CN117420814A

CN117420814A - Test method based on electric test bench, electric test bench and equipment

Info

Publication number: CN117420814A
Application number: CN202311427275.9A
Authority: CN
Inventors: 司佩强; 牛广智; 田磊; 郭鹏; 郭强
Original assignee: China National Heavy Duty Truck Group Jinan Power Co Ltd
Current assignee: China National Heavy Duty Truck Group Jinan Power Co Ltd
Priority date: 2023-10-30
Filing date: 2023-10-30
Publication date: 2024-01-19

Abstract

The application provides a test method based on an electrical test bench, the electrical test bench and equipment, and relates to the technical field of vehicle testing. The method comprises the following steps: the communication test is carried out on the sensors on the electric test bench through the control device respectively; performing fault test, simulation communication test and communication test of an internal system-level chip and a microcontroller of the high-performance computing platform through a control device; and sending the trained perception algorithm model, the fusion algorithm model and the planning control algorithm model through the control device, and carrying out algorithm model test. And visually presenting all the test result information to determine whether the electric test bench can work normally or not and diagnose the device connection problem. The sensor and the high-performance computing platform in the electric test rack can be normally used and put into automatic driving development in an acceleration mode.

Description

Test method based on electric test bench, electric test bench and equipment

Technical Field

The application relates to the technical field of vehicle testing, in particular to a testing method based on an electrical testing bench, the electrical testing bench and equipment.

Background

With the rapid development of trunk logistics truck intellectualization, the high-order intelligent driving technology is more and more widely applied in the field of trunk logistics trucks. The high-order intelligent driving technology comprises automatic driving, vehicle tracking, real-time road condition information feedback and other technologies. The automatic driving technology can ensure that the vehicle can safely run on the road when a driver is tired or needs to rest. The vehicle tracking technology can monitor the position and the state of the vehicle in real time, and can immediately take corresponding measures once abnormal conditions occur. The real-time road condition information feedback technology can feed the road condition information back to drivers in real time, help the drivers to avoid traffic jam areas and select the optimal driving route. Based on the application of the high-order intelligent driving technology, the fatigue problem of long-distance driving of a driver can be solved, the driving safety is improved, and an effective solution is provided for driving conditions.

Currently, in order to better realize automatic driving and improve driving safety, an intelligent driving system applied to the advanced intelligent driving technology in a vehicle is also required to be more and more complex. The high-order intelligent driving system not only comprises a camera, a laser radar, a millimeter wave radar, combined navigation, a high-performance computing platform and other numerous hardware, but also is provided with more complex software. The high-performance computing platform not only integrates a traditional embedded system, but also comprises a vehicle-mounted operating system, and the internally deployed basic software is also an important component of the high-performance computing platform. For this reason, in the development of the high-order intelligent driving system of the vehicle, a large amount of system test work is required to satisfy the development verification of the high-order intelligent driving system.

Aiming at a large number of test requirements, the construction of a test bench is the most efficient method. Based on the above, a test method based on an electrical test bench is needed at present, so that the electrical test bench, especially the electrical test bench of the high-order intelligent driving system for the trunk logistics truck, can complete the test work of the electrical test bench more quickly and comprehensively, and the electrical test bench is put into development and research of the high-order intelligent driving system more quickly.

Disclosure of Invention

The application provides a test method based on an electrical test bench, the electrical test bench and equipment, which are used for solving the problem of the test method of the electrical test bench which is not finished at present.

In a first aspect, the present application provides a test method based on an electrical test bench comprising: the system comprises a control device, a plurality of sensors and a high-performance computing platform; the method comprises:

the control device performs communication test on the plurality of sensors respectively to obtain a test result of the sensor communication test;

the control device respectively sends fault test information and simulation test information to the high-performance computing platform so as to enable the high-performance computing platform to perform fault test and simulation communication test, obtains fault result information generated by the high-performance computing platform according to the fault test information, and generates simulation result information according to the simulation test information;

The control device respectively sends communication test information to the high-performance computing platform so that the high-performance computing platform triggers the internal system-level chip and the microcontroller to carry out communication test to respectively acquire communication result information corresponding to the system-level chip and the microcontroller;

the control device sequentially sends the trained perception algorithm model, the fusion algorithm model and the planning control algorithm model to the high-performance computing platform, triggers the deployment operation of the high-performance computing platform, and sequentially acquires operation result information of the perception algorithm model, the fusion algorithm model and the planning control algorithm model;

the control device respectively carries out visual presentation on the test result, the fault result information, the simulation result information, the communication result information and the operation result information so as to realize the judgment of whether the electric test bench can work normally and the diagnosis of the device connection problem through the visual presentation of the test result, the fault result information, the simulation result information, the communication result information and the operation result information.

In one possible design, the control device sends fault test information and simulation test information to the high performance computing platform respectively, so that the high performance computing platform performs fault test and simulation communication test, obtains fault result information generated by the high performance computing platform according to the fault test information, and generates simulation result information according to the simulation test information, and includes:

The control device sends fault test information containing at least one sensor in fault to the high-performance computing platform through a preset BOB fault test box;

the control device acquires fault result information generated by the high-performance computing platform according to fault test information containing at least one sensor in the fault; the fault result information reflects whether the high-performance computing platform can correctly identify the sensor fault.

In one possible design, the control device sends communication test information to a high-performance computing platform respectively, so that the high-performance computing platform triggers an internal system-in-chip and a microcontroller to perform communication test, so as to obtain communication result information corresponding to the system-in-chip and the microcontroller respectively, and the control device comprises:

the control device sends communication test information to the high-performance computing platform through test equipment so that the high-performance computing platform triggers an internal system-in-chip and a microcontroller to carry out communication test; the test equipment comprises an Ethernet test device which communicates through Ethernet and a CAN test device which communicates through CAN;

the control device acquires to-be-transmitted SOC result information generated by the system-on-chip according to the communication test information, and acquires to-be-processed SOC result information received by the microcontroller and transmitted by the system-on-chip, so as to generate the communication result information based on whether the to-be-transmitted SOC result information is consistent with the to-be-processed SOC result information;

The control device acquires MCU result information to be transmitted, which is generated by the microcontroller according to the communication test information, and acquires MCU result information to be processed, which is received by the system-in-chip and transmitted by the microcontroller, so as to generate the communication result information based on the MCU result information to be transmitted and the MCU result information to be processed.

the control device generates and transmits simulation test CAN message information containing the whole vehicle state to the high-performance computing platform through a CAN test device;

and the control device acquires simulation result information generated by the high-performance computing platform according to the received simulation test CAN message information containing the whole vehicle state.

In one possible design, the control device sequentially sends the trained sensing algorithm model, the fusion algorithm model and the planning control algorithm model to the high-performance computing platform and triggers the deployment operation of the high-performance computing platform, and sequentially obtains operation result information of the sensing algorithm model, the fusion algorithm model and the planning control algorithm model, including:

The control device sends and deploys a trained perception algorithm model to the high-performance computing platform, and obtains perception operation result information of the perception algorithm model; the sensing operation result information is obtained by taking real-time acquisition information of the sensor as input and operating the sensing algorithm model;

the control device sends and deploys a trained fusion algorithm model to the high-performance computing platform, and acquires fusion operation result information of the fusion algorithm model; the fusion operation result information is obtained by taking the perception operation result information as input and operating the fusion algorithm model;

the control device sends and deploys a trained planning control algorithm model to the high-performance computing platform, and obtains planning control operation result information of the planning control algorithm model; and the planning control operation result information is obtained by taking the fusion operation result information as input and operating the planning control algorithm model.

In one possible design, the control device performs communication tests on the plurality of sensors respectively to obtain test results of the sensor communication tests, including:

The control device respectively acquires acquisition information of the camera, the laser radar, the millimeter wave radar and the combined inertial navigation so as to generate the test result based on the acquisition information.

In a second aspect, the present application provides an electrical test bench comprising: the system comprises a control device, a plurality of sensors and a high-performance computing platform; wherein,

the control device is used for respectively carrying out communication tests on the plurality of sensors so as to obtain test results of the sensor communication tests;

the control device is further used for respectively sending fault test information and simulation test information to the high-performance computing platform so as to enable the high-performance computing platform to perform fault test and simulation communication test, obtaining fault result information generated by the high-performance computing platform according to the fault test information and simulating result information generated according to the simulation test information;

the control device is further used for respectively sending communication test information to the high-performance computing platform for the communication test of the system-in-chip and the microcontroller, and respectively obtaining communication result information corresponding to the system-in-chip and the microcontroller;

the control device is also used for sequentially sending the trained perception algorithm model, the fusion algorithm model and the planning control algorithm model to the high-performance computing platform, triggering the deployment operation of the high-performance computing platform, and sequentially obtaining the operation result information of the perception algorithm model, the fusion algorithm model and the planning control algorithm model;

The control device is further used for respectively carrying out visual presentation on the test result, the fault result information, the simulation result information, the communication result information and the operation result information so as to determine whether the electrical test bench can work normally or not and diagnose the device and/or the connection problem through the visual presentation of the test result, the fault result information, the simulation result information, the communication result information and the operation result information.

Further, the method further comprises the following steps: a BOB fault test box; wherein the plurality of sensors are each connected with the high-performance computing platform; the BOB fault test box is connected in series between the plurality of sensors and the high-performance computing platform;

the control device is specifically used for: transmitting fault test information containing at least one sensor in fault to the high-performance computing platform through the BOB fault test box;

acquiring fault result information generated by the high-performance computing platform according to fault test information containing at least one sensor in the fault; the fault result information reflects whether the high-performance computing platform can correctly identify the sensor fault.

Further, the method further comprises the following steps: a testing device; the test equipment is respectively connected with the plurality of sensors and the high-performance computing platform;

The control device is specifically used for: communication test information is sent to the high-performance computing platform through test equipment so that the high-performance computing platform triggers an internal system-in-chip and a microcontroller to carry out communication test;

acquiring to-be-transmitted SOC result information generated by the system-on-chip according to the communication test information and receiving to-be-processed SOC result information transmitted by the system-on-chip by the microcontroller; and

and acquiring MCU result information to be transmitted generated by the microcontroller according to the communication test information and receiving the MCU result information to be processed transmitted by the microcontroller by the system-in-chip.

Further, the sensor comprises a camera, a laser radar, a millimeter wave radar and combined inertial navigation; the camera is connected with the high-performance computing platform through a GMSL (global system for mobile communications) line, the laser radar is connected with the high-performance computing platform through an Ethernet, and the millimeter wave radar and the combined inertial navigation are connected with the high-performance computing platform through a CAN (controller area network) line;

the control device is specifically used for: acquiring acquisition information of the camera and the laser radar through the Ethernet, and acquiring acquisition information of the millimeter wave radar and the combined inertial navigation through a CAN line, so as to generate the test result based on the acquisition information.

Further, the test equipment comprises an Ethernet test device and a CAN test device; the Ethernet testing device and the CAN testing device are respectively connected with the high-performance computing platform, and the CAN testing device is respectively connected with the millimeter wave radar and the combined inertial navigation;

the control device is specifically used for:

the communication test information is sent to the high-performance computing platform through the Ethernet test device and the CAN test device respectively so that the high-performance computing platform triggers the internal system-in-chip and the microcontroller to carry out communication test;

the system-level chip corresponding to the Ethernet test device and the CAN test device respectively obtains to-be-sent SOC result information generated by the system-level chip according to the communication test information and the microcontroller receives to-be-processed SOC result information sent by the system-level chip; and

and respectively acquiring MCU result information to be transmitted generated by the microcontroller corresponding to the Ethernet test device and the CAN test device according to the communication test information and receiving the MCU result information to be processed transmitted by the microcontroller by the system-in-chip.

Further, the system also comprises a power supply module, wherein the power supply module is used for respectively supplying power to the plurality of sensors, the BOB fault test box, the high-performance computing platform, the control device and the test equipment.

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

the memory stores computer-executable instructions;

and the processor executes the computer-executed instructions stored in the memory to realize the test method of the electrical test bench.

In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, are configured to implement a test method for an electrical test bench.

According to the test system, the sensor and the high-performance computing platform arranged in the electrical test bench are sequentially tested, communication tests are conducted on the sensor, fault tests, simulation communication tests and communication tests conducted on the high-performance computing platform trigger an internal system-level chip and a microcontroller, so that the sensor and the high-performance computing platform in the electrical test bench can be normally used and put into automatic driving development in an accelerated mode. And meanwhile, a trained perception algorithm model, a fusion algorithm model and a planning control algorithm model are further transferred to a high-performance computing platform and are triggered to be deployed and operated, the algorithm operation performance of the whole electric test bench is tested, the problem of system integration is found conveniently, and the electric test bench is adjusted timely according to the problem. Through visual presentation of the test results, developers can intuitively and clearly know the hardware or software problems of the electrical test bench and objectively display the performance of the electrical test bench. The test system further comprises an electric test bench, wherein the electric test bench can be maximally close to the test environment of the real vehicle, and the occurrence frequency of problems in the real vehicle test is reduced; and the problems tested in the real vehicle can be better analyzed and solved on the rack.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a testing method based on an electrical testing bench according to an embodiment of the present application;

FIG. 2 is a schematic flow chart of a fault testing method according to one embodiment of the present application;

FIG. 3 is a flow chart of a simulation communication testing method according to an embodiment of the present application;

FIG. 4 is a flow chart of a system on chip and microcontroller communication test method according to one embodiment of the present application;

FIG. 5 is a flow chart of a method for trained algorithm model testing provided by one embodiment of the present application;

FIG. 6 is a schematic diagram of an electrical test bench according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Reference numerals:

60-control means; 61-millimeter wave radar; 62-combined inertial navigation; 63-a camera; 64-lidar; 65-BOB fault test box; 66-a high performance computing platform; 67-CAN test device; 68-ethernet testing device.

Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application, as detailed in the accompanying claims, rather than all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Related concepts or nouns referred to in this application are explained first:

high performance computing platform (High Performance Computing, abbreviated as HPC): it uses a powerful processor cluster working in parallel, processes massive multidimensional datasets (big data), and solves complex problems at extremely high speeds. The platform integrates product resources such as computation, storage, network and the like, integrates software such as HPC special job management scheduling, cluster management and the like, and provides flexible, excellent-performance and self-service computing service for users.

In the prior art, the high-order intelligent driving system not only comprises a camera, a laser radar, a millimeter wave radar, a combination navigation, a high-performance computing platform and other hardware, but also is provided with more complex software, so that a large amount of system test work is required in the development of the high-order intelligent driving system of the vehicle so as to meet the development and verification of the high-order intelligent driving system.

Based on this, the inventive concept of the present application is: how to provide a test method based on an electric test bench, so that the electric test bench, especially the electric test bench of the high-order intelligent driving system for trunk logistics trucks, can complete the test work of the electric test bench more quickly and comprehensively, and the electric test bench is put into development and research of the high-order intelligent driving system more quickly.

Example 1

Fig. 1 is a schematic flow chart of a test method based on an electrical test bench according to an embodiment of the application. Wherein, electrical test bench includes: control device, a plurality of sensors, high performance computing platform.

As shown in fig. 1, the test method specifically includes steps S11 to S15:

s11, the control device performs communication tests on the plurality of sensors respectively to obtain test results of the sensor communication tests.

In this embodiment, the electrical test bench is an important device for performing advanced intelligent driving system development. Autopilot systems are required to perform a variety of tasks including positioning, path planning, obstacle avoidance, and the like. These tasks may require different types of data input. For example, high-precision global positioning (Global Positioning System, abbreviated as GPS) and inertial navigation systems can be used for positioning, while cameras and lidars can be used to detect obstacles on the road surface. In general, an electrical test bench is designed to simulate the real situation of automatic driving as much as possible, and for this purpose, a plurality of sensors are disposed on the electrical test bench. Communication between the sensor and the control device is the basis for ensuring that the entire driving system development operates smoothly. The control device performs communication test on the plurality of sensors to check whether the sensors installed on the test electric bench can normally collect information, which is the basis for ensuring normal operation of the electric test bench, so as to improve stability and reliability of the test for the electric test bench.

Specifically, the control device will establish a communication connection with each sensor in turn. During this process, the control device will send some specific signals to the sensor and then check whether the response returned by the sensor corresponds to the expected one. For example, the control device may require the sensor to return its current status information and then check whether this information matches the actual situation. Further, the control device evaluates the communication performance of each sensor. This includes speed, stability, reliability, etc. of the communication. Specifically, the control device checks whether the speed of the sensor returning data is fast enough to meet the real-time requirement of the system. Meanwhile, the control device can also check the communication stability of the sensor under various working conditions (such as temperature, humidity, voltage and the like). The control device evaluates and records the communication performance of each sensor according to the test result. The test results can more quickly and intuitively find potential problems so as to solve the problems, accelerate the development process of the electric test bench put into an automatic driving system, and provide reliable data support for subsequent algorithm processing tests and decision making tests.

S12, the control device respectively sends fault test information and simulation test information to the high-performance computing platform so as to carry out fault test and simulation communication test on the high-performance computing platform, obtains fault result information generated by the high-performance computing platform according to the fault test information, and generates simulation result information according to the simulation test information.

In this embodiment, the control device needs to send the fault test information and the simulation test information to the high-performance computing platform respectively, so that the high-performance computing platform performs the fault test and the simulation communication test, and simultaneously obtains and processes the fault result information and the simulation result information generated by the high-performance computing platform. The fault test and the simulation communication test are both aimed at a high-performance computing platform. On high performance computing platforms, many basic software programs are deployed that are responsible for handling various tasks, including data processing, system monitoring, sensor failure detection, and the like. For this reason, when the sensor fails, it is required that the high-performance computing platform can recognize and process the failure problem in time, and whether corresponding instruction information can be issued according to the simulated vehicle condition.

When fault testing is carried out, the control device can send fault testing information to the high-performance computing platform. Such information includes various possible fault conditions such as short circuit, open circuit, data errors, etc. of the sensor. The high performance computing platform can identify and judge which sensor has a problem according to the received fault test information, and what the specific fault is, and what processing is needed for the fault. For example, when a certain sensor fails in data transmission, the control device may send corresponding information to the high-performance computing platform to simulate the failure of the sensor. The high performance computing platform generates fault result information from this information to indicate which sensor has a problem, what the specific nature of the problem is, and possibly the solution. For another example, when the analog sensor is shorted, it is checked whether the high performance computing platform can find the problem in time and take corresponding measures (e.g., cut off power, send an alarm, etc.). After the fault test is completed, the high-performance computing platform generates corresponding fault result information and sends the corresponding fault result information to the control device. The result information contains the various fault conditions identified, as well as feedback for the various conditions. The method and the device ensure that the high-performance computing platform can find and process problems in time when encountering sensor faults, and are used for testing the deployment test base software on the high-performance computing platform so as to judge whether the high-performance computing platform can normally operate.

When the simulation test is carried out, the control device can send the simulation test information of the whole vehicle to the high-performance computing platform. The information includes various possible working conditions, such as temperature, humidity, voltage, etc., and various states of the whole vehicle, such as speed, acceleration, steering angle, etc. The high-performance computing platform can make corresponding reactions according to the received simulation test information simulating various working conditions. For example, when simulating an elevated temperature situation, the high performance computing platform recognizes and issues instructions to properly adjust the operating state to accommodate the new environmental conditions. Meanwhile, when the acceleration condition of the vehicle is simulated, whether the high-performance computing platform can correctly send out information for controlling the output power of the engine or not is judged, so that the acceleration requirement is met. After the simulation communication test is completed, the high-performance computing platform generates corresponding simulation result information and sends the simulation result information to the control device. The result information comprises reactions under various working conditions and possible problems, and through the simulation result information, the high-performance computing platform can evaluate whether the data information number can be correctly received, and whether feedback is finished according to the data signal or not and the feedback result is correctly output. Furthermore, in addition to the simulation test for simulating the movement condition of the whole vehicle, the simulation of the environmental condition, the simulation of the road condition and the like can be performed. For example, to simulate the driving situation of a vehicle in rainy or snowy weather, or to simulate a vehicle in a complex road condition. I.e. in different situations, e.g. whether an obstacle can be avoided normally, whether driving can be stabilized, etc. The test of the high-performance computing platform for receiving and transmitting data and the test of whether the high-performance computing platform can finish the work are also carried out.

And S13, the control device respectively sends communication test information to the high-performance computing platform so as to trigger the internal system-in-chip and the microcontroller to carry out communication test by the high-performance computing platform, and respectively acquire communication result information corresponding to the system-in-chip and the microcontroller.

In this embodiment, the high performance computing platform triggers the internal system-in-chip and the microcontroller to perform the communication test according to the received communication test information. Such information, which typically includes communication protocols, data transfer rates, data formats, etc., is a necessary parameter for the system on chip to communicate with the microcontroller. The system-level chip is a core part of an automatic driving system and is responsible for processing a large amount of data and executing complex algorithms. The microcontroller is responsible for controlling various hardware devices, such as sensors and actuators. The system-on-chip and the microcontroller each assume different tasks in the autopilot system, and the communication between them must ensure consistency of the data to ensure stable operation of the entire autopilot system.

In the communication test process, the system level chip and the microcontroller exchange and communicate data with the control device according to the designated communication protocol and data format. The test simulates the communication situation under the actual working environment, and can comprehensively test the communication capability of each internal component. The result information of the communication test comprises indexes such as whether communication is successful, whether data transmission is accurate, whether communication delay is stable and the like. These indicators are key criteria for evaluating the communication performance of the system. Meanwhile, the automatic driving system has high requirement on real-time performance, and the communication delay between the system-level chip and the microcontroller must be within an acceptable range so as to ensure that the automatic driving system can timely react. And the reliability of data transmission, the communication test can check whether the communication link between the system-in-chip and the microcontroller is reliable, whether the problems of packet loss, error and the like exist.

After the communication result information of the system-level chip and the microcontroller is acquired, the control device analyzes and processes the information. If the communication test is successful, the communication capability among all the internal components is normal, and stable data exchange can be maintained in actual operation. However, if communication failure or data transmission errors are found in the test, the control device can send out an alarm in time and record related information so as to facilitate troubleshooting and repair. The timely feedback mechanism ensures that the problem can be found in time before the electric test bench is put into development and use, and avoids the difficulty in software development caused by the communication problem of the system-in-chip and the microcontroller.

S14, the control device sequentially sends the trained perception algorithm model, the fusion algorithm model and the planning control algorithm model to the high-performance computing platform, triggers deployment operation of the high-performance computing platform, and sequentially acquires operation result information of the perception algorithm model, the fusion algorithm model and the planning control algorithm model.

In this embodiment, the control device sequentially transmits the trained perceptual algorithm model, the fusion algorithm model, and the planning control algorithm model to the high-performance computing platform. In this process, the high performance computing platform will load the received algorithm models into memory and run them in real time according to the current environment and state information. The sensing algorithm model processes the data acquired by the sensor to identify various information of the surrounding environment. And integrating the data acquired by different sensors by using the fusion algorithm model to form comprehensive environment cognition. And the planning control algorithm model makes a decision according to the perceived and fused information to plan the running path of the vehicle. Since these algorithmic models have been subjected to deep learning and big data training, and have been subjected to application of actual scenes. I.e. if the algorithm model deployment runs unsuccessful, it is stated that there is a problem with the connection of hardware or the deployment of software programs in the electrical test bench. Problems include, but are not limited to, hardware compatibility issues and system integration issues. Where hardware compatibility issues refer to the fact that a hardware device (e.g., a sensor) may not be compatible with a particular algorithm model even if the sensor and the high-energy computing platform are communicating properly. For example, an algorithmic model may require a particular type of sensor input that a sensor on a test bench cannot provide. The system integration problem refers to the need for the individual components to work together in a complex system. Even though each individual component may function properly, unexpected problems may occur when they work together. For example, an algorithmic model may present problems in processing data from multiple sensors. The trained perception algorithm model, fusion algorithm model and planning control algorithm model are deployed and operated, the electric test bench is tested more comprehensively, and whether the problem of algorithm operation exists on the electric test bench can be further found. The electric test bench is more deeply discovered and improved before being put into use, the process of putting the electric test bench into use is quickened, a stable experimental device is provided for the development of a follow-up automatic driving system, and the development of the follow-up automatic driving program is facilitated to be smoothly carried out.

And S15, the control device visually presents the test result, the fault result information, the simulation result information, the communication result information and the operation result information respectively so as to determine whether the electric test bench can work normally or not and diagnose the device connection problem through visual presentation of the test result, the fault result information, the simulation result information, the communication result information and the operation result information.

In the embodiment, the control device visually presents the test result, the fault result information, the simulation result information, the communication result information and the operation result information, so that the performance of each part of the electric test bench can be more intuitively known. For example, the response time, accuracy, sensitivity and other parameters of each sensor can be clearly displayed in a visual mode such as a chart, a curve, statistical data and the like. The presentation of these data can help engineers better understand the behavior of the sensor under different conditions and thus better determine whether the operating conditions of the device are satisfactory. For example, by visualizing the test results, engineers can observe whether a sensor is abnormal in a specific situation, and then quickly locate the problem and repair it. Visual presentation of fault result information, for example in the form of a chart or image, can clearly show whether the high performance computing platform is able to correctly identify the fault and to feedback operation accordingly based on the fault. And engineers can quickly locate a specific basic software program which corresponds to the preset fault and is deployed in the high-energy computing platform, and the basic software program can not identify the cause of the fault or make corresponding feedback. Visual presentation of simulation result information can help engineers better understand whether a high-performance computing platform can respond correspondingly according to corresponding scenes or conditions under different scenes. The visual mode is presented, so that the reaction and expected difference of the high-performance computing platform can be clearly known, and a reference direction is provided for the improvement of the electric test bench. Meanwhile, the visualization of the communication result information is helpful for evaluating the communication effect among all modules in the system, and can intuitively know parameters such as communication delay, packet loss rate, data transmission speed and the like among different modules, so that engineers are helped to judge the communication performance of the system, discover potential problems in time and optimize the system. The visual analysis not only provides a direction for optimizing the electric test bench, but also provides powerful support for fault diagnosis and problem solving of the electric test bench. Through scientific and reasonable data presentation mode, the safe, stable and reliable operation of the electric test bench is ensured.

According to the test system, the sensor and the high-performance computing platform arranged in the electrical test bench are sequentially tested, communication tests are conducted on the sensor, fault tests, simulation communication tests and communication tests conducted on the high-performance computing platform trigger an internal system-level chip and a microcontroller, so that the sensor and the high-performance computing platform in the electrical test bench can be normally used and put into automatic driving development in an accelerated mode. And meanwhile, a trained perception algorithm model, a fusion algorithm model and a planning control algorithm model are further transferred to a high-performance computing platform and are triggered to be deployed and operated, the algorithm operation performance of the whole electric test bench is tested, the problem of system integration is found conveniently, and the electric test bench is adjusted timely according to the problem.

In a specific embodiment, fig. 2 is a schematic flow chart of a fault testing method according to an embodiment of the present application. The further development of the above step S12 specifically includes steps S21 to S22:

s21, the control device sends fault test information containing at least one sensor in fault to the high-performance computing platform through a preset BOB fault test box;

S22, the control device acquires fault result information generated by the high-performance computing platform according to fault test information containing at least one sensor in the fault; the fault result information reflects whether the high performance computing platform can correctly identify the sensor fault.

In this embodiment, the purpose of the fault test is to simulate various possible fault conditions and to check whether the high performance computing platform is able to correctly identify and handle these faults. In the process, the control device sends fault test information containing at least one sensor in fault to the high-performance computing platform through a preset BOB fault test box. The BOB fault test box is a device specifically designed to simulate various sensor faults. It can simulate various possible fault conditions such as sensor failure, data errors, communication interruptions, etc. By using the BOB fault test cartridge, a comprehensive fault test can be performed without damaging the real sensor. Such simulated fault testing aims to verify whether a high performance computing platform is able to correctly identify the fault condition of the sensor. The high performance computing platform, upon receiving the fault test information, begins executing a fault identification program (the sensor fault identification program is a pre-deployed base software program). This procedure is designed based on the possible failure modes and data characteristics of the various sensors. By analyzing the received fault test information, it is possible to detect whether the sensor is in a fault state and the specific type of fault. For example, if the fault test information indicates a camera failure, the high performance computing platform may read the simulated camera failure and if this fault can be correctly identified and react appropriately, such as switching to a backup camera or alerting the driver to take over control. After the test is completed, the high-performance computing platform generates corresponding fault result information and sends the information back to the control device. The fault result information contains the type, location and possible cause of the sensor fault. To intuitively understand which sensor failed, as well as the nature of the failure. The control device, the high-performance computing platform and the preset BOB fault test box form a closed loop system. The method can realize faster and provide a powerful detection means for whether the basic software deployed in the high-performance computing platform can normally run.

In another embodiment, fig. 3 is a schematic flow chart of a method for testing simulated communication according to an embodiment of the present application. The further development of the above step S12 specifically includes steps S31 to S32:

s31, the control device generates and transmits simulation test CAN message information containing the whole vehicle state to the high-performance computing platform through the CAN test device;

s32, the control device acquires simulation result information generated by the high-performance computing platform according to the received simulation test CAN message information containing the whole vehicle state.

In this embodiment, the goal of the simulated communications test is to simulate various possible vehicle conditions and to check whether the high performance computing platform is able to properly receive and process such condition information. The control device CAN generate and send simulation test CAN message information containing the whole vehicle state to the high-performance computing platform through the CAN test device. Such information encompasses the status of various components of the vehicle, including the engine, the braking system, the suspension system, etc., such as vehicle speed, steering angle, braking status, etc. The simulation test CAN message information is designed to simulate various running conditions and environments so as to comprehensively test the response and performance of the high-performance computing platform under different situations.

The control device sends the simulation test CAN message information to the high-performance computing platform. The high-performance computing platform simulates corresponding vehicle states according to the information, and makes corresponding response instructions according to the information. For example, if the simulation test CAN message information indicates an increase in vehicle speed, the high performance computing platform may simulate an increase in vehicle speed and check whether the system is able to properly handle this condition, such as whether the driving strategy is able to be properly adjusted. After the operation is finished, the high-performance computing platform generates corresponding simulation result information and sends the information back to the control device. Such outcome information includes the outcome of each simulation test, such as being able to react correctly in the face of which simulated vehicle conditions are unrecognizable, or being unable to make corresponding feedback based on the simulated information, etc. Through analyzing the result information, the performance of the electric test bench in the face of various vehicle states can be known, whether the electric test bench can be correctly identified and corresponding response instructions can be made can be found, and the possible problems of the electric test bench can be further found. In addition, the result information can also be used as a basis for evaluating the performance of the electric test bench, so that a developer is helped to evaluate whether the electric test bench meets the expected performance standard. An important foundation is laid for the development of the automatic driving system in the follow-up electric test bench.

In one embodiment, fig. 4 is a schematic flow chart of a system-on-chip and microcontroller communication testing method according to one embodiment of the present application, which is a further development description of the above step S13, specifically includes steps S41 to S43:

s41, the control device sends communication test information to the high-performance computing platform through the test equipment so that the high-performance computing platform triggers the internal system-in-chip and the microcontroller to carry out communication test; the test equipment comprises an Ethernet test device which communicates through Ethernet and a CAN test device which communicates through CAN.

In this embodiment, the communication test is to ensure whether each internal component, such as the system-in-chip and the microcontroller, can effectively exchange information, so as to ensure that the communication between the system-in-chip and the microcontroller is reliable and stable. The test equipment comprises an Ethernet test device which communicates through Ethernet and a CAN test device which communicates through CAN. Among them, ethernet communication is a high-speed network protocol-based communication method, and is mainly used for ethernet communication inside a test system, such as communication between a system-on-chip and a microcontroller, and communication with external devices. CAN communication is a field bus standard dedicated to vehicle internal communication, and is mainly used for CAN communication in a test system, such as communication with sensors and actuators.

The control device sends the communication test information to the high-performance computing platform through the two test devices respectively. And after receiving the communication test, the high-performance computing platform triggers the internal system-level chip and the microcontroller to carry out the communication test. This test procedure includes aspects such as the speed of data transfer, accuracy, and responsiveness to various instructions. In this process, the system on chip and the microcontroller simulate various possible communication scenarios and record the test results. For example, in a data transmission test, it is checked whether data can be correctly transmitted and received; in the error detection test, it is checked whether or not an error can be correctly recognized and handled; in the communication interruption test, it is checked whether or not the communication interruption can be properly handled. Meanwhile, the test performed by the testing device is not only simple information transmission, but also comprehensive examination of various aspects of internal (system-level chip and microcontroller) communication protocols, data packet formats and the like. By using the Ethernet test device and the CAN test device, the control device CAN fully simulate the actual communication scene and ensure the communication capability of each component in the high-performance computing platform. Not only to ensure proper operation of the electrical test bench, but also to ensure that the electrical test bench can simulate and handle the development problems faced under various complex and extreme conditions.

S42, the control device acquires to-be-transmitted SOC result information generated by the system-on-chip according to the communication test information, and acquires to-be-processed SOC result information received by the microcontroller and transmitted by the system-on-chip, so as to generate communication result information based on whether the to-be-transmitted SOC result information is consistent with the to-be-processed SOC result information.

In this embodiment, when a communication test is performed, a System On Chip (SOC) performs analysis and encoding processing after receiving the communication test information to generate SOC result information to be transmitted. The SOC result information to be sent is sent to the microcontroller for further processing and response of the system. Such information may include various data and instructions, such as sensor data, control instructions, and the like. Meanwhile, the system-level chip also stores the SOC result information to be sent in an internal cache so as to check at any time. The microcontroller receives information sent by the system-on-chip, which is SOC result information to be processed. The microcontroller performs corresponding operations based on the information, such as reading and processing sensor data, executing control instructions, etc. The control device compares the SOC result information to be transmitted with the SOC result information to be processed (i.e., information sent by the system on a chip and information received by the microcontroller). If the two pieces of information are consistent, the communication between the system-on-chip and the microcontroller is normal, and the problems of errors, packet loss and the like do not occur. That is, if the system-in-chip sends a command to the microcontroller to perform a certain operation, the microcontroller will perform the corresponding operation after receiving the correct command. If the two pieces of information are not identical, a problem may occur in the communication process. For example, if the system-on-chip sends a command to the microcontroller to perform an operation, but the command received by the microcontroller is inconsistent with the command sent by the system-on-chip due to a communication error, the microcontroller may perform the wrong operation, or may not perform any operation at all. This may cause the high performance computing platform to fail and may even cause the system to crash.

S43, the control device acquires MCU result information to be transmitted, which is generated by the microcontroller according to the communication test information, and acquires MCU result information to be processed, which is received by the system-in-chip and transmitted by the microcontroller, so as to generate communication result information based on the MCU result information to be transmitted and the MCU result information to be processed.

In this embodiment, the microcontroller (Microcontroller Unit, MCU) generates MCU result information to be transmitted from the communication test information. The MCU result information to be transmitted may include control states of various hardware devices, such as readings of sensors, operating states of actuators, and the like. Such information needs to be processed and optimized through complex algorithms to ensure that the hardware devices can perform tasks accurately and efficiently. The MCU result information to be transmitted may be transmitted to the system on chip. The system-on-chip receives the MCU result information to be processed sent by the microcontroller. Such information may be real-time feedback on the status of the vehicle, such as the current speed, position, etc. of the vehicle. The system-in-chip needs to adjust its own algorithm and control strategy according to the feedback information. Such as adjusting the speed, direction, etc. of the vehicle. These control strategies need to be adjusted according to real-time environmental information and vehicle conditions to ensure that the vehicle can safely and accurately perform preset tasks.

Similarly, the control device can acquire and judge whether the MCU result information to be transmitted is consistent with the MCU result information to be processed, and generate communication result information. If the two pieces of information are identical, it is assumed that the communication between the microcontroller and the system on chip is normal and that the information transferred between them is reliable and accurate. If not, it is stated that there may be communication errors or other problems. For example, hardware faults (e.g., internal circuit damage) exist on the system on chip or the microcontroller itself; the firmware of the system-level chip or the microcontroller has errors, which may cause problems in the implementation of the communication protocol; the communication protocol of the system-level chip and the microcontroller is not matched; the unstable power supply of the system on chip or microcontroller may cause it to fail to operate properly, thereby affecting communication. A corresponding process is required for the system on a chip or microcontroller.

In one embodiment, FIG. 5 is a flow chart of a method for trained algorithm model testing provided in one embodiment of the present application. The further development of the above step S14 specifically includes steps S51 to S53:

s51, the control device sends and deploys the trained perception algorithm model to the high-performance computing platform, and obtains perception operation result information of the perception algorithm model; the sensing operation result information is obtained by taking real-time acquisition information of the sensor as input and operating the sensing algorithm model.

In this embodiment, the perception algorithm model is the core for realizing vehicle environment perception and obstacle detection. The perception algorithm model recognizes obstacles, vehicles, pedestrians, etc. on the road by processing data acquired in real time by the sensor, such as a camera, a laser radar, an ultrasonic sensor, etc. If the perception algorithm model runs successfully, the sensor can respond to the data reading instruction normally, and the high-performance computing platform can also identify and send out corresponding commands correctly. In this process, the control device will send the trained perceptual algorithm model to the high performance computing platform. The model is trained by deep learning and other technologies, and has the capability of efficiently processing and identifying sensor data. After the high-performance computing platform receives the perception algorithm model, the perception algorithm model is deployed to a specific computing unit so as to perform real-time environment perception tasks. The perceptual algorithm model may be a deep learning model, such as a convolutional neural network or a recurrent neural network, or a conventional computer vision algorithm, such as an algorithm formed by combining a direction gradient histogram (Histogram of Oriented Gradients, HOG) and a support vector machine (Support Vector Machine, SVM).

After the sensing algorithm model is deployed and operated, real-time acquisition information of the sensor is received as input. The information includes a picture shot by the camera, an obstacle distance detected by the laser radar, an ambient environment detected by the ultrasonic sensor, and the like. The perceptual algorithm model uses these data to perform complex calculations and analyses to identify and classify various objects in the environment, such as other obstacles, pedestrians, etc. The generated perceived operation result information includes various types of information such as the position, size, shape, speed, etc. of the object. The control device can acquire the perception operation result information of the perception algorithm model. Such outcome information includes the outcome of each test, such as which objects were correctly identified, which objects may be misidentified, etc. By analyzing the result information, a developer can know the performance of the perception algorithm model in the actual operation of the perception algorithm model deployed on the electrical test bench, and find out possible problems of the electrical test bench. In addition, the information of the perceived operation result can also be used as a basis for performance evaluation, so that a developer is helped to evaluate whether the electric test bench meets the expected performance standard. If the electric test bench can obtain the expected result, the electric test bench can completely realize the perception requirement on the automatic driving vehicle, and is a powerful support for the electric test bench to be put into automatic driving development.

S52, the control device sends and deploys the trained fusion algorithm model to the high-performance computing platform, and obtains fusion operation result information of the fusion algorithm model; and the fusion operation result information is obtained by taking the perception operation result information as input and operating the fusion algorithm model.

In this embodiment, after receiving the fusion algorithm model, the high-performance computing platform deploys the fusion algorithm model to a corresponding computing unit so as to perform a real-time data fusion task. Specifically, the fusion algorithm model is responsible for integrating and processing the information of the sensing operation results from different sensors so as to comprehensively analyze the surrounding environment. The control device sends and deploys the trained fusion algorithm model to the high-performance computing platform. The fusion algorithm model can receive the information of the sensing operation result as input through the training of technologies such as deep learning and the like, and performs efficient data integration and analysis. The fusion algorithm model may be a conventional data fusion algorithm, such as a kalman filter or a particle filter.

After the fusion algorithm model is deployed and operated, the perception operation result information generated by the perception algorithm model is used as input. The fusion algorithm model integrates the information and analyzes the relation between the information and the information, such as predicting the running track of other obstacles or judging the moving direction of pedestrians. And the fusion operation result information of the fusion algorithm model is output after model processing. The output is comprehensive knowledge of the whole environment, and is comprehensive of information such as position, speed, acceleration and the like of various objects. This information is used to provide more accurate and comprehensive environmental awareness for the autopilot system, helping the system to better understand the surrounding situation and make more intelligent driving decisions. Likewise, after the above operation is completed, the control device may acquire the operation result information of the fusion algorithm model. The fusion run result information includes the result of each test, such as which object trajectories were corrected or which objects were not properly identified, etc. By analyzing the result information, a developer can know the performance of the fusion algorithm model in actual operation, find out possible problems and formulate a corresponding optimization strategy for the electrical test bench. The electric test bench can meet the requirements of automatic driving development better.

S53, the control device sends and deploys the trained planning control algorithm model to the high-performance computing platform, and obtains planning control operation result information of the planning control algorithm model; the planning control operation result information is obtained by taking fusion operation result information as input and operating the planning control algorithm model.

In this embodiment, the planning control algorithm model is responsible for converting the fusion operation result information into specific driving decisions and behavior plans. Planning control algorithms enable safety and stability of an autonomous vehicle in a complex environment. The control device sends the trained planning control algorithm model to the high-performance computing platform and deploys the high-performance computing platform. The algorithm model has the processing capacity for various complex traffic situations through training technologies such as deep learning, machine learning and the like. The input data is the output of the fusion algorithm model, i.e. fusion operation result information. This information includes comprehensive knowledge of the environment surrounding the vehicle, including information on the location, speed, acceleration, etc. of various elements such as other vehicles, pedestrians, road signs, etc. The fusion algorithm model integrates the information into the input of the planning control algorithm model, and operates the corresponding algorithm to generate the planning control result information. The generated planning control result information may include various types of information such as which path the vehicle should travel, at what speed the vehicle should travel, when a turn or a brake is made, and the like. Such information can help the autopilot system make reasonable driving decisions and generate corresponding control instructions. For example, the engine, brake, steering, and other execution components of the vehicle are controlled to realize specific traveling actions.

Also, after the above operation is completed, the control device may acquire the operation result information of the planning control algorithm model. Such outcome information includes the outcome of each test, such as which driving decisions were properly generated, which decisions may require improvement, etc. By analyzing the result information, a developer can know the performance of the planning control algorithm model in actual operation and find out possible problems of the electrical test bench. And the perception algorithm model, the fusion algorithm model and the planning control algorithm model can realize data transmission among algorithms on the electric test rack, so that powerful support is provided for the development of automatic driving control input of the subsequent electric test rack.

In one embodiment, step S11 is further described, and specifically includes:

the control device respectively acquires acquisition information of the camera, the laser radar, the millimeter wave radar and the combined inertial navigation so as to generate a test result based on the acquisition information.

In this embodiment, the autopilot system needs to have rich environmental data, which is key to achieving intelligent decision making and safe driving. The sensors each have specific functions and advantages, and through the information they acquire, the surrounding environment can be comprehensively known, so that accurate driving decisions can be made. The selection of the sensor can be flexibly set according to the development requirement. Such as cameras, lidars, millimeter wave radars, and combination inertial. Wherein, the control device adopts a personal computer (Personal Computer, abbreviated as PC), and the communication test of the sensor is further described in detail herein: the communication test of the camera, the PC accesses the high-performance computing platform system through the Ethernet, opens the acquisition program of the camera, uses Linux to carry out remote file copy command (SCP for short), copies the acquired image data to the PC, checks the acquired image data by using a VLC (VideoLAN Client Media Player) media player, and checks whether the camera normally acquires images and the acquisition quality of the images; the communication test of the laser radar, the PC accesses the high-performance computing platform system through the Ethernet, can normally receive and respond (ping communication) to the IP address of the laser radar, opens the acquisition program of the laser radar, copies the acquired image data to the PC by using a Linux remote copy scp command, displays the image data by using an RVIZ tool, and checks whether the laser radar normally acquires point cloud and the acquisition quality of the point cloud; the communication test of the millimeter wave radar, the CAN test device is connected with the PC and the millimeter wave radar, and is used for checking whether the message signal of the millimeter wave radar is normally received on the upper computer of the PC and whether the state message of the millimeter wave radar is normally displayed; the communication test of the combined inertial navigation is that the CAN test device is connected with the PC and the combined inertial navigation to check whether the message signal of the combined inertial navigation is normally received on the upper computer of the PC and whether the state message of the combined inertial navigation is normally displayed. It should be further noted that, before the sensor communication test, the sensor driver of the high-performance computing platform is updated and kept consistent with the software of the sensor.

It should be noted here that the test bench needs to be set up before the electrical test bench is tested. According to the test requirements in the practical project, including the detailed test cases of sensor communication test, basic software test and algorithm model test of the high-order intelligent driving system, analyzing the hardware composition of the electric test bench and test equipment, and combining the hardware architecture of the high-order intelligent driving system to formulate a schematic diagram scheme of the electric test bench. And building a corresponding electric test bench according to the schematic diagram. The electric test bench can be maximally close to the test environment of the real vehicle, so that the frequency of occurrence of problems in the real vehicle test is reduced; and the problems tested in the real vehicle can be better analyzed and solved on the rack. Further, the development of an autopilot system may be put into practice for an electrical test bench that has completed testing. For example, the development of sensing algorithms, fusion algorithms, and planning control algorithms. Specifically, the sensing algorithm is deployed on a high-performance computing platform, after the communication test of the camera and the laser radar is passed, the PC accesses the high-performance computing platform system, whether the sensing output module of the camera and the laser radar operates normally or not is observed, whether the output of the sensing result can be stably output or not is observed, and the operation stability of the sensing algorithm is preliminarily verified. Likewise, a fusion algorithm or a planning control algorithm is deployed to realize whether the developed fusion algorithm or planning control algorithm can normally operate and the stability of operation.

The embodiment of the invention can divide the functional modules of the electronic device or the main control device according to the method example, for example, each functional module can be divided corresponding to each function, and two or more functions can be integrated in one processing unit. The integrated units may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present invention, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.

Fig. 6 is a schematic structural diagram of an electrical test bench according to an embodiment of the present application. Comprising the following steps: control device 60, a plurality of sensors, a high performance computing platform 66, wherein,

the control device 60 is configured to perform communication tests on the plurality of sensors respectively, so as to obtain a test result of the sensor communication test;

the control device 60 is further configured to send fault test information and simulation test information to the high-performance computing platform 66, so that the high-performance computing platform 66 performs fault test and simulation communication test, obtains fault result information generated by the high-performance computing platform 66 according to the fault test information, and generates simulation result information according to the simulation test information;

The control device 60 is further configured to send communication test information to the high-performance computing platform 66 for the system-on-chip and the microcontroller to perform communication test, and obtain communication result information corresponding to the system-on-chip and the microcontroller, respectively;

the control device 60 is further configured to sequentially send the trained sensing algorithm model, the fusion algorithm model and the planning control algorithm model to the high-performance computing platform 66, trigger deployment and operation of the high-performance computing platform, and sequentially obtain operation result information of the sensing algorithm model, the fusion algorithm model and the planning control algorithm model;

the control device 60 is further configured to visually present the test result, the fault result information, the simulation result information, the communication result information, and the operation result information, so as to determine whether the electrical test bench can work normally and diagnose the device and/or the connection problem through visual presentation of the test result, the fault result information, the simulation result information, the communication result information, and the operation result information.

Further, the method further comprises the following steps: BOB fault test box 65; wherein the plurality of sensors are each coupled to the high performance computing platform 66; the BOB fault cartridge 65 is serially connected between the plurality of sensors and the high-performance computing platform 66;

The control device 60 is specifically configured to: transmitting fault test information including at least one sensor at the time of a fault to the high performance computing platform 66 through the BOB fault test box 65;

acquiring fault result information generated by the high-performance computing platform 66 according to fault test information including at least one sensor at the time of a fault; the fault result information reflects whether the high performance computing platform 66 can properly identify the sensor fault.

Further, the method further comprises the following steps: a testing device; the test equipment is connected to a plurality of sensors and a high performance computing platform 66, respectively;

the control device 60 is specifically configured to: communication test information is sent to the high-performance computing platform 66 through the test equipment, so that the high-performance computing platform 66 triggers the internal system-in-chip and the microcontroller to perform communication test;

acquiring to-be-transmitted SOC result information generated by the system-level chip according to the communication test information and receiving to-be-processed SOC result information transmitted by the system-level chip by the microcontroller; and

and acquiring MCU result information to be transmitted generated by the microcontroller according to the communication test information and receiving the MCU result information to be processed transmitted by the microcontroller by the system-level chip.

Further, the sensor includes a camera 63, a laser radar 64, a millimeter wave radar 61 and a combined inertial navigation 62; the camera 63 is connected with the high-performance computing platform 66 through a GMSL line, the laser radar 64 is connected with the high-performance computing platform 66 through an Ethernet, and the millimeter wave radar 61 and the combined inertial navigation 62 are connected with the high-performance computing platform 66 through a CAN line; specifically, two ends of the BOB fault test box 65 are respectively connected to the sensor and the high-performance computing platform 66 through GMSL coaxial cables, vehicle-mounted ethernet coaxial cables and a CAN bus, where the GMSL coaxial cables and the vehicle-mounted ethernet coaxial cables require custom-made coaxial signal (for example, fachkreis Automobil, abbreviated as Fakra) connectors to adapt to interfaces of the camera 63, the laser radar 64 and the high-performance computing platform 66.

The control device 60 is specifically configured to: acquisition information of the camera 63 and the laser radar 64 is acquired through the ethernet, and acquisition information of the millimeter wave radar 61 and the combined inertial navigation 62 is acquired through the CAN line to generate a test result based on the acquisition information.

The camera 63 is one of the sensors commonly used in an automatic driving system. Images and video can be captured, providing visual information. The cameras 63 can identify various road elements such as road signs, traffic signals, pedestrians, other vehicles, etc., and assist the automated driving system in understanding the traffic environment. Through image processing and computer vision algorithms, the camera 63 can realize the functions of target detection, lane recognition, obstacle detection and the like, and provides accurate perception data for the automatic driving vehicle. Lidar 64 (Light Detection and Ranging) is a sensor that uses a laser beam to measure distance, speed and direction. The lidar 64 determines the distance of surrounding objects by emitting laser beams and measuring the time they return. Such high accuracy measurements make lidar 64 very useful in mapping, obstacle avoidance and positioning. Objects surrounding the vehicle, including stationary and moving obstructions, may be detected, providing important spatial information for the autopilot system. The millimeter wave radar 61 is a radar system that performs detection using the millimeter wave band. The millimeter wave radar 61 has a higher resolution than a normal radar, can operate in severe weather conditions, and can provide more detailed information for a target around the vehicle. Millimeter wave radar 61 is commonly used in autonomous parking systems for short-range obstacle detection and autonomous driving of vehicles. The combined inertial navigation 62 system is a navigation system that incorporates sensors such as accelerometers, gyroscopes, and magnetometers. By measuring acceleration, angular velocity, and magnetic field information of the vehicle, the combined inertial navigation 62 system can achieve high accuracy vehicle positioning and attitude estimation. The positioning error possibly occurring in the environments such as urban canyons and the like of the GPS can be compensated, and the accurate navigation and positioning of the vehicle are ensured.

Further, the test equipment comprises an ethernet test device 68 and a CAN test device 67; the Ethernet testing device and the CAN testing device 67 are respectively connected with the high-performance computing platform 66, and the CAN testing device 67 is respectively connected with the millimeter wave radar 61 and the combined inertial navigation 62;

the control device 60 is specifically configured to: the communication test information is sent to the high-performance computing platform 66 through the Ethernet test device 68 and the CAN test device 67 respectively, so that the high-performance computing platform 66 triggers the internal system-in-chip and the microcontroller to carry out communication test;

the system-level chip corresponding to the Ethernet test device 68 and the CAN test device 67 respectively obtains the SOC result information to be sent generated by the system-level chip according to the communication test information and the microcontroller receives the SOC result information to be processed sent by the system-level chip; and

and respectively acquiring MCU result information to be transmitted generated by the microcontrollers corresponding to the Ethernet test device 68 and the CAN test device 67 according to the communication test information and receiving the MCU result information to be processed transmitted by the microcontrollers by the system-in-chip.

Further, a power module is included, which supplies power to the plurality of sensors, the BOB fault test box 65, the high-performance computing platform 66, the control device 60, and the test equipment, respectively. Specifically, the power supply module has two paths of 24V voltage output, one path is defined as KL30, the other path is defined as KL15, and the two paths of output can be controlled independently; the power supply line bundle of the system needs to select a proper cable according to the maximum current of the high-performance computing platform 66, the laser radar 64, the millimeter wave radar 61, the combined inertial navigation 62 and other devices, and the high-performance computing platform 66 and the sensor which are powered on can work normally.

The electronic device provided in this embodiment may perform the method of the foregoing embodiment, and its implementation principle and technical effects are similar, which is not described herein.

In the foregoing detailed description, the modules may be implemented as a processor, which may execute computer-executable instructions stored in a memory, such that the processor performs the methods described above.

Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 7, the electronic device 70 includes: at least one processor 701 and a memory 702. The electronic device 70 further comprises communication means 703. Wherein the processor 701, the memory 702 and the communication means 703 are connected by a bus 704.

In a specific implementation, at least one processor 701 executes computer-executable instructions stored in a memory 702, such that the at least one processor 701 performs the above-described method performed on the electronic device side as described above.

The specific implementation process of the processor 701 can be referred to the above method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.

In the above embodiment, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.

The memory may comprise high speed RAM memory or may further comprise non-volatile storage NVM, such as at least one disk memory.

The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or one type of bus.

The scheme provided by the embodiment of the invention is introduced aiming at the functions realized by the electronic equipment and the main control equipment. It will be appreciated that the electronic device or the master device, in order to implement the above-described functions, includes corresponding hardware structures and/or software modules that perform the respective functions. The present embodiments can be implemented in hardware or a combination of hardware and computer software in combination with the various exemplary elements and algorithm steps described in connection with the embodiments disclosed in the embodiments of the present invention. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may implement the described functionality using different approaches for each particular application, but such implementation is not to be considered as beyond the scope of the embodiments of the present invention.

The application also provides a computer readable storage medium, in which computer executable instructions are stored, which when executed by a processor, implement the above test method.

The computer readable storage medium described above may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. A readable storage medium can be any available medium that can be accessed by a general purpose or special purpose computer.

An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. In the alternative, the readable storage medium may be integral to the processor. The processor and the readable storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). The processor and the readable storage medium may reside as discrete components in an electronic device or a master device.

The present application also provides a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any one of the embodiments described above.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims

1. A test method based on an electrical test bench, the electrical test bench comprising: the system comprises a control device, a plurality of sensors and a high-performance computing platform; the method comprises:

2. The method of claim 1, wherein the controlling means sends fault test information and simulation test information to the high performance computing platform, respectively, for the high performance computing platform to perform fault test and simulation communication test, and obtains fault result information generated by the high performance computing platform according to the fault test information, and generates simulation result information according to the simulation test information, comprising:

3. The method of claim 1, wherein the controlling means respectively sends communication test information to a high performance computing platform, so that the high performance computing platform triggers an internal system-in-chip and a microcontroller to perform communication test, so as to respectively obtain communication result information corresponding to the system-in-chip and the microcontroller, and the method comprises:

4. The method of claim 3, wherein the controlling means sends fault test information and simulation test information to the high performance computing platform, respectively, for the high performance computing platform to perform fault test and simulation communication test, and obtains fault result information generated by the high performance computing platform according to the fault test information, and generates simulation result information according to the simulation test information, comprising:

5. The method according to claim 1, wherein the control device sequentially sends the trained perception algorithm model, the fusion algorithm model and the planning control algorithm model to the high-performance computing platform and triggers the deployment operation thereof, and sequentially obtains operation result information of the perception algorithm model, the fusion algorithm model and the planning control algorithm model, and the method comprises:

6. The method according to any one of claims 1 to 5, wherein the controlling means performs communication tests on the plurality of sensors, respectively, to obtain test results of the sensor communication tests, including:

7. An electrical test bench, comprising: the system comprises a control device, a plurality of sensors and a high-performance computing platform; wherein,

8. The electrical test bench of claim 7 further comprising: a BOB fault test box; wherein the plurality of sensors are each connected with the high-performance computing platform; the BOB fault test box is connected in series between the plurality of sensors and the high-performance computing platform;

the control device is specifically used for:

transmitting fault test information containing at least one sensor in fault to the high-performance computing platform through the BOB fault test box;

9. The electrical test bench of claim 7 or 8, further comprising: a testing device; the test equipment is respectively connected with the plurality of sensors and the high-performance computing platform;

the control device is specifically used for:

communication test information is sent to the high-performance computing platform through test equipment so that the high-performance computing platform triggers an internal system-in-chip and a microcontroller to carry out communication test;

10. The electrical test bench of claim 9 wherein said sensors include cameras, lidars, millimeter wave radars and combined inertial navigation; the camera is connected with the high-performance computing platform through a GMSL (global system for mobile communications) line, the laser radar is connected with the high-performance computing platform through an Ethernet, and the millimeter wave radar and the combined inertial navigation are connected with the high-performance computing platform through a CAN (controller area network) line;

The control device is specifically used for:

acquiring acquisition information of the camera and the laser radar through the Ethernet, and acquiring acquisition information of the millimeter wave radar and the combined inertial navigation through a CAN line, so as to generate the test result based on the acquisition information.

11. The electrical test bench of claim 10 wherein the test equipment comprises an ethernet test device and a CAN test device; the Ethernet testing device and the CAN testing device are respectively connected with the high-performance computing platform, and the CAN testing device is respectively connected with the millimeter wave radar and the combined inertial navigation;

the control device is specifically used for:

12. The electrical test bench of any of claim 9 further comprising a power module that powers a plurality of said sensors, BOB fault cartridges, high-performance computing platforms, control devices, and test equipment, respectively.

13. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;

the memory stores computer-executable instructions;

the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 6.

14. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 6.