KR102682475B1 - Self-driving car driving ability evaluation system based on road traffic laws using a test track - Google Patents

Abstract

An autonomous vehicle driving ability evaluation system based on road traffic laws using a test track will be launched. The self-driving car driving ability evaluation system based on road traffic laws using a test track that was launched is a self-driving car driving ability evaluation system based on road traffic laws using a test track to verify the safety and smooth communication of road users before evaluating autonomous vehicles on actual roads. A test track that transmits and extracts evaluation results from a virtual environment-based evaluation system, extracts evaluation grades and driving certification sections from the test track evaluation operation system, and generates evaluation items and scenario data based on road traffic laws that must be performed in the driving section. Evaluation environment creation department; In order to apply virtual environment-linked MR technology within the track, map-based road information is generated, traffic facility information and moving object data that must be recognized by various sensors possessed by self-driving cars are generated to create a virtual environment-linked evaluation scenario, and the above evaluation is performed. A law-based virtual environment evaluation scenario generation unit that transmits scenarios to autonomous vehicle ADAS and virtual environment simulations; It is characterized by including a test track driving evaluation unit that generates trajectory analysis and evaluation data through track driving data and simulation driving data of the vehicle driving on the track.

Description

Self-driving car driving ability evaluation system based on road traffic laws using a test track}

The present invention is a self-driving car driving ability evaluation system, and more specifically, a test track using MR technology that links with a virtual environment to evaluate the road traffic law-based self-driving car driving ability on a test track. It is about the driving ability evaluation system.

Recently, as the automobile industry and various sensing technologies have advanced and communication infrastructure has expanded, interest in and research on self-driving vehicles that autonomously drive to their destination without driver intervention have been actively conducted.

Autonomous vehicles (autonomous vehicles) use various cameras, sensors, and high-precision maps to recognize, judge, and act on surrounding vehicles, pedestrians, and objects, and control the vehicle without driver intervention to autonomously drive to a set destination. It means a vehicle that can.

If the safety of these self-driving vehicles is not secured, it can lead to a major casualty accident, so it is essential to evaluate and test how quickly and accurately they can recognize and respond to various unexpected situations and events.

Currently, in order to measure the functions and performance of self-driving cars, domestic and foreign self-driving-related manufacturers and government agencies have built test tracks to perform various evaluations and are conducting evaluations in environments similar to actual road environments within limited areas.

Meanwhile, to ensure the safety and reliability of self-driving cars, autonomous driving-related companies such as manufacturers and research institutes conduct evaluation and verification using a virtual environment in advance and then conduct track and real-road tests.

Through a virtual environment-based autonomous vehicle evaluation system, various evaluation environments are created and evaluated within a limited time by performing integrated evaluation of the vehicle from autonomous driving software, but it does not reflect the dynamics model of the actual vehicle and does not reflect road surface friction or There is a lack of consistency with the road environment.

In order to evaluate driving functions and performance on various tracks, tracks are constructed and evaluated, but before evaluating autonomous vehicles in the actual road environment, there is a track that reflects the evaluation items and geometry that measures interaction with road users. need.

In addition, in order to apply various evaluation items on the constructed test track, MR (Mixed Reality) technology is used to create and evaluate various road environments and moving objects by linking the precise maps and sensor information used in autonomous vehicles with the virtual environment. A system is needed.

Registered Patent No. 10-2541430 Registered Patent No. 10-2528362

The present invention was created in response to development needs and to improve the problems of the conventional problems described above. It utilizes a test track using MR technology that links with a virtual environment to evaluate the driving ability of autonomous vehicles based on road traffic laws on a test track. The purpose is to provide an autonomous vehicle driving ability evaluation system based on road traffic laws.

However, the purpose of the present invention is not limited to this, and of course, purposes and effects that can be understood from the means of solving the problem or embodiments are also included even if not explicitly mentioned.

The road traffic law-based autonomous vehicle driving ability evaluation system using a test track of the present invention to achieve the above-mentioned purpose is based on the road traffic law using a test track to verify the safety and smooth communication of road users before driving an autonomous vehicle on a real road. In the self-driving car driving ability evaluation system, the evaluation results are extracted from the virtual environment-based evaluation system, the evaluation grade and driving certification section are extracted from the test track evaluation operation system, and the road traffic law-based evaluation items that must be performed in the driving section are included. A test track evaluation environment generation unit that generates scenario data; In order to apply virtual environment-linked MR technology within the track, map-based road information is generated, traffic facility information and moving object data that must be recognized by various sensors possessed by self-driving cars are generated to create a virtual environment-linked evaluation scenario, and the above evaluation is performed. A law-based virtual environment evaluation scenario generation unit that transmits scenarios to autonomous vehicle ADAS and virtual environment simulations; It is characterized by including a test track driving evaluation unit that generates trajectory analysis and evaluation data through track driving data and simulation driving data of the vehicle driving on the track.

The test track evaluation environment creation unit extracts the road traffic law evaluation results evaluated in the virtual environment, extracts the evaluation grade and driving certification section applied to the test track evaluation operation system by the user, and provides law-based road structure evaluation items and It can be configured to select evaluation items for each driving section within the track from the traffic safety facility and mobile vehicle operation database, and transmit data for creating a virtual environment-linked evaluation scenario to the law-based virtual environment evaluation scenario generation unit.

The law-based virtual environment evaluation scenario generation unit sets the driving difficulty level based on the data identified in the test track evaluation environment generation unit, and generates road information in the openDrive format presented by ASAM and a precision map including dynamic information, Generates traffic facility information recognized by driving sensors including vision, lidar, radar, and GPS possessed by self-driving cars, generates moving object data reflecting emergency situation data and user safety evaluation item data, and generates 6-layer ASAM openSCENARIO-based It can be configured to create a virtual environment evaluation scenario with a structure and transmit it to the autonomous vehicle ADAS and virtual environment simulation.

The test track driving evaluation unit analyzes the driving trajectory through the track driving information collected through the track operating system and the simulation driving information collected through virtual environment simulation when the autonomous vehicle drives on the track, and the detection line installed in the track operating system Extract detection information within the test track through data, extract video information collected from CCTV installed in the track operation system and camera information attached to the vehicle, and evaluate including pedestrians and adjacent vehicles among the data performed in the virtual environment simulation. It can be configured to extract moving object information that affects, generate performance evaluation results for pre-selected evaluation items based on the extracted information data, and transmit them to the test track evaluation operating system.

According to the above, the present invention enables self-driving technology and step-by-step evaluation by linking limited evaluation items evaluated on existing test tracks to a virtual environment and evaluating them by reflecting various static/dynamic variables, thereby increasing the reliability of autonomous driving evaluation. There is an effect that can be improved.

In addition, by measuring the functions and performance of autonomous vehicles as well as evaluating items based on international traffic rules and road traffic laws for interaction with other vehicles and safety, an environment can be adapted to the actual road environment during subsequent actual road evaluations. can contribute to building.

In addition, to ensure consistency and reliability with future virtual environments and real road evaluation systems, various test data can be provided in a safe environment without contact with other vehicles on a track similar to the actual road environment.

In addition, the various and beneficial advantages and effects of the present invention are not limited to the above-described content, and may be more easily understood in the process of explaining specific embodiments of the present invention.

1 is a block diagram of a road traffic law-based autonomous vehicle driving ability evaluation system utilizing a test track according to an embodiment of the present invention;
Figure 2 is an overall flowchart showing the evaluation of autonomous vehicle driving ability by an autonomous vehicle driving ability evaluation system based on road traffic laws using a test track according to an embodiment of the present invention;
Figures 3 to 5 are partial flow diagrams individually illustrating the detailed methods of each component in the overall flow diagram of Figure 2.

The above objects, other objects, features and advantages of the present invention will be easily understood through the following preferred embodiments related to the attached drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms. Rather, the embodiments introduced herein are provided so that the disclosed content will be thorough and complete and so that the spirit of the present invention can be sufficiently conveyed to those skilled in the art.

In this specification, when an element is referred to as being on another element, it means that it may be formed directly on the other element or that a third element may be interposed between them. Additionally, in the drawings, the thickness of components is exaggerated for effective explanation of technical content.

The terms used in this specification are for describing embodiments and are not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, 'comprises' and/or 'comprising' does not exclude the presence or addition of one or more other elements.

In describing specific embodiments below, various specific details have been written to explain the invention in more detail and to aid understanding. However, a reader skilled in the art to understand the present invention will recognize that it can be used without these specific details. In some cases, it is mentioned in advance that when describing the invention, parts that are commonly known but are not significantly related to the invention are not described in order to prevent confusion without any reason in explaining the invention.

Hereinafter, with reference to the attached drawings, a road traffic law-based autonomous vehicle driving ability evaluation system and driving ability evaluation method using a test track according to an embodiment of the present invention will be described.

The autonomous vehicle driving ability evaluation system based on road traffic laws using a test track according to an embodiment of the present invention includes a test track evaluation environment generation unit 100, a law-based virtual environment evaluation scenario generation unit 200, and a test track driving evaluation unit. It is configured to include 300.

The test track evaluation environment creation unit 100 collects the evaluation results performed in the preliminary virtual environment-based evaluation system and the authentication information of the self-driving car to be evaluated through the test track evaluation operation system, and performs a virtual environment linkage evaluation based on this. It is configured to generate scenario basic data.

In other words, the test track evaluation environment creation unit 100 extracts the evaluation results from the virtual environment-based evaluation system, extracts the evaluation grade and driving certification section from the test track evaluation operation system, and performs road traffic law-based evaluation that must be performed in the driving section. It is configured to generate basic data to create evaluation scenarios linked to items and virtual environments.

Specifically, referring to FIGS. 1 to 3, the test track evaluation environment creation unit 100 extracts the road traffic law evaluation results evaluated in the virtual environment (S110) and evaluates the evaluation requested by the user through the test track evaluation operating system. Extract the grade and driving certification section (S120), select evaluation items for each driving section within the track from the law-based road structure evaluation items, traffic safety facilities, and mobile vehicle operation database (S130), and based on this, a virtual environment linked evaluation scenario. It is configured to generate basic data for creation (S140) and transmit it to the law-based virtual environment evaluation scenario generation unit 200.

The test track evaluation environment creation unit 100 may include a database including an evaluation item DB for each road structure, a traffic safety facility DB, and a mobile vehicle operation DB.

The law-based virtual environment evaluation scenario generation unit 200 sets the driving difficulty based on virtual environment evaluation performance data in order to make the most of the physically created structure and provides various terrain information and sensors to perform an evaluation based on road traffic laws. It is configured to create a virtual environment evaluation scenario by generating injection data for information.

The law-based virtual environment evaluation scenario generation unit 200 generates map-based road information to apply virtual environment-linked MR technology within the track and generates traffic facility information and moving object data that must be recognized by various sensors possessed by the autonomous vehicle. Create a virtual environment linkage evaluation scenario.

Specifically, referring to FIGS. 1, 2, and 4, the law-based virtual environment evaluation scenario generation unit 200 sets the driving difficulty level based on the data identified by the test track evaluation environment generation unit 100 (S210) ), generate road information on a precision map including the openDrive format and dynamic information presented by ASAM (S220), and generate traffic facility information recognized by various sensors such as vision, lidar, radar, and GPS possessed by autonomous vehicles ( S230), generate moving object data reflecting emergency situation data and user safety evaluation item data (S240), create a virtual environment evaluation scenario with a 6-layer structure based on ASAM openSCENARIO (S250), and generate road information and map information , It is configured to transmit traffic facility information, moving object data, and virtual environment evaluation scenarios to autonomous vehicle ADAS (Advanced Driver Assistance System) and virtual environment simulation.

The law-based virtual environment evaluation scenario generation unit 200 may include a database including an evaluation item DB for each road structure, a traffic safety facility evaluation item DB, an unexpected situation evaluation item DB, and a user safety evaluation item DB.

Meanwhile, the autonomous vehicle ADAS communicates with the track operating system, and the track operating system can collect track driving information from the autonomous vehicle ADAS when the autonomous vehicle drives on the track, and the collected track driving information is collected by the test track driving evaluation unit ( 300).

In addition, the virtual environment simulation is simulated based on the received virtual environment evaluation scenario, and the simulation driving information collected through the simulation can be provided to the test track driving evaluation unit 300.

The test track driving evaluation unit 300 determines the driving trajectory based on simulation data performed in a virtual environment simulation and various track driving information such as location information, detection information, and speed information collected from the on-track operating system while driving on the test track. It is configured to analyze and generate evaluation result data.

Specifically, referring to FIGS. 1, 2, and 5, the test track driving evaluation unit 300

The test track driving evaluation unit 300 analyzes the driving trajectory through information and simulation results collected through the track operating system when the autonomous vehicle drives on the track (S310), and tests using detection line data installed in the track operating system. Extract detection information within the track (S320), extract video information collected from CCTV installed in the track operating system and camera information attached to the vehicle (S330), and include pedestrians and adjacent vehicles among the data performed in the virtual environment simulation. Extracts moving object information that affects the evaluation (S340), generates performance evaluation results for pre-selected evaluation items based on the extracted information data (S350), and operates a test track evaluation using the generated performance evaluation results. It is configured to transmit to the system.

Analysis of the driving trajectory in the test track driving evaluation unit 300 collects track driving information through a track operation system when an autonomous vehicle drives on a track, collects simulation driving information through virtual environment simulation, and collects track driving information from the collected track. It may consist of analyzing the driving trajectory by comparing and determining whether the track driving information and the simulation driving information match based on the driving information and the collected simulation driving information. This is to determine whether driving is normal and analyze the driving trajectory by matching the track driving information from the actual track and the virtual simulation driving information.

The test track driving evaluation unit 300 may include a database including a track stop line/lane detection DB, CCTV vision data DB, virtual environment simulation DB, and moving object sensor DB.

In this way, the present invention generates test track driving evaluation results by linking the limited evaluation items evaluated on the existing test track with the virtual environment, so the accuracy of the test track driving evaluation is high, the evaluation reliability can be increased, and dynamic/static variables can be adjusted. Through the reflected evaluation, autonomous driving technology and step-by-step evaluation can be possible.

Although the present invention has been shown and described in connection with preferred embodiments for illustrating the principles of the present invention, the present invention is not limited to the configuration and operation as shown and described. Rather, those skilled in the art will be able to understand that many changes and modifications can be made to the present invention without departing from the spirit and scope of the appended claims. Accordingly, all such appropriate changes, modifications and equivalents shall be considered to fall within the scope of the present invention.

100...Test track evaluation environment creation department
200...Law-based virtual environment evaluation scenario generation department
300...Test track driving evaluation department

Claims (4)

In an autonomous vehicle driving ability evaluation system based on road traffic laws using a test track to verify the safety and smooth communication of road users before evaluating autonomous vehicles on actual roads,
A test track evaluation environment creation unit that extracts evaluation results from a virtual environment-based evaluation system, extracts evaluation grades and driving certification sections from the test track evaluation operation system, and generates evaluation items and scenario data based on road traffic laws that must be performed in the driving section. ;
In order to apply virtual environment-linked MR technology within the track, map-based road information is generated, traffic facility information and moving object data that must be recognized by various sensors possessed by self-driving cars are generated to create a virtual environment-linked evaluation scenario, and the above evaluation is performed. A law-based virtual environment evaluation scenario generation unit that transmits scenarios to autonomous vehicle ADAS and virtual environment simulations;
It includes a test track driving evaluation unit that generates trajectory analysis and evaluation data through track driving data and simulation driving data of the driving vehicle on the track,
The test track evaluation environment creation unit,
Extract road traffic law evaluation results evaluated in a virtual environment,
Extracts the evaluation grade and driving certification section applied to the test track evaluation operation system by the user,
Select evaluation items for each driving section within the track from law-based road structure evaluation items, traffic safety facilities, and mobile vehicle operation database,
Data for creating a virtual environment-linked evaluation scenario is transmitted to the law-based virtual environment evaluation scenario generation unit,
The law-based virtual environment evaluation scenario generation unit,
Setting the driving difficulty level based on the data identified in the test track evaluation environment creation unit,
Generates precision map road information including openDrive format and dynamic information presented by ASAM,
Generates traffic facility information recognized by driving sensors including vision, lidar, radar, and GPS possessed by self-driving cars,
Generate moving object data reflecting emergency situation data and user safety evaluation item data,
ASAM openSCENARIO-based virtual environment evaluation scenario with a 6-layer structure is created and transmitted to autonomous vehicle ADAS and virtual environment simulation.
The test track driving evaluation unit,
When an autonomous vehicle drives on a track, the driving trajectory is analyzed through track driving information collected through the track operation system and simulation driving information collected through virtual environment simulation.
Detection information within the test track is extracted through detection line data installed in the track operating system,
Extract video information collected from CCTV installed in the track operating system and camera information attached to the vehicle,
From the data performed in the virtual environment simulation, information on moving objects that affect the evaluation, including pedestrians and adjacent vehicles, is extracted,
A road traffic law-based autonomous vehicle driving ability evaluation system utilizing a test track, characterized in that performance evaluation results for pre-selected evaluation items are generated based on the extracted information data and transmitted to the test track evaluation operation system.
delete delete delete

Images