Control function test system for a line control dump truck

By designing an automated test system for the control functions of a drive-by-wire dump truck, the problem of low testing efficiency in existing technologies has been solved, and efficient and accurate functional testing has been achieved.

CN121523287BActive Publication Date: 2026-08-04XIAN MAIN FUNCTION INTELLIGENT TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
XIAN MAIN FUNCTION INTELLIGENT TECH CO LTD
Filing Date
2025-11-04
Publication Date
2026-08-04

AI Technical Summary

Technical Problem

Existing testing methods for drive-by-wire dump trucks rely on computer-assisted manual operation, resulting in low testing efficiency and inaccurate test results.

Method used

A control function testing system for a drive-by-wire dump truck was designed, including a test command sending device, a data relay device, and a test command execution terminal. Through an automated command sending and execution process, the system enables remote and local control function testing of the drive-by-wire dump truck.

Benefits of technology

It improves the efficiency of functional testing of drive-by-wire dump trucks, enhances the accuracy of test results, and reduces the influence of human intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121523287B_ABST
    Figure CN121523287B_ABST
Patent Text Reader

Abstract

This disclosure relates to a control function testing system for a drive-by-wire dump truck, belonging to the field of automated testing technology. The system includes: a test command sending device, a data relay device, and a test command execution terminal. The test command sending device determines the test category of the drive-by-wire dump truck under test and the corresponding test function. It generates functional test commands and sends them to the data relay device. The data relay device processes the functional test commands to obtain executable commands and sends them to the test command execution terminal. The test command execution terminal controls the drive-by-wire dump truck under test to execute the executable commands, obtains the command execution result, and feeds back the execution result to the test command sending device via the data relay device for display. This disclosure improves testing efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of automated testing technology, and more specifically, to a control function testing system for a drive-by-wire dump truck. Background Technology

[0002] Existing functional testing methods for drive-by-wire dump trucks require manual testing assisted by a host computer; however, this method suffers from low testing efficiency.

[0003] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this disclosure is to provide a control function testing system for a drive-by-wire dump truck, thereby overcoming, to at least some extent, the problem of low testing efficiency caused by the limitations and defects of related technologies.

[0005] According to one aspect of this disclosure, a control function testing system for a drive-by-wire dump truck is provided, comprising: a test instruction sending device, a data relay device, and a test instruction execution terminal. The test instruction sending device is communicatively connected to the test instruction execution terminal via the data relay device. Specifically: the test instruction sending device is configured to, in response to an input operation on a control function test interface, determine the test category of the drive-by-wire dump truck to be tested and the test function corresponding to the test category; the test instruction sending device is configured to generate a function test instruction based on the test category and the test function corresponding to the test category, and send the function test instruction to the data relay device; the data relay device is configured to process the function test instruction to obtain an execution instruction, and send the execution instruction to the test instruction execution terminal; the test instruction execution terminal is configured to control the drive-by-wire dump truck to be tested to execute the execution instruction to obtain an instruction execution result, and feed back the instruction execution result to the test instruction sending device via the data relay device for displaying the instruction execution result.

[0006] In one exemplary embodiment of this disclosure, the test instruction sending device is further configured to: invoke an instruction sending function corresponding to the category to be tested, and store the functional test instruction in a preset instruction storage container based on the instruction sending function; invoke a functional instruction sending request associated with the function to be tested corresponding to the category to be tested from a preset instruction sending request database based on the instruction sending function; update the historical variable values ​​in the functional instruction sending request according to the current variable values ​​of the functional test instruction in the instruction storage container based on the instruction sending function to obtain an instruction sending request message, and send the instruction sending request message to the data relay device at preset time intervals.

[0007] In an exemplary embodiment of this disclosure, the data relay device is further configured to: read the current variable value in the received instruction sending request message corresponding to the functional test instruction, and associate the current variable value with a historical variable field associated with the test function corresponding to the test category to obtain a current variable field; determine the current operation rule required to perform logical operations on the current variable value in the current variable field, and perform logical operations on the current variable value in the current variable field based on the current operation rule to obtain a target variable field; generate an instruction to be executed based on the target variable field, and send the instruction to be executed to the test instruction execution terminal via a preset first controller local area network channel; wherein, the test instruction execution terminal is the vehicle controller of the wire-controlled dump truck to be tested.

[0008] In an exemplary embodiment of this disclosure, the test instruction execution terminal is configured to: in response to the instruction to be executed, determine the instruction execution subject in the wire-controlled dump truck under test required to execute the instruction to be executed and the instruction operation to be executed by the instruction execution subject; control the instruction execution subject to execute the instruction operation to obtain the instruction execution result corresponding to the instruction to be executed, and feed back the instruction execution result to the data relay device via a preset first controller local area network.

[0009] In one exemplary embodiment of this disclosure, the control function testing system for the drive-by-wire dump truck further includes a multi-protocol interface tool. The multi-protocol interface tool is used to acquire an instruction to be executed and the corresponding instruction execution result based on a preset second controller local area network channel, and to send the instruction to be executed and the corresponding instruction execution result to an application client corresponding to the multi-protocol interface tool. In response to a query operation targeting an instruction execution time node, the application client displays the instruction to be executed corresponding to that time node and the corresponding instruction execution result, so that functional testers can determine the cause of instruction execution failure based on the displayed instruction execution result.

[0010] In one exemplary embodiment of this disclosure, the test category includes a remote function test category and / or a short-range function test category, and the test function includes a remote test function and / or a short-range test function; the remote test function includes at least one of basic operation control function, autonomous navigation and path planning function, loading and unloading operation management function, and additional functions; the short-range test function includes at least one of real-time vehicle status monitoring function, precise path planning and scheduling function, system operation control function, and intelligent obstacle avoidance scheduling function.

[0011] In one exemplary embodiment of this disclosure, the functional test instructions include remote functional test instructions and / or short-range functional test instructions; the remote functional test instructions include at least one of a first remote functional test instruction corresponding to the basic operation control function, a second remote functional test instruction corresponding to the autonomous navigation and path planning function, a third remote functional test instruction corresponding to the loading and unloading operation management function, and a fourth remote functional test instruction corresponding to the additional function; the short-range functional test instructions include at least one of a first short-range functional test instruction corresponding to the real-time vehicle status monitoring function, a second short-range functional test instruction corresponding to the precise path planning and scheduling function, a third short-range functional test instruction corresponding to the system operation control function, and a fourth short-range functional test instruction corresponding to the intelligent obstacle avoidance and scheduling function.

[0012] In an exemplary embodiment of this disclosure, the first remote function test instruction is generated as follows: a preset instruction generation model is invoked, and the remote function test category and the basic operation control function corresponding to the remote function test category are input into the preset instruction generation model to obtain the first remote function test instruction; wherein, the preset instruction generation model includes an embedded mapping layer, an encoding layer, and a hybrid expert model, and the first remote function test instruction includes one or more remote sub-function test instructions, each of the remote sub-function test instructions including an instruction identifier, an instruction name, an instruction execution order, an instruction execution detail, and an instruction execution entity that executes the remote sub-function test instruction.

[0013] In one exemplary embodiment of this disclosure, a remote function test category and the basic operation control function corresponding to the remote function test category are input into the preset instruction generation model to obtain a first remote function test instruction. This includes: generating basic information to be predicted based on the remote function test category and the basic operation control function corresponding to the remote function test category, and generating context information to be predicted based on preset model prompt information; embedding and mapping the basic information to be predicted based on an embedding mapping layer to obtain a first remote test instruction feature, and embedding and mapping the context information to be predicted based on an embedding mapping layer to obtain a first context sequence; encoding the first remote test instruction feature and the first context sequence based on an encoding layer to obtain a first overall context representation, and generating an instruction based on the first context sequence and the first overall context representation using the hybrid expert model to obtain the first remote function test instruction.

[0014] In an exemplary embodiment of this disclosure, the hybrid expert model includes a gated network model and multiple expert neural network models; wherein, generating a first remote function test instruction based on the hybrid expert model of the first context sequence and the overall representation of the first context includes: determining, based on the gated network model and the first context sequence, the first model weights required for the instruction generation task of each of the expert neural network models in the dimension of instruction execution order, the second model weights required for the instruction generation task in the dimension of instruction execution detail, and the third model weights required for the instruction generation task in the dimension of instruction execution subject; and determining, based on the first model weights, the second model weights, and the third model weights, the instruction generation task of each of the expert neural network models is... The system comprises a first target neural network model for instruction generation tasks in the instruction execution order dimension, a second target neural network model for instruction generation tasks in the instruction execution detail dimension, and a third target neural network model for instruction generation tasks in the instruction execution subject dimension. The first context sequence and the overall representation of the first context are input into the first target neural network model, the second target neural network model, and the third target neural network model, respectively, to obtain the first instruction prediction result in the instruction execution order dimension, the second instruction prediction result in the instruction execution detail dimension, and the third instruction prediction result in the instruction execution subject dimension. Based on the first instruction prediction result, the second instruction prediction result, and the third instruction prediction result, the first remote functional test instruction is obtained.

[0015] The functional testing system for a wire-controlled dump truck provided in this disclosure, on the one hand, determines the test category of the wire-controlled dump truck and the corresponding test function of the test category by responding to input operations on the control function test interface through a test command sending device; then, the test command sending device generates functional test commands for the test category and the corresponding test function, and sends the functional test commands to a data relay device; subsequently, the data relay device processes the functional test commands to obtain execution commands, and sends the execution commands to a test command execution terminal; finally, the test command execution terminal controls the wire-controlled dump truck under test to execute the execution commands to obtain the command execution result, and feeds back the command execution result to the test command sending device via the data relay device for display, thereby realizing automatic testing of the wire-controlled dump truck and solving the problem of low testing efficiency caused by the need for manual testing with the assistance of a host computer in the prior art, thus improving the functional testing efficiency of the wire-controlled dump truck; on the other hand, since the wire-controlled dump truck can be automatically tested, the accuracy of the obtained test results is improved.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] Figure 1 This diagram schematically illustrates an example architecture of a functional testing system for a drive-by-wire dump truck according to an exemplary embodiment of this disclosure.

[0019] Figure 2 The diagram schematically illustrates a structural example of generating a large model according to a preset instruction based on an example embodiment of the present disclosure.

[0020] Figure 3 The diagram schematically illustrates a structural example of a hybrid expert model in a large model generated according to a preset instruction of an exemplary embodiment of the present disclosure.

[0021] Figure 4 The diagram illustrates a scenario example of a specific process for determining a test category according to an exemplary embodiment of this disclosure.

[0022] Figure 5The diagram illustrates a scenario example of a specific process for determining a function to be tested corresponding to a test category, according to an example embodiment of this disclosure.

[0023] Figure 6 An example diagram illustrating a remote subfunction test instruction obtained according to an exemplary embodiment of the present disclosure is shown.

[0024] Figure 7 The illustration shows an example scenario of displaying the execution result of the obtained instructions according to an example embodiment of the present disclosure.

[0025] Figure 8 The illustration shows an example scenario of displaying instruction issuance and vehicle-side feedback data based on a time node, according to an example embodiment of the present disclosure. Detailed Implementation

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0027] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0028] As the depth of open-pit mining increases, the difficulty of mining also increases, leading to increasingly prominent problems such as high transportation costs for minerals and slag, labor shortages, and frequent safety accidents. To address these issues, the construction of smart mines and unmanned mines has emerged. Furthermore, autonomous driving technology, as a crucial component of smart and unmanned mines, has matured significantly in recent years and gained favor among mining companies, with many intelligent driving companies launching their own unmanned dump trucks. Simultaneously, to quickly and safely resolve simple malfunctions of unmanned dump trucks, remote control and local control methods have emerged. The purpose of remote and / or local control of unmanned trucks is to allow operators to move the dump truck away from the malfunction area or resolve simple problems remotely without entering the mine pit, via a remote control cabin; or, on-site personnel can quickly take over the unmanned dump truck from away from the main road using a local application to move it away from the malfunction area or resolve simple problems manually.

[0029] In practical applications, if precise control of unmanned transport vehicles is required via remote and / or local control, corresponding functional tests must be performed on the unmanned transport vehicles before they begin formal operation. Existing functional testing solutions can be implemented through a combination of host computer and manual assistance. For example, the host computer sends corresponding instructions to the unmanned transport vehicle, and then the execution results of the instructions are collected manually to determine whether the instructions were executed successfully. However, this method not only suffers from low testing efficiency but also from inaccurate test results.

[0030] Based on this, this example embodiment first provides a functional testing system for a drive-by-wire dump truck. Specifically, refer to... Figure 1As shown, the functional testing system for the drive-by-wire dump truck may include a test command sending device 110, a data relay device 120, and a test command execution terminal 130. The test command sending device is communicatively connected to the test command execution terminal via the data relay device. The test command sending device described herein may also be referred to as a remote or local test host computer. The data relay device described herein may be a Guangcheng device, and the test command execution terminal described herein may be the vehicle controller in the drive-by-wire dump truck under test. Of course, the functional testing system for the drive-by-wire dump truck may also include a multi-protocol interface tool 140, which may be a Tongxing device. In practical applications, the test command sending device responds to input operations on the control function test interface, determines the test category of the drive-by-wire dump truck under test, and the corresponding test function. Based on the test category and the corresponding test function, the test command sending device generates a function test command and sends it to a data transfer device. The data transfer device processes the function test command to obtain an execution command and sends it to the test command execution terminal. The test command execution terminal controls the drive-by-wire dump truck under test to execute the execution command, obtains the execution result, and feeds back the execution result to the test command sending device via the data transfer device for display.

[0031] In one possible example embodiment, the remote or local host computer is used to simulate a remote cockpit or local APP, sending the necessary instructions to the core of the drive-by-wire system—the vehicle control unit (VCU)—to instruct the drive-by-wire dump truck to perform corresponding operations and display the execution results on the host computer; simultaneously, the Guangcheng device is a data relay device used to connect the remote / local host computer and the vehicle end, and also connects with the Tongxing device's self-driving CAN (Controller) system. The AreaNetwork (Controller Area Network) channel and the remote / local driving CAN channel are connected in parallel to process the data sent by the host computer and send it to the VCU, allowing the drive-by-wire dump truck to execute corresponding commands and feed back the command execution results to the host computer. Furthermore, a CAN bus is an essential tool for connecting the vehicle to the computer's CAN bus software; commonly used models are four-channel and five-channel. When using it, select the appropriate CAN bus according to the CAN bus software database and channel hardware settings, and connect it to the corresponding CAN channel line. It's important to note that the CAN bus is needed because the host computer is used to simulate the remote cockpit and the local remote control APP / controller. The data sent or received only comes from the remote and local CAN channels, and cannot receive or send data to other CAN channels. Therefore, to test, archive, and observe the data fed back from other CAN channels on the vehicle, a CAN bus is needed to parse the data from other CAN channels and display simple numerical changes.

[0032] In the aforementioned functional testing system for the wire-controlled dump truck, on the one hand, the test command sending device responds to input operations on the control function test interface to determine the test category of the wire-controlled dump truck to be tested and the corresponding test function; then, the test command sending device generates functional test commands for the test category and the corresponding test function, and sends the functional test commands to the data transfer device; subsequently, the data transfer device processes the functional test commands to obtain the execution commands, and sends the execution commands to the test command execution terminal; finally, the test command execution terminal controls the wire-controlled dump truck to be tested to execute the execution commands to obtain the command execution results, and the data transfer device feeds back the command execution results to the test command sending device for display, thus realizing automatic testing of the wire-controlled dump truck. This solves the problem of low testing efficiency caused by the need for manual testing with the assistance of a host computer in the prior art, and improves the functional testing efficiency of the wire-controlled dump truck; on the other hand, because the wire-controlled dump truck can be automatically tested, the accuracy of the obtained test results is improved.

[0033] The functional testing system for the drive-by-wire dump truck described in the exemplary embodiments of this disclosure will be explained and described in detail below with reference to the accompanying drawings.

[0034] First, the technical implementation principle of the exemplary embodiments of this disclosure will be explained and described. Specifically, the functional testing system for the wire-controlled dump truck described in the exemplary embodiments of this disclosure is designed in the forward direction by designing a host computer program and selecting appropriate computer and vehicle-side connection tools and software, based on the basic premise of testing the remote / local control function of the vehicle. This solves the problems of inconvenience in testing the remote / local control function of unmanned mining dump trucks and the need for a large number of testers, and reduces the influencing factors in the testing process to standardize the testing of basic remote / local functions. Furthermore, the functional testing system for the wire-controlled dump truck described in the exemplary embodiments of this disclosure is designed in the forward direction by comprehensively considering factors such as testing difficulty, required tools, testing accuracy, data recording and archiving, and operation process archiving, based on the basic premise of realizing the testing of non-network functions in the remote / local control of the vehicle.

[0035] Secondly, the preset instruction generation model involved in the exemplary embodiments of this disclosure will be explained and described. Specifically, refer to... Figure 2 As shown, the pre-defined instruction generation model described herein includes an embedding mapping layer 210, an encoding layer 220, and a hybrid expert model 230; further, refer to Figure 3 As shown, the hybrid expert model described here may include a gated network model and multiple expert neural network models. It should be noted that the role of each model layer in the instruction generation process will be detailed later, and will not be elaborated further here.

[0036] The following will combine Figure 2 as well as Figure 3 right Figure 1 The control function test system of the drive-by-wire dump truck shown will be further explained and described.

[0037] In one example embodiment, the test command sending device first needs to respond to the input operation of the control function test interface to determine the test category of the drive-by-wire dump truck under test and the test function corresponding to the test category. The test category described herein may include remote function test categories and / or short-range function test categories, and the test function described herein includes remote test functions and / or short-range test functions. The remote test functions described herein may include, but are not limited to, basic operation control functions, autonomous navigation and path planning functions, loading and unloading operation management functions, and additional functions, etc. The short-range test functions described herein may include, but are not limited to, real-time vehicle status monitoring functions, precise path planning and scheduling functions, system operation control functions, and intelligent obstacle avoidance scheduling functions, etc. It should also be noted that the remote and short-range test function indications described herein are for illustrative purposes only, and can be set according to actual needs in actual applications; this example does not impose any special restrictions on this.

[0038] In one example embodiment, the specific process for determining the test categories and corresponding test functions described above can be implemented as follows: When it is necessary to test the remote control function or the local control function of a wire-controlled dump truck, a control function test interface can be displayed on the display interface of the display device corresponding to the unmanned vehicle dispatching system; then, the tester can click on the interactive control corresponding to the remote control function or the interactive control corresponding to the local interaction function in the control function test interface; taking the remote control function as an example, a specific scenario example diagram can be referred to. Figure 4 As shown; based on this, the remote sub-function display interface corresponding to the remote control function can be displayed, and then the sub-function to be tested can be selected; for example, the sub-function to be tested is the basic operation control function in the remote test function. Specific scenario examples can be found in the diagram. Figure 5 As shown.

[0039] In one example embodiment, the test instruction sending device also needs to generate functional test instructions based on the determined test category and the corresponding test function. Specifically, the functional test instructions described herein may include, but are not limited to, remote functional test instructions and short-range functional test instructions. Furthermore, the remote functional test instructions described herein may include, but are not limited to, a first remote functional test instruction corresponding to the basic operation control function, a second remote functional test instruction corresponding to the autonomous navigation and path planning function, a third remote functional test instruction corresponding to the loading and unloading operation management function, and a fourth remote functional test instruction corresponding to the additional function, etc. The short-range functional test instructions described herein may include, for example, a first short-range functional test instruction corresponding to the real-time vehicle status monitoring function, a second short-range functional test instruction corresponding to the precise path planning and scheduling function, a third short-range functional test instruction corresponding to the system operation control function, and a fourth short-range functional test instruction corresponding to the intelligent obstacle avoidance and scheduling function, etc.

[0040] In one example embodiment, taking a first remote function test instruction as an example, the specific generation process can be implemented as follows: A preset instruction generation model is invoked, and the remote function test category and the basic operation control function corresponding to the remote function test category are input into the preset instruction generation model to obtain the first remote function test instruction. The first remote function test instruction includes one or more remote sub-function test instructions. Each remote sub-function test instruction includes an instruction identifier, instruction name, instruction execution order, instruction execution details, and the instruction execution entity that executes the remote sub-function test instruction. For details, please refer to... Figure 6As shown. Here, the instruction identifier refers to the code of the remote sub-function test instruction, or it can be used to represent the execution order within the overall instruction set; the instruction name refers to the specific name of the remote sub-function test instruction, such as accelerator, pedal, torque, speed, etc.; the instruction execution order refers to the specific stage in which the remote sub-function test instruction should be executed, such as the previous instruction being A, the next instruction being C, etc.; for example, in instructions such as engine start, vehicle parking, cargo box lifting, stopping, and lowering, the engine start execution order is first, followed by vehicle parking, etc.; the instructions recorded here... The execution details refer to the specific objectives that the remote sub-function test instruction needs to achieve, such as testing the responsiveness of the throttle, the responsiveness of the turn signals, or whether the pedals function properly. The instruction execution subject recorded here can refer to the components in the drive-by-wire dump truck under test that need to be invoked to execute the instruction, such as the headlights, the throttle, or the accelerator pedal. In actual application, the specific information included in the obtained functional test instruction can be set according to actual needs. This example does not impose any special restrictions on this. This part can be adaptively set during the fine-tuning of the instruction generation model based on instruction fine-tuning.

[0041] In one exemplary embodiment, the remote function test category and the basic operation control function corresponding to the remote function test category are input into the preset instruction generation model to obtain the first remote function test instruction. This can be achieved as follows: generating basic information to be predicted based on the remote function test category and the basic operation control function corresponding to the remote function test category, and generating context information to be predicted based on preset model prompt information; embedding and mapping the basic information to be predicted based on the embedding mapping layer to obtain the first remote test instruction feature, and embedding and mapping the context information to be predicted based on the embedding mapping layer to obtain the first context sequence; encoding the first remote test instruction feature and the first context sequence based on the encoding layer to obtain the first overall context representation, and generating the instruction based on the first context sequence and the first overall context representation using a hybrid expert model to obtain the first remote function test instruction. Specifically, the embedding mapping layer described here may include an embedding embedding mapping layer and a BERT embedding mapping layer. In practical applications, the embedding embedding mapping layer can be used to embed and map the basic information to be predicted to obtain the first remote test instruction feature, and the BERT embedding mapping layer can be used to embed and map the context information to be predicted to obtain the first context sequence. The preset model prompt information described here may be: Please generate the corresponding test instruction based on the input information. The obtained test instruction should include xxxxxx. In the process of instruction generation, it is necessary to comprehensively consider dimensions such as xxxxx; ... In practical applications, the corresponding model prompt information can be configured according to actual needs. This example does not impose any special restrictions on this.

[0042] In one example embodiment, the generation of a first remote function test instruction based on a hybrid expert model using a first context sequence and a first overall representation of the context can be achieved as follows: A gated network model determines, based on the first context sequence, the first model weights required for instruction generation tasks in the instruction execution order dimension, the second model weights required for instruction generation tasks in the instruction execution detail dimension, and the third model weights required for instruction generation tasks in the instruction execution subject dimension of each expert neural network model; based on the first model weights, the second model weights, and the third model weights, a first target neural network model required for instruction generation tasks in the instruction execution order dimension, a second target neural network model required for instruction generation tasks in the instruction execution detail dimension, and a third target neural network model required for instruction generation tasks in the instruction execution subject dimension are determined from each expert neural network model; the first context sequence and the first overall representation of the context are input into the first target neural network model, the second target neural network model, and the third target neural network model, respectively, to obtain a first instruction prediction result in the instruction execution order dimension, a second instruction prediction result in the instruction execution detail dimension, and a third instruction prediction result in the instruction execution subject dimension; and the first remote function test instruction is obtained based on the first instruction prediction result, the second instruction prediction result, and the third instruction prediction result. It should be added that the reason for generating corresponding functional test instructions from multiple different dimensions is to comprehensively consider the convenience and accuracy of the obtained functional test instructions, thereby improving the accuracy of the test results.

[0043] In one example embodiment, the test instruction sending device can send functional test instructions to the data relay device in the following manner: calling the instruction sending function corresponding to the test category, and storing the functional test instruction in a preset instruction storage container based on the instruction sending function; calling the functional instruction sending request associated with the test function corresponding to the test category from the preset instruction sending request database based on the instruction sending function; updating the historical variable values ​​in the functional instruction sending request according to the current variable values ​​of the functional test instruction in the instruction storage container to obtain an instruction sending request message, and sending the instruction sending request message to the data relay device at preset time intervals. In other words, in practical applications, once the functional test instructions are generated, the instruction sending function (such as the remote takeover function) can be called. Then, the instructions are stored in bytes (i.e., the instruction storage container) based on the instruction sending function. Next, the instruction sending function sends the message containing the byte content through the Guangcheng device at a fixed period. Furthermore, during the sending process, the remote takeover function is called and the value of the variable corresponding to the remote takeover request is changed. Then, the sending function sends the message containing the value of the remote takeover request variable at regular intervals to realize the specific sending process.

[0044] In one example embodiment, after the data relay device receives the functional test instruction, it can process the received functional test instruction to obtain an execution instruction, and then send the execution instruction to the test instruction execution terminal. The data processing of the functional test instruction to obtain the execution instruction can be achieved as follows: The current variable value is read from the received instruction sending request message corresponding to the functional test instruction, and the current variable value is associated and stored in a historical variable field associated with the test function corresponding to the test category to obtain a current variable field; the current operation rule required for logical operation on the current variable value in the current variable field is determined, and logical operation is performed on the current variable value in the current variable field based on the current operation rule to obtain a target variable field; an execution instruction is generated based on the target variable field, and the execution instruction is sent to the test instruction execution terminal via a preset first controller local area network channel. In other words, in practical applications, the message content can be read and the 8 bytes of content in the message can be stored into the corresponding variable according to the communication protocol; then, the variable content can be processed (addition, subtraction, multiplication, and division of the content, and units can be added) to obtain the target variable field; finally, the corresponding instruction to be executed can be generated and sent; for example, in the throttle sensitivity test, if it needs to be increased from 10% to 15%, the target variable field can be obtained by using the addition operation rule.

[0045] In one example embodiment, after the test instruction execution terminal receives the instruction to be executed, it can control the wire-controlled dump truck under test to execute the instruction to obtain the instruction execution result, and feed the instruction execution result back to the test instruction sending device via a data relay device to display the instruction execution result; specifically, the specific determination process of the instruction execution result described here can be implemented in the following way: in response to the instruction to be executed, determine the instruction execution subject in the wire-controlled dump truck under test and the instruction operation to be executed by the instruction execution subject; control the instruction execution subject to execute the instruction operation to obtain the instruction execution result corresponding to the instruction to be executed, and feed the instruction execution result back to the data relay device via a preset first controller area network (i.e., self-driving CAN and remote / short-range control CAN, etc.). For example, to test throttle sensitivity, the throttle is increased from 12% to 15%, and the corresponding command execution result is obtained. Alternatively, the current throttle data obtained from relevant sensors can be used to determine the command execution result. Another example is testing the raising and lowering of the cargo bed of a drive-by-wire dump truck (e.g., returning it to its original position from a raised state). The cargo bed is lowered from its raised state to its original position, and the corresponding command execution result is obtained. This command execution result can also be obtained based on the current position data of the cargo bed obtained from relevant sensors. It should also be noted that after the relay device receives the command execution result, it can process the result and feed it back to the host computer, allowing the host computer to display the command execution result. The specific displayed command execution result can be found in [reference needed]. Figure 7 As shown; the specific processing procedure of the relay equipment for the command execution result may include, but is not limited to: receiving data packets sent by the vehicle controller → reading the packet content and storing the 8 bytes of content in the packet into the corresponding variable according to the communication protocol → processing the variable content (addition, subtraction, multiplication, and division of the content, and adding units) → periodically updating the corresponding content on the host computer. For example, taking the throttle as an example, the specific processing procedure is as follows: receiving a packet containing the vehicle-side throttle percentage data → storing the data related to the throttle percentage in the packet into the throttle variable → processing the throttle data according to the communication protocol (resolution, offset), adding the unit % → updating the throttle on the host computer display interface at a period of 100ms.

[0046] In one possible example embodiment, after the tester views the instruction execution result, if the actual instruction execution result is inconsistent with the expected instruction execution result, it can be determined that the instruction execution failed. Under this premise, the tester can visually display and record the data received through the satellite device, allowing the tester to draw the desired conclusions based on the data, and use it as important evidence in the testing process. The data can be extracted and verified again when needed later. Specifically, this can be achieved as follows: the multi-protocol interface tool (i.e., the satellite device) obtains the instruction to be executed and the instruction execution result corresponding to the instruction based on a preset second controller LAN (i.e., other CANs besides autonomous CAN and remote / near control CAN) channel, and sends the instruction to be executed and the instruction execution result corresponding to the instruction to be executed to the application client corresponding to the multi-protocol interface tool; the application client responds to the query operation for the instruction execution time node, displays the instruction to be executed corresponding to the instruction execution time node and the instruction execution result corresponding to the instruction to be executed, so that the functional tester can determine the reason for the instruction execution failure based on the displayed instruction execution result. The application client described here refers to the Tongxing software client associated with the Tongxing device. It can be used to visually display and record data received through the Tongxing device, allowing testers to draw desired conclusions from the data and use it as important evidence in the testing process. The data can be retrieved and verified again when needed later. Taking basic function testing in the host computer as an example, the specific verification process can be implemented as follows: The Tongxing software records data during the testing process, such as commands issued by the host computer and monitored vehicle-side feedback. After the test is completed, if any problematic items or feedback that was not noticed during the test are found, the command issuance and vehicle-side feedback data at the corresponding time point (the time point is determined based on experience and command changes) are checked on the Tongxing software. Based on the command issuance and vehicle-side feedback data at that time point, the reason for the command execution failure can be determined. Specific scenario example diagrams can be found in the provided image. Figure 8 As shown; based on this, the goal of further improving testing efficiency can be achieved.

[0047] Thus, the functional testing system for the drive-by-wire dump truck described in the exemplary embodiments of this disclosure has been fully implemented. Based on the foregoing description, it can be understood that the functional testing system for the drive-by-wire dump truck described in the exemplary embodiments of this disclosure, on the one hand, reduces the software and hardware involved in the testing process and lowers the difficulty of use by designing the host computer program and selecting appropriate computer and vehicle-side connection tools and software; in terms of specific testing, by writing programs and designing a one-click testing function, the system reduces testing influencing factors and improves testing standardization; on the other hand, since it can include both remote and local basic function tests, and can automatically execute tests that previously required manual clicking, such as engine start, parking, and gearbox shifting, and determine whether the vehicle-side feedback after the command is issued is correct, and record the commands and feedback, the functional testing efficiency of the drive-by-wire dump truck can be further improved.

[0048] Furthermore, the above figures are merely illustrative of the processes included in a system according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0049] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention described herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not invented by this disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A control function testing system for a drive-by-wire dump truck, characterized in that, include: The system comprises a test command sending device, a data relay device, and a test command execution terminal, wherein the test command sending device is communicatively connected to the test command execution terminal via the data relay device; wherein: The test instruction sending device is used to respond to input operations on the control function test interface to determine the test category of the wire-controlled dump truck to be tested and the test function corresponding to the test category; The test instruction sending device is used to generate functional test instructions based on the test category and the corresponding test function, and send the functional test instructions to the data relay device; the functional test instructions include remote functional test instructions; the remote functional test instructions include a first remote functional test instruction corresponding to the basic operation control function; the first remote functional test instruction is generated by a preset instruction generation model, the preset instruction generation model includes an embedding mapping layer, an encoding layer and a hybrid expert model, the hybrid expert model includes a gated network model and multiple expert neural network models; The data relay device is used to process the functional test instructions to obtain instructions to be executed, and to send the instructions to be executed to the test instruction execution terminal; The test command execution terminal is used to control the wire-controlled dump truck under test to execute the command to be executed to obtain the command execution result, and to feed back the command execution result to the test command sending device via the data relay device so as to display the command execution result; The generation of the first remote function test instruction through the instruction generation model is achieved as follows: Basic information to be predicted is generated based on the remote function test category and the corresponding basic operation control function; context information to be predicted is generated based on preset model prompts; the basic information to be predicted is embedded and mapped using an embedding mapping layer to obtain the first remote test instruction features; the context information to be predicted is embedded and mapped using the embedding mapping layer to obtain the first context sequence; the first remote test instruction features and the first context sequence are encoded using an encoding layer to obtain the overall representation of the first context; and the gating network model determines the first model weights required for the instruction generation task in the instruction execution order dimension, the second model weights required for the instruction generation task in the instruction execution detail dimension, and the instruction weights required for the instruction execution subject dimension, based on the first context sequence. Assign weights to the third model required for the task generation; based on the first model weights, the second model weights, and the third model weights, determine from each of the expert neural network models the first target neural network model required for the instruction generation task in the instruction execution order dimension, the second target neural network model required for the instruction generation task in the instruction execution detail dimension, and the third target neural network model required for the instruction generation task in the instruction execution subject dimension; input the first context sequence and the overall representation of the first context to the first target neural network model, the second target neural network model, and the third target neural network model respectively to obtain the first instruction prediction result in the instruction execution order dimension, the second instruction prediction result in the instruction execution detail dimension, and the third instruction prediction result in the instruction execution subject dimension, and obtain the first remote function test instruction based on the first instruction prediction result, the second instruction prediction result, and the third instruction prediction result.

2. The control function testing system for the drive-by-wire dump truck according to claim 1, characterized in that, The test command sending device is also used for: Invoke the instruction sending function corresponding to the category to be tested, and store the functional test instruction into a preset instruction storage container based on the instruction sending function; The instruction sending function retrieves the function instruction sending request associated with the function to be tested corresponding to the category to be tested from the preset instruction sending request database; The instruction sending function updates the historical variable values ​​in the function instruction sending request based on the current variable values ​​of the function test instructions in the instruction storage container to obtain an instruction sending request message, and sends the instruction sending request message to the data relay device at preset time intervals.

3. The control function testing system for a drive-by-wire dump truck according to claim 1, characterized in that, The data relay equipment is also used for: Read the current variable value in the instruction sending request message corresponding to the received functional test instruction, and store the current variable value in the historical variable field associated with the test function corresponding to the test category to obtain the current variable field; Determine the current operation rules required to perform logical operations on the current variable value in the current variable field, and perform logical operations on the current variable value in the current variable field based on the current operation rules to obtain the target variable field; Based on the target variable field, an instruction to be executed is generated and sent to the test instruction execution terminal via a preset first controller LAN channel; wherein, the test instruction execution terminal is the vehicle controller of the wire-controlled dump truck to be tested.

4. The control function testing system for a drive-by-wire dump truck according to claim 1, characterized in that, The test instruction execution terminal is used for: In response to the instruction to be executed, determine the instruction execution subject in the wire-controlled dump truck under test required to execute the instruction to be executed, and the instruction operation to be executed by the instruction execution subject; The control instruction execution entity performs instruction operations to obtain the instruction execution result corresponding to the instruction to be executed, and feeds back the instruction execution result to the data relay device via a preset first controller local area network.

5. The control function testing system for a drive-by-wire dump truck according to claim 1, characterized in that, The control function testing system for the drive-by-wire dump truck also includes a multi-protocol interface tool; The multi-protocol interface tool is used to obtain the instruction to be executed and the instruction execution result corresponding to the instruction based on the preset second controller LAN channel, and send the instruction to be executed and the instruction execution result corresponding to the instruction to be executed to the application client corresponding to the multi-protocol interface tool; In response to a query operation targeting an instruction execution time node, the application client displays the instruction to be executed corresponding to that instruction execution time node and the instruction execution result corresponding to that instruction, so that functional testers can determine the reason for instruction execution failure based on the displayed instruction execution result.

6. The control function testing system for a drive-by-wire dump truck according to claim 1, characterized in that, The categories to be tested include remote function test categories and / or short-range function test categories, and the functions to be tested include remote functions to be tested and / or short-range functions to be tested; The remote test function includes at least one of the following: basic operation control function, autonomous navigation and path planning function, loading and unloading operation management function, and additional functions. The short-range test functions include at least one of the following: real-time vehicle status monitoring, precise path planning and scheduling, system operation control, and intelligent obstacle avoidance scheduling.

7. The control function testing system for a drive-by-wire dump truck according to claim 6, characterized in that, The functional test instructions also include short-range functional test instructions; The remote function test command also includes at least one of the following: a second remote function test command corresponding to the autonomous navigation and path planning function, a third remote function test command corresponding to the loading and unloading operation management function, and a fourth remote function test command corresponding to the additional function. The short-range function test instructions include at least one of the following: a first short-range function test instruction corresponding to the real-time vehicle status monitoring function, a second short-range function test instruction corresponding to the precise path planning and scheduling function, a third short-range function test instruction corresponding to the system operation control function, and a fourth short-range function test instruction corresponding to the intelligent obstacle avoidance and scheduling function.

8. The control function testing system for a drive-by-wire dump truck according to claim 7, characterized in that, The first remote function test instruction includes one or more remote sub-function test instructions. Each remote sub-function test instruction includes an instruction identifier, an instruction name, an instruction execution order, an instruction execution detail, and an instruction execution entity that executes the remote sub-function test instruction.