KR102324978B1 - VR video development method for enhancing reliability for and evaluation system for autonomous driving therewith - Google Patents

Abstract

The present invention develops a VR image that can provide various unexpected situations that may occur on the road, and at the same time uses these VR images to virtually generate various simulations, events, and unexpected situations to respond to the autonomous vehicle response. A method for developing a VR image for self-driving evaluation that can maximize the safe driving ability of an autonomous driving vehicle by calculating the evaluation score (grade) for the autonomous driving vehicle and increase the reliability and safety of the evaluation of the safe driving ability of the autonomous driving vehicle, and autonomous driving using the same It is about a safe driving ability evaluation system.

Description

A VR image development method for autonomous driving evaluation with increased reliability and an autonomous driving safe driving ability evaluation system using the same

The present invention relates to a VR image development method for autonomous driving evaluation and an autonomous driving safe driving ability evaluation system using the same. Maximizing the safe driving ability of autonomous vehicles and safe driving of autonomous vehicles at the same time by calculating evaluation scores (grades) for the responses of autonomous vehicles by virtually generating various simulations, events, and unexpected situations using It relates to a VR image development method for autonomous driving evaluation that can increase the reliability and safety of ability evaluation, and an autonomous driving safe driving ability evaluation system using the same.

Recently, as the automobile industry and various sensing technologies are advanced and communication infrastructure is expanded, interest in and research on autonomous vehicles that autonomously drive to a destination without a driver's operation are being actively conducted.

An autonomous vehicle (autonomous vehicle) uses various cameras, sensors, and high-precision maps to recognize, judge, and act on surrounding vehicles, pedestrians, and objects to autonomously drive to a set destination by controlling the vehicle without a mouth. means a vehicle with

If safety is not ensured, these autonomous vehicles can lead to large-scale fatal accidents, so evaluation and testing of how quickly and accurately recognizes and responds to various unexpected situations and events is essential.

However, since there is still no evaluation system to thoroughly verify the performance of autonomous vehicles in advance, development methods for developing VR images to generate various unexpected situations, events, and simulations that may occur during actual autonomous driving; There is an urgent need to research an autonomous vehicle evaluation system to accurately evaluate and test the response of an autonomous vehicle according to the developed VR image.

1 is a view showing an autonomous vehicle safety inspection method disclosed in Korean Patent Registration No. 10-1943422 (Title of the Invention: Autonomous Vehicle Safety Inspection System and Safety Inspection Method).

The self-driving vehicle safety inspection method (hereinafter referred to as the prior art) 900 of FIG. 1 includes a test sensor value input step 330 of inputting the test sensor value through an information input device, and a test sensor value input step 330 . A first inspection step 340 of examining the operating characteristics of the autonomous vehicle operating in response to the test sensor value input in the , and a first comparison step 350 of comparing the test result and the test sensor value in the first inspection step ) and the determination result in the first comparison step 350 is performed when it is determined that the test result in the first inspection step 340 and the corresponding result that can be expected from the test sensor value are not the same within the preset range and a second action step 360 of changing a specific value of the action control table stored in the electronic control device, and a second operation characteristic of the autonomous vehicle while driving the autonomous vehicle according to the action control table modified in the action step The test result in the test step 370 and the second test step 370 is compared with the test sensor value, and the result of comparison is a corresponding result that can be expected from the test result in the second test step 370 and the value of the test sensor. A second comparison step 380 of re-performing the action step when it is determined that the values do not match within a preset range, and the determination result in the first comparison step 350 and the inspection result in the first inspection step 340 When it is determined that the corresponding result that can be expected from the and test sensor value is the same within the preset range, and the determination result in the second comparison step 380 is determined from the test result and the test sensor value in the second inspection step 370 . It is performed when it is determined that the predictable response result is the same within a preset range, and consists of a safety inspection end step 390 of activating transmission and reception of information between a plurality of sensors installed in the autonomous vehicle and the electronic control device.

The prior art 300 configured as described above uses test sensor values corresponding to sensor values detected by various sensors installed in the autonomous driving vehicle to inspect the operation of the autonomous driving vehicle, and uses the test result to examine the autonomous driving vehicle. The safety of the vehicle is checked and, if necessary, the set value of the operation control table set in the autonomous driving vehicle is modified so that the vehicle can safely operate.

In general, autonomous vehicles are configured to recognize surrounding objects and situations using cameras and sensors installed on a vehicle body, and various events and unexpected situations occur on the actual road.

However, the prior art 300 has a structural limitation in that it cannot verify the cognitive situation through image analysis obtained by photographing the camera because it is configured to verify safety simply by inputting a test sensor value.

In addition, the abrupt situations occurring on the actual road are not uniform and have different difficulties because they have a wide variety of variables.

In addition, the prior art 300 has a disadvantage in that the accuracy and reliability of the verification is lowered because the verification is performed using only the test sensor value rather than generating an actual unexpected situation virtually. For example, in the prior art 300, since the test is operated by simply inputting the test sensor value of the distance sensor, verification of whether the object detection of the actual distance sensor within the detection area is accurately performed is structurally impossible. It has limitations.

The present invention is to solve this problem, and the problem of the present invention is to develop a VR image that can provide various unexpected situations that may occur on the road, and at the same time, various simulations, events and unexpected situations using these VR images It is possible to maximize the safe driving ability of autonomous driving vehicles by calculating the evaluation score (grade) for the response of the autonomous driving vehicle by generating the This is to provide a VR image development method for self-driving evaluation and an autonomous driving safe driving ability evaluation system using the same.

In addition, another problem to be solved by the present invention is the first event information, which is an event for evaluating the response to a sudden situation of the autonomous driving vehicle, etc., the second event information and the driving mode for evaluating the response to the failure and disorder when developing a VR image. A VR image development method for self-driving evaluation that can provide various events that can occur on a real road to an autonomous vehicle by being configured to develop a VR image so that the third event information for evaluating the response to the transition matches the timeline and to provide an autonomous driving safe driving capability evaluation system using the same.

In addition, another solution to the present invention is to detect virtual measurement values for each sensor for each of the first, second, and third events along the timeline of the corresponding VR image during autonomous driving evaluation, and then send it to the ECU of the autonomous vehicle. A VR image development method that can maximize the reliability and accuracy of evaluation by calculating the evaluation score (grade) for the response of the autonomous vehicle by analyzing the motion vector input from the ECU at the same time as outputting it, and autonomous driving safe driving ability using the same It is intended to provide an evaluation system.

In the autonomous driving safe driving ability evaluation system for evaluating the safe driving ability of the autonomous driving vehicle (C) including an ECU (Electronic Control Unit), a camera, and sensors, the solution of the present invention for solving the above problems: The autonomous driving safety driving ability evaluation system receives and registers a VR image, which is an image corresponding to actual driving, and an event image of each of the first predetermined events, which are preset scenarios for evaluating the response to an unexpected situation, as an input and is registered. video register; a memory in which the VR image registered by the VR image registration unit and event values and contents of each of the first event information included in the VR image are stored; An exhibition module that is executed when a user requests a test and displays the VR image, an event information extraction module that extracts first event information according to a timeline of a VR image displayed by the exhibition module, and the event information extraction module VR image display unit including an event information parsing module for inputting the extracted first event information to the emergency response evaluation unit; An emergency response evaluation unit that analyzes the motion vector of the response driving received from the ECU and the first event of the VR image, and calculates a first evaluation score, which is an evaluation score for responding to an unexpected situation of the autonomous driving vehicle (C) Including, wherein the VR image registration unit analyzes the video problems of the general driver's license test and selects a video suitable to be built as a VR image, and then receives a VR image generated based on the selected video problem, and the VR image registration unit The operation process of the VR image registration method (S30) is a video screening step (S331) of analyzing the video problems of the previous general driver's license test and selecting a video suitable to be built as a VR video; an event application checking step (S332) of determining whether the videos selected by the video selection step (S331) can be created as events of the VR video; a virtual reality test scenario construction step (S333) of constructing a virtual reality test scenario environment as a 3D model based on the video problem determined to be applicable to the event by the event application check step (S332); an event setting step (S334) of setting event values such as a time to collision (TTC, Time To Collision) in the 3D model built by the virtual reality test scenario building step (S333); a simulation implementation step (S335) of performing a simulation on the 3D model in which the event is set by the event setting step (S334); A log data collection step (S336) of collecting log data of the autonomous vehicle (C) for each event during simulation through the simulation implementation step (S335); An evaluation test possibility analysis step (S337) of analyzing the log data collected by the log data collection step (S336) to determine whether the 3D model is suitable as an evaluation test target is included.

In addition, in the present invention, the emergency response evaluation unit includes: a first event information input module for receiving first event information from the VR image display unit; Detecting a virtual measurement value for each sensor of the autonomous driving vehicle (C) according to the input first event information by using the input first event information and preset position and identification information for each sensor of the autonomous driving vehicle (C) Virtual measurement value detection module for each sensor; an output module for outputting the virtual measurement value for each sensor detected by the virtual measurement value detection module for each sensor to the ECU of the autonomous vehicle (C); a motion vector input module for receiving a motion vector from the ECU of the autonomous vehicle (C); An analysis module that analyzes the motion vector information and the first event information input by the motion vector input module using a preset emergency response evaluation algorithm to analyze the coping driving of the autonomous vehicle C corresponding to the first event ; A first evaluation of calculating a first evaluation score that is an evaluation score for coping with a sudden situation of the autonomous driving vehicle C for a first event by using the analysis data detected by the analysis module and the preset difficulty level of the first event It is preferable to include a score calculation module.

delete

In addition, in the present invention, the autonomous driving safe driving ability evaluation system further includes an obstacle response evaluation unit, the second event information corresponding to the obstacle is matched to the timeline in the VR image, and the event information extraction module is provided to the exhibition module. extracts second event information according to the timeline of the VR image displayed by The unit includes a second event information input module for receiving second event information from the VR image display unit; Using the input second event information and preset location and identification information for each sensor of the autonomous driving vehicle (C), a failure event-value for each sensor of the autonomous driving vehicle (C) is detected according to the input second event information. a sensor-specific failure event-value detection module; a second output module for outputting the failure event-value for each sensor detected by the sensor-specific failure event-value detection module to the ECU of the autonomous vehicle (C); a second motion vector input module for receiving a motion vector from the ECU of the autonomous vehicle (C); A second analysis of coping driving of the autonomous vehicle C corresponding to the second event by analyzing the motion vector information and the second event information input by the second motion vector input module using a preset failure evaluation algorithm analysis module; A second evaluation score, which is an evaluation score for coping with an obstacle of the autonomous driving vehicle (C) for a second event, is calculated using the analysis data detected by the second analysis module and the preset difficulty level of the second event It is preferable to include an evaluation score calculation module.

In addition, in the present invention, the autonomous driving safe driving ability evaluation system further includes a driving mode change response evaluation unit, the third event information corresponding to the driving mode change is matched to the timeline in the VR image, and the event information extraction module is Extracts third event information according to the timeline of the VR image displayed by the exhibition module, and the event information parsing module inputs the third event information extracted by the event information extraction module to the driving mode change response evaluation unit and a third event information input module for receiving third event information from the VR image display unit; When third event information is input through the third event information input module, a driving mode change event-value output module that generates a driving mode change event-value indicating driving mode change and outputs it to the ECU of the autonomous vehicle (C) ; a third motion vector input module for receiving a motion vector from the ECU of the autonomous vehicle (C); To analyze the coping driving of the autonomous vehicle (C) corresponding to the third event by analyzing the motion vector information and the third event information input by the third motion vector input module using a preset driving mode conversion evaluation algorithm a third analysis module; The third evaluation score, which is the driving mode conversion evaluation score of the autonomous driving vehicle (C) for the third event, is calculated by using the analysis data detected by the third analysis module and the preset difficulty level of the third event. 3 It is preferable to further include an evaluation score calculation module.

According to the present invention having the above problems and solutions, VR images that can provide various unexpected situations that may occur on the road are developed, and at the same time, various simulations, events, and unexpected situations are generated virtually using these VR images. By calculating the evaluation score (grade) for the response of the autonomous driving vehicle, it is possible to maximize the safe driving ability of the autonomous driving vehicle, and at the same time increase the reliability and safety of the safe driving ability evaluation of the autonomous driving vehicle.

In addition, according to the present invention, when developing a VR image, the first event information, which is an event for evaluating the response to a sudden situation of the autonomous driving vehicle, the second event information for evaluating the response to the failure and disorder, and the driving mode conversion By developing a VR image so that the third event information for evaluating the coping matches the timeline, it is possible to provide the autonomous vehicle with various events that may occur on the actual road.

In addition, according to the present invention, during autonomous driving evaluation, virtual measurement values for each sensor for each of the first, second, and third events according to the timeline of the corresponding VR image are detected, and then output to the ECU of the corresponding autonomous driving vehicle and at the same time The reliability and accuracy of evaluation can be maximized by analyzing the motion vector input from the ECU and calculating the evaluation score (grade) for the self-driving vehicle's response.

In addition, according to the present invention, since it is possible to accurately evaluate by classifying the autonomous driving vehicle's coping driving, failure, and driving mode change to various unexpected situations, the safety and reliability of the autonomous driving vehicle can be significantly improved.

In addition, according to the present invention, it is possible to build a license system in consideration of both the autonomous vehicle and the driver.

In addition, according to the present invention, it is possible to construct an objective indicator through simulation tests for various environments and situations that may occur during actual road and driving.

1 is a view showing an autonomous vehicle safety inspection method disclosed in Korean Patent Registration No. 10-1943422 (Title of the Invention: Autonomous Driving Vehicle Safety Inspection System and Safety Inspection Method).
2 is a block diagram showing a parking management system according to an embodiment of the present invention.
3 is a flowchart illustrating a VR image registration method that is an operation process of the VR image registration unit of FIG. 2 .
4 is an exemplary diagram illustrating a VR image registered by FIG. 3 .
FIG. 5 is a block diagram illustrating the VR image display unit of FIG. 2 .
6 is a block diagram illustrating an emergency response evaluation unit of FIG. 2 .
FIG. 7 is a block diagram illustrating the failure coping evaluation unit of FIG. 2 .
FIG. 8 is an exemplary diagram for explaining the failure coping evaluation unit of FIG. 7 .
9 is a block diagram illustrating a driving mode change response evaluation unit of FIG. 2 .

Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.

2 is a block diagram showing a parking management system according to an embodiment of the present invention.

The autonomous driving safe driving ability evaluation system 1, which is an embodiment of the present invention, develops a VR image that provides an event for driving, failure, and driving mode change of the autonomous driving vehicle (C) that may occur on an actual road at the same time. By using these VR images, various simulations, events, and unexpected situations are generated virtually, and evaluation scores (grades) are calculated for the response of the autonomous driving vehicle, thereby maximizing the safe driving ability of the autonomous driving vehicle and autonomous driving. This is to increase the reliability and safety of the evaluation of the safe driving ability of the vehicle.

In addition, as shown in FIG. 2 , the autonomous driving safe driving capability evaluation system 1 includes a control unit 30 , a memory 31 , a data transmission/reception unit 32 , a VR image registration unit 33 , and a test request unit 34 . ), VR image display unit 35, emergency response evaluation unit 36, obstacle response evaluation unit 37, driving mode change response evaluation unit 38, final evaluation score calculation unit 39, additional service unit 40 ) is made of

The autonomous driving safe driving capability evaluation system 1 is connected to the ECU (Electronic Control Unit) of the autonomous driving vehicle C to transmit and receive data.

When receiving a request to register a VR image from a user, the controller 30 executes the VR image registration unit 33 .

In addition, the control unit 30 receives a request for autonomous driving evaluation from the user by the test request unit 34, the VR image display unit 35, the emergency response evaluation unit 36, the obstacle response evaluation unit 37, and the driving mode conversion The coping evaluation unit 38 is executed.

The memory 31 stores VR images registered by the VR image registration unit 33 . At this time, the VR image is a 3D image in which a basic image including a real road, a building, a signal system, etc. is mapped, and an event image in which preset first, second, and third event information is generated at the same time as a vehicle, pedestrian, and structure are mapped. it means.

At this time, the first event information is composed of event values and contents of each emergency for evaluating the response to the emergency situation of the autonomous driving vehicle (C), and the second event information is the response to the failure of the autonomous driving vehicle (C) It consists of the event value and contents of each obstacle for evaluating , and the third event information consists of the event value and contents of each driving mode for evaluating the response to the driving mode change. That is, the VR image displays an event image in which at least one of the first, second, and third events occurs according to the timeline.

Also, first, second, and third event information of each VR image is stored in the memory 31 .

In addition, a sensor reference table in which identification information and location information of each sensor of the autonomous vehicle C are matched is preset and stored in the memory 31 .

Also, the driving motion vector is stored in the memory 31 from the ECU (Electronic Control Unit) of the autonomous vehicle C through the data transmission/reception unit 32 .

In addition, in the memory 31, the driving motion vector received from the ECU of the autonomous driving vehicle C according to the occurrence of the first event is an input value, and an evaluation score (grade) for the driving motion vector is an output value. The evaluation algorithm is stored. That is, the sudden situation evaluation algorithm is an algorithm for detecting the evaluation score (grade) of autonomous driving by analyzing the driving motion vector according to the occurrence of the first event.

In addition, in the memory 31, the driving motion vector received from the ECU of the autonomous driving vehicle C according to the occurrence of the second event is an input value, and the evaluation score (grade) for the driving motion vector is an output value. The algorithm is stored. That is, the obstacle evaluation algorithm is an algorithm for detecting the evaluation score (grade) for the obstacle by analyzing the driving motion vector according to the occurrence of the second event.

In addition, the memory 31 has a driving motion vector transmitted from the ECU of the autonomous driving vehicle C according to the occurrence of the third event as an input value, and a preset driving mode in which an evaluation score (grade) for the driving motion vector is an output value. A conversion evaluation algorithm is stored. That is, the driving mode change evaluation algorithm is an algorithm for detecting the evaluation score (grade) for the driving mode change by analyzing the driving motion vector according to the occurrence of the third event.

The data transmission/reception unit 32 transmits/receives data to and from the ECU of the autonomous vehicle C under the control of the control unit 30 .

FIG. 3 is a flowchart illustrating a VR image registration method that is an operation process of the VR image registration unit of FIG. 2 , and FIG. 4 is an exemplary view showing the VR image registered by FIG. 3 .

The VR image registration unit 33 registers the pre-made VR image 900 according to a user's request and stores it in the memory 31 at the same time.

In this case, the VR image includes a basic image including an actual road, a building, a signal system, etc., and refers to a 3D image in which an event image, which is any one of the first, second, and third events, is synthesized according to the timeline.

That is, the VR image shows the first events, which are various unexpected situations that may occur on the actual road, the second events for the disabled that may occur during actual driving, and the third event, which is a driving mode change that may occur during actual driving, on the timeline. will occur accordingly.

Also, the VR image registration unit 33 stores the identification information of the VR image requested to be registered and the first, second, and third event information included in the corresponding VR image in the memory 31 .

At this time, the first event information is composed of event values and contents of each emergency for evaluating the response to the emergency situation of the autonomous driving vehicle (C), and the second event information is the response to the failure of the autonomous driving vehicle (C) It consists of the event value and contents of each obstacle for evaluating , and the third event information consists of the event value and contents of each driving mode for evaluating the response to the driving mode change.

Referring to FIG. 3, looking at the VR image registration method (S33), which is the operation process of the VR image registration unit, the VR image registration method (S33) analyzes the video problems of the previous general driver's license test to create a video suitable for building a VR image A video screening step (S331) of screening, an event application check step (S332) for determining whether the videos selected by the video screening step (S331) can be written as an event of a VR video (S332), and an event application check step (S332) ), the 3D constructed by the virtual reality test scenario building step (S333) and the virtual reality test scenario building step (S333) to build the virtual reality test scenario environment as a 3D model based on the video problem determined to be applicable to the event by An event setting step (S334) of setting event values such as time to collision (TTC, Time To Collision) in the model, and a simulation implementation step of performing a simulation on the 3D model in which the event is set by the event setting step (S334) (S335) ), and during simulation through the simulation implementation step (S335), the log data collected by the log data collection step (S336) of collecting the log data of the autonomous vehicle for each event, and the log data collection step (S336) It consists of an evaluation test possibility analysis step (S337) of analyzing whether the corresponding 3D model is suitable for the evaluation test target.

At this time, the VR image registration unit 33 stores the 3D model as a VR image in the memory 31 when it is determined that the 3D model is suitable for the evaluation test through the evaluation test possibility analysis step S337.

The test request unit 34 receives a request for autonomous driving evaluation according to a user's request.

In this case, when the control unit 30 receives a request for autonomous driving evaluation from the user by the test request unit 34 , the VR image display unit 35 , the emergency response evaluation unit 36 , the obstacle response evaluation unit 37 , and the driving mode changeover The coping evaluation unit 38 is executed.

FIG. 5 is a block diagram illustrating the VR image display unit of FIG. 2 .

The VR image display unit 35 of FIG. 5 is executed under the control of the controller 30 when a request for autonomous driving evaluation is received from the user through the test request unit 34 .

Also, as shown in FIG. 5 , the VR image display unit 35 includes an exhibition module 351 , an event information extraction module 353 , and an event information parsing module 355 .

The display module 351 displays the VR image registered by the VR image registration unit 33 .

The event information extraction module 353 extracts event information currently generated according to the timeline of the VR image displayed by the exhibition module 351 .

The event information parsing module 355 detects to which of the first, second, and third events the corresponding event belongs through the identification information of the event information extracted by the event information extraction module 353 .

In addition, when the type of the detected event is the first event, the event information parsing module 355 inputs event information to the emergency response evaluation unit 36 .

In addition, the event information parsing module 334 inputs the event information to the failure response evaluation unit 37 when the type of the detected event is the second event.

In addition, the event information parsing module 334 inputs the event information to the driving mode change response evaluation unit 38 when the type of the detected event is the third event.

That is, when the autonomous driving safe driving ability evaluation system 3 of the present invention is tested, the VR image is displayed by the VR image display unit 35 and the first, second, and third event information input from the VR image display unit displayed at the same time When the first, second, and third events occur using Through the analysis, it is possible to calculate the evaluation score for coping with an unexpected situation, the evaluation score for coping with the field, and the evaluation score for coping with the driving mode change.

6 is a block diagram illustrating an emergency response evaluation unit of FIG. 2 .

As shown in FIG. 6, the emergency response evaluation unit 36 includes a first event information input module 361, a virtual measurement value detection module 362 for each sensor, an output module 363, and a motion vector input module ( 364 ), an analysis module 365 , and a first evaluation score calculation module 366 .

The first event information input module 361 is executed when receiving the first event information from the VR image display unit 35 . In this case, the first event information consists of event values and contents of a scenario for evaluating response to a sudden situation, and in detail, includes identification information, event values, and contents for identifying the type of the corresponding event.

That is, when the first event occurs in the currently displayed VR image, the first event information is detected by the VR image display unit 35 and input to the first event information input module 361 .

The virtual measurement value detection module 362 for each sensor refers to the first event information input through the first event information input module 361 and the sensor reference table stored in the memory 31 , and the autonomous driving vehicle according to the first event (C) The virtual measurement value for each sensor is extracted.

In this case, the virtual measurement value is defined as a measurement value measured by each sensor of the autonomous vehicle C corresponding to the first event when the first event occurs.

The output module 363 outputs the virtual measured value for each sensor detected by the virtual measured value detection module 362 for each sensor to the ECU of the autonomous vehicle C through the data transmission/reception unit 31 .

That is, the autonomous vehicle (C) is configured to detect the occurrence of the first event through image analysis obtained by capturing a surveillance image by a provided camera, and each sensor is a virtual measurement value for each sensor input through the output module 363 . By being configured to detect the occurrence of the first event through

At this time, the ECU of the autonomous driving vehicle C outputs motion vector information corresponding to the coping driving to the autonomous driving safe driving capability evaluation system 3 when the coping driving for the first event is performed.

The motion vector input module 364 receives the motion vector transmitted from the ECU of the autonomous vehicle C through the data transmission/reception unit 32 .

The analysis module 365 analyzes the motion vector information input by the motion vector input module 364 and the first event information input through the first event information input module 361 by using a preset unexpected situation evaluation algorithm. Coping driving of the autonomous driving vehicle C corresponding to the first event is analyzed.

The first evaluation score calculation module 366 utilizes the analysis data detected by the analysis module 365 and the difficulty level of the first event to determine the autonomous driving evaluation score of the autonomous vehicle C for the first event ( first evaluation score) is calculated.

FIG. 7 is a block diagram illustrating the failure coping evaluation unit of FIG. 2 .

As shown in FIG. 7 , the failure response evaluation unit 37 includes a second event information input module 371 , a failure event for each sensor-value detection module 372 , a second output module 373 , and a second movement It consists of a vector input module 374 , a second analysis module 375 , and a second evaluation score calculation module 376 .

The second event information input module 371 receives second event information from the VR image display unit 35 . In this case, the second event information consists of event values and contents of the scenario for evaluating the response to failures and failures, and in detail, consists of identification information, event values and contents for identifying the type of the corresponding event.

That is, the second event information is input to the failure response evaluation unit 37 by the VR image display unit 35 when a failure occurs in at least one of the sensors.

The failure event-value detection module 372 for each sensor refers to the second event information input through the second event information input module 371 and the sensor reference table stored in the memory 31 for autonomous driving according to the second event. A failure event-value for each sensor of the vehicle C is detected.

In this case, the failure event-value is defined as a value that can be determined as a failure by at least one of the sensors of the autonomous vehicle C.

The second output module 373 outputs the failure event value for each sensor detected by the sensor-specific failure event-value detection module 372 to the ECU of the autonomous vehicle C through the data transmission/reception unit 31 .

At this time, when the ECU of the autonomous vehicle C receives a failure event-value for each sensor through the second output module 373 , it performs a response driving for a failure according to the input failure event-value for each sensor, and the second When the coping driving for the event is made, the motion vector information corresponding to the coping driving is output to the autonomous driving safe driving ability evaluation system 3 .

The second motion vector input module 374 receives the motion vector transmitted from the ECU of the autonomous vehicle C through the data transmission/reception unit 32 .

The second analysis module 375 uses a preset failure evaluation algorithm to determine the motion vector information input by the second motion vector input module 374 and the second event information input through the second event information input module 371 . , and the coping driving of the autonomous vehicle C corresponding to the second event is analyzed.

FIG. 8 is an exemplary diagram for explaining the failure coping evaluation unit of FIG. 7 .

As shown in FIG. 8 , the obstacle coping evaluation unit 37 classifies the second event, that is, the grade of the obstacle into a low speed driving mode 910 , a manual driving mode 920 , and an emergency stop mode 930 .

For example, the low-speed driving mode 910 means a driving mode in the event of a failure that does not significantly affect autonomous driving and is defined as a driving mode in which autonomous driving is performed while sufficiently securing safety, and the manual driving mode 920 is low-speed driving Mode 920 means a driving mode in case of a more severe failure and is defined as a driving mode in which control is transferred to a driver who has been approved in advance, and the emergency stop mode 930 means a driving mode in case of a failure that greatly affects autonomous driving. It is defined as a driving mode that notifies an emergency stop after an emergency stop in a safe zone when a driver who is unable to drive manually is in the driver's seat in a transition to manual operation mode.

That is, the second analysis module 375 of the obstacle coping evaluation unit 37 may analyze the driving mode according to the difficulty level of the second event to analyze whether an accurate driving mode according to the generated obstacle is established.

The second evaluation score calculation module 376 evaluates the failure response of the autonomous driving vehicle C for the second event by using the analysis data detected by the second analysis module 375 and the difficulty level of the second event. A score (second evaluation score) is calculated.

9 is a block diagram illustrating a driving mode change response evaluation unit of FIG. 2 .

As shown in FIG. 9 , the driving mode change response evaluation unit 38 includes a third event information input module 381 , a driving mode change event-value detection module 382 , a third output module 383 , and a second It consists of three motion vector input module 384 , a third analysis module 385 , and a third evaluation score calculation module 386 .

The third event information input module 381 receives third event information from the VR image display unit 35 . In this case, the third event information consists of an event-value and contents for informing the change of driving mode, and in detail, includes identification information for identifying the type of the corresponding event, event values, and contents.

That is, the third event information is input to the driving mode change response evaluation unit 38 by the VR image display unit 35 when it is necessary to switch from the driving mode to the manual mode or from the manual mode to the driving mode.

When the third event information is input through the third event information input module 381 , the driving mode change event-value detection module 382 detects a driving mode change event-value indicating the driving mode change.

The third output module 383 controls the data transmission/reception unit 32 so that the driving mode change event-value detected by the driving mode change event-value detection module 382 is output to the ECU.

At this time, when the ECU of the autonomous vehicle C receives a driving mode change event-value through the third output module 383 , it performs a driving mode change according to the input driving mode change event-value, and a motion vector The information is output to the autonomous driving safe driving ability evaluation system (3).

The third motion vector input module 384 receives the motion vector received from the ECU of the autonomous vehicle C through the data transmission/reception unit 32 .

The third analysis module 385 uses a preset driving mode conversion evaluation algorithm to determine the motion vector information input by the third motion vector input module 384 and the third event information input module 381 input through the third motion vector input module 381 . By analyzing the event information, the coping driving of the autonomous vehicle C corresponding to the third event is analyzed.

For example, the third analysis module 385 determines whether the driver took over the control right when switching to the manual driving mode and drove, whether the driver has prior education and license (permission), or a driver without a license, autonomously It may be configured to analyze whether the driving state is maintained or an emergency stop is performed, and to analyze whether the transfer of control right is accurately performed when switching to the autonomous driving mode.

Returning to FIG. 2 and looking at the final evaluation score calculation unit 39, the final evaluation score calculation unit 39 includes the emergency response evaluation unit 36, the obstacle response evaluation unit 37, and the driving mode change response evaluation unit 38 ) by summing and processing the evaluation scores calculated by ) to finally calculate the evaluation score of the corresponding autonomous vehicle (C).

In this case, the final evaluation score calculation unit 39 may be configured to determine pass/fail by comparing a preset critical score with the calculated final evaluation score.

The supplementary service unit 40 performs various other well-known services required for testing the autonomous vehicle C.

As such, the autonomous driving safe driving ability evaluation system 1 according to an embodiment of the present invention develops VR images that can provide various unexpected situations that may occur on the road, and at the same time uses these VR images to conduct various simulations, events and By calculating the evaluation score (grade) for the response of the autonomous vehicle to an unexpected situation, it maximizes the safe driving ability of the autonomous vehicle and at the same time improves the reliability and safety of the evaluation of the safe driving ability of the autonomous vehicle. can be raised

In addition, the autonomous driving safe driving ability evaluation system (1) of the present invention is used to evaluate the first event information, which is an event for evaluating the response to a sudden situation of the autonomous driving vehicle, when developing a VR image, and to evaluate the response to failures and obstacles. The VR image is developed so that the second event information and the third event information for evaluating the response to the driving mode change match the timeline, so that various events that may occur on the road can be provided to the autonomous vehicle. .

In addition, the autonomous driving safe driving ability evaluation system 1 of the present invention detects the virtual measurement value for each sensor for each of the first, second, and third events according to the timeline of the VR image during the autonomous driving evaluation, and then The reliability and accuracy of the evaluation can be maximized by outputting the output to the ECU of the autonomous vehicle and analyzing the motion vector input from the ECU to calculate the evaluation score (grade) for the response of the autonomous vehicle.

In addition, the autonomous driving safe driving ability evaluation system 1 of the present invention can significantly improve the safety and reliability of the autonomous driving vehicle because it can classify and accurately evaluate the autonomous driving vehicle's coping driving, failure, and driving mode conversion for various unexpected situations. be able to

In addition, the autonomous driving safe driving ability evaluation system 1 of the present invention can build a license system in consideration of both the autonomous driving vehicle and the driver.

In addition, the autonomous driving safe driving ability evaluation system 1 of the present invention can build objective indicators through simulation tests for various environments and situations that may occur during actual road and driving.

1: Self-driving safety driving ability evaluation system
30: control unit 31: memory 32: data transmitting and receiving unit
33: VR video registration section 34: test request section 35: test VR video display section
36: Emergency response evaluation unit 37: Disability coping evaluation unit
38: driving mode change response evaluation unit 39: final evaluation score calculation unit
40: additional service unit 351: exhibition module 353: event information extraction module
355: event information parsing module 361: second event information input module
362: virtual measurement value detection module for each sensor 363: output module
364: motion vector input module 365: analysis module
366: second evaluation score calculation module 371: second event information input module
372: sensor-specific failure event-value detection module 373: second output module
374: second motion vector input module 375: second analysis module
376: second evaluation score calculation module 381: third event information input module
382: driving mode change event-value detection module
383: third output module 384: third motion vector input module
385: third analysis module 386: third evaluation score calculation module

Claims (5)

In an autonomous driving safe driving ability evaluation system for evaluating the safe driving ability of an autonomous driving vehicle (C) including an ECU (Electronic Control Unit), a camera and sensors:
The autonomous driving safety driving ability evaluation system is
a VR image registration unit that receives and registers a VR image, which is an image obtained by synthesizing an event image of each of the first events, which are preset scenarios, which are preset scenarios for evaluating response to an unexpected situation, to a virtual image corresponding to actual driving;
a memory in which the VR image registered by the VR image registration unit and event values and contents of each of the first event information included in the VR image are stored;
An exhibition module that is executed when a user requests a test and displays the VR image, an event information extraction module that extracts first event information according to a timeline of a VR image displayed by the exhibition module, and the event information extraction module VR image display unit including an event information parsing module for outputting the first event information extracted by;
An emergency response evaluation unit that analyzes the motion vector of the response driving received from the ECU and the first event of the VR image, and calculates a first evaluation score, which is an evaluation score for responding to an unexpected situation of the autonomous driving vehicle (C) including,
The VR image registration unit
After analyzing the video problems of the general driver’s license test and selecting a video suitable for building a VR video, the VR video generated based on the selected video problem is registered,
The VR image registration method (S30), which is the operation process of the VR image registration unit, is
A video screening step (S331) of analyzing the video problems of the previous general driver's license test and selecting a video suitable to be built as a VR video;
an event application checking step (S332) of determining whether the videos selected by the video selection step (S331) can be created as events of the VR video;
a virtual reality test scenario construction step (S333) of building a virtual reality test scenario environment as a 3D model based on the video problem determined to be applicable to the event by the event application check step (S332);
an event setting step (S334) of setting event values such as a time to collision (TTC, Time To Collision) in the 3D model built by the virtual reality test scenario building step (S333);
a simulation implementation step (S335) of performing a simulation on the 3D model in which the event is set by the event setting step (S334);
A log data collection step (S336) of collecting log data of the autonomous vehicle (C) for each event during simulation through the simulation implementation step (S335);
Autonomous driving safety, characterized in that it analyzes the log data collected by the log data collection step (S336) and analyzes whether the 3D model is suitable for the evaluation test, comprising an evaluation test possibility analysis step (S337); Driving ability evaluation system. delete According to claim 1, wherein the emergency response evaluation unit
a first event information input module for receiving first event information from the VR image display unit;
Detecting a virtual measurement value for each sensor of the autonomous driving vehicle (C) according to the input first event information by using the input first event information and preset position and identification information for each sensor of the autonomous driving vehicle (C) Virtual measurement value detection module for each sensor;
an output module for outputting the virtual measurement value for each sensor detected by the virtual measurement value detection module for each sensor to the ECU of the autonomous vehicle (C);
a motion vector input module for receiving a motion vector from the ECU of the autonomous vehicle (C);
An analysis module that analyzes the motion vector information and the first event information input by the motion vector input module using a preset emergency response evaluation algorithm to analyze the coping driving of the autonomous vehicle C corresponding to the first event ;
A first evaluation of calculating a first evaluation score that is an evaluation score for coping with a sudden situation of the autonomous driving vehicle C for a first event by using the analysis data detected by the analysis module and the preset difficulty level of the first event Autonomous driving safe driving ability evaluation system, characterized in that it comprises a score calculation module. The method of claim 3, wherein the autonomous driving safe driving ability evaluation system further comprises an obstacle coping evaluation unit,
In the VR image, the second event information corresponding to the disability is matched to the timeline,
The event information extraction module extracts second event information according to the timeline of the VR image displayed by the exhibition module,
The event information parsing module inputs the second event information extracted by the event information extraction module to the failure response evaluation unit,
The failure response evaluation unit
a second event information input module for receiving second event information from the VR image display unit;
Using the input second event information and preset location and identification information for each sensor of the autonomous driving vehicle (C), a failure event-value for each sensor of the autonomous driving vehicle (C) is detected according to the input second event information. a sensor-specific failure event-value detection module;
a second output module for outputting the failure event-value for each sensor detected by the sensor-specific failure event-value detection module to the ECU of the autonomous vehicle (C);
a second motion vector input module for receiving a motion vector from the ECU of the autonomous vehicle (C);
A second analysis of coping driving of the autonomous vehicle C corresponding to the second event by analyzing the motion vector information and the second event information input by the second motion vector input module using a preset failure evaluation algorithm analysis module;
A second evaluation score, which is an evaluation score for coping with an obstacle of the autonomous driving vehicle (C) for a second event, is calculated using the analysis data detected by the second analysis module and the preset difficulty level of the second event Self-driving safety driving ability evaluation system, characterized in that it comprises an evaluation score calculation module. The method of claim 4, wherein the autonomous driving safe driving ability evaluation system further comprises a driving mode change response evaluation unit,
In the VR image, the third event information corresponding to the driving mode change is matched to the timeline,
The event information extraction module extracts third event information according to the timeline of the VR image displayed by the exhibition module,
The event information parsing module inputs the third event information extracted by the event information extraction module to the driving mode change response evaluation unit,
The driving mode change response evaluation unit
a third event information input module for receiving third event information from the VR video display unit;
When third event information is input through the third event information input module, a driving mode change event-value output module that generates a driving mode change event-value indicating driving mode change and outputs it to the ECU of the autonomous vehicle (C) ;
a third motion vector input module for receiving a motion vector from the ECU of the autonomous vehicle (C);
To analyze the coping driving of the autonomous vehicle (C) corresponding to the third event by analyzing the motion vector information and the third event information input by the third motion vector input module using a preset driving mode conversion evaluation algorithm a third analysis module;
The third evaluation score, which is the driving mode conversion evaluation score of the autonomous driving vehicle (C) for the third event, is calculated by using the analysis data detected by the third analysis module and the preset difficulty level of the third event. 3 Autonomous driving safe driving ability evaluation system, characterized in that it further comprises an evaluation score calculation module.

Images