Driver response duration evaluation method, device, equipment, medium and program product

Abstract

The invention provides a driver response duration evaluation method, device and equipment, a medium and a program product. According to the method, after an obstacle type, obstacle motion data, an initial state of a driver, an eye state of the driver, vehicle driving data and an evaluation mode are obtained, a scene type is determined according to the obstacle type and the obstacle motion data; determining a driver target state according to the driver initial state, the driver eye state and the vehicle driving data; and finally, according to the scene type, the driver target state, the evaluation mode and the obstacle distance, determining the driver response duration. According to the scheme, the driver response duration is determined by determining the scene type and the driver target state, the matching degree between the driver response duration and the scene and the driver state is improved, and the accuracy of the driver response duration is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, device, medium, and program product for assessing driver reaction time. Background Technology

[0002] Automatic Emergency Braking (AEB) is an active safety technology for automobiles that can warn or brake before a collision to improve vehicle safety.

[0003] In existing technologies, the implementation of AEB technology typically involves setting a fixed driver reaction time. After determining the collision duration, if the collision duration is less than or equal to the driver reaction time, braking is initiated; if the collision duration is longer than the driver reaction time, a warning is issued.

[0004] However, drivers are affected by other factors, and the driver reaction time in existing technologies is fixed, resulting in low accuracy of driver reaction time. Summary of the Invention

[0005] The driver reaction time assessment method, apparatus, device, medium, and program products provided in this application are intended to solve the problem that the accuracy of driver reaction time is low because the driver reaction time is fixed in the prior art.

[0006] In a first aspect, embodiments of this application provide a method for assessing driver reaction time, including:

[0007] Acquire obstacle type, obstacle motion data, driver initial state, driver eye state, vehicle driving data, and evaluation mode; the obstacle motion data includes obstacle distance.

[0008] The scene type is determined based on the obstacle type and the obstacle motion data;

[0009] The driver's target state is determined based on the driver's initial state, the driver's eye state, and the vehicle driving data;

[0010] The driver's reaction time is determined based on the scenario type, the driver's target state, the evaluation mode, and the obstacle distance.

[0011] In one possible implementation, determining the scene type based on the obstacle type and the obstacle motion data includes:

[0012] If the obstacle type is a vehicle and the obstacle motion data meets the first preset condition, then the scene type is determined to be a following scene.

[0013] If the obstacle type is a vehicle and the obstacle motion data does not meet the first preset condition, then the scene type is determined to be another scene.

[0014] If the obstacle type is a pedestrian and the obstacle motion data meets the second preset condition, then the scene type is determined to be a pedestrian crossing scene.

[0015] If the obstacle type is a pedestrian and the obstacle motion data does not meet the second preset condition, then the scene type is determined to be another scene.

[0016] If the obstacle type is neither a vehicle nor a pedestrian, then the scene type is determined to be another scene.

[0017] In one possible implementation, if the obstacle type is a vehicle, the obstacle motion data also includes the relative speed of the obstacle and the direction of travel of the obstacle. The first preset condition is: the relative speed of the obstacle is less than a preset speed threshold, the angle between the direction of travel of the obstacle and the direction of travel of the vehicle is less than a preset angle threshold, and the distance of the obstacle is less than a first preset distance threshold.

[0018] If the obstacle type is a pedestrian, the obstacle motion data also includes the pedestrian direction, and the second preset condition is: the angle between the pedestrian direction and the vehicle's driving direction is within a preset orthogonal angle range and the obstacle distance is less than a second preset distance threshold.

[0019] In one possible implementation, the driver's initial state is a normal state, an error reporting state, or an inattentive state, wherein the inattentive state includes at least one of a drowsy state, a prolonged inattentive state, and a short-term inattentive state.

[0020] The driver's eye state can be described as a state of eyes closed for a long time, a state of eyes closed for a short time, or a state of eyes not closed.

[0021] The vehicle driving data includes lane departure indicator, steering wheel angle, and brake pedal opening. The lane departure indicator is used to indicate whether the vehicle has deviated from the current lane.

[0022] In one possible implementation, determining the driver's target state based on the driver's initial state, the driver's eye state, and the vehicle driving data includes:

[0023] If the driver's initial state is normal, then the driver's target state is determined to be normal.

[0024] If the driver's initial state is an error state, then the driver's target state is determined to be an unknown state;

[0025] If the driver's initial state is one of distraction, then the driver's target state is determined based on the distraction state, the driver's eye state, and the vehicle driving data.

[0026] In one possible implementation, determining the driver's target state based on the distracted state, the driver's eye state, and the vehicle driving data includes:

[0027] Based on the state of distraction, the driver's eye state, and the vehicle driving data, determine whether the third and fourth preset conditions are met;

[0028] If both the third and fourth preset conditions are met, then the driver's target state is determined to be drowsy and distracted.

[0029] If the third preset condition is met and the fourth preset condition is not met, then the driver's target state is determined to be drowsy.

[0030] If the third preset condition is not met, and the fourth preset condition is met, then the driver's target state is determined to be a distracted state.

[0031] If neither the third preset condition nor the fourth preset condition is met, then the driver's target state is determined to be normal.

[0032] In one possible implementation, the third preset condition is: the distracted state includes a drowsy state, and the driver's eye state is a prolonged closed-eye state;

[0033] The fourth preset condition is: the distracted state includes a long-term distracted state and a short-term distracted state; the lane departure indicator indicates that the vehicle is deviating from the current lane; the steering wheel angle is less than a preset angle and the brake pedal opening is less than a preset opening.

[0034] In one possible implementation, determining the driver's reaction time based on the scenario type, the driver's target state, the evaluation mode, and the obstacle distance includes:

[0035] Based on the scenario type, the driver's target state, and the obstacle distance, as well as the correspondence between scenario type, driver's target state, distance, and reaction time distribution data, the target distribution data is determined.

[0036] Based on the preset correspondence between modes and percentiles, determine the target percentile corresponding to the evaluation mode;

[0037] The driver's reaction time is determined based on the target distribution data and the target percentile.

[0038] In one possible implementation, the evaluation mode is either a conservative mode or an aggressive mode;

[0039] The percentile corresponding to the conservative mode is greater than the percentile corresponding to the radical mode.

[0040] In one possible implementation, before acquiring obstacle type, obstacle motion data, driver initial state, driver eye state, vehicle driving data, and evaluation mode, the method further includes:

[0041] Acquire reaction time distribution data for multiple baseline distances corresponding to each scenario type and each driver's target state;

[0042] For each scenario type and each driver target state, the mean reaction time and standard deviation of each benchmark distance are calculated based on the reaction time distribution data of multiple benchmark distances corresponding to the scenario type and the driver target state.

[0043] For each scenario type and each driver target state, interpolation is performed based on the mean and standard deviation of reaction time for each reference distance corresponding to the scenario type and the driver target state to obtain the reaction time distribution data for each distance. For each distance, a correspondence is established between the scenario type, the driver target state, the distance, and the reaction time distribution data for the distance, and then the data is stored.

[0044] In one possible implementation, before determining the driver's reaction time based on the target distribution data and the target percentile, the method further includes:

[0045] If the driver's target state is unknown, or the scenario type is other scenarios, the preset safety percentile will be used as the updated target percentile.

[0046] Determining the driver's reaction time based on the target distribution data and the target percentile includes:

[0047] The driver's reaction time is determined based on the target distribution data and the updated target percentile.

[0048] In one possible implementation, the method further includes:

[0049] If a lidar malfunction or camera malfunction is detected, the driver's reaction time will be updated to a preset time.

[0050] In one possible implementation, the method further includes:

[0051] If the driver's reaction time exceeds a preset safe time threshold, the driver's reaction time is updated to the preset safe time threshold.

[0052] In one possible implementation, determining the driver's reaction time based on the scenario type, the driver's target state, the evaluation mode, and the obstacle distance includes:

[0053] The scene type, the driver's target state, the evaluation mode, and the obstacle distance are input into the reaction time prediction model to obtain the driver's reaction time. The reaction time prediction model is a pre-trained neural network model used to determine the driver's reaction time based on the scene type, driver's target state, evaluation mode, and obstacle distance.

[0054] Secondly, embodiments of this application provide a driver reaction time assessment device, including components for performing the driver reaction time assessment method described in any one of the first aspects.

[0055] Thirdly, embodiments of this application provide an electronic device, including:

[0056] Processor, memory, communication interface;

[0057] The memory is used to store the executable instructions of the processor;

[0058] The processor is configured to execute the driver reaction time assessment method according to any one of the first aspects by executing the executable instructions.

[0059] Fourthly, embodiments of this application provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the driver reaction time assessment method described in any of the first aspects.

[0060] Fifthly, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, is used to implement the driver reaction time assessment method described in any of the first aspects.

[0061] The driver reaction time assessment method, apparatus, device, medium, and program product provided in this application obtain obstacle type, obstacle motion data, driver's initial state, driver's eye state, vehicle driving data, and assessment mode. Based on the obstacle type and obstacle motion data, the scenario type is determined; based on the driver's initial state, driver's eye state, and vehicle driving data, the driver's target state is determined; and finally, the driver's reaction time is determined based on the scenario type, driver's target state, assessment mode, and obstacle distance. This solution improves the matching degree between driver reaction time and scenario / driver state by determining the scenario type and driver's target state, thus improving the accuracy of driver reaction time assessment. Attached Figure Description

[0062] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0063] Figure 1a A flowchart illustrating an embodiment of the driver reaction time assessment method provided in this application;

[0064] Figure 1b A flowchart illustrating the driver reaction time assessment method provided in this application;

[0065] Figure 2 A flowchart illustrating Embodiment 2 of the driver reaction time assessment method provided in this application;

[0066] Figure 3 A flowchart illustrating Embodiment 3 of the driver reaction time assessment method provided in this application;

[0067] Figure 4 A flowchart illustrating Embodiment 4 of the driver reaction time assessment method provided in this application;

[0068] Figure 5 A schematic diagram of the structure of an embodiment of the driver reaction time assessment device provided in this application;

[0069] Figure 6 This is a schematic diagram of the structure of an electronic device provided in this application.

[0070] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0071] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0072] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0073] Automatic Emergency Braking (AEB) is an active safety technology for automobiles that can warn or brake before a collision to improve vehicle safety.

[0074] In existing technologies, the implementation of AEB (Autonomous Emergency Braking) technology typically involves setting a fixed driver reaction time. After determining the collision duration, if the collision duration is less than or equal to the driver's reaction time, braking is initiated; if the collision duration exceeds the driver's reaction time, a warning is issued. However, drivers are affected by other factors, and the fixed driver reaction time in existing technologies leads to lower accuracy in driver reaction time, resulting in either premature or delayed warnings and braking.

[0075] To address the problems existing in the prior art, the inventors, during their research on driver reaction time assessment methods, discovered that driver reaction time is related to the scene and the driver's state. Therefore, based on obstacle type, obstacle movement data, driver's initial state, driver's eye state, and vehicle driving data, the scene type and the driver's target state can be determined. Then, by combining the assessment mode and obstacle distance, the driver's reaction time can be determined, improving the matching degree between driver reaction time and scene and driver state, and thus improving the accuracy of driver reaction time assessment. Based on the above inventive concept, the driver reaction time assessment scheme in this application was designed.

[0076] The subject executing the driver reaction time assessment method in this application can be a controller in the vehicle, an on-board terminal, a user terminal, a server, etc. This application does not limit it. The controller is used as an example for explanation below.

[0077] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0078] The following provides an example illustrating the application scenarios of the driver reaction time assessment method provided in this application.

[0079] For example, in this application scenario, a driver is driving a vehicle on a highway when a vehicle in front of him is braking.

[0080] In order to determine whether braking or a warning is needed, the controller in this vehicle acquires obstacle type, obstacle motion data, driver initial state, driver eye state, vehicle driving data, and evaluation mode. The obstacle motion data includes obstacle distance.

[0081] Then, based on the type of obstacle and obstacle movement data, the scene type is determined; based on the driver's initial state, the driver's eye state, and vehicle driving data, the driver's target state is determined.

[0082] Then, the driver's reaction time is determined based on the scenario type, the driver's target state, the assessment mode, and the distance to the obstacle.

[0083] The controller also calculates the collision duration. If the collision duration is less than or equal to the driver's reaction time, the controller will brake the vehicle. If the collision duration is greater than the driver's reaction time but less than or equal to the warning duration, the controller will issue a warning. The warning duration is the sum of the driver's reaction time and the reserved time.

[0084] It should be noted that the reserved time can be 1 second, 2 seconds, 3 seconds, etc. This application embodiment does not limit the reserved time, which can be determined according to the actual situation.

[0085] It should be noted that the above scenario is only an example of an application scenario provided by the embodiments of this application. The embodiments of this application do not limit the actual form of the various devices included in the scenario, nor do they limit the interaction method between devices. In the specific application of the solution, it can be set according to actual needs.

[0086] The technical solution of this application will now be described in detail through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0087] Figure 1a This is a flowchart illustrating an embodiment of the driver reaction time assessment method provided in this application. This embodiment describes how the controller determines the scenario type and the driver's target state, and then, in conjunction with the assessment mode and obstacle distance, determines the driver's reaction time. The method in this embodiment can be implemented through software, hardware, or a combination of both. Figure 1a As shown, the driver reaction time assessment method specifically includes the following steps:

[0088] S101: Acquire obstacle type, obstacle motion data, driver initial state, driver eye state, vehicle driving data, and evaluation mode.

[0089] In this step, to avoid collisions between the vehicle and obstacles ahead, the controller needs to assess the driver's reaction time. This involves first acquiring information such as obstacle type, obstacle motion data, driver's initial state, driver's eye state, vehicle driving data, and the assessment mode.

[0090] It should be noted that, as an example, the vehicle can be equipped with LiDAR or cameras to acquire point cloud data or images of the area in front of the vehicle. This allows for target detection and tracking, yielding obstacle type and obstacle motion data, including obstacle distance. The obstacle distance is the distance between the vehicle and the obstacle. Obstacle type and motion data can also be obtained through other methods.

[0091] It should be noted that, as an example, a vehicle may have a Driver Monitoring System (DMS), which uses cameras or sensors to detect the driver's facial features, eye movements, head posture, and other behavioral patterns to obtain the driver's initial state and eye state. Alternatively, the driver's initial state and eye state can also be obtained through other methods.

[0092] The driver's initial state is either normal, error-reporting, or distracted. Distracted state includes at least one of drowsy, prolonged distraction, and short-term distraction. Prolonged distraction indicates that the driver may remain distracted for a longer period than a preset threshold, while short-term distraction indicates that the driver may remain distracted for a shorter period than a preset threshold.

[0093] The driver's eye status is categorized as prolonged eye closure, short-term eye closure, or open eye closure. Prolonged eye closure indicates that the driver may have maintained this state for more than a preset threshold, while short-term eye closure indicates that the driver may have maintained this state for less than a preset threshold.

[0094] Vehicle driving data includes lane departure warning, steering wheel angle, and brake pedal opening. The lane departure warning is used to indicate whether the vehicle has deviated from the current lane.

[0095] It should be noted that, as an example, the vehicle is equipped with a lidar or camera, which can acquire point cloud data or images of the side of the vehicle, thereby enabling target detection, determining the distance between the vehicle and the lane lines, and thus obtaining a lane departure indicator.

[0096] It should be noted that the assessment mode is a mode pre-set by the driver in the vehicle, representing the driver's assessment of the driver's reaction time. The assessment mode is either conservative or aggressive. Under the same conditions, the driver's reaction time in the conservative mode is longer than that in the aggressive mode.

[0097] It should be noted that the controller can preprocess the acquired obstacle type, obstacle motion data, driver initial state, driver eye state, and vehicle driving data, such as filtering, removing outliers, time alignment, and supplementing missing values.

[0098] S102: Determine the scene type based on obstacle type and obstacle motion data.

[0099] In this step, after the controller obtains the obstacle type and obstacle motion data, it determines the scene type based on the obstacle type and obstacle motion data, since the driver's reaction time is related to the current scene.

[0100] The obstacle type is a vehicle, pedestrian, or other type.

[0101] When the obstacle type is a vehicle, the obstacle motion data also includes the obstacle's relative speed and direction of travel. The obstacle's relative speed is the speed of the obstacle relative to the vehicle.

[0102] When the obstacle type is pedestrian, the obstacle motion data also includes pedestrian direction.

[0103] The scenario type is following a vehicle, pedestrian crossing, or other scenarios.

[0104] S103: Determine the driver's target state based on the driver's initial state, the driver's eye state, and vehicle driving data.

[0105] In this step, after the controller obtains the driver's initial state, the driver's eye state, and the vehicle's driving data, it is also necessary to determine the driver's target state based on the driver's initial state, the driver's eye state, and the vehicle's driving data, since the driver's reaction time is related to the driver's state.

[0106] The driver's target state is normal, unknown, drowsy and distracted, or drowsy or distracted.

[0107] It should be noted that the execution order of steps S102 and S103 can be as follows: step S102 is executed first, followed by step S103; step S103 is executed first, followed by step S102; or steps S102 and S103 are executed simultaneously. This embodiment does not limit the execution order of steps S102 and S103, and it can be determined according to the actual situation.

[0108] S104: Determine the driver's reaction time based on the scenario type, driver's target state, evaluation mode, and obstacle distance.

[0109] In this step, after the controller obtains the scene type and the driver's target state, the driver's reaction time is also related to the evaluation mode and the distance to obstacles. Therefore, the driver's reaction time is determined based on the scene type, the driver's target state, the evaluation mode, and the distance to obstacles.

[0110] In one implementation, target distribution data is determined based on scene type, driver target state, obstacle distance, and the correspondence between scene type, driver target state, distance, and reaction time distribution data.

[0111] It should be noted that the reaction time distribution data follows a normal distribution. When the scenario type and the driver's target state are the same, the standard deviation of the normal distribution is positively correlated with distance, and the mean of the normal distribution is also positively correlated with distance.

[0112] Then, based on the pre-defined correspondence between modes and percentiles, the target percentile corresponding to the evaluation mode is determined. The evaluation mode is either a conservative mode or an aggressive mode. The percentile corresponding to the conservative mode is greater than the percentile corresponding to the aggressive mode.

[0113] For example, the percentile corresponding to the conservative mode is P90, and the percentile corresponding to the aggressive mode is P50. The percentile corresponding to the conservative mode is P85, and the percentile corresponding to the aggressive mode is P55. The percentile corresponding to the conservative mode is P80, and the percentile corresponding to the aggressive mode is P45. This application does not limit the correspondence between modes and percentiles; it can be determined according to the actual situation.

[0114] Then, based on the target distribution data and the target percentile, the driver's reaction time is determined. That is, the reaction time corresponding to the target percentile in the target distribution data is taken as the driver's reaction time.

[0115] It should be noted that after determining the target percentile, the controller can update it to further improve vehicle safety. If the driver's target state is unknown, or the scenario type is different, and a longer reaction time is required to improve vehicle safety, the preset safety percentile will be used as the updated target percentile. Then, based on the target distribution data and the updated target percentile, the driver's reaction time is determined.

[0116] The preset safety percentile can be P95, P90, P85, etc. This application embodiment does not limit the preset safety percentile, and it can be determined according to the actual situation.

[0117] In another implementation, the scene type, driver target state, evaluation mode, and obstacle distance are input into the reaction time prediction model to obtain the driver's reaction time. The reaction time prediction model is a pre-trained neural network model used to determine the driver's reaction time based on the scene type, driver target state, evaluation mode, and obstacle distance.

[0118] It should be noted that after the controller determines the driver's reaction time, in order to further improve its accuracy, it can determine whether the lidar is faulty, whether the camera is faulty, and whether the driver's reaction time exceeds the preset safe time threshold.

[0119] If a malfunction is detected in the lidar or camera, it indicates that there may be abnormalities in the obtained obstacle type, obstacle movement data, driver's initial state, driver's eye state, and vehicle driving data, resulting in inaccurate driver reaction time. In this case, the driver reaction time will be updated to the preset time.

[0120] The preset duration can be 0.5 seconds, 0.8 seconds, 1 second, 1.2 seconds, etc. This application embodiment does not limit the preset duration, and it can be determined according to the actual situation.

[0121] If the driver's reaction time exceeds the preset safe reaction time threshold, it indicates that the determined driver's reaction time is inaccurate, and the driver's reaction time will be updated to the preset safe reaction time threshold.

[0122] The preset safety duration threshold can be 1.2 seconds, 1.5 seconds, 2 seconds, etc. This application embodiment does not limit the preset safety duration threshold, and it can be determined according to the actual situation.

[0123] The controller will then calculate the collision duration. If the collision duration is less than or equal to the driver's reaction time, it means it's too late to warn the driver to brake, and the controller can automatically brake the vehicle. If the collision duration is greater than the driver's reaction time but less than or equal to the warning duration, an alarm will be issued to remind the driver to brake in time. The warning duration is the sum of the driver's reaction time and the reserved time. If the collision duration is greater than the warning duration, no alarm will be issued to avoid premature warnings that could affect the driver.

[0124] For example, Figure 1b A flowchart illustrating the driver reaction time assessment method provided in this application is shown below. Figure 1b As shown, the scene type is determined based on the obstacle type and obstacle motion data; the driver's target state is determined based on the driver's initial state, driver's eye state, and vehicle driving data; and the driver's reaction time is determined based on the scene type, driver's target state, evaluation mode, and obstacle distance.

[0125] The driver reaction time assessment method provided in this embodiment obtains obstacle type, obstacle motion data, driver's initial state, driver's eye state, vehicle driving data, and assessment mode. Based on the obstacle type and obstacle motion data, it determines the scenario type; based on the driver's initial state, driver's eye state, and vehicle driving data, it determines the driver's target state; and finally, based on the scenario type, driver's target state, assessment mode, and obstacle distance, it determines the driver's reaction time. This solution improves the matching degree between driver reaction time and scenario / driver state by determining the scenario type and driver's target state, thus improving the accuracy of driver reaction time and ultimately enhancing driving safety.

[0126] Figure 2 This is a flowchart illustrating a second embodiment of the driver reaction time assessment method provided in this application. Based on the above embodiments, this application describes how the controller determines the scene type according to the obstacle type and obstacle movement data. Figure 2 As shown, the driver reaction time assessment method specifically includes the following steps:

[0127] S201: Determine whether the obstacle type is a vehicle; if the obstacle type is a vehicle, proceed to steps S202-S204; if the obstacle type is not a vehicle, proceed to step S205.

[0128] In this step, after the controller obtains the obstacle type and obstacle motion data, it needs to determine whether the obstacle type is a vehicle in order to determine the scene type.

[0129] S202: Determine whether the obstacle motion data meets the first preset condition; if the obstacle motion data meets the first preset condition, then execute step S203; if the obstacle motion data does not meet the first preset condition, then execute step S204.

[0130] In this step, if the controller determines that the obstacle type is a vehicle, it also needs to determine whether the obstacle motion data meets the first preset condition.

[0131] The first preset condition is: the relative speed of the obstacle is less than the preset speed threshold, the angle between the direction of travel of the obstacle and the direction of travel of the vehicle is less than the preset angle threshold, and the distance to the obstacle is less than the first preset distance threshold.

[0132] It should be noted that the preset speed threshold can be 10km / h, 15km / h, 20km / h, etc.; the preset angle threshold can be 10 degrees, 15 degrees, 20 degrees, etc.; and the first preset distance threshold can be 10 meters, 20 meters, 50 meters, etc. This application embodiment does not limit the preset speed threshold, preset angle threshold, and first preset distance threshold; they can be determined according to actual conditions.

[0133] S203: The scenario type is determined to be a following scenario.

[0134] S204: The scene type is determined to be other scenes.

[0135] In the above steps, if the controller determines that the obstacle movement data meets the first preset condition, it means that the speed of the vehicle and the vehicle in front are similar, the driving direction is the same, and the distance between the vehicle and the vehicle in front is small, and the scene type can be determined as a following scene.

[0136] If the controller determines that the obstacle movement data does not meet the first preset condition, it means that the speed difference between the vehicle and the vehicle in front is large, the driving direction is not the same, or the distance between the vehicle and the vehicle in front is large, and the scene type can be determined as other scenes.

[0137] S205: Determine whether the obstacle type is a pedestrian; if the obstacle type is a pedestrian, proceed to steps S206-S208; if the obstacle type is not a pedestrian, proceed to step S208.

[0138] In this step, if the controller determines that the obstacle type is not a vehicle, it still needs to determine whether the obstacle type is a pedestrian.

[0139] S206: Determine whether the obstacle motion data meets the second preset condition; if the obstacle motion data meets the second preset condition, then execute step S207; if the obstacle motion data does not meet the second preset condition, then execute step S208.

[0140] In this step, if the controller determines that the obstacle type is a pedestrian, it also needs to determine whether the obstacle motion data meets the second preset condition.

[0141] The second preset condition is: the angle between the pedestrian's direction and the vehicle's direction of travel is within the preset orthogonal angle range and the distance to the obstacle is less than the second preset distance threshold.

[0142] It should be noted that the preset orthogonal angle range can be 80-100 degrees, 85-95 degrees, 75-105 degrees, etc.; the second preset distance threshold can be 10 meters, 20 meters, 50 meters, etc. This application embodiment does not limit the preset orthogonal angle range and the second preset distance threshold, which can be determined according to the actual situation.

[0143] S207: The scene type is determined to be a pedestrian crossing scene.

[0144] S208: Determine the scene type as other scenes.

[0145] In the above steps, if the controller determines that the obstacle movement data meets the second preset condition, it means that a pedestrian is crossing the road in front of the vehicle and the distance between the vehicle and the pedestrian is small, and the scene type can be determined as a pedestrian crossing scene.

[0146] If the controller determines that the obstacle movement data does not meet the second preset condition, it means that the pedestrian in front of the vehicle is not crossing the road, or the distance between the vehicle and the pedestrian is large, and the scene type can be determined as other scenes.

[0147] If the controller determines that the obstacle type is not a pedestrian, that is, when the obstacle type is neither a vehicle nor a pedestrian, then the scene type is determined to be another scene.

[0148] The driver reaction time assessment method provided in this embodiment determines the scene type by determining whether the obstacle type is a vehicle or a pedestrian, and whether the obstacle movement data meets the first preset condition or the second preset condition, thereby improving the accuracy of scene type.

[0149] Figure 3 This is a flowchart illustrating Embodiment 3 of the driver reaction time assessment method provided in this application. Based on the above embodiments, this application describes how the controller determines the driver's target state based on the driver's initial state, the driver's eye state, and vehicle driving data. Figure 3 As shown, the driver reaction time assessment method specifically includes the following steps:

[0150] S301: Determine whether the driver's initial state is normal; if the driver's initial state is normal, proceed to step S302; if the driver's initial state is not normal, proceed to step S303.

[0151] In this step, after the controller obtains the driver's initial state, the driver's eye state, and the vehicle's driving data, some of the driver's initial state is not very accurate and needs to be post-processed to obtain the driver's target state. First, it is determined whether the driver's initial state is normal.

[0152] S302: Determine that the driver's target state is normal.

[0153] In this step, if the controller determines that the driver's initial state is normal and the DMS detection is accurate, then the driver's target state is determined to be normal.

[0154] S303: Determine whether the driver's initial state is an error state; if the driver's initial state is an error state, proceed to step S304; if the driver's initial state is not an error state, proceed to step S305.

[0155] In this step, if the controller determines that the driver's initial state is not normal, it also needs to determine whether the driver's initial state is an error state.

[0156] The error status is the status of the error message output by DMS.

[0157] S304: The driver's target state is determined to be unknown.

[0158] In this step, if the controller determines that the driver's initial state is an error state, it means that the driver's specific state cannot be determined. In order for the solution to be executable, the driver's target state is determined to be an unknown state.

[0159] S305: Determine the driver's target state based on the driver's distracted state, eye state, and vehicle driving data.

[0160] In this step, if the controller determines that the driver's initial state is not an error state, and therefore not a normal state either, it indicates that the driver's initial state is one of distraction. The driver's target state can be determined based on the state of distraction, the driver's eye state, and vehicle driving data.

[0161] Specifically, based on the state of distraction, the driver's eye state, and vehicle driving data, it is determined whether the third and fourth preset conditions are met.

[0162] The third precondition is that the driver's attention is distracted, including drowsy state, and the driver's eyes are closed for a long time.

[0163] The fourth preset condition is: distracted state including long-term distraction state and short-term distraction state, lane departure warning indicating that the vehicle is deviating from the current lane, steering wheel angle is less than preset angle and brake pedal opening is less than preset opening.

[0164] It should be noted that the preset turning angle can be 5 degrees, 10 degrees, 15 degrees, etc., and the preset opening can be 1%, 2%, 3%, etc. The embodiments of this application do not limit the preset opening, which can be determined according to the actual situation.

[0165] If the third preset condition is met, it means that the DMS has detected driver drowsiness and the driver has kept his eyes closed for a long time, which confirms that the driver is currently drowsy.

[0166] If all four preset conditions are met, it means that the DMS has detected driver distraction and the vehicle has deviated from the current lane. The driver has not made any directional corrections or decelerations, thus confirming that the driver is currently distracted.

[0167] If both the third and fourth preset conditions are met, then the driver's target state is determined to be drowsy and distracted.

[0168] If the third preset condition is met and the fourth preset condition is not met, then the driver's target state is determined to be drowsy.

[0169] If the third preset condition is not met, but the fourth preset condition is met, then the driver's target state is determined to be a distracted state.

[0170] If neither the third nor the fourth preset condition is met, it means that the driver is driving the vehicle normally, and the driver's target state is determined to be normal.

[0171] The driver reaction time assessment method provided in this embodiment determines the driver's target state by considering the driver's initial state, the driver's eye state, vehicle driving data, and whether the third and fourth preset conditions are met, thereby improving the accuracy of the driver's target state.

[0172] Figure 4 This is a flowchart illustrating Embodiment 4 of the driver reaction time assessment method provided in this application. Based on the above embodiments, this embodiment explains the correspondence between the controller generating scene type, driver target state, distance, and reaction time distribution before assessing the driver's reaction time. Figure 4 As shown, the driver reaction time assessment method specifically includes the following steps:

[0173] S401: Obtain reaction time distribution data for multiple baseline distances corresponding to each scenario type and each driver's target state.

[0174] In this step, in order to subsequently evaluate the driver's reaction time, the controller first needs to generate the correspondence between scenario type, driver target state, distance, and reaction time distribution. First, obtain the reaction time distribution data for multiple baseline distances corresponding to each scenario type and each driver target state.

[0175] S402: For each scenario type and each driver target state, calculate the mean reaction time and standard deviation of each benchmark distance based on the reaction time distribution data of multiple benchmark distances corresponding to the scenario type and the driver target state.

[0176] In this step, after the controller obtains the reaction time distribution data of multiple reference distances corresponding to each scenario type and each driver target state, it calculates the mean reaction time and standard deviation of each reference distance for each scenario type and each driver target state based on the reaction time distribution data of multiple reference distances corresponding to that scenario type and that driver target state.

[0177] The mean of all reaction times in the reaction time distribution data is called the reaction time mean. The standard deviation of all reaction times in the reaction time distribution data is called the reaction time standard deviation.

[0178] S403: For each scenario type and each driver target state, interpolation is performed based on the mean and standard deviation of the reaction time for each reference distance corresponding to the scenario type and the driver target state to obtain the reaction time distribution data for each distance. For each distance, a correspondence is established between the scenario type, the driver target state, the distance, and the reaction time distribution data for that distance, and then the data is stored.

[0179] In this step, after the controller obtains the mean and standard deviation of the reaction time for multiple reference distances corresponding to each scenario type and each driver target state, it performs interpolation processing for each scenario type and each driver target state based on the mean and standard deviation of the reaction time for each reference distance corresponding to that scenario type and that driver target state to obtain the reaction time distribution data for each distance.

[0180] In other words, by interpolating the mean reaction time for each baseline distance corresponding to the scenario type and the driver's target state, the mean reaction time for each distance under the same scenario type and driver's target state can be obtained. Similarly, by interpolating the standard deviation of the reaction time for each baseline distance corresponding to the same scenario type and driver's target state, the standard deviation of the reaction time for each distance under the same scenario type and driver's target state can be obtained. Finally, for each distance, the standard deviation and mean reaction time of that distance generate the reaction time distribution data for that distance.

[0181] Then, for each distance, a corresponding relationship is established between the scene type, the driver's target state, the distance and the reaction time distribution data for that distance, and then stored.

[0182] The driver reaction time assessment method provided in this embodiment improves the efficiency of generating this correspondence by interpolating the reaction time distribution data of multiple benchmark distances corresponding to each scenario type and each driver target state, and generating a correspondence between the controller-generated scenario type, driver target state, distance and reaction time distribution.

[0183] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0184] Figure 5 This is a schematic diagram of the structure of an embodiment of the driver reaction time assessment device provided in this application; as shown below. Figure 5 As shown, the driver reaction time assessment device 50 includes components for implementing the aforementioned driver reaction time assessment method, specifically including:

[0185] The acquisition module 51 is used to acquire obstacle type, obstacle motion data, driver initial state, driver eye state, vehicle driving data and evaluation mode. The obstacle motion data includes obstacle distance.

[0186] Processing module 52 is used for:

[0187] The scene type is determined based on the obstacle type and obstacle motion data;

[0188] Determine the driver's target state based on the driver's initial state, the driver's eye state, and vehicle driving data;

[0189] The duration determination module 53 is used to determine the driver's reaction time based on the scenario type, driver target state, evaluation mode, and obstacle distance.

[0190] Furthermore, the processing module 52 is specifically used for:

[0191] If the obstacle type is a vehicle and the obstacle motion data meets the first preset condition, then the scene type is determined to be a following scene.

[0192] If the obstacle type is a vehicle and the obstacle motion data does not meet the first preset condition, then the scene type is determined to be another scene.

[0193] If the obstacle type is a pedestrian and the obstacle motion data meets the second preset condition, then the scene type is determined to be a pedestrian crossing scene.

[0194] If the obstacle type is a pedestrian and the obstacle motion data does not meet the second preset condition, then the scene type is determined to be another scene.

[0195] If the obstacle type is neither a vehicle nor a pedestrian, then the scene type is determined to be another scene.

[0196] Furthermore, if the obstacle type is a vehicle, the obstacle motion data also includes the relative speed of the obstacle and the direction of travel of the obstacle. The first preset condition is: the relative speed of the obstacle is less than a preset speed threshold, the angle between the direction of travel of the obstacle and the direction of travel of the vehicle is less than a preset angle threshold, and the distance of the obstacle is less than a first preset distance threshold.

[0197] If the obstacle type is a pedestrian, the obstacle motion data also includes the pedestrian direction. The second preset condition is: the angle between the pedestrian direction and the vehicle's driving direction is within a preset orthogonal angle range and the obstacle distance is less than the second preset distance threshold.

[0198] Furthermore, the driver's initial state is a normal state, an error reporting state, or an inattentive state, and the inattentive state includes at least one of a drowsy state, a prolonged inattentive state, and a short-term inattentive state.

[0199] The driver's eye state is either a prolonged state of eye closure, a short state of eye closure, or an open state of eye closure;

[0200] Vehicle driving data includes lane departure warning, steering wheel angle, and brake pedal opening. The lane departure warning is used to indicate whether the vehicle has deviated from the current lane.

[0201] Furthermore, the processing module 52 is specifically used for:

[0202] If the driver's initial state is normal, then the driver's target state is determined to be normal.

[0203] If the driver's initial state is an error state, then the driver's target state is determined to be an unknown state;

[0204] If the driver's initial state is one of distraction, the driver's target state is determined based on the state of distraction, the driver's eye state, and vehicle driving data.

[0205] Furthermore, the processing module 52 is specifically used for:

[0206] Based on the state of distraction, the driver's eye state, and vehicle driving data, determine whether the third and fourth preset conditions are met;

[0207] If both the third and fourth preset conditions are met, then the driver's target state is determined to be drowsy and distracted.

[0208] If the third preset condition is met and the fourth preset condition is not met, then the driver's target state is determined to be drowsy.

[0209] If the third preset condition is not met, but the fourth preset condition is met, then the driver's target state is determined to be a distracted state.

[0210] If neither the third nor the fourth preset condition is met, then the driver's target state is determined to be normal.

[0211] Furthermore, the third precondition is: the state of distracted attention includes drowsiness, and the driver's eye state is a prolonged closed-eye state;

[0212] The fourth preset condition is: distracted state including long-term distraction state and short-term distraction state, lane departure warning indicating that the vehicle is deviating from the current lane, steering wheel angle is less than preset angle and brake pedal opening is less than preset opening.

[0213] Furthermore, the duration determination module 53 is specifically used for:

[0214] Based on the scenario type, driver target state, and obstacle distance, as well as the correspondence between scenario type, driver target state, distance, and reaction time distribution data, the target distribution data are determined.

[0215] Based on the pre-defined correspondence between patterns and percentiles, determine the target percentile corresponding to the evaluation pattern;

[0216] The driver's reaction time is determined based on the target distribution data and the target percentile.

[0217] Furthermore, the evaluation model is either a conservative model or a radical model;

[0218] The percentile corresponding to the conservative mode is greater than the percentile corresponding to the radical mode.

[0219] Furthermore, before acquiring obstacle type, obstacle motion data, driver initial state, driver eye state, vehicle driving data and evaluation mode, the acquisition module 51 is also used to acquire reaction time distribution data of multiple reference distances corresponding to each scene type and each driver target state.

[0220] Processing module 52 is also used for:

[0221] For each scenario type and each driver target state, the mean reaction time and standard deviation of each benchmark distance are calculated based on the reaction time distribution data of multiple benchmark distances corresponding to the scenario type and driver target state.

[0222] For each scenario type and each driver target state, interpolation is performed based on the mean and standard deviation of reaction time for each baseline distance corresponding to the scenario type and driver target state to obtain the reaction time distribution data for each distance. For each distance, a correspondence is established between the scenario type, driver target state, distance, and reaction time distribution data for distance, and then the data is stored.

[0223] Furthermore, before determining the driver's reaction time based on the target distribution data and target percentiles, the time determination module 53 is also used for:

[0224] If the driver's target state is unknown, or the scenario type is other scenarios, the preset safety percentile will be used as the updated target percentile.

[0225] Module 53 for determining duration is specifically used for:

[0226] The driver's reaction time is determined based on the target distribution data and the updated target percentiles.

[0227] Furthermore, the duration determination module 53 is also used for:

[0228] If a lidar malfunction or camera malfunction is detected, the driver's reaction time will be updated to the preset time.

[0229] Furthermore, the duration determination module 53 is also used for:

[0230] If the driver's reaction time exceeds the preset safe time threshold, the driver's reaction time will be updated to the preset safe time threshold.

[0231] Furthermore, the duration determination module 53 is specifically used for:

[0232] The scene type, driver target state, evaluation mode, and obstacle distance are input into the reaction time prediction model to obtain the driver's reaction time. The reaction time prediction model is a pre-trained neural network model used to determine the driver's reaction time based on the scene type, driver target state, evaluation mode, and obstacle distance.

[0233] The driver reaction time assessment device provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0234] Figure 6 This is a schematic diagram of the structure of an electronic device provided in this application. Figure 6 As shown, the electronic device 60 includes:

[0235] Processor 61, memory 62, and communication interface 63;

[0236] Memory 62 is used to store executable instructions of processor 61;

[0237] The processor 61 is configured to execute the technical solutions in any of the foregoing method embodiments by executing executable instructions.

[0238] Optionally, the memory 62 can be either standalone or integrated with the processor 61.

[0239] Optionally, when the memory 62 is a device independent of the processor 61, the electronic device 60 may further include:

[0240] Bus 64, memory 62 and communication interface 63 are connected to processor 61 through bus 64 and complete communication with each other. Communication interface 63 is used to communicate with other devices.

[0241] Optionally, the communication interface 63 can be implemented using a transceiver. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write databases, and read-only databases). The memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk drive.

[0242] Bus 64 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0243] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0244] The electronic device is used to execute the technical solutions in any of the foregoing method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0245] This application also provides a readable storage medium storing a computer program thereon, which, when executed by a processor, implements the technical solutions provided in any of the foregoing method embodiments.

[0246] This application also provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the technical solutions provided in any of the foregoing method embodiments.

[0247] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0248] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A driver reaction time length evaluation method characterized by, The method comprises: obtaining an obstacle type, obstacle motion data, a driver initial state, a driver eye state, vehicle driving data and an evaluation mode, wherein the obstacle motion data comprises an obstacle distance; determining a scene type according to the obstacle type and the obstacle motion data; determining a driver target state according to the driver initial state, the driver eye state and the vehicle driving data; determining a driver reaction time according to the scene type, the driver target state, the evaluation mode and the obstacle distance.

2. The method of claim 1, wherein, The determination of the scene type according to the obstacle type and the obstacle motion data comprises: if the obstacle type is a vehicle and the obstacle motion data satisfies a first preset condition, determining that the scene type is a following vehicle scene; if the obstacle type is a pedestrian and the obstacle motion data satisfies a second preset condition, determining that the scene type is a pedestrian crossing road scene.

3. The method of claim 2, wherein, if the obstacle type is a vehicle, the obstacle motion data further comprises a relative speed of the obstacle and a driving direction of the obstacle, and the first preset condition is that the relative speed of the obstacle is less than a preset speed threshold, an included angle between the driving direction of the obstacle and a driving direction of the vehicle is less than a preset angle threshold, and the obstacle distance is less than a first preset distance threshold; if the obstacle type is a pedestrian, the obstacle motion data further comprises a pedestrian direction, and the second preset condition is that an included angle between the pedestrian direction and the driving direction of the vehicle belongs to a preset orthogonal angle range and the obstacle distance is less than a second preset distance threshold.

4. The method of claim 1, wherein, The driver initial state is a normal state, an error reporting state or an attention distraction state, and the attention distraction state comprises at least one of a drowsy state, a long-time distraction state and a short-time distraction state. The driver eye state is a long-time eye closure state, a short-time eye closure state or an eye open state. The vehicle driving data comprises a lane deviation identifier, a steering wheel angle and a brake pedal opening degree, and the lane deviation identifier is used to indicate whether the vehicle deviates from a current lane.

5. The method of claim 4, wherein, The determination of the driver target state according to the driver initial state, the driver eye state and the vehicle driving data comprises: if the driver initial state is the normal state, determining that the driver target state is the normal state; if the driver initial state is the error reporting state, determining that the driver target state is an unknown state; if the driver initial state is the attention distraction state, determining the driver target state according to the attention distraction state, the driver eye state and the vehicle driving data.

6. The method of claim 5, wherein, The determination of the driver target state according to the attention distraction state, the driver eye state and the vehicle driving data comprises: judging whether a third preset condition and a fourth preset condition are established according to the attention distraction state, the driver eye state and the vehicle driving data; if both the third preset condition and the fourth preset condition are established, determining that the driver target state is a drowsy distraction state. if the third preset condition is established and the fourth preset condition is not established, determining that the driver target state is a drowsy state; if the third preset condition is not established and the fourth preset condition is established, determining that the driver target state is a distracted state; if the third preset condition and the fourth preset condition are not established, determining that the driver target state is a normal state.

7. The method of claim 6, wherein, the third preset condition is that the attention dispersion state includes a drowsy state, and the driver eye state is a long-time closed-eye state; the fourth preset condition is that the attention dispersion state includes a long-time distracted state and a short-time distracted state, the lane deviation identifier indicates that the vehicle deviates from the current lane, the steering wheel rotation angle is less than a preset rotation angle, and the brake pedal opening degree is less than a preset opening degree.

8. The method of claim 1, wherein, The method further comprises: determining target distribution data according to the scene type, the driver target state, and the obstacle distance, and a corresponding relationship between scene type, driver target state, distance, and reaction time distribution data; determining a target percentile corresponding to the evaluation mode according to a preset corresponding relationship between mode and percentile; determining the driver reaction time according to the target distribution data and the target percentile.

9. The method of claim 8, wherein, The evaluation mode is a conservative mode or an aggressive mode; The percentile corresponding to the conservative mode is greater than the percentile corresponding to the aggressive mode.

10. The method according to any one of claims 1 to 9, characterized in that, Before the obstacle type, obstacle motion data, driver initial state, driver eye state, vehicle driving data, and evaluation mode are obtained, the method further comprises: obtaining reaction time distribution data of a plurality of reference distances corresponding to each scene type and each driver target state; for each scene type and each driver target state, calculating the reaction time mean and the reaction time standard deviation of each reference distance according to the reaction time distribution data of the plurality of reference distances corresponding to the scene type and the driver target state; for each scene type and each driver target state, performing interpolation processing according to the reaction time mean and the reaction time standard deviation of each reference distance corresponding to the scene type and the driver target state to obtain the reaction time distribution data of each distance, and for each distance, establishing a corresponding relationship between the scene type, the driver target state, the distance, and the reaction time distribution data of the distance and storing it.

11. The method of claim 8, wherein, Before determining the driver reaction time according to the target distribution data and the target percentile, the method further comprises: if the driver target state is an unknown state or the scene type is other, a preset safety percentile is used as an updated target percentile; determining the driver reaction time according to the target distribution data and the updated target percentile. The method further comprises:

12. The method according to any one of claims 1 to 9, characterized in that, ​ If a laser radar fault or a camera fault is detected, the driver reaction time is updated to a preset time length.

13. The method according to any one of claims 1 to 9, characterized in that, The method further comprises: If the driver reaction time is greater than a preset safety time length threshold, the driver reaction time is updated to the preset safety time length threshold.

14. The method of claim 1, wherein, The driver reaction time is determined according to the scene type, the driver target state, the evaluation mode and the obstacle distance, comprising: The scene type, the driver target state, the evaluation mode and the obstacle distance are input into a reaction time prediction model to obtain the driver reaction time, the reaction time prediction model being a neural network model pre-trained for determining the driver reaction time according to the scene type, the driver target state, the evaluation mode and the obstacle distance.

15. A driver reaction time length evaluation device characterized by comprising: A device for implementing the driver reaction time evaluation method of any one of claims 1 to 14.

16. An electronic device, comprising: Comprise: A processor, a memory, a communication interface; The memory is used to store executable instructions of the processor; Wherein, the processor is configured to execute the driver reaction time evaluation method of any one of claims 1 to 14 by executing the executable instructions.

17. A readable storage medium, having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the driver reaction time evaluation method of any one of claims 1 to 14.

18. A computer program product, characterised in that, Comprise a computer program, the computer program is executed by the processor to implement the driver reaction time evaluation method of any one of claims 1 to 14.

Images