the operation duration corresponding to each of the work operations and the planned duration includes:

[0027] Based on the operation duration corresponding to each of the operation operations, the total operation duration corresponding to the vehicle operation plan is calculated, and the time difference between the plan duration and the total operation duration is calculated to obtain the total driving time corresponding to the vehicle driving plan;

[0028] Determine the driving distance corresponding to each vehicle driving sub-plan;

[0029] Based on the total driving time and the driving distance corresponding to each of the vehicle driving sub-plans, the vehicle driving time corresponding to each of the vehicle driving sub-plans is calculated.

[0030] By adopting the above technical solution, the total duration of the vehicle operation plan is calculated according to the operation duration of each operation operation, and the total duration of the vehicle driving plan is obtained by comparing it with the planned duration. Furthermore, the driving duration of each sub-plan is calculated according to the driving distance corresponding to each vehicle driving sub-plan, which can ensure the reasonable allocation of time among different sub-plans, help avoid time waste and inefficiency, and improve overall operating efficiency.

[0031] In a possible implementation, determining whether to adjust the working instruction based on the working image of the vehicle to be controlled includes:

[0032] Identifying the working image of the vehicle to be controlled and determining the current action of the vehicle to be controlled;

[0033] Determining at least two expected vehicle actions corresponding to the current moment in the work plan;

[0034] Calculating the similarity between the current action and each of the expected vehicle actions, and determining whether there is a target expected vehicle action, the similarity between the target expected vehicle action and the current action being greater than a similarity threshold;

[0035] If the target expected vehicle action exists, it is determined that there is no need to adjust the work instruction.

[0036] By adopting the above technical solution, the working image of the controlled vehicle is identified to determine its current action. This step relies on advanced image recognition technology, which can accurately capture and identify the vehicle action. Then, the current action is calculated similar to at least two expected vehicle actions corresponding to the current moment in the work plan. By comparing the difference between the current action and the expected action, it can be more accurately determined whether the vehicle is operating according to the plan. When there is a target expected vehicle action with a similarity greater than a threshold to the current action, it means that the vehicle is operating according to the plan and there is no need to adjust the work instructions.

[0037] In a possible implementation, when the target predicted vehicle action does not exist, the method further includes:

[0038] Determining a contextual relationship between the current action and the expected vehicle action;

[0039] If the current action is before the expected vehicle action, determining based on the current action that no work is performed in the current cycle;

[0040] Based on the unperformed work and the duration corresponding to the current cycle, the work instruction corresponding to each moment is regenerated.

[0041] By adopting the above technical solution, the relationship between the current action and the expected vehicle action can be automatically identified, and the deviation in the operation process can be identified at the first time. When the current action is ahead of the expected vehicle action, it means that the vehicle is working ahead of schedule or not according to the plan, so the work instructions are regenerated so that the vehicle to be controlled can work according to the plan, and the overall operation efficiency is improved by adapting to the changes in the operation process.

[0042] In the second aspect, the present application provides an engineering vehicle control device based on an AI algorithm, which adopts the following technical solution:

[0043] An engineering vehicle control device based on AI algorithm, comprising:

[0044] An acquisition module, used for acquiring a work plan of the vehicle to be controlled that has not been performed in the current cycle, wherein the work plan includes a vehicle driving plan and a vehicle operation plan, wherein the vehicle driving plan is a preset driving trajectory of the vehicle, and the vehicle operation plan is an operation operation performed by the vehicle in chronological order;

[0045] A generating module, used for generating work instructions corresponding to each moment in the current cycle based on the work plan;

[0046] A sending module, used to send the work instructions to the terminal of the vehicle to be controlled in sequence according to the time corresponding to each work instruction, and obtain the working image of the vehicle to be controlled in real time;

[0047] A determination module is used to determine whether to adjust the working instruction based on the working image of the vehicle to be controlled.

[0048] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0049] An electronic device, comprising:

[0050] at least one processor;

[0051] Memory;

[0052] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the engineering vehicle control method based on the AI ​​algorithm described in the first aspect above.

[0053] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0054] A computer-readable storage medium, comprising: storing a computer program that can be loaded by a processor and execute the engineering vehicle control method based on the AI ​​algorithm described in the first aspect above.

[0055] In summary, this application includes the following beneficial technical effects:

[0056] By obtaining the work plans that the controlled vehicle has not performed in the current cycle, and generating the corresponding work instructions for each moment based on these plans, it can ensure that the engineering vehicle works according to the preset driving trajectory and operation sequence, thereby reducing the labor cost during the work of the engineering vehicle. Furthermore, it not only relies on the pre-set work plan, but also monitors its working status by obtaining the working image of the controlled vehicle in real time. Based on the analysis of the working image, it can intelligently determine whether the work instructions need to be adjusted to adapt to the changes in the actual situation, which not only ensures that the engineering vehicle can work in the optimal state, but also can respond quickly when encountering emergencies to avoid potential safety hazards and efficiency losses. In addition, by continuously collecting and analyzing work image data, it is also possible to continuously optimize future work plans and instruction generation strategies, further improving the operating efficiency and intelligence level of engineering vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a schematic diagram of the connection and interaction between an electronic device and a terminal on an engineering vehicle provided in an embodiment of the present application;

[0058] Figure 2 It is a flowchart of an engineering vehicle control method based on an AI algorithm provided in an embodiment of the present application;

[0059] Figure 3 It is a block diagram of an engineering vehicle control device based on an AI algorithm provided in an embodiment of the present application;

[0060] Figure 4 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following is combined with Figure 1 -Attached Figure 4 This application is described in further detail.

[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] In order to facilitate understanding of the technical solution proposed in this application, several elements introduced in the description of this application are first introduced here. It should be understood that the following introduction is only for the convenience of understanding these elements, so as to understand the content of the embodiments of this application, and does not necessarily cover all possible situations.

[0064] Engineering vehicles are the backbone of a construction project, mainly used for transportation, excavation, and repair of the project, and are one of the indispensable tools on the construction site. Common engineering vehicles mainly include the following categories: heavy transport vehicles: used to transport large amounts of materials, such as earthwork, stone, and building materials; large cranes: used to hoist heavy equipment and components, such as steel structures and bridge components; excavators: earthmoving machinery that uses a machine bucket to dig materials, suitable for excavating earthwork; bulldozers: used for earthwork excavation, transportation, or rock and soil processing, widely used in open-air sites; road rollers: mostly used for filling and compaction of large-scale projects such as high-grade highways, railways, expressways, and airport runways; loaders: engineering machinery used to transport earthwork and stone, widely used in the construction of large-scale projects such as highways, railways, ports, docks, and mines; power repair vehicles: engineering vehicles specifically used for repairing and maintaining power system failures; engineering rescue vehicles: engineering vehicles used to respond to natural disasters and emergencies and conduct emergency rescue.

[0065] Engineering vehicles such as excavators and loaders are usually operated by drivers on site. With the advancement of technology, the concept of remote intelligent control of excavators and other engineering vehicles has emerged, allowing operators to use handles or controllers to control them when they are close to the mechanical equipment. However, when the operator uses the handle or controller to control the engineering vehicle, he still needs to operate near the engineering vehicle and monitor the working status of the engineering vehicle, which does not reduce the labor cost during the operation of the engineering vehicle.

[0066] In view of this, the embodiment of the present application provides an engineering vehicle control method based on an AI algorithm, such as Figure 1 As shown, the electronic device establishes connections with the terminals 101 on each engineering vehicle respectively, and the electronic device can obtain the vehicle driving information and vehicle operation information of each terminal 101. The electronic device can also control the corresponding driving and operation of each engineering vehicle.

[0067] The present application embodiment provides an engineering vehicle control method based on an AI algorithm, such as Figure 2 As shown, the method provided in the embodiment of the present application is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S201 to S204, wherein:

[0068] Step S201: Obtain the work plan of the vehicle to be controlled that has not been performed in the current cycle.

[0069] Among them, the current cycle can be the time period required for the vehicle to be controlled to complete the current work plan. The work plan includes a vehicle driving plan and a vehicle operation plan. The vehicle driving plan is the preset driving trajectory of the vehicle, and the vehicle operation plan is the operation operation performed by the vehicle in chronological order. Specifically, the vehicle driving plan includes the path that the vehicle needs to travel in the time period between the current moment and the end moment of the current cycle, that is, the vehicle driving plan includes various positions during the driving process. At the same time, the vehicle operation plan includes various operation operations and the position corresponding to each operation operation, wherein there may be multiple operation operations between two adjacent sub-trajectories. Exemplarily, taking an excavator as an example, the vehicle driving plan of the excavator in the current cycle is from position A through trajectory a to position B, and then through trajectory b to position C. The vehicle operation plan can be that the excavator digs four times at position B. In this example, digging four times is four operation operations.

[0070] When there is a task to be performed by an engineering vehicle, an engineering vehicle of the same type as that required for the task is selected from multiple idle engineering vehicles based on the type of engineering vehicle required for the task as the vehicle to be controlled. Furthermore, based on the duration required for the task and the position corresponding to the task, a trajectory of the vehicle to be controlled from the current position to the position corresponding to the task is generated, and a trajectory from the position corresponding to the task to the end position of the task is generated, so as to obtain a vehicle driving plan for the vehicle to be controlled, and based on the requirements of the task and the position corresponding to the task, a vehicle operation plan for the vehicle to be controlled is generated to obtain a vehicle operation plan corresponding to the current cycle and a vehicle driving plan corresponding to the current cycle. The duration required for the task can be obtained by prediction based on historical data, or by receiving the duration input by the staff, and this is not limited in the embodiments of the present application.

[0071] Step S202: Based on the work plan, generate work instructions corresponding to each moment in the current cycle.

[0072] Among them, the work instruction is used to instruct the vehicle to be controlled to drive or perform work operations.

[0073] After obtaining the work plan of the vehicle to be controlled, the work instructions corresponding to each moment in the current cycle can be generated. Specifically, the preset driving speed of the vehicle to be controlled can be obtained, and based on the preset driving trajectory of the vehicle to be controlled in the vehicle driving plan, the first duration required for the vehicle driving trajectory of the vehicle to be controlled is calculated, and based on the difference between the remaining duration of the current cycle and the first duration, the second duration required for the vehicle operation plan of the vehicle to be controlled is obtained. Based on the position corresponding to each operation operation and the order corresponding to each operation operation, the preset driving trajectory of the vehicle to be controlled is divided into multiple preset sub-trajectories, and the first sub-duration corresponding to each preset sub-trajectory is obtained according to the proportion of each preset sub-trajectory in the preset driving trajectory. At the same time, the number of operation operations and the average value of the second duration are calculated, and the second sub-duration corresponding to each operation operation is calculated. Each preset sub-trajectory and the operation operation are sorted in time order to obtain a target sequence, and the work instructions corresponding to each moment in the current cycle are obtained based on the sub-duration corresponding to each preset sub-trajectory and the second sub-duration corresponding to each operation operation.

[0074] More specifically, the sub-duration corresponding to the first element (preset sub-trajectory or operation) in the target sequence determines the work instruction corresponding to each moment in the sub-duration as the work instruction corresponding to the first element; and the sub-duration corresponding to the second element (preset sub-trajectory or operation) in the target sequence determines the work instruction corresponding to each moment in the sub-duration as the work instruction corresponding to the second element; similarly, the work instruction corresponding to each moment of each element in the target sequence can be obtained to obtain the work instruction corresponding to each moment in the current cycle. Among them, the work instruction corresponding to the expected sub-trajectory is to drive according to the trajectory, and the work instruction corresponding to the operation is to perform the operation according to the corresponding preset action. Different types of engineering vehicles have different corresponding preset actions during the work process. The preset action is entered in advance, and one operation corresponds to at least one preset action.

[0075] Step S203: sending the work instructions to the terminal of the vehicle to be controlled in sequence according to the time corresponding to each work instruction, and acquiring the work image of the vehicle to be controlled in real time.

[0076] Among them, the vehicle to be controlled is equipped with an image acquisition device or a holographic imaging device, which can capture a working image containing the current action of the complete vehicle to be controlled.

[0077] After obtaining the work instructions corresponding to each moment, according to the time corresponding to each work instruction, when the corresponding time is reached, the work instruction is sent to the terminal with the controlled vehicle, and based on the image acquisition device or holographic imaging device installed on the vehicle to be controlled, the working image of the vehicle to be controlled is acquired in real time.

[0078] Step S204: Determine whether to adjust the working instruction based on the working image of the vehicle to be controlled.

[0079] After obtaining the working image of the vehicle to be controlled, the shape of the vehicle to be controlled in the working image is identified based on the image recognition algorithm to identify the image state of the vehicle to be controlled, obtain the current state corresponding to the vehicle to be controlled at the current moment, and calculate the similarity between the current state and the image state based on the cosine distance. If the similarity between the current state and the image state is greater than the preset similarity, it means that the vehicle to be controlled is operating according to the work plan at this time, and there is no need to adjust the work instructions at this time; if the similarity between the current state and the image state is not greater than the preset similarity, it means that the vehicle to be controlled may not be operating according to the work plan at this time, and the work instructions need to be adjusted at this time. Among them, the image state can be a driving state or an operating state, and the current state can be a driving state or an operating state.

[0080] Furthermore, when the work order needs to be adjusted, the current position of the vehicle to be controlled is obtained, and a trajectory of the vehicle to be controlled from the current position to the position corresponding to the task is generated, and a trajectory corresponding to the position corresponding to the task to the end position of the task is generated, so as to obtain a vehicle travel plan of the vehicle to be controlled, and at the same time, based on the requirements of the task and the position corresponding to the task, a vehicle operation plan of the vehicle to be controlled is generated, and the work order of the vehicle to be controlled is regenerated based on the vehicle travel plan and the vehicle operation plan of the vehicle to be controlled. Among them, the process of generating the work order of the vehicle to be controlled is consistent with the process of generating the work order of the vehicle to be controlled in the above step S203, and the embodiment of the present application is not limited to this.

[0081] The embodiment of the present application provides a control method for engineering vehicles based on an AI algorithm. By acquiring the work plans that have not been performed by the controlled vehicle in the current cycle and generating the corresponding work instructions for each moment based on these plans, it is possible to ensure that the engineering vehicle works according to the preset driving trajectory and operation sequence, thereby reducing the labor cost during the work of the engineering vehicle. Furthermore, it not only relies on the pre-set work plan, but also monitors its working status by acquiring the working image of the controlled vehicle in real time. Based on the analysis of the working image, it can intelligently determine whether the work instructions need to be adjusted to adapt to changes in the actual situation, which not only ensures that the engineering vehicle can work in the optimal state, but also can respond quickly when encountering emergencies to avoid potential safety hazards and efficiency losses. In addition, by continuously collecting and analyzing work image data, future work plans and instruction generation strategies can be continuously optimized to further improve the operating efficiency and intelligence level of engineering vehicles.

[0082] In a possible implementation of the embodiment of the present application, in the above step S202, based on the work plan, a work instruction corresponding to each moment in the current cycle is generated, including:

[0083] Based on the vehicle driving plan and the vehicle operation plan, generate a first work instruction and a second work instruction corresponding to each moment in the current cycle;

[0084] Based on the first working instruction and the second working instruction, the working instruction corresponding to each moment in the current cycle is obtained.

[0085] The first working instruction is used to instruct the vehicle to be controlled to travel, and the second working instruction is used to instruct the vehicle to be controlled to operate.

[0086] Specifically, the total duration of the current cycle (i.e., the duration between the current moment and the end moment of the current cycle) can be divided into several small time periods (e.g., one time period per minute or every few seconds), and each time period corresponds to a specific moment. Furthermore, for each moment, the position, speed, steering, and other states that the vehicle should be in at that moment are determined according to the vehicle driving plan. These state information are organized into the first work instruction, for example: "At XX moment, the vehicle should travel to XX position at XX speed and prepare to turn to XX direction."

[0087] Similarly, for each moment, according to the vehicle operation plan, determine whether the vehicle needs to perform an operation at that moment, as well as the specific type, location, duration, etc. of the operation. These operation information are organized into a second work instruction, for example: "At XX time, the vehicle should perform XX operation at XX location for XX time".

[0088] Furthermore, the first working instruction and the second working instruction at each moment are integrated to form a working instruction set at that moment, which includes all driving and working instructions that the vehicle should execute at that moment.

[0089] A possible implementation of the embodiment of the present application, in the above embodiment, when the vehicle operation plan includes the operation position, based on the vehicle driving plan and the vehicle operation plan, generating the first work instruction and the second work instruction corresponding to each moment in the current cycle, includes:

[0090] Predict the operation duration corresponding to each operation in the vehicle operation plan, and determine the planned duration of the current cycle from the current time to the end time;

[0091] Based on the vehicle operation plan, the vehicle driving plan is divided into a plurality of vehicle driving sub-plans;

[0092] Determine the vehicle driving time corresponding to each vehicle driving sub-plan based on the operation time and the planned time corresponding to each operation;

[0093] Based on the vehicle driving sub-plan and the vehicle driving time corresponding to each vehicle driving sub-plan, a first work instruction corresponding to each moment in the current cycle is generated, and based on the vehicle driving time corresponding to each vehicle driving sub-plan, a second work instruction corresponding to each moment in the current cycle is determined.

[0094] Among them, each work operation corresponding to each engineering vehicle type corresponds to a work operation duration.

[0095] Specifically, after obtaining the vehicle operation plan of the vehicle to be controlled, the estimated operation duration corresponding to each operation operation in the vehicle operation plan can be obtained based on the type of engineering vehicle to be controlled and the various operation operations included in the vehicle operation plan, and the duration from the current moment to the end moment of the current cycle can be calculated to obtain the planned duration.

[0096] Since the driving and operation of the engineering vehicle are generally performed separately rather than simultaneously in completing the task engineering, the vehicle driving plan can be divided into multiple vehicle driving sub-plans based on the vehicle operation plan of the vehicle to be controlled. Specifically, each operation position can be used as an intermediate node, and the expected driving trajectory of the vehicle to be controlled can be divided into multiple driving sub-trajectories to obtain multiple vehicle driving sub-plans. Furthermore, after obtaining the operation duration and planned duration corresponding to each operation operation, the total vehicle driving duration can be obtained based on the total vehicle driving duration = planned duration - the sum of the operation duration corresponding to the operation operation, and the vehicle driving duration corresponding to each vehicle driving sub-plan can be obtained based on the ratio of each driving sub-trajectory to the driving trajectory.

[0097] Furthermore, each driving sub-trajectory and work operation is sorted in chronological order to obtain a target sequence, and based on the sub-duration corresponding to each driving sub-trajectory and the second sub-duration corresponding to each work operation, the first work instruction and the second work instruction corresponding to each moment in the current cycle are obtained.

[0098] More specifically, the first element in the target sequence is obtained, and it is determined whether the first element is a driving sub-trajectory or a working operation. If the first element is a driving sub-trajectory, the work instruction corresponding to the first element at each moment in the sub-time length corresponding to the first element is taken as the first work instruction, and the second work instruction is determined to be none; the second element in the target sequence is obtained, and it is determined whether the second element is a driving sub-trajectory or a working operation. If the second element is a working operation, the second work instruction corresponding to each moment in the sub-time length corresponding to the second element in the target sequence is determined as the work instruction corresponding to the second element, and the first work instruction corresponding to each moment in the sub-time length corresponding to the second element is determined to be none; similarly, the first work instruction and the second work instruction corresponding to each element in the target sequence at each moment are obtained to obtain the first work instruction and the second work instruction corresponding to each moment in the current cycle.

[0099] A possible implementation of the embodiment of the present application is that in the above embodiment, based on the vehicle operation plan, the vehicle driving plan is divided into multiple vehicle driving sub-plans, including:

[0100] Sort each operation position in the vehicle operation plan in chronological order to obtain an operation position sequence;

[0101] Each work position in the work position sequence is taken as a division point, so as to divide the vehicle driving plan into a plurality of vehicle driving sub-plans based on the division point.

[0102] Among them, the time sequence is the order in which time develops naturally.

[0103] Specifically, the extracted working positions may be sorted in chronological order based on the chronological order of the working positions in the vehicle working plan to form a working position sequence.

[0104] Each work position in the work position sequence is regarded as a potential split point, which will be used to split the vehicle driving plan into multiple sub-plans, where each work position corresponds to a split point.

[0105] Furthermore, based on the determined division points, the vehicle driving plan is divided into multiple vehicle driving sub-plans, each of which should cover the driving path and necessary time arrangements from the previous division point to the current division point. Specifically, for the first division point (i.e., the first work position), the vehicle driving sub-plan should start from the starting point and end at the first work position. For subsequent division points, the vehicle driving sub-plan should start from the previous work position, go through the necessary driving path, and reach the current work position, thereby obtaining multiple vehicle driving sub-plans after division.

[0106] A possible implementation of the embodiment of the present application, in the above embodiment, based on the operation duration and the planned duration corresponding to each operation operation, determining the vehicle driving duration corresponding to each vehicle driving sub-plan includes:

[0107] Based on the operation time corresponding to each operation operation, the total operation time corresponding to the vehicle operation plan is calculated, and the time difference between the plan time and the total operation time is calculated to obtain the total driving time corresponding to the vehicle driving plan;

[0108] Determine the driving distance corresponding to each vehicle driving sub-plan;

[0109] Based on the total driving time and the driving distance corresponding to each vehicle driving sub-plan, the vehicle driving time corresponding to each vehicle driving sub-plan is calculated.

[0110] After obtaining the operation duration and planned duration corresponding to each operation, the vehicle driving duration corresponding to each vehicle driving sub-plan can be determined. Specifically, each operation and its corresponding operation duration are listed. The operation duration of each operation is accumulated to obtain the total operation duration of the entire vehicle operation plan, and the total operation duration is subtracted from the planned duration to obtain the remaining time difference. This difference is the total driving duration corresponding to the vehicle driving plan, and this time difference includes the total time required for all vehicles to travel between the operation points.

[0111] Furthermore, the driving distance corresponding to each vehicle driving sub-plan (the driving plan of each vehicle from the starting point to the end point) is determined according to the map or the pre-set route. The driving time is allocated in proportion to the total driving time and the driving distance of each vehicle driving sub-plan. For example, if the driving distance of a vehicle driving sub-plan accounts for 1 / 3 of the total distance, then the driving time of the sub-plan should also be 1 / 3 of the total driving time.

[0112] In a possible implementation of the embodiment of the present application, in the above step S204, determining whether to adjust the working instruction based on the working image of the vehicle to be controlled includes:

[0113] Identify the working image of the vehicle to be controlled and determine the current action of the vehicle to be controlled;

[0114] Determining at least two expected vehicle actions corresponding to the current time in the work plan;

[0115] Calculate the similarity between the current action and each expected vehicle action, and determine whether there is a target expected vehicle action, and the similarity between the target expected vehicle action and the current action is greater than a similarity threshold;

[0116] If the target expected vehicle action exists, it is determined that no adjustment to the work order is required.

[0117] In order to facilitate the recognition of the actions of the engineering vehicle, an image recognition system can be established, which can recognize various possible actions of the engineering vehicle, such as driving, stopping, turning, loading, unloading, etc. The image recognition system is trained through machine learning and can accurately match the engineering vehicle actions in the image with the preset action labels.

[0118] Specifically, after obtaining the working image of the vehicle to be controlled, the image recognition system can be used to perform real-time recognition of the working image of the vehicle to be controlled. The image recognition system will analyze the vehicle shape, position, angle and other information in the image, compare it with the preset action library, and determine the current action of the vehicle.

[0119] Furthermore, the expected vehicle action corresponding to the current moment is obtained. The work plan contains multiple possible actions (for example, driving, digging, etc.), so the current moment may correspond to at least two expected vehicle actions. After obtaining the expected vehicle action corresponding to the current moment, the similarity between the current action and each expected vehicle action can be calculated based on the similarity calculation rules defined in advance. The defined similarity calculation rules are formulated based on multiple dimensions such as the shape, direction, speed, etc. of the action, and are used to measure the similarity between the current action and each expected vehicle action, and set a similarity threshold to determine which expected vehicle action the current action is closest to.

[0120] Furthermore, among all the predicted vehicle actions, the action whose similarity with the current action is greater than a similarity threshold is found and determined as the target predicted vehicle action.

[0121] If there is a target expected vehicle action and its similarity is high enough (i.e., greater than the set threshold), the current vehicle action is considered to be consistent with the expectations in the work plan and there is no need to adjust the work instructions.

[0122] If there is no target expected vehicle action, or the similarity of all expected vehicle actions is below a threshold, it is considered that the current vehicle action does not match the expectations in the work plan, and the work instructions need to be adjusted to ensure that the vehicle can work as planned.

[0123] In a possible implementation manner of the embodiment of the present application, in the above embodiment, when there is no target predicted vehicle action, the method further includes:

[0124] Determine the context of the current action and the expected vehicle action;

[0125] If the current action is before the expected vehicle action, then based on the current action, it is determined that no work is performed in the current cycle;

[0126] Based on the unperformed work and the duration corresponding to the current cycle, the work instructions corresponding to each moment are regenerated.

[0127] When the image recognition system fails to find a target predicted vehicle action that matches the current vehicle action, the work instruction can be regenerated. Specifically, the context of the current action and the predicted vehicle action can be determined, whether the work has been completed in the current cycle can be determined, and the work instruction can be regenerated based on this information. More specifically, by comparing the predicted vehicle action sequence listed in the work plan, it is analyzed whether the current vehicle action is logically located before or after one or some predicted actions, or is a completely unrelated action. Among them, the work plan corresponds to a preset vehicle action sequence, which is obtained by sorting according to the time development.

[0128] If the current action is before the expected vehicle action corresponding to the current moment, it means that there is no work done in the current cycle, or the work progress is not in line with the plan, and the work instructions corresponding to each moment need to be regenerated. Specifically, the current position of the vehicle to be controlled is obtained, and based on the trajectory of the vehicle to be controlled from the current position to the position corresponding to the task, and the trajectory from the position corresponding to the task to the position corresponding to the task end position, the vehicle driving plan of the vehicle to be controlled is obtained, and at the same time, based on the requirements of the task and the position corresponding to the task, the vehicle operation plan of the vehicle to be controlled is generated, and the work instructions of the vehicle to be controlled are regenerated based on the vehicle driving plan and the vehicle operation plan of the vehicle to be controlled. Among them, the process of generating the work instructions of the vehicle to be controlled is consistent with the process of generating the work instructions of the vehicle to be controlled in the above step S203, and the embodiment of the present application is not limited to this.

[0129] If the current action is after the expected vehicle action corresponding to the current moment, the work instruction is not adjusted; if the current action is not related to any preset vehicle action in the preset vehicle action sequence, a stop instruction is generated and sent to the terminal of the vehicle to be controlled.

[0130] The above-mentioned embodiment introduces an engineering vehicle control method based on an AI algorithm from the perspective of a method flow, and the following embodiment introduces an engineering vehicle control device based on an AI algorithm from the perspective of a virtual module or a virtual unit. For details, please refer to the following embodiment.

[0131] See also Figure 3 The engineering vehicle control device 30 based on the AI ​​algorithm may specifically include: an acquisition module 301, a generation module 302, a sending module 303 and a determination module 304, specifically:

[0132] An engineering vehicle control device based on AI algorithm, comprising:

[0133] The acquisition module 301 is used to acquire the work plan of the vehicle to be controlled that has not been performed in the current cycle. The work plan includes a vehicle driving plan and a vehicle operation plan. The vehicle driving plan is a preset driving trajectory of the vehicle, and the vehicle operation plan is an operation operation performed by the vehicle in chronological order.

[0134] A generating module 302 is used to generate a work instruction corresponding to each moment in the current cycle based on the work plan;

[0135] The sending module 303 is used to send the work instructions to the terminal of the vehicle to be controlled in sequence according to the time corresponding to each work instruction, and obtain the working image of the vehicle to be controlled in real time;

[0136] The determination module 304 is used to determine whether to adjust the work instruction based on the work image of the vehicle to be controlled.

[0137] In a possible implementation of the embodiment of the present application, when the generation module 302 generates the work instructions corresponding to each moment in the current cycle based on the work plan, it can be specifically used to:

[0138] Based on the vehicle driving plan and the vehicle operation plan, generate a first work instruction and a second work instruction corresponding to each moment in the current cycle;

[0139] Based on the first working instruction and the second working instruction, the working instruction corresponding to each moment in the current cycle is obtained.

[0140] In a possible implementation of the embodiment of the present application, the vehicle operation plan includes an operation position, and the generation module 302 generates the first work instruction and the second work instruction corresponding to each moment in the current cycle based on the vehicle driving plan and the vehicle operation plan, which can be specifically used to:

[0141] Predict the operation duration corresponding to each operation in the vehicle operation plan, and determine the planned duration of the current cycle from the current time to the end time;

[0142] Based on the vehicle operation plan, the vehicle driving plan is divided into a plurality of vehicle driving sub-plans;

[0143] Determine the vehicle driving time corresponding to each vehicle driving sub-plan based on the operation time and the planned time corresponding to each operation;

[0144] Based on the vehicle driving sub-plan and the vehicle driving time corresponding to each vehicle driving sub-plan, a first work instruction corresponding to each moment in the current cycle is generated, and based on the vehicle driving time corresponding to each vehicle driving sub-plan, a second work instruction corresponding to each moment in the current cycle is determined.

[0145] In a possible implementation of the embodiment of the present application, when the generation module 302 divides the vehicle driving plan into a plurality of vehicle driving sub-plans based on the vehicle operation plan, it can be specifically used to:

[0146] Sort each operation position in the vehicle operation plan in chronological order to obtain an operation position sequence;

[0147] Each work position in the work position sequence is taken as a division point, so as to divide the vehicle driving plan into a plurality of vehicle driving sub-plans based on the division point.

[0148] In a possible implementation of the embodiment of the present application, when the generation module 302 determines the vehicle driving duration corresponding to each vehicle driving sub-plan based on the operation duration and the planned duration corresponding to each operation operation, it can be specifically used to:

[0149] Based on the operation time corresponding to each operation operation, the total operation time corresponding to the vehicle operation plan is calculated, and the time difference between the plan time and the total operation time is calculated to obtain the total driving time corresponding to the vehicle driving plan;

[0150] Determine the driving distance corresponding to each vehicle driving sub-plan;

[0151] Based on the total driving time and the driving distance corresponding to each vehicle driving sub-plan, the vehicle driving time corresponding to each vehicle driving sub-plan is calculated.

[0152] In a possible implementation of the embodiment of the present application, when the determination module 304 determines whether to adjust the work instruction based on the work image of the vehicle to be controlled, it can be specifically used to:

[0153] Identify the working image of the vehicle to be controlled and determine the current action of the vehicle to be controlled;

[0154] Determining at least two expected vehicle actions corresponding to the current time in the work plan;

[0155] Calculate the similarity between the current action and each expected vehicle action, and determine whether there is a target expected vehicle action, and the similarity between the target expected vehicle action and the current action is greater than a similarity threshold;

[0156] If the target expected vehicle action exists, it is determined that no adjustment to the work order is required.

[0157] In a possible implementation of the embodiment of the present application, the engineering vehicle control 30 based on the AI ​​algorithm may also include:

[0158] A relationship determination module, used to determine the contextual relationship between the current action and the expected vehicle action;

[0159] a work determination module, for determining that no work is performed in a current cycle based on the current action if the current action is before the expected vehicle action;

[0160] The instruction generation module is used to regenerate the work instruction corresponding to each moment based on the time period corresponding to the unperformed work and the current cycle.

[0161] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0162] See also Figure 4 , the embodiment of the present application also introduces an electronic device from the perspective of a physical device, such as Figure 4 As shown, Figure 4The electronic device 40 shown includes: a processor 401 and a memory 403. The processor 401 and the memory 403 are connected, such as through a bus 402. Optionally, the electronic device 40 may also include a transceiver 404. It should be noted that in actual applications, the transceiver 404 is not limited to one, and the structure of the electronic device 40 does not constitute a limitation on the embodiments of the present application.

[0163] Processor 401 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 401 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0164] The bus 402 may include a path to transmit information between the above components. The bus 402 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 402 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0165] The memory 403 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0166] The memory 403 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 401. The processor 401 is used to execute the application code stored in the memory 403 to implement the contents shown in the above method embodiment.

[0167] The electronic devices include but are not limited to: mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be servers, etc. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0168] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0169] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0170] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A control method for an engineering vehicle based on an AI algorithm, characterized in that: include: Obtaining a work plan of the vehicle to be controlled that has not been performed in the current cycle, wherein the work plan includes a vehicle driving plan and a vehicle operation plan, wherein the vehicle driving plan is a preset driving trajectory of the vehicle, and the vehicle operation plan is an operation performed by the vehicle in chronological order; Based on the work plan, generate work instructions corresponding to each moment in the current cycle; According to the time corresponding to each work instruction, the work instruction is sent to the terminal of the vehicle to be controlled in sequence, and the work image of the vehicle to be controlled is acquired in real time; determining whether to adjust the working instruction based on the working image of the vehicle to be controlled; The step of generating a work instruction corresponding to each moment in the current cycle based on the work plan includes: Based on the vehicle driving plan and the vehicle operation plan, generating a first work instruction and a second work instruction corresponding to each moment in the current cycle; Based on the first working instruction and the second working instruction, obtaining the working instruction corresponding to each moment in the current cycle; Wherein, the vehicle operation plan includes an operation position, and the generating of the first operation instruction and the second operation instruction corresponding to each moment in the current cycle based on the vehicle driving plan and the vehicle operation plan includes: Predicting the operation duration corresponding to each operation in the vehicle operation plan, and determining the planned duration of the current cycle from the current moment to the end moment; Based on the vehicle operation plan, dividing the vehicle travel plan into a plurality of vehicle travel sub-plans; Determine the vehicle driving duration corresponding to each vehicle driving sub-plan based on the operation duration corresponding to each of the work operations and the planned duration; Based on the vehicle driving sub-plan and the vehicle driving time corresponding to each vehicle driving sub-plan, a first work instruction corresponding to each moment in the current cycle is generated, and based on the vehicle driving time corresponding to each vehicle driving sub-plan, a second work instruction corresponding to each moment in the current cycle is determined.

2. The engineering vehicle control method based on AI algorithm according to claim 1 is characterized in that: The vehicle operation plan is based on which the vehicle driving plan is divided into a plurality of vehicle driving sub-plans, including: Sorting each operation position in the vehicle operation plan in chronological order to obtain an operation position sequence; Each work position in the work position sequence is taken as a division point, so as to divide the vehicle driving plan into a plurality of vehicle driving sub-plans based on the division points.

3. The engineering vehicle control method based on AI algorithm according to claim 1 is characterized in that: The determining, based on the operation duration corresponding to each of the operation operations and the planned duration, the vehicle driving duration corresponding to each vehicle driving sub-plan includes: Based on the operation duration corresponding to each of the operation operations, the total operation duration corresponding to the vehicle operation plan is calculated, and the time difference between the plan duration and the total operation duration is calculated to obtain the total driving time corresponding to the vehicle driving plan; Determine the driving distance corresponding to each vehicle driving sub-plan; Based on the total driving time and the driving distance corresponding to each of the vehicle driving sub-plans, the vehicle driving time corresponding to each of the vehicle driving sub-plans is calculated.

4. The engineering vehicle control method based on AI algorithm according to claim 1 is characterized in that: The determining whether to adjust the working instruction based on the working image of the vehicle to be controlled includes: Identifying the working image of the vehicle to be controlled and determining the current action of the vehicle to be controlled; Determining at least two expected vehicle actions corresponding to the current moment in the work plan; Calculating the similarity between the current action and each of the expected vehicle actions, and determining whether there is a target expected vehicle action, the similarity between the target expected vehicle action and the current action being greater than a similarity threshold; If the target expected vehicle action exists, it is determined that there is no need to adjust the work instruction.

5. The engineering vehicle control method based on AI algorithm according to claim 4 is characterized in that: When the target predicted vehicle action does not exist, the method further includes: Determining a contextual relationship between the current action and the expected vehicle action; If the current action is before the expected vehicle action, determining based on the current action that no work is performed in the current cycle; Based on the unperformed work and the duration corresponding to the current cycle, the work instruction corresponding to each moment is regenerated.

6. An engineering vehicle control device based on AI algorithm, characterized in that: include: An acquisition module, used for acquiring a work plan of the vehicle to be controlled that has not been performed in the current cycle, wherein the work plan includes a vehicle driving plan and a vehicle operation plan, wherein the vehicle driving plan is a preset driving trajectory of the vehicle, and the vehicle operation plan is an operation operation performed by the vehicle in chronological order; A generating module, used for generating work instructions corresponding to each moment in the current cycle based on the work plan; A sending module, used to send the work instructions to the terminal of the vehicle to be controlled in sequence according to the time corresponding to each work instruction, and obtain the working image of the vehicle to be controlled in real time; A determination module, used for determining whether to adjust the working instruction based on the working image of the vehicle to be controlled; Wherein, when the generating module generates the work instructions corresponding to each moment in the current cycle based on the work plan, it is specifically used to: Based on the vehicle driving plan and the vehicle operation plan, generating a first work instruction and a second work instruction corresponding to each moment in the current cycle; Based on the first working instruction and the second working instruction, obtaining the working instruction corresponding to each moment in the current cycle; Wherein, the vehicle operation plan includes an operation position, and the generating module generates the first working instruction and the second working instruction corresponding to each moment in the current cycle based on the vehicle driving plan and the vehicle operation plan, specifically for: Predicting the operation duration corresponding to each operation in the vehicle operation plan, and determining the planned duration of the current cycle from the current moment to the end moment; Based on the vehicle operation plan, dividing the vehicle travel plan into a plurality of vehicle travel sub-plans; Determine the vehicle driving duration corresponding to each vehicle driving sub-plan based on the operation duration corresponding to each of the work operations and the planned duration; Based on the vehicle driving sub-plan and the vehicle driving time corresponding to each vehicle driving sub-plan, a first work instruction corresponding to each moment in the current cycle is generated, and based on the vehicle driving time corresponding to each vehicle driving sub-plan, a second work instruction corresponding to each moment in the current cycle is determined.

7. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the engineering vehicle control method based on the AI ​​algorithm as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the engineering vehicle control method based on the AI ​​algorithm as described in any one of claims 1 to 5.

Images