Road test method for verifying reliability of self-driving function of intelligent networked automobile

Abstract

The invention discloses a road test method for verifying reliability of a self-driving function of an intelligent networked automobile. The road test method comprises the following steps: S1, arranging an automatic driving test road site with unexpected events, weather factors and capability guidance; s2, a data acquisition system is installed at a vehicle automatic driving controller, and an automatic recording and judging system is installed on an automatic driving test road site; s3, on the automatic driving test road, the automatic driving automobile product is controlled to carry out a function reliability test, and automatic driving of each test scene is completed at a preset highest vehicle speed; and S4, when the self-driving automobile product completes driving in the test scene, analyzing driving data and separation data recorded in the test process of the self-driving automobile product through an analysis system, and carrying out reliability detection and analysis on conditions of sensing deviation, insufficient design decision planning and hardware fault of the self-driving automobile product.

Description

Technical Field

[0001] The present invention and the field of autonomous driving vehicle road testing specifically relate to a road testing method for verifying the reliability of the self-driving function of an intelligent connected vehicle. Background Art

[0002] The closed test field test of autonomous driving technology for intelligent connected vehicles is a rehearsal before autonomous driving vehicles enter open road testing, which mainly includes stability testing, adaptability testing of autonomous driving road testing, and testing subject management capability testing. An organized and targeted testing method is used in the closed test field to verify autonomous driving technology and ensure the safe advancement of the autonomous driving industry. We continue to be committed to building a multi-dimensional, full-scenario testing, evaluation and service capability system. From scenario-based testing to testing based on natural driving environments, by setting up a continuous, uninterrupted, and challenging natural driving environment based on a real traffic environment during the test, we can not only test the comprehensive performance of autonomous driving more effectively, but also effectively achieve accelerated testing and improve test efficiency.

[0003] In the context of the transition from closed road testing to large-scale open road testing of intelligent connected vehicles, the number and types of scenarios encountered by test vehicles on open roads are increasing. Among them, responding to high-risk or accident scenarios caused by system failures, policy defects, and exceeding the design operating domain is the key to open road testing. Reproduction testing of such scenarios is carried out in closed test sites, namely key scenario restoration testing. Closed test sites reproduce key scenarios based on the traffic environment, participants and their trajectory information of key scenarios, using safe and controllable road environments and simulated traffic participant facilities to help test subjects further verify autonomous driving technology or solve product functional defects; At present, the most widely used product testing methods are simulation testing and closed field testing. The specific method of simulation testing is: the test is carried out in a simulated scene in the laboratory, and the autonomous driving car controller simulates the working process of the product in the simulated scene to find the defects of the product in various scenes, but the disadvantage of this method is that the simulated data is purely virtual and cannot truly reflect the various situations that may be encountered in real driving. Therefore, the existing simulation test method cannot simulate the various situations in the actual work of the product, and thus cannot comprehensively evaluate the defects of the product. The specific method of closed field testing is: the autonomous driving car is tested on a closed road, and it is difficult to find the defects of the product in various real scenes, but the disadvantage of this method is that the results can only be judged by the vehicle's response to the scene, and the scene is limited to various functional scenes, lacking scenes such as unexpected events and weather factors. Therefore, it is difficult to find the product in various special scenes and hidden defects in the existing closed field test, so a road test method for verifying the reliability of the self-driving function of intelligent networked vehicles is provided. Summary of the invention

[0004] The purpose of the present invention is to provide a road testing method for verifying the reliability of the self-driving function of an intelligent connected vehicle in view of the defects of the prior art, so as to solve the problems raised by the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle, the specific steps are as follows: Step S1: Arrange unexpected events, weather factors, and capability-oriented autonomous driving test road sites; Step S2: installing a data acquisition system at the vehicle automatic driving controller, and installing an automatic recording and determination system on the automatic driving test road site; Step S3: On the autonomous driving test road, control the autonomous driving vehicle product to conduct a functional reliability test, and complete the autonomous driving of each test scenario at a preset maximum vehicle speed; Step S4: When the autonomous driving vehicle product completes the driving of the test scenario, the driving data and disengagement data recorded by the autonomous driving vehicle product during the test are analyzed through the analysis system, and reliability detection and analysis are performed on the autonomous driving vehicle product's perception bias, insufficient design decision planning, and hardware failure conditions.

[0006] As a preferred technical solution of the present invention, the reliability detection in step S4 further includes the following steps: Step S41: During the reliability test of the autonomous driving vehicle product, the vehicle data information of each test scene is collected in real time through the automated recording and judgment system, and the judgment and control information of the autonomous driving vehicle product on the scene is collected in real time through the data collection system; Step S42: Analyze and compare various parameter information of the autonomous driving vehicle product in each scenario through the analysis system to obtain the situation during the reliability test; Step S421: When the position and speed value deviation of a certain scene is greater than a preset value, it is determined that the reliability of the autonomous driving vehicle product does not meet the standard and does not meet the requirements; Step S422: When the position and speed values ​​of a certain scene meet the preset values, check the judgment and control information of the scene by the autonomous driving vehicle product. When the recognition and control deviation of a certain scene is greater than the preset value, it does not meet the requirements; Step S423: While determining whether the reliability of the autonomous driving vehicle product meets the design requirements, the preset category information of the driving scenario is stored in real time.

[0007] As a preferred technical solution of the present invention, the preset category information of the driving scene includes data information of accidents and weather factors.

[0008] As a preferred technical solution of the present invention, the data acquisition system in step S2 includes a data acquisition module, a data transmission module and a data storage module, and the data acquisition module is a data collector.

[0009] As a preferred technical solution of the present invention, the automatic record determination system includes an information acquisition module, an information transmission module and a data storage module.

[0010] As a preferred technical solution of the present invention, the analysis system includes a data acquisition module, a data analysis module, a data comparison module, a data judgment module and a data upload module.

[0011] As a preferred technical solution of the present invention, the data acquisition system and the automatic record determination system are both connected to the analysis system, and the analysis system is connected to the server via the Internet.

[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention can solve the problem that the simulation test in the prior art cannot provide the problem that the sensor receiving signal is affected by environmental factors such as vibration, and the accidental passing cannot be discovered, and comprehensively and reliably verify the reliability of the autonomous driving car under various (accidental events, weather) factors, thereby improving the quality of the test product.

[0013] (1) The present invention establishes a road test method for verifying the reliability of the self-driving function of an intelligent connected vehicle, thereby forming an autonomous driving vehicle testing process oriented towards unexpected events, weather factors, and capabilities, thereby improving the reliability of autonomous driving vehicles under various external factors.

[0014] (2) The present invention establishes a road test method for verifying the reliability of the self-driving function of an intelligent connected vehicle, thereby forming a multi-dimensional reliability evaluation of the self-driving function of an intelligent connected vehicle and improving the reliability determination requirements of autonomous driving vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a module schematic diagram of the autonomous driving vehicle product data acquisition system of the present invention; Figure 3 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.

[0017] Example: See Figure 1-3 The present invention provides a technical solution: a road test method for verifying the reliability of the self-driving function of an intelligent network-connected vehicle, and the specific steps are as follows: Step S1: Arrange unexpected events, weather factors, and capability-oriented autonomous driving test road sites; Step S2: installing a data acquisition system at the vehicle automatic driving controller, and installing an automatic recording and determination system on the automatic driving test road site; Step S41: During the reliability test of the autonomous driving vehicle product, the vehicle data information of each test scene is collected in real time through the automated recording and judgment system, and the judgment and control information of the autonomous driving vehicle product on the scene is collected in real time through the data collection system; Step S42: Analyze and compare various parameter information of the autonomous driving vehicle product in each scenario through the analysis system to obtain the situation during the reliability test; Step S421: When the position and speed value deviation of a certain scene is greater than a preset value, it is determined that the reliability of the autonomous driving vehicle product does not meet the standard and does not meet the requirements; Step S422: When the position and speed values ​​of a certain scene meet the preset values, check the judgment and control information of the scene by the autonomous driving vehicle product. When the recognition and control deviation of a certain scene is greater than the preset value, it does not meet the requirements; Step S423: while determining whether the reliability of the autonomous driving vehicle product meets the design requirements, storing preset category information of the driving scene in real time; Step S3: On the autonomous driving test road, control the autonomous driving vehicle product to conduct a functional reliability test, and complete the autonomous driving of each test scenario at a preset maximum vehicle speed; Step S4: When the autonomous driving vehicle product completes the driving of the test scenario, the driving data and disengagement data recorded by the autonomous driving vehicle product during the test are analyzed through the analysis system, and reliability detection and analysis are performed on the autonomous driving vehicle product's perception bias, insufficient design decision planning, and hardware failure conditions.

[0018] The preset category information of driving scenarios includes data information of unexpected events and weather factors.

[0019] The data acquisition system in step S2 includes a data acquisition module (used to collect various test data on the autonomous driving vehicle), a data transmission module (uploading the collected data to the server via wireless transmission) and a data storage module (used to classify and store the data uploaded to the server). The data acquisition module is a data collector.

[0020] The automated recording and determination system includes an information collection module (used to collect data detected by equipment on the test road site), an information transmission module (transmitting the collected data to the server) and a data storage module (storing the uploaded data).

[0021] The analysis system includes a data acquisition module (obtaining the detected data through the server), a data analysis module (analyzing the detected data), a data comparison module (analyzing and comparing the acquired data), a data judgment module (judging the analyzed data) and a data upload module (uploading the judgment results to the client).

[0022] The data acquisition system and the automatic recording and determination system are both connected to the analysis system, and the analysis system is connected to the server via the Internet.

[0023] Working principle: A road test method to verify the reliability of the self-driving function of an intelligent connected vehicle. The specific steps are as follows: Step S1: Arrange unexpected events, weather factors, and capability-oriented autonomous driving test road sites; Step S2: installing a data acquisition system at the vehicle automatic driving controller, and installing an automatic recording and determination system on the automatic driving test road site; Step S41: During the reliability test of the autonomous driving vehicle product, the vehicle data information of each test scene is collected in real time through the automated recording and judgment system, and the judgment and control information of the autonomous driving vehicle product on the scene is collected in real time through the data collection system; Step S42: Analyze and compare various parameter information of the autonomous driving vehicle product in each scenario through the analysis system to obtain the situation during the reliability test; Step S421: When the position and speed value deviation of a certain scene is greater than a preset value, it is determined that the reliability of the autonomous driving vehicle product does not meet the standard and does not meet the requirements; Step S422: When the position and speed values ​​of a certain scene meet the preset values, check the judgment and control information of the scene by the autonomous driving vehicle product. When the recognition and control deviation of a certain scene is greater than the preset value, it does not meet the requirements; Step S423: while determining whether the reliability of the autonomous driving vehicle product meets the design requirements, storing preset category information of the driving scene in real time; Step S3: On the autonomous driving test road, control the autonomous driving vehicle product to conduct a functional reliability test, and complete the autonomous driving of each test scenario at a preset maximum vehicle speed; Step S4: When the autonomous driving vehicle product completes the driving of the test scenario, the driving data and disengagement data recorded by the autonomous driving vehicle product during the test are analyzed through the analysis system, and reliability detection and analysis are performed on the autonomous driving vehicle product's perception bias, insufficient design decision planning, and hardware failure conditions.

[0024] The above embodiments only express the implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

Claims

1. A road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle, characterized in that: The specific steps are as follows: Step S1: Arrange unexpected events, weather factors, and capability-oriented autonomous driving test road sites; Step S2: installing a data acquisition system at the vehicle automatic driving controller, and installing an automatic recording and determination system on the automatic driving test road site; Step S3: On the autonomous driving test road, control the autonomous driving vehicle product to conduct a functional reliability test, and complete the autonomous driving of each test scenario at a preset maximum vehicle speed; Step S4: When the autonomous driving vehicle product completes the driving of the test scenario, the driving data and disengagement data recorded by the autonomous driving vehicle product during the test are analyzed through the analysis system, and reliability detection and analysis are performed on the autonomous driving vehicle product's perception bias, insufficient design decision planning, and hardware failure conditions.

2. The road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle according to claim 1, characterized in that: The reliability test in step S4 further includes the following steps: Step S41: During the reliability test of the autonomous driving vehicle product, the vehicle data information of each test scene is collected in real time through the automated recording and judgment system, and the judgment and control information of the autonomous driving vehicle product on the scene is collected in real time through the data collection system; Step S42: Analyze and compare various parameter information of the autonomous driving vehicle product in each scenario through the analysis system to obtain the situation during the reliability test; Step S421: When the position and speed value deviation of a certain scene is greater than a preset value, it is determined that the reliability of the autonomous driving vehicle product does not meet the standard and does not meet the requirements; Step S422: When the position and speed values ​​of a certain scene meet the preset values, check the judgment and control information of the scene by the autonomous driving vehicle product. When the recognition and control deviation of a certain scene is greater than the preset value, it does not meet the requirements; Step S423: While determining whether the reliability of the autonomous driving vehicle product meets the design requirements, the preset category information of the driving scenario is stored in real time.

3. The road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle according to claim 2, characterized in that: The preset category information of the driving scene includes data information of accidents and weather factors.

4. The road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle according to claim 1, characterized in that: The data acquisition system in step S2 includes a data acquisition module, a data transmission module and a data storage module, and the data acquisition module is a data collector.

5. The road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle according to claim 4, characterized in that: The automatic record determination system comprises an information acquisition module, an information transmission module and a data storage module.

6. The road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle according to claim 5, characterized in that: The analysis system includes a data acquisition module, a data analysis module, a data comparison module, a data judgment module and a data upload module.

7. The road test method for verifying the reliability of the self-driving function of an intelligent networked vehicle according to claim 6, characterized in that: The data acquisition system and the automatic recording and determination system are both connected to the analysis system, and the analysis system is connected to the server via the Internet.

Images