Vehicle testing method, device and equipment based on data recharge, medium and product

Abstract

The invention discloses a vehicle testing method, device and equipment based on data recharge, a medium and a product. The method comprises the steps that in response to a first auxiliary driving instruction of a control module to an auxiliary driving simulation module, the first auxiliary driving instruction is sent to a pre-trained vehicle dynamics model based on a recharge processing module; determining vehicle driving data based on a vehicle dynamics model according to the first auxiliary driving instruction; the auxiliary driving simulation module is controlled based on the control module according to the vehicle driving data to obtain function execution attribute data; sending the function execution attribute data to the vehicle dynamics model based on the recharge processing module, and re-executing the steps of determining the vehicle driving data, determining the function execution attribute data and respectively sending the function execution attribute data to the test module and the recharge processing module; and in response to the test ending event, determining a test result of testing the auxiliary driving simulation module based on the test module according to the function execution attribute data.

Description

Technical Field

[0001] This invention relates to the field of computer processing technology, and in particular to a vehicle testing method, apparatus, equipment, medium, and product based on data backfeeding. Background Technology

[0002] In recent years, with the gradual popularization of advanced driver assistance systems (ADAS), users have increasingly higher requirements for the safety of these systems. Before vehicle production, it is usually necessary to test the driver assistance functions of the systems on the vehicle (such as automatic emergency braking).

[0003] Currently, testing of driver assistance functions primarily relies on real-time vehicle data generated during actual vehicle driving to perform data feedback tests on the system's driver assistance features. However, this vehicle data is only valid before the driver assistance function activation request is triggered. This is because this vehicle data is used to determine whether the driver assistance function needs to be activated. Once the driver assistance function is activated, the system automatically takes over driving assistance according to preset algorithms and logic, rather than continuing to rely on real-time vehicle data. When testing driver assistance functions via data feedback, the vehicle data changes upon activation, making it impossible to simulate the impact of input vehicle data after function activation on the driver assistance function. Summary of the Invention

[0004] This invention provides a vehicle testing method, apparatus, equipment, medium, and product based on data feedback, to simulate the impact of input vehicle body data on the function after the activation of the assisted driving function, improve the accuracy of vehicle assisted driving function testing, and ensure the safety and reliability of assisted driving function execution.

[0005] According to one aspect of the present invention, a vehicle testing method based on data backfeeding is provided, applied to a vehicle testing system, wherein the vehicle testing system integrates a backfeeding processing module, a communication module, a control module, a vehicle-associated assisted driving simulation module, and a testing module, the method comprising:

[0006] In response to the first assisted driving instruction from the control module to the assisted driving simulation module, the first assisted driving instruction is sent to the pre-trained vehicle dynamics model based on the feedback processing module.

[0007] Based on the vehicle dynamics model and the first assisted driving instruction, the vehicle driving data is determined and sent to the communication module, so that the communication module sends the vehicle driving data to the feedback processing module and the feedback processing module sends the vehicle driving data to the control module.

[0008] The control module controls the assisted driving simulation module based on the vehicle driving data to obtain function execution attribute data, and sends the function execution attribute data to the test module and the feedback processing module respectively.

[0009] Based on the recharge processing module, the function execution attribute data is sent to the vehicle dynamics model, and the steps of determining vehicle driving data, determining function execution attribute data, and sending the function execution attribute data to the test module and the recharge processing module are re-executed.

[0010] In response to the test end event, the test result of the test on the assisted driving simulation module is determined based on the functional execution attribute data of the test module.

[0011] According to another aspect of the present invention, a vehicle testing device based on data refeedback is provided, configured in a vehicle testing system, wherein the vehicle testing system integrates a refeedback processing module, a communication module, a control module, a vehicle-associated assisted driving simulation module, and a testing module, the device comprising:

[0012] The backfeed processing module is used to respond to the first assisted driving command from the control module to the assisted driving simulation module, and send the first assisted driving command to the pre-trained vehicle dynamics model based on the backfeed processing module.

[0013] The vehicle dynamics model is used to determine vehicle driving data based on the first assisted driving command, and send the vehicle driving data to the communication module, so that the communication module sends the vehicle driving data to the feedback processing module, and so that the feedback processing module sends the vehicle driving data to the control module.

[0014] The control module is used to control the assisted driving simulation module based on the vehicle driving data, obtain function execution attribute data, and send the function execution attribute data to the test module and the feedback processing module respectively.

[0015] The recharge processing module is used to send the function execution attribute data to the vehicle dynamics model based on the recharge processing module, and re-execute the steps of determining vehicle driving data, determining function execution attribute data, and sending the function execution attribute data to the test module and the recharge processing module respectively;

[0016] The testing module is used to determine the test results of the assisted driving simulation module in response to a test end event, based on the functional execution attribute data of the testing module.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor; and a memory communicatively connected to said at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle testing method based on data refeeding as described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle testing method based on data refeeding as described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements a vehicle testing method based on data refeedback as described in any embodiment of the present invention.

[0022] The technical solution of this invention involves responding to a first assisted driving instruction from the control module to the assisted driving simulation module, sending the first assisted driving instruction to a pre-trained vehicle dynamics model based on the feedback processing module; determining vehicle driving data based on the vehicle dynamics model according to the first assisted driving instruction, and sending the vehicle driving data to the communication module, so that the communication module sends the vehicle driving data to the feedback processing module, and the feedback processing module sends the vehicle driving data to the control module; controlling the assisted driving simulation module based on the vehicle driving data to obtain function execution attribute data, and sending the function execution attribute data to the test module and the feedback processing module respectively; and the feedback processing module then processes the function execution attributes... Data is sent to the vehicle dynamics model, and the steps of determining vehicle driving data, determining function execution attribute data, and sending the function execution attribute data to the test module and the backfeeding processing module are re-executed. In response to the test end event, the test module determines the test result of the assisted driving simulation module based on the function execution attribute data. This solves the problem of poor accuracy in the functional testing of assisted driving systems based on data backfeeding in existing technologies. It enables the control module to send the first assisted driving command to the pre-trained vehicle dynamics model when controlling the assisted driving simulation module with the first assisted driving command, allowing the vehicle dynamics model to determine vehicle driving data based on the first assisted driving command. The vehicle driving data is sent to the backfeeding processing module via the communication module, and the backfeeding processing module sends the vehicle driving data to the control module. Then, based on the vehicle driving data, the control module controls the assisted driving simulation module to obtain function execution attribute data, which is sent to the test module and the backfeeding processing module respectively. The backfeeding processing module then sends the function execution attribute data to the vehicle dynamics model, enabling the vehicle dynamics model to re-execute the operation of determining vehicle driving data. The control module controls the assisted driving simulation module based on newly received vehicle driving data to obtain function execution attribute data. This function execution attribute data is then sent to the test module and the backfeed processing module. Based on the function execution attribute data, the test module determines the test results for the assisted driving simulation module. This improves the accuracy of the backfeed test of the assisted driving simulation module, thereby ensuring the safety, reliability, and stability of the assisted driving function execution.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a vehicle testing method based on data refeedback according to Embodiment 1 of the present invention;

[0026] Figure 2 This is a flowchart of a vehicle testing method based on data refeedback according to Embodiment 2 of the present invention;

[0027] Figure 3 This is a schematic diagram of the structure of a vehicle characterization test system provided according to Embodiment 3 of the present invention;

[0028] Figure 4 This is a flowchart of a vehicle testing method based on data refeedback provided in Embodiment 3 of the present invention;

[0029] Figure 5 This is a schematic diagram of a vehicle testing device based on data refeedback according to Embodiment 4 of the present invention;

[0030] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the vehicle testing method based on data backfeeding according to an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1 This is a flowchart of a vehicle testing method based on data backfeeding according to Embodiment 1 of the present invention. This embodiment is applicable to the situation of backfeeding simulation testing of vehicle's assisted driving functions. The method can be executed by a vehicle testing device based on data backfeeding, which can be implemented in hardware and / or software. This device can be configured in a vehicle testing system, which integrates a backfeeding processing module, a communication module, a control module, a vehicle-associated assisted driving simulation module, and a testing module. Figure 1 As shown, the method includes:

[0035] S110, in response to the first assisted driving instruction from the control module to the assisted driving simulation module, the first assisted driving instruction is sent to the pre-trained vehicle dynamics model based on the feedback processing module.

[0036] The assisted driving simulation module can be a module that simulates driving assistance functions. For example, it can be a module that simulates the Automatic Emergency Braking (AEB) function in an Advanced Driver Assistance System (ADAS). The first assisted driving command can be a program or electrical signal used to control the assisted driving simulation module to execute assisted driving functions; for example, it can be a braking request. The backfeeding processing module can be an HMI (Human-Machine Interface) backfeeding tool. The vehicle dynamics model can be a pre-trained model used to simulate the physical behavior and dynamic characteristics of the vehicle and to provide feedback on real vehicle information.

[0037] In this embodiment, when the backfeeding processing module detects that the control module sends an assisted driving instruction to the assisted driving simulation module, or when the backfeeding processing module receives an assisted driving instruction sent by the control module to the assisted driving simulation module, the received assisted driving instruction can be used as the first assisted driving instruction. Furthermore, the backfeeding processing module can send the first assisted driving instruction to the pre-trained vehicle dynamics model so that the vehicle dynamics model can provide feedback on vehicle information based on the first assisted driving instruction.

[0038] To simulate the assisted driving function in real-world scenarios, the actual scenario data of the vehicle can be sent to the control module before the control module issues the first assisted driving command to the assisted driving simulation module. This allows the control module to determine whether to trigger the assisted driving function based on the actual scenario data. If triggered, the control module then controls the assisted driving simulation module to execute the assisted driving function based on the first assisted driving command.

[0039] In this embodiment, before the first assisted driving instruction is sent to the pre-trained vehicle dynamics model by the feedback processing module in response to the first assisted driving instruction from the control module to the assisted driving simulation module, at least one set of vehicle scene data can be sent to the communication module by the feedback processing module, so that the communication module sends the vehicle scene data to the control module; the control module determines whether the vehicle scene data meets the preset assisted driving conditions, and if so, sends the vehicle scene data that meets the preset assisted driving conditions to the communication module; the communication module synchronizes the vehicle scene data that meets the preset assisted driving conditions to the vehicle dynamics model and sends the first assisted driving instruction to the feedback processing module; the pre-trained vehicle dynamics model is initialized based on the vehicle scene data, so that the feedback processing module sends the first assisted driving instruction to the initialized vehicle dynamics model.

[0040] The vehicle scene data can include vehicle data, surrounding environment data, or scene description data related to triggering the assisted driving function. For example, vehicle scene data includes, but is not limited to, signals from sensors on the vehicle, such as camera data, LiDAR data, vehicle speed, and rotation angle. For instance, taking triggering the assisted driving braking function as an example, each set of vehicle scene data in this scenario is related to triggering the assisted driving braking function. For example, one set of vehicle scene data might be: the vehicle collides head-on with a solid object at a speed of 50 km / h. Another set of vehicle scene data might be: simulating a rear-end collision with a vehicle in front or a collision with a wall on a city road. The preset assisted driving conditions can be pre-configured to determine whether the assisted driving function can be triggered. For example, preset assisted driving conditions might include triggering the assisted driving function when the speed is greater than a preset speed threshold, or triggering the assisted driving function when the braking distance between the vehicle and the obstacle in front is less than a preset threshold and the speed is greater than the preset speed threshold. The control module is used to determine whether the assisted driving function needs to be activated and generates corresponding assisted driving commands. The communication module is used to transmit data between the various modules, ensuring data synchronization and communication. For example... The communication module can be the vehicle's bus system (such as CAN, LIN, Ethernet, etc.) or a communication interface (such as Carsim API).

[0041] During actual vehicle assisted driving testing, the feedback processing module sends at least one set of vehicle scene data to the communication module sequentially or in parallel. Upon receiving any set of vehicle scene data, the communication module sends it to the control module. The control module analyzes the vehicle scene data using algorithms and logic (such as safe distance and speed thresholds) or compares the data with preset assisted driving conditions to determine if the conditions are met. If met, the control module sends the vehicle scene data meeting the preset conditions to the communication module. The communication module (e.g., CAN bus or Ethernet) then synchronizes the received vehicle scene data meeting the preset conditions to the vehicle dynamics model and sends a first assisted driving command carrying the vehicle scene data to the feedback processing module. The vehicle dynamics model initializes using the received vehicle scene data (such as initial speed and position), and after initialization, the model is ready to receive assisted driving commands. After receiving the first assisted driving command from the control module, the feedback processing module sends the command to the initialized vehicle dynamics model.

[0042] This method can simulate different driving scenarios to trigger driver assistance functions, improve the accuracy and authenticity of testing driver assistance functions, and ensure the safety and reliability of driver assistance functions before they are applied to actual vehicles.

[0043] In this embodiment, the communication module includes an Ethernet module and a local area network (LAN) module, wherein the LAN module can be a CAN device. The control module includes a perception service unit and a controller unit. The perception service unit can be a functional module integrated in a System-on-Chip (SoC), used to handle complex assisted driving computational tasks, such as using image processing, machine learning algorithms, etc., to analyze vehicle driving data or vehicle scene data to determine whether to trigger assisted driving functions or how to brake safely.

[0044] Based on this, at least one set of vehicle scene data can be sent to the communication module based on the recharge processing module, so that the communication module can send the vehicle scene data to the control module, including: sending the same set of vehicle scene data to the Ethernet module and the local area network module respectively based on the recharge processing module, so that the Ethernet module can send the vehicle scene data to the perception service unit, and the local area network module can send the vehicle scene data to the controller unit.

[0045] In this implementation, the feedback processing module can send the same set of vehicle scene data to both the Ethernet module and the LAN module. The Ethernet module communicates with the perception service unit, sending vehicle scene data to it, while the LAN module communicates with the controller unit, sending the same data to it. This approach ensures efficient data forwarding and flexible data integration. Furthermore, it facilitates collaborative determination by the perception service unit and controller unit to determine whether to trigger assisted driving functions, effectively improving data processing efficiency and ensuring the accuracy of functional testing of both units.

[0046] Furthermore, when the control module determines whether the vehicle scene data meets the preset assisted driving conditions, and if so, sends the vehicle scene data that meets the preset assisted driving conditions to the communication module: the perception service unit can perform perception processing based on the vehicle scene data to obtain the perception result, and send the perception result to the controller unit; the controller unit can determine whether the preset assisted driving conditions are met based on the vehicle scene data and the perception result, and if so, send the vehicle scene data that meets the preset assisted driving conditions to the local area network module.

[0047] Among them, the perception result is the result of the perception service unit using the perception process to process vehicle scene data, including perception, recognition, and decision-making.

[0048] In other words, the perception service unit can perform perception processing based on vehicle scene data to obtain perception results, which are then sent to the controller unit. After receiving the vehicle scene data and perception results, the controller unit can determine whether preset assisted driving conditions have been met. If so, it considers that the assisted driving function needs to be triggered and sends the vehicle scene data indicating that the preset assisted driving conditions have been met to the local area network module. This allows the local area network module to then send the vehicle scene data indicating that the preset assisted driving conditions have been met to the feedback processing module.

[0049] Alternatively, the vehicle testing system can also integrate a data forwarding unit that communicates with the Ethernet module. In this way, the controller unit can send vehicle scenario data that meets preset assisted driving conditions to the data forwarding unit. The data forwarding unit then transmits the vehicle scenario data to the Ethernet module, which in turn transmits the data to the feedback processing module.

[0050] It should be noted that once the assisted driving function is triggered, the vehicle dynamics model takes over the vehicle's state (such as deceleration and wheel speed). If vehicle scene data continues to be fed back (such as maintaining a speed of 50 km / h), it will contradict the actual state calculated by the vehicle dynamics model (such as the vehicle speed decreasing due to braking), leading to input confusion in the control module. To solve this problem, after responding to the first assisted driving command from the control module to the assisted driving simulation module, the control feedback processing module prohibits the transmission of vehicle scene data to the local area network module.

[0051] In other words, the data feedback tool terminates the vehicle scenario data feedback process and stops transmitting vehicle scenario data to the control module via the local area network module. This method can ensure the accuracy and stability of the assisted driving function test.

[0052] S120. Based on the vehicle dynamics model and the first assisted driving instruction, determine the vehicle driving data and send the vehicle driving data to the communication module, so that the communication module sends the vehicle driving data to the feedback processing module and the feedback processing module sends the vehicle driving data to the control module.

[0053] The vehicle driving data can be real-world driving status data based on feedback from a vehicle dynamics model. For example, vehicle driving data includes, but is not limited to, vehicle speed, deceleration, steering angle, steering rate, torque, wheel speed, distance to the vehicle in front, etc.

[0054] In this embodiment, the vehicle dynamics model analyzes the vehicle's current driving state based on the first assisted driving command, obtaining vehicle driving data. This vehicle driving data is then sent to the communication module. The communication module sends the received vehicle driving data to the feedback processing module. The feedback processing module sends the vehicle driving data to the control module, enabling the control module to perform assisted driving control on the assisted driving simulation module based on the vehicle driving data.

[0055] S130. The control module controls the assisted driving simulation module based on vehicle driving data to obtain function execution attribute data, and sends the function execution attribute data to the test module and the backfeeding processing module respectively.

[0056] Among them, the function execution attribute data refers to the execution result of the driver assistance function.

[0057] In this embodiment, the control module controls the assisted driving simulation module based on vehicle driving data. The assisted driving simulation module, according to the control commands from the control module, simulates the execution process of the assisted driving function and generates function execution attribute data. For example, the assisted driving simulation module simulates the dynamic behavior of the vehicle using simulation software (such as CarSim, PreScan, etc.) to generate function execution attribute data. Optionally, the function execution attribute data includes, but is not limited to, braking distance, steering angle, activation time of primary braking, activation time of secondary braking, deceleration time, activation time of warning, vehicle position coordinates at each time point, relative obstacle coordinates, deceleration time, etc. Further, the function execution attribute data is sent to both the test module and the backfeed processing module. This allows the test module to perform performance evaluation and testing based on the function execution attribute data. The backfeed processing module then sends the function execution attribute data to the vehicle dynamics model, which analyzes the vehicle's driving state to obtain vehicle driving data, forming a backfeed test closed loop.

[0058] S140. Based on the recharge processing module, the function execution attribute data is sent to the vehicle dynamics model, and the steps of determining vehicle driving data, determining function execution attribute data, and sending function execution attribute data to the test module and the recharge processing module are re-executed.

[0059] In this embodiment, the re-feedback processing module sends the function execution attribute data to the vehicle dynamics model, so that the vehicle dynamics model re-executes the steps of determining vehicle driving data, the control module determining function execution attribute data, and sending the function execution attribute data to the test module and the re-feedback processing module respectively. That is, it returns to execute steps S120, S130, and S140, forming a re-feedback test closed loop. This continues until the test termination condition is met.

[0060] S150. In response to the test end event, determine the test result of the test on the assisted driving simulation module based on the function execution attribute data of the test module.

[0061] The test completion event can be any event that meets the test completion conditions. For example, the test completion conditions could be that the number of backflow cycles reaches a preset number, the backflow cycle duration reaches a preset duration, or functional execution attribute data is obtained in a single test round, etc. That is, the test result for the assisted driving simulation module can be determined after all tests are completed, or a test result for the assisted driving simulation module can be determined after each piece of functional execution attribute data is received. The test result can be an evaluation result generated by the test module based on the functional execution attribute data, such as pass / fail status, performance indicators, problem records, longitudinal braking distance Xdec (i.e., the distance the vehicle has traveled from the moment the brake pedal is touched (or the brake lever is activated) when the vehicle is braking suddenly at a specified initial speed until the vehicle comes to a stop), etc.

[0062] In this embodiment, a test termination event can be considered detected when the test termination condition is met. Furthermore, based on preset test standards and evaluation indicators, the functional execution attribute data can be evaluated using the test module. For example, braking distance should be less than a certain threshold, and steering angle should be within a certain range. The test results for the assisted driving simulation module can then be analyzed to verify whether the assisted driving function meets design requirements and safety standards.

[0063] For example, functional execution attribute data, including the activation time of Level 1 assisted driving braking, can be captured, and key parameters such as longitudinal braking distance Xdec can be calculated as test results. A score can also be calculated at the end of the data feedback. Furthermore, based on the test results, it is possible to verify whether the assisted driving function meets design requirements and safety standards, and to verify the optimization effect of the vehicle testing method based on data feedback, simulating assisted driving function testing and regression testing, thereby improving the efficiency and accuracy of feedback testing.

[0064] It should be noted that after determining the test results for the driver assistance simulation module, a test report can be generated based on the results to improve readability. The test report should include at least the test results, detailed performance data, problem logs, and improvement suggestions. The test report format includes, but is not limited to, Excel, PDF, widgets, and web pages. When test results are determined in batches, test reports can be generated to clearly present the test results and facilitate quick identification of problems with the driver assistance function.

[0065] The technical solution of this invention involves responding to a first assisted driving instruction from the control module to the assisted driving simulation module, sending the first assisted driving instruction to a pre-trained vehicle dynamics model based on the feedback processing module; determining vehicle driving data based on the vehicle dynamics model according to the first assisted driving instruction, and sending the vehicle driving data to the communication module, so that the communication module sends the vehicle driving data to the feedback processing module, and the feedback processing module sends the vehicle driving data to the control module; controlling the assisted driving simulation module based on the vehicle driving data to obtain function execution attribute data, and sending the function execution attribute data to the test module and the feedback processing module respectively; and the feedback processing module then processes the function execution attributes... Data is sent to the vehicle dynamics model, and the steps of determining vehicle driving data, determining function execution attribute data, and sending the function execution attribute data to the test module and the backfeeding processing module are re-executed. In response to the test end event, the test module determines the test result of the assisted driving simulation module based on the function execution attribute data. This solves the problem of poor accuracy in the functional testing of assisted driving systems based on data backfeeding in existing technologies. It enables the control module to send the first assisted driving command to the pre-trained vehicle dynamics model when controlling the assisted driving simulation module with the first assisted driving command, allowing the vehicle dynamics model to determine vehicle driving data based on the first assisted driving command. The vehicle driving data is sent to the backfeeding processing module via the communication module, and the backfeeding processing module sends the vehicle driving data to the control module. Then, based on the vehicle driving data, the control module controls the assisted driving simulation module to obtain function execution attribute data, which is sent to the test module and the backfeeding processing module respectively. The backfeeding processing module then sends the function execution attribute data to the vehicle dynamics model, enabling the vehicle dynamics model to re-execute the operation of determining vehicle driving data. The control module controls the assisted driving simulation module based on newly received vehicle driving data to obtain function execution attribute data. This function execution attribute data is then sent to the test module and the backfeed processing module. Based on the function execution attribute data, the test module determines the test results for the assisted driving simulation module. This improves the accuracy of the backfeed test of the assisted driving simulation module, thereby ensuring the safety, reliability, and stability of the assisted driving function execution.

[0066] Example 2

[0067] Figure 2This is a flowchart of a vehicle testing method based on data refeeding according to Embodiment 2 of the present invention. Building upon the foregoing embodiments, before sending assisted driving commands to the pre-trained vehicle dynamics model based on the refeeding processing module, the vehicle dynamics model can be pre-trained. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0068] like Figure 2 As shown, the method specifically includes the following steps:

[0069] S210. Obtain multiple training samples, including vehicle scene data sets, which include at least the ground friction coefficient, vehicle body mass, and air drag coefficient.

[0070] It should be noted that the data in the vehicle scenario data group is similar to the vehicle scenario data in the above groups, and will not be described in detail here.

[0071] To improve the accuracy of vehicle dynamics models, it is possible to acquire as many and rich sets of vehicle scene data as possible to obtain multiple training samples.

[0072] Taking a new car testing scenario as an example, the parameters affecting the vehicle's braking performance during testing are within a limited range, including: the coefficient of friction with the ground, vehicle mass, and drag coefficient. Successful test scenario data can be collected as training samples. Using the vehicle testing system provided in this embodiment, and assuming the test module outputs the expected test results, the parameters of the vehicle dynamics model can be adjusted. When the adjusted parameters cover a sufficient number of successful new car test training samples, a well-trained vehicle dynamics model can be obtained.

[0073] S220. For each training sample, the training sample is sent to the communication module based on the backfeeding processing module, so that the communication module sends the training sample to the control module.

[0074] In this embodiment, the training samples can be sent to the Ethernet module and the LAN module in the communication module based on the feedback processing module. The Ethernet module sends the vehicle scene data sets in the training samples to the perception service unit, and the LAN module sends the training samples to the controller unit.

[0075] S230. Based on the control module, determine whether the vehicle scene data group in the training sample meets the preset assisted driving conditions. If so, send the vehicle scene data group that meets the preset assisted driving conditions to the communication module.

[0076] In this embodiment, the perception service unit performs perception processing based on the vehicle scene data set in the training samples to obtain a second perception result, and sends the second perception result to the controller unit. The controller unit determines whether the preset assisted driving conditions have been met based on the vehicle scene data set and the second perception result. If so, it sends the vehicle scene data set that meets the preset assisted driving conditions to the local area network module and the Ethernet module respectively.

[0077] It should be noted that the methods for perceiving and processing vehicle scene data groups and determining whether preset assisted driving conditions have been met are similar to those for perceiving and processing vehicle scene data and determining whether preset assisted driving conditions have been met, and will not be elaborated here.

[0078] S240: Based on the communication module, the vehicle scene data group that has reached the preset assisted driving conditions is synchronized to the dynamic model to be trained, and the second assisted driving command is sent to the feedback processing module.

[0079] The second assisted driving command can be a program or electrical signal used to control the assisted driving simulation module to perform assisted driving functions. The dynamic model to be trained can be a vehicle dynamic model whose model parameters need to be adjusted. In this case, there is an error between the dynamic model to be trained and the actual vehicle, in order to eliminate the error problem between the model simulation and the actual vehicle.

[0080] In this embodiment, the communication module synchronizes the vehicle scene data group that meets the preset assisted driving conditions to the dynamic model to be trained, and sends the second assisted driving command to the feedback processing module so that the dynamic model to be trained can perform model initialization.

[0081] S250: The dynamic model to be trained is initialized based on the vehicle scene data group so that the feedback processing module can send the second assisted driving command to the initialized dynamic model to be trained.

[0082] S260. Based on the dynamic model to be trained and according to the second assisted driving command, determine the vehicle operation data and send the vehicle operation data to the communication module, so that the communication module sends the vehicle operation data to the feedback processing module and the feedback processing module sends the vehicle operation data to the control module.

[0083] The vehicle driving data can be real-world operating status data based on feedback from a vehicle dynamics model. For example, vehicle driving data includes, but is not limited to, vehicle speed, deceleration, steering angle, steering rate, torque, wheel speed, and distance to the vehicle in front.

[0084] In this embodiment, the dynamics model to be trained analyzes the vehicle's operating state according to the second assisted driving command, obtaining vehicle operating data. This vehicle operating data is then sent to the communication module. The communication module sends the received vehicle operating data to the feedback processing module. The feedback processing module sends the vehicle operating data to the control module, enabling the control module to perform assisted driving control on the assisted driving simulation module based on the vehicle driving data.

[0085] S270. The control module controls the assisted driving simulation module based on vehicle operation data, obtains function execution attribute information, and sends the function execution attribute information to the test module.

[0086] Among them, the function execution attribute information refers to the execution result of the driver assistance function.

[0087] In this embodiment, the control module controls the assisted driving simulation module based on vehicle operation data. The assisted driving simulation module, according to the control commands from the control module, simulates the execution process of the assisted driving function and generates function execution attribute information. Optionally, the function execution attribute information includes, but is not limited to, braking distance, steering angle, activation time of primary braking, activation time of secondary braking, deactivation time of braking, activation time of warning, vehicle position coordinates at each time point, relative obstacle coordinates, deceleration time, etc. Further, the function execution attribute information is sent to both the test module and the backfeed processing module. This allows the test module to perform performance evaluation and testing based on the function execution attribute information. The backfeed processing module then sends the function execution attribute information to the vehicle dynamics model, which analyzes the vehicle's operating state to obtain vehicle operation data, forming a backfeed test closed loop.

[0088] Alternatively, the function execution attribute information can be sent to the data forwarding module, which in turn sends it to the Ethernet module. The Ethernet module then sends the information to both the test module and the re-feedback processing module.

[0089] S280. Based on the functional execution attribute information of the test module, determine the test attributes corresponding to the training samples.

[0090] Among them, test attributes can be the evaluation results generated by the test module based on the functional execution attribute data.

[0091] In this embodiment, the testing module can evaluate the functional execution attribute information based on preset test standards and evaluation indicators, such as braking distance being less than a certain threshold and steering angle being within a certain range. This analyzes the performance of the assisted driving function and obtains the test attributes corresponding to the training sample. The accuracy of the dynamic model under training in simulating real vehicle conditions can then be verified based on the test results.

[0092] S290. When the test attributes do not meet the preset test conditions, the model parameters in the dynamic model to be trained are corrected to obtain a trained vehicle dynamic model.

[0093] Among them, the preset test conditions can be conditions used to characterize whether the test attributes meet the test requirements.

[0094] In this embodiment, it can be determined whether the test attribute meets the preset test conditions. Optionally, the preset test conditions can be that the test attribute is in a pass test state, the longitudinal braking distance Xdec is less than a preset distance, and no collision occurs. Furthermore, when the test attribute does not meet the preset test conditions, the model parameters in the dynamics model to be trained can be corrected so that the test attribute determined by the dynamics model to be trained based on the corrected parameters meets the preset test conditions, until a trained vehicle dynamics model is obtained.

[0095] In this embodiment, after the control module controls the assisted driving simulation module based on vehicle operation data and obtains the function execution attribute information, the control module can send the function execution attribute information to the feedback processing module; the feedback processing module sends the function execution attribute information to the vehicle dynamics model, and re-executes the steps of determining vehicle operation data, determining function execution attribute information, and determining test attributes corresponding to training samples.

[0096] In other words, after executing S270, the function execution attribute information can be sent from the control module to the feedback processing module; the feedback processing module then sends the function execution attribute information to the vehicle dynamics model, and steps S260 and S270 are re-executed. At the end of the loop, the test module determines the test attributes corresponding to the training samples based on the last received function execution attribute information, improving the accuracy of test attributes during the feedback closed-loop test.

[0097] In this embodiment, when the test attribute does not meet the preset test conditions, the model parameters in the dynamic model to be trained are corrected, including: in response to the loop end event corresponding to the training sample, the test module determines the test attribute corresponding to the training sample based on the received partial function execution attribute information.

[0098] Specifically, the loop termination event can be an event that meets the test loop termination condition. For example, the test loop termination condition could be that the number of loops reaches a preset number, or the loop duration reaches a preset duration. That is, after all tests are completed, the test module can determine the test attribute corresponding to the training sample based on the last received function execution attribute information. Alternatively, it can determine the test attribute corresponding to the training sample based on all received function execution attribute information. Or, it can determine the test attribute corresponding to the training sample based on some received function execution attribute information.

[0099] It should be noted that, to improve model accuracy, training samples whose test attributes do not meet the preset test conditions can be used as negative examples to verify the performance of the vehicle dynamics model. Once the final test attributes meet the preset test conditions (such as the requirements for passing the CNCAP test standard), the test attributes can be considered to have met expectations.

[0100] To improve the accuracy of driver assistance function testing, training samples whose test attributes meet preset test conditions can be used as a set of vehicle scenario data. In actual test scenarios, the feedback processing module sends at least one set of vehicle scenario data to the communication module, which then sends the vehicle scenario data to the control module, ensuring the accuracy of driver assistance function testing.

[0101] Example 3

[0102] As an optional embodiment of the above embodiments, specific application scenario examples are provided to enable those skilled in the art to further understand the technical solutions of the embodiments of the present invention. Specifically, please refer to the following detailed content.

[0103] Taking the Automatic Emergency Braking (AEB) function in driver assistance systems as an example, this embodiment introduces the vehicle testing method based on data feedback. See also... Figure 3 , Figure 3 This diagram illustrates the structure of the vehicle testing system provided in this embodiment. A vehicle testing method based on data feedback can be implemented using this vehicle testing system.

[0104] In this embodiment, the vehicle testing system includes an ADAS (Advanced Driver Assistance Systems) controller, an Ethernet switch (i.e., an Ethernet module), a CAN device (i.e., a local area network module), and a PC (host computer). The ADAS controller includes a SoC (System on Chip) and an MCU (Microcontroller Unit). The CAN device can be selected from Kvaser CAN and Vector CANOE, depending on the actual operating system. The host computer deploys HMI (Human Machine Interface) software and a vehicle dynamics model. The HMI includes a backfeed processing module and a testing module. The testing module includes data acquisition and display tools and an automatic scoring tool. The ADAS controller deploys a perception service unit and a data forwarding module on the SoC side, and a control service (i.e., a controller unit) on the microcontroller unit. The vehicle dynamics model (taking Carsim as an example) includes two operating modes: API call and service operation. The technical solution provided in this embodiment can adopt the API call method, whereby the backfeed processing module interacts with the vehicle dynamics model by calling the Carsim API.

[0105] Taking data flow as an example, the vehicle testing method provided by this invention is described.

[0106] The PC-based HMI software receives the data package (including vehicle scene data) for the assisted driving test. The feedback processing module extracts the vehicle scene data required by the perception algorithm from the offline data package. This data is then sent to the ADAS controller's SOC-side perception service unit via Ethernet (i.e., perception feedback). The perception service unit outputs the perception results to the MCU-side control service. Simultaneously, the feedback processing module extracts vehicle scene data of the vehicle body information from the offline data package and feeds it back to the control service via CAN (i.e., MCU feedback), simulating the vehicle body signal input obtained by the control service from the actual vehicle. The feedback processing module interacts with the vehicle dynamics model by calling APIs. During MCU feedback, vehicle scene data is synchronized to the dynamics model for initialization, and data such as pedal and steering wheel states are synchronized to the dynamics model for state updates. The vehicle dynamics model outputs vehicle speed, acceleration, steering angle, and other vehicle driving data (i.e., model feedback 1) through its own simulation logic, allowing the feedback processing module to obtain the vehicle driving data via the corresponding API. The regulatory control service transmits assisted driving commands (including braking request signals) to the SOC-side data forwarding module, which then transmits them via Ethernet to the feedback processing module (i.e., MCU feedback 1). Therefore, the feedback processing module can receive assisted driving commands in real time. Once the feedback processing module detects a braking request, it immediately cuts off the input of vehicle scene data from the original offline data packet and replaces it with vehicle driving data fed back from the model. This data is also fed back to the regulatory control service (i.e., model feedback 2) via the CAN device as input for the vehicle body signals after braking is triggered. This triggers a new closed-loop feedback: after receiving the model feedback input, the regulatory control service updates the function execution attribute data. The feedback processing module receives the function execution attribute data, calls the API to transmit the current function execution attribute data to the vehicle dynamics model (i.e., MCU feedback 2), the dynamics model updates the vehicle driving data, and then inputs it back to the regulatory control service through the model feedback link, forming a closed-loop feedback link in the structure diagram: "MCU output -> MCU feedback 1 -> MCU feedback 2 -> Model feedback 1 -> Model feedback 2 -> MCU output".

[0107] Continue to refer to Figure 3 The functional execution attribute data of the control service is transmitted to the data acquisition and display tool via Ethernet through the data forwarding module (i.e., MCU feedback 1). The perception service unit, after receiving the feedback input, not only sends a copy of the perception results to the control service but also transmits it to the data acquisition and display tool via Ethernet. In other words, the data acquisition and display tool can obtain detailed vehicle status feedback data in real time, including vehicle braking request signals, vehicle speed, coordinate position, and perceived obstacle location information, and record them all into the data packet, forming a closed-loop test link of feedback + data acquisition.

[0108] Considering the discrepancy between current vehicle dynamics model simulations and real-vehicle testing, the vehicle testing method provided in this invention corrects the model parameters in the vehicle dynamics model (as the dynamics model to be trained) using a positive sample training method, resulting in a trained vehicle dynamics model. Taking braking test scenarios as an example, the parameters affecting the braking effect of a vehicle in braking tests are within a limited range, including: ground friction coefficient, vehicle body mass, and air drag coefficient. Successful braking test scenario data sets of vehicles can be collected. Using a vehicle testing system, the model parameters of the vehicle dynamics model are adjusted based on the premise that the test attributes corresponding to the training samples meet expectations. When the adjusted parameters can cover a sufficient number of successful braking test cases, the current vehicle dynamics model can be used as a standard real-vehicle simulation model. This model is then used to backfeed data from failed braking cases to verify the effectiveness of the vehicle dynamics model. If the final test attributes meet the requirements of the braking test standard, the test attributes are considered to meet expectations. It should be noted that each training sample (i.e., the vehicle scenario data set) has a score item and a weight ratio. Based on an automatic scoring tool, the score of each training sample is multiplied by a weight coefficient to obtain the final total score, which is used as the test attribute to determine whether the training sample test passes. The scoring is based on three real-world vehicle test results: longitudinal braking distance Xdec, braking time Tdec, and bus warning distance Xfcw. These three parameters can be calculated using the activation times of AEB Level 1 braking, AEB Level 2 braking, AEB braking deactivation, and FCW warning, along with the corresponding vehicle position coordinates and relative obstacle coordinates at each time point. By automatically capturing real-time parameters including the activation time of AEB Level 1 braking, key parameters such as the longitudinal braking distance Xdec are automatically calculated. This allows for the automatic calculation of the test attributes of the training samples at the end of the refeeding process. For multi-scenario datasets already collected, the vehicle testing system can be used for batch refeeding and automatic scoring, thus covering all test scenarios, verifying algorithm optimization effects, simulating functional and regression tests, and greatly improving the efficiency of algorithm refeeding testing.

[0109] The technical solution provided by this invention supports the automatic generation of scoring reports for the aforementioned automatic scoring tools. Report formats include, but are not limited to, Excel, PDF, widgets, and web pages; the content includes scene name, scene type, vehicle offset, vehicle speed, test item weighting coefficient, individual item scores, and total score. When batch vehicle scene data is fed back, the automatic scoring tool will automatically obtain the scores for each item and generate a scoring report; the report clearly displays the test results, facilitating quick identification of completed and uncompleted tasks by the algorithm, greatly improving algorithm optimization efficiency.

[0110] Figure 4A flowchart illustrating the vehicle testing method based on data refeedback provided by this invention. The vehicle testing method includes:

[0111] S300: Before triggering the AEB (Autonomous Emergency Braking) function, sensor and MCU re-feedback are performed, including:

[0112] S301: The PC-side data feedback module selects an offline data package that includes vehicle scenario data, and supports dataset selection. If a dataset is selected, this process is executed for the data in each specific scenario, and then all data is automatically processed sequentially.

[0113] S302: The recharge processing module executes the perception recharge process, transmitting vehicle scene data to the ADAS perception service module via the Ethernet module.

[0114] S303: The ADAS-side perception service module outputs perception results, which are transmitted to the PC-side data acquisition and display tool via the Ethernet module for perception result collection. Simultaneously, the perception results are also transmitted to the ADAS-side control service as input.

[0115] S304: The recharge processing module executes the MCU recharge process, transmitting vehicle scene data to the ADAS control service via CAN device.

[0116] S305: The ADAS-side control service combines perception input and vehicle scene data input, and outputs control commands and MCU feedback results. These are then forwarded to the PC-side feedback processing module and data acquisition and display tool via the data forwarding module to collect the MCU feedback results.

[0117] S306: The PC-side backfeeding processing module synchronizes vehicle scene data to the PC-side vehicle dynamics model via API calls for state initialization.

[0118] S400: When the MCU feedback result is a driver assistance command, it is considered that the driver assistance function has been triggered. After the driver assistance function (such as AEB function) is triggered, data feedback is used from the vehicle dynamics model, including:

[0119] S401: The PC-side recharge processing module continues to perform sensor-based recharge, the same as S302.

[0120] S402: The ADAS terminal continues to output the perception results, and the data is transferred to the PC terminal to collect the perception results, the same as S303.

[0121] S403: The PC-side power-back processing module terminates the MCU power-back process and stops S304.

[0122] S404: The PC-side backfeeding processing module will synchronize the captured MCU feedback results (such as AEB braking requests) to the vehicle dynamics model in real time as a trigger.

[0123] S405: The PC-side vehicle dynamics model outputs vehicle speed, acceleration, steering angle, and other vehicle body signals through its own simulation logic, and allows the feedback processing module to obtain vehicle driving data through the corresponding API.

[0124] S406: The PC-side recharge processing module transmits the vehicle driving data fed back by the model to the ADAS-side control service via the CAN device.

[0125] S407: The ADAS-side control service receives the input and outputs functional execution attribute data containing control instructions, which is then forwarded to the PC via the data forwarding module, similar to S305.

[0126] S28: The PC-side backfeeding processing module obtains the function execution attribute data and executes S404 in a loop.

[0127] S500: When the test termination condition is triggered, such as the AEB test vehicle coming to a stop or a collision occurring, the scoring mechanism is activated, including:

[0128] S501: The PC-based data acquisition and display tool obtains real-time parameters, including the activation time of AEB Level 1 braking, and automatically calculates key parameters such as the longitudinal braking distance Xdec, thereby automatically calculating the test results.

[0129] S502: The PC-based automatic scoring tool marks the test results and waits for all backfeed test cases to be executed before automatically generating a test report.

[0130] The technical solution provided by this invention introduces a vehicle testing system based on a vehicle dynamics model. This system integrates sub-modules for data refeeding, data acquisition, and the dynamics model. The data acquisition tools involved can capture the activation moment of the ADAS function in real time. The refeeding module can precisely control the vehicle signal input using offline data before the ADAS function is activated, and obtain feedback from the vehicle simulation signal by triggering the vehicle dynamics model after the ADAS function is activated. Simultaneously, to eliminate the error between the simulation model and the real vehicle, the vehicle testing system adjusts the parameters of the vehicle dynamics model, assuming the test attributes meet expectations. When the adjusted parameters cover a sufficient number of successful test cases, it can serve as a standard real-vehicle simulation model. This model is then used to refeed data from failed cases to verify the algorithm optimization effect and improve the reliability of the refeeding test. Furthermore, the testing module can capture real-time parameters, including the activation moment of AEB (Autonomous Emergency Braking) Level 1 braking, and automatically calculate key parameters such as the longitudinal braking distance Xdec. This allows for automatic calculation of test results at the end of the refeeding process, improving the efficiency and accuracy of the refeeding test. Furthermore, by using the API interface built into the vehicle dynamics model, the communication latency between the backfeeding processing module and the dynamics model is reduced, improving the system's reliability and reducing the error compared to the actual vehicle.

[0131] Example 4

[0132] Figure 5 This is a schematic diagram of a vehicle testing device based on data refeedback according to Embodiment 4 of the present invention. The device is configured in a vehicle testing system, which integrates a refeedback processing module, a communication module, a control module, a vehicle-associated assisted driving simulation module, and a testing module, such as... Figure 5 As shown, the device includes: a recharge treatment module 610, a vehicle dynamics model 620, a control module 630, a recharge treatment module 640, and a test module 650.

[0133] The system includes a backfeeding processing module 610, which, in response to a first assisted driving instruction from the control module to the assisted driving simulation module, sends the first assisted driving instruction to a pre-trained vehicle dynamics model based on the backfeeding processing module; a vehicle dynamics model 620, which, based on the vehicle dynamics model and the first assisted driving instruction, determines vehicle driving data and sends the vehicle driving data to the communication module, so that the communication module sends the vehicle driving data to the backfeeding processing module, and the backfeeding processing module sends the vehicle driving data to the control module; and a control module 630, which, based on the vehicle driving data... The driver assistance simulation module is controlled to obtain function execution attribute data, which is then sent to the test module and the backfeed processing module. The backfeed processing module 640 is used to send the function execution attribute data to the vehicle dynamics model based on the backfeed processing module, and to re-execute the steps of determining vehicle driving data, determining function execution attribute data, and sending the function execution attribute data to the test module and the backfeed processing module. The test module 650 is used to determine the test result of testing the driver assistance simulation module based on the function execution attribute data in response to a test end event.

[0134] The technical solution of this embodiment solves the problem of poor accuracy in functional testing of driving assistance systems based on data feedback in the prior art. It achieves this by having the first driving assistance command sent from the control module to the pre-trained vehicle dynamics model via the feedback processing module when the control module controls the driving assistance simulation module. This allows the vehicle dynamics model to determine vehicle driving data based on the first driving assistance command. The vehicle driving data is then sent to the feedback processing module via the communication module, which in turn sends it to the control module. Furthermore, the control module controls the driving assistance simulation module based on the vehicle driving data to obtain functional execution attribute data, which is then sent to both the testing module and the feedback processing module. Finally, the feedback processing module sends the functional execution attribute data to the vehicle dynamics model, enabling the vehicle dynamics model to re-execute the operation of determining vehicle driving data. The control module controls the assisted driving simulation module based on newly received vehicle driving data to obtain function execution attribute data. This function execution attribute data is then sent to the test module and the backfeed processing module. Based on the function execution attribute data, the test module determines the test results for the assisted driving simulation module. This improves the accuracy of the backfeed test of the assisted driving simulation module, thereby ensuring the safety, reliability, and stability of the assisted driving function execution.

[0135] Optionally, based on the above-described apparatus, the apparatus may further include:

[0136] The first data sending unit is used to send at least one set of vehicle scene data to the communication module based on the feedback processing module, so that the communication module sends the vehicle scene data to the control module;

[0137] The assisted driving condition judgment unit is used to determine whether the vehicle scene data meets the preset assisted driving conditions based on the control module. If so, the vehicle scene data that meets the preset assisted driving conditions is sent to the communication module.

[0138] The data synchronization unit is used to synchronize vehicle scene data that meets the preset assisted driving conditions to the vehicle dynamics model based on the communication module, and send the first assisted driving command to the feedback processing module.

[0139] The model initialization unit is used to initialize the vehicle dynamics model based on the vehicle scene data according to the pre-trained vehicle dynamics model, so that the feedback processing module can send the first assisted driving command to the initialized vehicle dynamics model.

[0140] Based on the above-mentioned device, optionally, the communication module includes an Ethernet module and a local area network module, and the control module includes a sensing service unit and a controller unit;

[0141] The first data sending unit is configured to send the same set of vehicle scene data to the Ethernet module and the local area network module respectively based on the feedback processing module, so that the Ethernet module sends the vehicle scene data to the perception service unit and the local area network module sends the vehicle scene data to the controller unit.

[0142] Based on the above device, optionally, an assisted driving condition judgment unit is used to perform perception processing based on the vehicle scene data by the perception service unit to obtain a perception result, and send the perception result to the controller unit; the controller unit determines whether a preset assisted driving condition has been met based on the vehicle scene data and the perception result, and if so, sends the vehicle scene data that meets the preset assisted driving condition to the local area network module.

[0143] Optionally, based on the above-described apparatus, the apparatus may further include:

[0144] The data transmission prohibition unit is used to control the feedback processing module to prevent the vehicle scene data from being sent to the local area network module.

[0145] Optionally, based on the above-described apparatus, the apparatus further includes: a module training module for training the vehicle dynamics model; wherein the module training module includes:

[0146] A training sample determination unit is used to acquire multiple training samples, wherein the training samples include a vehicle scene data set, and the vehicle scene data set includes at least the ground friction coefficient, the vehicle body mass, and the air drag coefficient.

[0147] A determining unit is configured to, for each training sample, send the training sample to the communication module based on the backfeeding processing module, so that the communication module sends the training sample to the control module;

[0148] The first judgment unit is used to determine whether the vehicle scene data group in the training sample meets the preset assisted driving conditions based on the control module. If so, the vehicle scene data group that meets the preset assisted driving conditions is sent to the communication module.

[0149] The data group synchronization unit is used to synchronize the vehicle scene data group that has reached the preset assisted driving conditions to the dynamic model to be trained based on the communication module, and send the second assisted driving command to the feedback processing module.

[0150] An initialization unit is used to initialize the dynamic model to be trained based on the vehicle scene data group, so that the feedback processing module can send the second assisted driving command to the initialized dynamic model to be trained.

[0151] The vehicle operation data determination unit is used to determine vehicle operation data based on the dynamic model to be trained and according to the second assisted driving command, and send the vehicle operation data to the communication module, so that the communication module sends the vehicle operation data to the feedback processing module, and so that the feedback processing module sends the vehicle operation data to the control module.

[0152] The function execution attribute information determination unit is used to control the assisted driving simulation module based on the vehicle operation data by the control module, obtain function execution attribute information, and send the function execution attribute information to the test module;

[0153] The test attribute determination unit is used to determine the test attribute corresponding to the training sample based on the attribute information executed by the test module according to the function.

[0154] The vehicle dynamics model determination unit is used to correct the model parameters in the dynamics model to be trained when the test attribute does not meet the preset test conditions, so as to obtain a trained vehicle dynamics model.

[0155] Optionally, based on the above-described apparatus, the apparatus may further include:

[0156] An attribute information sending unit is used to send the function execution attribute information to the feedback processing module based on the control module.

[0157] The repetitive execution unit is used to send the function execution attribute information to the vehicle dynamics model based on the feedback processing module, and re-execute the steps of determining vehicle operation data, determining function execution attribute information, and determining test attributes corresponding to the training samples.

[0158] Based on the above-mentioned device, optionally, a vehicle dynamics model determination unit is used to determine the test attributes corresponding to the training sample in response to a loop end event corresponding to the training sample, based on the test module's received partial functional execution attribute information.

[0159] Optionally, based on the above-described apparatus, the apparatus may further include:

[0160] The vehicle scene data determination unit is used to take the training samples whose test attributes meet the preset test conditions as a set of vehicle scene data, and send at least one set of vehicle scene data to the communication module based on the feedback processing module.

[0161] The vehicle testing device based on data refeeding provided in the embodiments of the present invention can execute the vehicle testing method based on data refeeding provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0162] Example 5

[0163] Figure 6 This is a schematic diagram of the structure of an electronic device implementing the vehicle testing method based on data feedback according to embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0164] like Figure 6As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from storage unit 18 into the random access memory 13. The random access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0165] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0166] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle testing methods based on data feedback.

[0167] In some embodiments, the data-backflow-based vehicle testing method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the data-backflow-based vehicle testing method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the data-backflow-based vehicle testing method by any other suitable means (e.g., by means of firmware).

[0168] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0169] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0170] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0171] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0172] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0173] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0174] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from read-only memory 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0175] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the vehicle testing method based on data refeedback as provided in any embodiment of this invention.

[0176] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0177] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0178] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle testing method based on data feedback, characterized in that, The method is applied to a vehicle testing system, which integrates a backfeed processing module, a communication module, a control module, a vehicle-associated assisted driving simulation module, and a testing module. The method includes: In response to the first assisted driving instruction from the control module to the assisted driving simulation module, the first assisted driving instruction is sent to the pre-trained vehicle dynamics model based on the feedback processing module. Based on the vehicle dynamics model and the first assisted driving instruction, the vehicle driving data is determined and sent to the communication module, so that the communication module sends the vehicle driving data to the feedback processing module and the feedback processing module sends the vehicle driving data to the control module. The control module controls the assisted driving simulation module based on the vehicle driving data to obtain function execution attribute data, and sends the function execution attribute data to the test module and the feedback processing module respectively. Based on the recharge processing module, the function execution attribute data is sent to the vehicle dynamics model, and the steps of determining vehicle driving data, determining function execution attribute data, and sending the function execution attribute data to the test module and the recharge processing module are re-executed. In response to the test end event, the test result of the test on the assisted driving simulation module is determined based on the functional execution attribute data of the test module.

2. The method according to claim 1, characterized in that, Before sending the first assisted driving instruction to the pre-trained vehicle dynamics model based on the feedback processing module in response to the first assisted driving instruction from the control module to the assisted driving simulation module, the method further includes: Based on the recharge processing module, at least one set of vehicle scene data is sent to the communication module, so that the communication module sends the vehicle scene data to the control module; The control module determines whether the vehicle scene data meets the preset assisted driving conditions. If so, the vehicle scene data that meets the preset assisted driving conditions is sent to the communication module. Based on the communication module, the vehicle scene data that meets the preset assisted driving conditions is synchronized to the vehicle dynamics model, and the first assisted driving command is sent to the feedback processing module; The pre-trained vehicle dynamics model is initialized based on the vehicle scene data, so that the feedback processing module can send the first assisted driving command to the initialized vehicle dynamics model.

3. The method according to claim 2, characterized in that, The communication module includes an Ethernet module and a local area network module, and the control module includes a sensing service unit and a controller unit; The step of sending at least one set of vehicle scene data to the communication module based on the recharge processing module, so that the communication module sends the vehicle scene data to the control module, includes: Based on the feedback processing module, the same set of vehicle scene data is sent to the Ethernet module and the local area network module respectively, so that the Ethernet module sends the vehicle scene data to the perception service unit, and the local area network module sends the vehicle scene data to the controller unit.

4. The method according to claim 3, characterized in that, The step of determining whether the vehicle scene data meets the preset assisted driving conditions based on the control module, and if so, sending the vehicle scene data that meets the preset assisted driving conditions to the communication module, includes: The perception service unit performs perception processing based on the vehicle scene data to obtain perception results, and sends the perception results to the controller unit. The controller unit determines whether the preset assisted driving conditions have been met based on the vehicle scene data and the perception results. If so, the vehicle scene data that meets the preset assisted driving conditions is sent to the local area network module.

5. The method according to claim 3, characterized in that, Following the first assisted driving command from the control module to the assisted driving simulation module, the method further includes: The control module is configured to prevent the vehicle scene data from being sent to the local area network module.

6. The method according to claim 1, characterized in that, Before sending the assisted driving command to the pre-trained vehicle dynamics model based on the feedback processing module, the method further includes: The vehicle dynamics model is obtained through training; wherein, The training process yields the vehicle dynamics model, including: Multiple training samples are acquired, wherein the training samples include a vehicle scene data set, and the vehicle scene data set includes at least the ground friction coefficient, the vehicle body mass, and the air drag coefficient. For each training sample, the training sample is sent to the communication module based on the backfeeding processing module, so that the communication module sends the training sample to the control module; Based on the control module, it is determined whether the vehicle scene data group in the training sample meets the preset assisted driving conditions. If so, the vehicle scene data group that meets the preset assisted driving conditions is sent to the communication module. Based on the communication module, the vehicle scene data group that meets the preset assisted driving conditions is synchronized to the dynamic model to be trained, and the second assisted driving command is sent to the feedback processing module; The dynamic model to be trained is initialized based on the vehicle scene data set so that the feedback processing module can send the second assisted driving command to the initialized dynamic model to be trained. Based on the dynamic model to be trained, the vehicle operation data is determined according to the second assisted driving command, and the vehicle operation data is sent to the communication module, so that the communication module sends the vehicle operation data to the feedback processing module, and the feedback processing module sends the vehicle operation data to the control module. The control module controls the assisted driving simulation module based on the vehicle operation data to obtain function execution attribute information, and sends the function execution attribute information to the test module. Based on the functional execution attribute information, the test module determines the test attribute corresponding to the training sample. When the test attribute does not meet the preset test conditions, the model parameters in the dynamic model to be trained are corrected to obtain a trained vehicle dynamic model.

7. The method according to claim 6, characterized in that, After the control module controls the assisted driving simulation module based on the vehicle operation data to obtain function execution attribute information, the method further includes: The control module sends the function execution attribute information to the backfeeding processing module. Based on the refeedback processing module, the function execution attribute information is sent to the vehicle dynamics model, and the steps of determining vehicle operation data, determining function execution attribute information, and determining test attributes corresponding to the training samples are re-executed. Accordingly, when the test attribute does not meet the preset test conditions, the step of correcting the model parameters in the dynamic model to be trained includes: In response to the loop end event corresponding to the training sample, the test module determines the test attribute corresponding to the training sample based on the received partial function execution attribute information.

8. The method according to claim 6 or 7, characterized in that, The method further includes: Training samples whose test attributes satisfy the preset test conditions are respectively used as a set of vehicle scene data, and at least one set of vehicle scene data is sent to the communication module based on the feedback processing module.

9. A vehicle testing device based on data refeedback, characterized in that, Configured in a vehicle testing system, the vehicle testing system integrates a recharge processing module, a communication module, a control module, a vehicle-associated assisted driving simulation module, and a testing module. The device includes: The backfeed processing module is used to respond to the first assisted driving command from the control module to the assisted driving simulation module, and send the first assisted driving command to the pre-trained vehicle dynamics model based on the backfeed processing module. The vehicle dynamics model is used to determine vehicle driving data based on the first assisted driving command, and send the vehicle driving data to the communication module, so that the communication module sends the vehicle driving data to the feedback processing module, and so that the feedback processing module sends the vehicle driving data to the control module. The control module is used to control the assisted driving simulation module based on the vehicle driving data, obtain function execution attribute data, and send the function execution attribute data to the test module and the feedback processing module respectively. The recharge processing module is used to send the function execution attribute data to the vehicle dynamics model based on the recharge processing module, and re-execute the steps of determining vehicle driving data, determining function execution attribute data, and sending the function execution attribute data to the test module and the recharge processing module respectively; The testing module is used to determine the test results of the assisted driving simulation module in response to a test end event, based on the functional execution attribute data of the testing module.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle testing method based on data refeedback as described in any one of claims 1-8.

Images