Virtual reality-based driver risk perception ability evaluation system and method

Abstract

The application discloses a kind of based on virtual reality's driver risk perception ability evaluation system and method, system uses VR driving simulator and management platform construction, management platform includes VR road traffic risk driving scene library and evaluation database, the system has strong sense of immersion, small interference and the like advantages.Start evaluation, VR driving simulator selects multiple driving scenes from driving scene library to form evaluation driving scene combination, management platform receives and stores the driving person driving control and gaze position and driving scene information sent by VR driving simulator in real time, calculates the risk perception accuracy score, risk perception speed score and average travel speed of driver in each VR road traffic risk driving scene, calculates the risk perception ability score of driver in each driving scene one by one, the risk perception ability score in all driving scenes is weighted average to obtain the comprehensive risk perception ability score of driver, the method has the advantages of accurate, simple and easy to understand.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of driver safety risk management, and particularly relates to a driver risk perception ability evaluation system and method based on virtual reality. BACKGROUND

[0002] Drivers are the primary factor affecting road traffic safety, and good risk perception ability is one of the basic quality requirements for drivers to avoid road traffic accidents and achieve safe driving. Many road traffic accidents occur because drivers fail to perceive the risks existing in the traffic environment in advance and fail to take timely avoidance measures. At present, questionnaires, pictures, videos and other methods are commonly used to evaluate the risk perception ability of drivers. These evaluation methods cannot provide good immersion for drivers on the one hand, and the differences between the actual driving operation and the driving state are large on the other hand, and the accuracy is poor, thereby affecting the reliability and validity of the evaluation results of the risk perception ability of drivers. SUMMARY

[0003] Therefore, the present application provides a driver risk perception ability evaluation system and method based on virtual reality, which overcomes the defects of poor accuracy and low reliability of the evaluation results of the driver risk perception ability evaluation method in the prior art.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0005] In a first aspect, the present application provides a driver risk perception ability evaluation system based on virtual reality, comprising: a VR driving simulator and a management platform, wherein the VR driving simulator and the management platform are connected by a network to realize real-time communication;

[0006] The VR driving simulator is an evaluation platform, which is used for driver login, collection of driving manipulation information and gaze position information during simulated driving of the driver, running of a VR road traffic risk driving scene, and display of risk perception ability evaluation results.

[0007] The management platform comprises a VR road traffic risk driving scene library and an evaluation database, which are used for management of the VR road traffic risk driving scene and the evaluation data, and calculation of the risk perception ability evaluation results. The VR road traffic risk driving scene library is an electronic information database containing the VR road traffic risk driving scene, which comprises 3D models, risk degrees, risk reaction time windows and reference driving speed information of each scene.

[0008] Preferably, based on historical typical road traffic risk data, VR road traffic risk driving scenes are formed by three-dimensional modeling, and scene features in each VR road traffic risk driving scene include: traffic environment, road type, risk type, risk location, risk size, risk color, and the risk degree of each VR road traffic risk driving scene is determined according to the scene features; and the risk reaction time window and the reference driving speed of each VR road traffic risk driving scene are determined according to the evolution process of the risk in each VR road traffic risk driving scene.

[0009] In a second aspect, the embodiments of the present application provide a virtual reality-based driver risk perception ability evaluation method, which comprises:

[0010] When the driver starts the evaluation, the VR driving simulator selects k (k>1) driving scenes for evaluation from the VR road traffic risk driving scene library according to preset selection rules to form an evaluation driving scene combination;

[0011] When the driver simulates driving in the driving cabin, the management platform receives and stores the driving control information and gaze position information of the driver and the VR road traffic risk driving scene information sent by the VR driving simulator in real time;

[0012] After the selected k road traffic risk driving scenes are evaluated, the management platform calculates the risk perception accuracy score, the risk perception speed score, and the average driving speed of the driver in each VR road traffic risk driving scene according to the received and stored driving control information and gaze position information of the driver and the VR road traffic risk driving scene information;

[0013] The risk perception ability score of the driver in each driving scene is calculated one by one;

[0014] The risk perception ability scores of the driver in all driving scenes are weighted and averaged to obtain the comprehensive risk perception ability score of the driver.

[0015] Preferably, the risk perception accuracy score Q i of the driver in the i(th) (i≤k) VR road traffic risk driving scene is calculated according to the following formula:

[0016] The number m i of gaze points of the driver in the risk reaction time window of the i(th) VR road traffic risk driving scene is calculated;

[0017] The number n i of gaze points of the driver in the risk area in the risk reaction time window of the i(th) VR road traffic risk driving scene is calculated;

[0018] (n i / m iif the value is not less than a preset threshold R i , the driver is deemed to have perceived the risk in the ith VR road traffic risk driving scene, and the risk perception accuracy score Q i of the driver in the ith VR road traffic risk driving scene is assigned a full score; otherwise, the driver is deemed not to have perceived the risk in the ith VR road traffic risk driving scene, and the risk perception accuracy score Q i of the driver in the ith VR road traffic risk driving scene is assigned a score of 0.

[0019] Preferably, if the risk perception accuracy score Q i of the driver in the ith VR road traffic risk driving scene is a full score, the risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is further calculated. i If the risk perception accuracy score Q i of the driver in the ith VR road traffic risk driving scene is 0, the risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is assigned a score of 0.

[0020] Preferably, the process of further calculating the risk perception speed score P i of the driver in the ith VR road traffic risk driving scene includes:

[0021] If the driver releases the accelerator pedal within the risk reaction time window of the ith VR road traffic risk driving scene, the calculation process of the risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is as follows:

[0022] The first time t ai at which the driver starts to release the accelerator pedal within the risk reaction time window of the ith VR road traffic risk driving scene is extracted.

[0023] The risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is calculated.

[0024]

[0025] wherein t si is the start time of the risk reaction time window in the ith VR road traffic risk driving scene, and t ei is the end time of the risk reaction time window in the ith VR road traffic risk driving scene.

[0026] If the driver does not release the accelerator pedal and does not step on the brake pedal within the risk reaction time window of the ith VR road traffic risk driving scene, but takes the wait-to-brake behavior, the risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is calculated as follows:

[0027] The first time t bi at which the driver starts to step on the brake pedal within the risk reaction time window of the ith VR road traffic risk driving scene is extracted.

[0028] The risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is calculated as follows:

[0029]

[0030] If the driver does not release the accelerator pedal and does not step on the brake pedal within the risk reaction time window of the ith VR road traffic risk driving scene, but takes the wait-to-brake behavior, the risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is calculated as follows:

[0031] The first time t ci at which the driver starts to take the wait-to-brake behavior by shifting his foot from the accelerator pedal to the brake pedal within the risk reaction time window of the ith VR road traffic risk driving scene is extracted.

[0032] The risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is calculated as follows:

[0033]

[0034] Preferably, if the driver does not release the accelerator pedal, does not step on the brake pedal, and does not take the wait-to-brake behavior within the risk reaction time window of the ith VR road traffic risk driving scene, the risk perception speed score P i of the driver in the ith VR road traffic risk driving scene is assigned a score of 0.

[0035] Preferably, the average driving speed V si of the vehicle within the risk reaction time window of the ith VR road traffic risk driving scene, from the start time t ai at which the driver starts to release the accelerator pedal, or the start time t bi at which the driver starts to step on the brake pedal, or the start time t ci at which the driver starts to take the wait-to-brake behavior, is calculated as follows:

[0036]

[0037] wherein: j i is the total number of speed values from t si to t ai or t bi or t ci , t i is the time point of t ai or t bi or t ci .

[0038] Preferably, the risk perception ability score S1, S2, … S i of the driver in the k VR road traffic risk driving scenarios is calculated one by one. k wherein the risk degree D i and the reference speed V 0i of the ith VR road traffic risk driving scenario are combined, and the risk perception speed score P i of the driver in the ith VR road traffic risk driving scenario and the average driving speed V The risk perception ability score S i of the driver in the ith VR road traffic risk driving scenario is calculated by the following formula:

[0039]

[0040] Preferably, the comprehensive risk perception ability score S of the driver is calculated by weighted average of the risk perception ability scores of the driver in all driving scenarios by the following formula:

[0041]

[0042] The technical scheme of the present application has the following advantages:

[0043] This invention provides a virtual reality-based driver risk perception ability evaluation system and method. The system is built using a VR driving simulator and a management platform. The management platform includes a VR road traffic risk driving scenario library and an evaluation database. This system has advantages such as strong immersion and low interference. At the start of the evaluation, the VR driving simulator selects multiple driving scenarios from the scenario library to form an evaluation driving scenario combination. The management platform receives and stores the driver's driving operation, gaze position information, and driving scenario information sent by the VR driving simulator in real time. It calculates the driver's risk perception accuracy score, risk perception speed score, and average driving speed in each VR road traffic risk driving scenario, calculating the driver's risk perception ability score for each scenario. The weighted average of the risk perception ability scores from all driving scenarios is then used to calculate the driver's comprehensive risk perception ability score. This method has advantages such as accurate evaluation and ease of understanding. Attached Figure Description

[0044] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of a specific example of a driver risk perception ability evaluation system based on virtual reality provided in an embodiment of the present invention.

[0046] Figure 2 This is a flowchart illustrating a specific example of a driver risk perception ability evaluation method based on virtual reality provided in this embodiment of the invention. Detailed Implementation

[0047] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0049] Example 1

[0050] This invention provides a driver risk perception ability evaluation system based on virtual reality, such as... Figure 1 As shown, it includes:

[0051] The VR driving simulator 1 and the management platform 2 realize real-time communication through network connection.

[0052] The VR driving simulator 1 is used as an evaluation platform, which is used for driver login, collection of driving control information and gaze position information during simulated driving of the driver, running of a VR road traffic risk driving scene, display of a risk perception ability evaluation result, and the like.

[0053] The management platform 2 includes a VR road traffic risk driving scene library and an evaluation database, which are used for management of the VR road traffic risk driving scene and the evaluation data, calculation of the risk perception ability evaluation result, and the like.Specifically, the VR road traffic risk driving scene is designed based on typical road traffic risks and is three-dimensionally modeled. s e According to the evolution process of the risk in each VR road traffic risk driving scene, the risk reaction time window [t

[0054] The driver risk perception ability evaluation system provided by the embodiment of the present application is constructed by using a VR driving simulator and a management platform, can provide a good evaluation environment for evaluation of the risk perception ability of the driver, and has the advantages of strong immersion and small interference.

[0055] Embodiment 2

[0056] The embodiment of the present application provides a driver risk perception ability evaluation method based on virtual reality, as shown in the following formula: Figure 2

[0057] Step S1: When the driver starts the evaluation, the VR driving simulator selects k (k>1) driving scenes for evaluation from the VR road traffic risk driving scene library according to a preset selection rule to form an evaluation driving scene combination.

[0058] In the embodiment of the present application, the preset selection rule is determined according to the actual driving ability to be tested, so that the corresponding driving scene is selected to form the evaluation driving scene combination.

[0059] ​Step S2: When the driver simulates driving in the driver's cabin, the management platform receives and stores the driving manipulation information and gaze position information of the driver and the VR road traffic risk driving scene information sent by the VR driving simulator in real time.

[0060] In practical applications, when the driver simulates driving in the driver's cabin, the VR driving simulator collects the driving manipulation information of the driver on the steering wheel, brake pedal, accelerator pedal and other manipulation mechanisms in real time and sends it to the management platform for storage, and the visual tracking instrument built-in in the VR head-mounted display in the VR driving simulator collects the gaze position information of the driver in real time and sends it to the management platform for storage.

[0061] Step S3: After the selected k VR road traffic risk driving scenes are evaluated, the management platform calculates the risk perception accuracy score Q i , risk perception speed score P i and average driving speed V

[0062] Further, the calculation process of the risk perception accuracy score Q i of the driver in the i-th VR road traffic risk driving scene includes:

[0063] 1) Calculate the number m i of gaze points of the driver in the risk reaction time window of the i-th VR road traffic risk driving scene;

[0064] 2) Calculate the number n i of gaze points of the driver in the risk area in the risk reaction time window of the i-th VR road traffic risk driving scene;

[0065] 3) Calculate the value of (n i / m i ), if the value is not less than a preset threshold R i , it is considered that the driver perceives the risk in the i-th VR road traffic risk driving scene, and the risk perception accuracy score Q i of the driver in the i-th VR road traffic risk driving scene is assigned as full score (for example, 100 points, which is only an example, not limited to this); otherwise, it is considered that the driver does not perceive the risk in the i-th VR road traffic risk driving scene, and the risk perception accuracy score Q i of the driver in the i-th VR road traffic risk driving scene is assigned as 0 score.

[0066] If the risk perception accuracy score Qi is full score, then further calculate the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i ; otherwise, if the risk perception accuracy score Q of the driver in the ith VR road traffic risk driving scene i is 0 score, then assign the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i to 0 score.

[0067] In the embodiment of the present application, the risk perception accuracy score Q of the driver in the ith VR road traffic risk driving scene i is full score, then further calculate the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i .

[0068] 1) In the embodiment of the present application, if the driver releases the accelerator pedal in the risk reaction time window of the ith VR road traffic risk driving scene, then the calculation process of the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i is as follows:

[0069] a) extract the first time t ai at which the driver starts to release the accelerator pedal in the risk reaction time window of the ith VR road traffic risk driving scene;

[0070] b) calculate the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i :

[0071]

[0072] wherein t si is the start time of the risk reaction time window in the ith VR road traffic risk driving scene, and t ei is the end time of the risk reaction time window in the ith VR road traffic risk driving scene;

[0073] 2) In the embodiment of the present application, if the driver does not release the accelerator pedal but steps on the brake pedal in the risk reaction time window of the ith VR road traffic risk driving scene, then the calculation process of the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i is as follows:

[0074] a) extract the first time t bi at which the driver starts to step on the brake pedal in the risk reaction time window of the ith VR road traffic risk driving scene;

[0075] b) calculating the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i :

[0076]

[0077] 3) In the embodiment of the present application, if the driver does not release the accelerator pedal, does not step on the brake pedal, and does not take the brake-waiting behavior within the risk reaction time window of the ith VR road traffic risk driving scene, the risk perception speed score P of the driver in the ith VR road traffic risk driving scene is calculated as follows: i

[0078] a) extracting the first time t at which the driver starts to take the brake-waiting behavior by shifting the foot from the accelerator pedal to the brake pedal within the risk reaction time window of the ith VR road traffic risk driving scene ci ;

[0079] b) calculating the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i :

[0080]

[0081] 4) In the embodiment of the present application, if the driver does not release the accelerator pedal, does not step on the brake pedal, and does not take the brake-waiting behavior within the risk reaction time window of the ith VR road traffic risk driving scene, the risk perception speed score P of the driver in the ith VR road traffic risk driving scene is assigned as 0. i

[0082] Further, in the embodiment of the present application, the average driving speed of the vehicle within the risk reaction time window of the ith VR road traffic risk driving scene from the starting time t of the risk reaction time window to the first time t at which the driver starts to release the accelerator pedal, or the first time t at which the driver starts to step on the brake pedal, or the first time t at which the driver starts to take the brake-waiting behavior is calculated as follows: si ai bi ci

[0083]

[0084] wherein j i is the total number of speed values from t si to t ai or t bi or t ci in the ith VR road traffic risk driving scene, and t i is t ai or t bi ​​​​​​or t ci the moment.

[0085] Step S4: Calculate the risk perception ability score S1, S2, … S of the driver in the k VR road traffic risk driving scenes one by one. i ,…S k .

[0086] The embodiment of the present application combines the risk degree D of the i-th VR road traffic risk driving scene i and the reference speed V 0i , and the risk perception speed score P of the driver in the i-th VR road traffic risk driving scene i and the average driving speed V The risk perception ability score S of the driver in the i-th VR road traffic risk driving scene is calculated by the following formula: i

[0087]

[0088] Step S5: The comprehensive risk perception ability score S of the driver is calculated by weighted average of the risk perception ability scores of the driver in all driving scenes.

[0089]

[0090] It should be noted that the scoring system adopted by each index for quantitative evaluation can be 100 points, 5 points or 10 points.

[0091] The virtual reality driver risk perception ability evaluation method provided by the embodiment of the present application calculates the risk perception accuracy score, the risk perception speed score and the average driving speed of the driver in each VR road traffic risk driving scene one by one; then calculates the risk perception ability score of the driver in each driving scene one by one, and finally calculates the comprehensive risk perception ability score of the driver by weighted average of the risk perception ability scores of the driver in all driving scenes, which has the advantages of accurate evaluation and simple and easy understanding.

[0092] Obviously, the above embodiments are only examples for clearly illustrating, but not limit the embodiments. For those skilled in the art, other different forms of changes or variations can be made on the basis of the above description. Here, all the embodiments need not and cannot be exhausted. The obvious changes or variations derived therefrom are still within the protection scope of the present application.​

Claims

1. A virtual reality-based method for evaluating a driver's risk perception ability, characterized by, The method comprises the following steps: When the driver starts the evaluation, the VR driving simulator selects k driving scenes for evaluation from the VR road traffic risk driving scene library according to preset selection rules to form an evaluation driving scene combination, wherein k>1; When the driver simulates driving in the driving cabin, the management platform receives and stores the driving manipulation information and gaze position information of the driver and the VR road traffic risk driving scene information sent by the VR driving simulator in real time; After the selected k road traffic risk driving scenes are evaluated, the management platform calculates the risk perception accuracy score, the risk perception speed score and the average driving speed of the driver in each VR road traffic risk driving scene according to the received and stored driving manipulation information and gaze position information of the driver and the VR road traffic risk driving scene information; the risk perception ability score of the driver in each driving scene is calculated; wherein the risk perception accuracy score is calculated by the ratio of the number of gaze points in the risk area in the risk reaction time window to the total number of gaze points, and compared with a preset threshold to assign a full score or 0; the risk perception speed score is calculated according to the difference between the time when the first time the accelerator pedal / brake pedal is released or stepped on and the risk reaction time window only when the risk perception accuracy is full score, and 0 if no action is taken; the average driving speed is the average speed from the start of the risk reaction time window to the first operation time; The comprehensive risk perception ability score of the driver is calculated by weighted average of the risk perception ability scores of the driver in all driving scenes.

2. The virtual reality-based driving risk perception evaluation method according to claim 1, characterized in that, The risk perception accuracy score Q of the driver in the ith VR road traffic risk driving scene i The calculation process comprises: calculating the number m of driver gaze points within the risk reaction time window for the ith VR road traffic risk driving scenario i where i ≤ k; calculating the number n of driver gaze points on the risk area within the risk reaction time window for the ith VR road traffic risk driving scenario i ; The value of the calculation (n i / m i ) is determined, and if the value is not less than a preset threshold R i , it is considered that the driver perceives the risk in the i-th VR road traffic risk driving scene, and the risk perception accuracy score Q i of the driver in the i-th VR road traffic risk driving scene is assigned a full score; otherwise, it is considered that the driver does not perceive the risk in the i-th VR road traffic risk driving scene, and the risk perception accuracy score Q i of the driver in the i-th VR road traffic risk driving scene is assigned a score of 0.

3. The virtual reality-based driving risk perception evaluation method according to claim 2, characterized in that, If the risk perception accuracy score Q of the driver in the i-th VR road traffic risk driving scene is i full marks, then further calculate the risk perception speed score P of the driver in the i-th VR road traffic risk driving scene i If the risk perception accuracy score Q of the driver in the i-th VR road traffic risk driving scene is i 0 points, then the risk perception speed score P of the driver in the i-th VR road traffic risk driving scene is i assigned as 0 points.

4. The virtual reality-based driving risk perception evaluation method according to claim 3, characterized in that, The further calculating the risk perception speed score P of the driver in the ith VR road traffic risk driving scene i includes: If the driver has the accelerator pedal off within the risk response time window of the ith VR road traffic risk driving scene, the risk perception speed score P of the driver in the ith VR road traffic risk driving scene is calculated as follows: i The calculation process is as follows: extracting a first time t at which the driver starts to release the accelerator pedal within a risk reaction time window of the driver in the ith VR road traffic risk driving scene ai ; calculating a risk perception speed score P of the driver in the i-th VR road traffic risk driving scene i : wherein: t si is the start time of the risk reaction time window in the i-th VR road traffic risk driving scenario, t ei is the end time of the risk reaction time window in the i-th VR road traffic risk driving scenario; If the driver does not release the accelerator pedal within the risk response time window of the ith VR road traffic risk driving scene, but steps on the brake pedal, the risk perception speed score P of the driver in the ith VR road traffic risk driving scene is i The calculation process is as follows: extracting a first time t at which the driver starts to step on the brake pedal within a risk response time window of the driver in the ith VR road traffic risk driving scene bi ; calculating a risk perception speed score P of the driver in the i-th VR road traffic risk driving scene i : If the driver does not release the accelerator pedal and does not step on the brake pedal within the risk response time window of the ith VR road traffic risk driving scene, but takes the wait-to-brake behavior, the risk perception speed score P of the driver in the ith VR road traffic risk driving scene is calculated as follows: i The calculation process is as follows: extracting the first time t at which the driver starts to take the wait-to-brake behavior from the shift of the foot from the accelerator pedal to the brake pedal within the risk reaction time window of the driver in the ith VR road traffic risk driving scene ci ; calculating a risk perception speed score P of the driver in the i-th VR road traffic risk driving scene i :

5. The virtual reality-based driving risk perception evaluation method according to claim 4, characterized in that, If the driver does not release the accelerator pedal, does not step on the brake pedal, and does not take the wait-to-brake action within the risk response time window of the ith VR road traffic risk driving scene, the risk perception speed score P of the driver in the ith VR road traffic risk driving scene is assigned a value of 0. i assigned a value of 0.

6. The virtual reality-based driving risk perception evaluation method according to claim 4, characterized in that, the risk reaction time window of the ith VR road traffic risk driving scenario, from the start time t si to the first time t when the driver starts to release the accelerator pedal ai , or the first time t when the driver starts to step on the brake pedal bi , or the first time t when the driver starts to take the wait-to-brake behavior ci , the average driving speed of the vehicle Where: j i For the i-th VR road traffic risk driving scenario, from t si to t ai or t bi or t ci Total velocity values, t i For t ai or t bi or t ci At that moment.

7. The virtual reality-based driving human risk perception ability evaluation method according to any one of claims 4-6, characterized in that, Calculate the risk perception scores S1, S2, LS of the driver in each of the k VR road traffic risk driving scenarios. i ,LS k Among them, the risk level D of the i-th VR road traffic risk driving scenario is combined with the risk level D. i and reference speed V 0i And the driver's risk perception speed score P in the i-th VR road traffic risk driving scenario. i and average vehicle speed The risk perception score S of the driver in the i-th VR road traffic risk driving scenario is calculated using the following formula. i :

8. The virtual reality-based driving human risk perception ability evaluation method according to claim 7, characterized in that, The comprehensive risk perception ability score S of the driver is calculated by weighted average of the risk perception ability scores of the driver in all driving scenes through the following formula:

9. A virtual reality-based driver risk perception ability evaluation system, characterized by, The system comprises a VR driving simulator and a management platform, which are connected by a network to realize real-time communication; The VR driving simulator is an evaluation platform for driver login, collection of driving manipulation information and gaze position information during simulated driving, running of VR road traffic risk driving scenes, and display of risk perception ability evaluation results; The management platform comprises a VR road traffic risk driving scene library and an evaluation database for managing VR road traffic risk driving scenes and evaluation data, and calculating risk perception ability evaluation results; the VR road traffic risk driving scene library is an electronic information database containing VR road traffic risk driving scenes, which includes the 3D model, risk degree, risk reaction time window and reference driving speed information of each scene; Based on historical typical road traffic risk data, VR road traffic risk driving scenes are formed by three-dimensional modeling; the scene features in each VR road traffic risk driving scene include traffic environment, road type, risk type, risk position, risk size, and risk color; the risk degree of each VR road traffic risk driving scene is determined according to the scene features; the risk reaction time window and the reference driving speed of each VR road traffic risk driving scene are determined according to the evolution process of the risk in each VR road traffic risk driving scene.

Images