Methods for evaluating the driving safety of vehicle drivers

Abstract

This invention provides a method for evaluating the driving safety of vehicle drivers. [Solution] In the method for evaluating the driving safety (FB) of a vehicle (1) according to the present invention, the driver of the vehicle (1) is identified as a person inside the vehicle (1), the driver's individual physiological characteristics and driving-specific characteristics, as well as the driver's media usage characteristics, are acquired, processed, and stored over a preset period of time during driving operations, a driving safety (FS) value is calculated based on the acquired characteristics, and recommendations or warnings are output inside the vehicle (1) according to the calculated driving safety (FS) value.

Description

Technical Field

[0001] The present invention relates to a method for evaluating the driving safety of a vehicle driver, where the driver is identified as a person in the vehicle.

Background Art

[0002] From the following Patent Document 1, a method for identifying the usage behavior of an automotive system is known. The automotive system provides functions that can be used by the driver. In this method, corresponding data regarding the usage of the functions is transmitted to a central computer via a communication device arranged inside the vehicle. The following Patent Document 2 discloses a method for detecting that the driving ability of a vehicle driver is gradually decreasing. Here, the individual driving-specific behavior, physiological characteristics, and emotional characteristics of the driver, as well as the health data of the driver, are acquired, and these are combined and evaluated to identify the driving ability.

[0003] The following Patent Document 3 discloses a system including a motion sensor that can mainly map the movements of a driver in real time during driving. Based on these data, events leading to driver distraction can be detected.

[0004] The following Patent Document 4 relates to a computer-implemented method for playing media content, where the mental state of a user is detected based on sensor data.

[0005] The following Patent Document 5 relates to a method and apparatus for detecting dangerous vehicle events and encouraging the use of functions for avoiding the occurrence of dangerous events.

[0006] The following Patent Document 6 relates to a hands-free system fixed to a vehicle's sun visor and communicating with a remote hands-free system.

Prior Art Documents

Patent Documents

[0007] [Patent Document 1] German Patent Application Publication No. 10, 2012 014 191, Specification A1 [Patent Document 2] German Patent Application Publication No. 10 2021 003 489 Specification A1 [Patent Document 3] U.S. Patent Application Publication No. 2016 0 046 298, Specification A1 [Patent Document 4] U.S. Patent Application Publication No. 2021 0 398 562 Specification A1 [Patent Document 5] U.S. Patent Application Publication No. 2022 0 242 233 A1 Specification [Patent Document 6] U.S. Patent Application Publication No. 2007 0 275 770 Specification A1 [Overview of the Initiative] [Problems that the invention aims to solve]

[0008] The object of the present invention is to provide a method for evaluating the driving safety of a vehicle driver. [Means for solving the problem]

[0009] This problem is solved by a method having the features described in claim 1, according to the present invention.

[0010] Advantageous embodiments of the present invention are subject to the dependent claims.

[0011] According to the present invention, in a method for evaluating the driving safety of a vehicle driver, the vehicle driver is identified as a person inside the vehicle, and the driver's individual physiological characteristics, driving-specific characteristics, and media utilization characteristics are acquired, processed, and stored over a preset time during driving. Furthermore, a driving safety value is calculated based on the acquired characteristics, and recommendations or warnings are output within the vehicle according to the calculated driving safety value. Furthermore, driving safety is mapped as a function of vehicle and media utilization characteristics. In particular, the individual driving safety of a driver can be mapped based on vehicle utilization characteristics and media utilization characteristics. Based on the performed function approximation, vehicle utilization characteristics and media utilization characteristics that have a particularly negative impact on the driving safety value are identified. For this purpose, for example, a method can be used in which the characteristics that have the strongest influence on the function value for driving safety evaluation are applied to each function approximation.

[0012] By using this method, the risk of driver distraction can be reduced, particularly with regard to the use of media, thereby reducing the risk of accidents for the vehicle and, in some cases, for road users in the immediate vicinity of the vehicle.

[0013] In particular, the risk of accidents can be significantly reduced by detecting individual vehicle and media use that increases the personal risk of being involved in a traffic accident and / or causing a traffic accident. This is because media use, especially inside a vehicle, can cause distraction. In other words, by applying this method, drivers can adapt their behavior and thereby reduce the risk of accidents.

[0014] To this end, in one embodiment of this method, the driver's physiological characteristics are calculated based on the driver's heart rate, respiratory rate, and skin conductance. Based on these physiological characteristics, it is possible to determine whether the driver is relatively relaxed or stressed. In particular, under stressful conditions, the risk of accidents may increase because, for example, the driver may react hastily and / or overlook other road users.

[0015] In a further embodiment, driver-specific characteristics are calculated based on the vehicle's acceleration, wheel rotation speed, engine speed, driver assistance interventions, the vehicle's lateral position within the lane, and / or the distance to the vehicle ahead. Based on these driver-specific characteristics, a correlation can be established between driver distraction and the driver's driving style caused by that distraction. When the distance to the vehicle ahead decreases, and / or when the vehicle crosses a lane marking, it can be assumed that the vehicle's driver is distracted, particularly due to the use of certain media, such as the operation of a mobile device.

[0016] In possible variations of this method, media usage characteristics are calculated based on the operation of mobile terminal devices, the operation of the vehicle's infotainment system, and / or the set volume of media playback within the vehicle. For example, if the volume of media playback is relatively high, the driver of that vehicle is more distracted from driving events than other drivers, so even with the same preconditions, the driving safety evaluations of the two drivers will differ.

[0017] In one embodiment, the driver's media use is analyzed using a computer-assisted speech analysis method. In particular, media use can be analyzed using computer-assisted speech analysis in relation to its content and the mood it brings to the driver based on that content, thereby evaluating the driver's driving safety during vehicle operation and, depending on the situation, warnings can be given about driver distraction due to this media use.

[0018] Therefore, one embodiment of the present method is capable of identifying the driver's emotion based on the acquired face signal, voice signal, and / or physiological signal. By relying on the identified driver's emotion, it becomes possible to relatively reliably determine that the driver is distracted by media use.

[0019] Furthermore, in one embodiment, the present method is adapted to recommend alternative media use in the vehicle to the driver based on at least the value of driving safety predicted using the media use signal. For this purpose, in particular, the media use of the vehicle driver is analyzed in real time. At this time, a value for driving safety evaluation is calculated, and for example, depending on the calculated physiological value of the driver, it is recommended that the driver consume, i.e., listen to, a relaxing medium such as music.

[0020] Furthermore, in one possible embodiment, the individual physiological characteristic values and driving-specific characteristic values of the driver, as well as the media use characteristic values of the driver, acquired over a preset time during driving operation, are transmitted to a central computer unit connected to the vehicle in a data-technical manner.

[0021] As an alternative or addition to the processing and storage of the characteristic values acquired in the vehicle, these characteristic values can also be transmitted to the central computer unit for aggregation, processing, and storage. At this time, the vehicles of the vehicle fleet transmit the respectively acquired characteristic values to the central computer unit in order to identify the characteristic values and, in particular, to identify factors related to the vehicle fleet, such as media use and respective distraction.

[0022] Hereinafter, embodiments of the present invention will be described in detail based on the drawings.

Brief Description of the Drawings

[0023] [Figure 1] It is a schematic diagram of an apparatus for implementing a method for evaluating the driving safety of a vehicle driver. [Figure 2]This figure shows a schematic one-dimensional graph of driving safety dependent on media usage. [Modes for carrying out the invention]

[0024] In all of the figures, corresponding parts are denoted by the same reference numeral.

[0025] Figure 1 shows vehicle 1 and the apparatus for performing a method for evaluating the driving safety FB of the driver of vehicle 1 (not shown in detail), and Figure 2 shows graph D of the driving safety FS which depends on the media used MN.

[0026] In general, driver distraction while operating vehicle 1 is known to account for a relatively large proportion of traffic accidents. In this case, media use MN in particular, i.e., the use of mobile devices, especially smartphone operation, podcast settings, music, and / or operation of the vehicle 1's infotainment system, can be a cause of driver distraction.

[0027] The method described below is used to make the driver of vehicle 1 aware of which individual media usage MNs increase their personal risk of being involved in and / or causing a traffic accident. Furthermore, this method allows the driver to adapt their behavior and thereby reduce the risk of an accident.

[0028] The device comprises a control unit 2, for example a further control unit 3 of the assistant system, at least one in-vehicle microphone 4, at least one vital sensor 5, at least one in-vehicle camera 6, at least one exterior camera 7, and a central computer unit 8 to which the vehicle 1, in particular the control unit 2, is data-technically connected. The vehicle 1 belongs to a vehicle fleet to which other vehicles (not shown) belong, and these vehicles are also data-technically connected to the central computer unit 8.

[0029] In particular, signals acquired by the in-vehicle microphone 4, vital sensors 5, in-vehicle camera 6, exterior camera 7, and further control unit 3 are aggregated and recorded in control unit 2. At this time, the interaction between the driver and vehicle 1 is recorded, or rather stored, in control unit 2.

[0030] The driver of vehicle 1 is identified based on a personalized vehicle key and / or based on the input of a personal identification number to the vehicle, based on a number of methods, for example, by image signals acquired by an in-vehicle camera 6 and / or an external camera 7, and based on a well-known method, for example, by using computer-assisted vision related to facial recognition. In particular, since the driver is identified as a person (individual), the acquired signals and the values ​​and data acquired based on those signals can be uniquely assigned to that person. For example, the driver's personal information and characteristics, such as age and / or whether the driver is a smoker, may or can be stored in the personal driver profile.

[0031] Therefore, individual physiological and driving-specific characteristic values / data can be calculated (identified) within the vehicle 1 based on the signals acquired by the aforementioned sensor systems installed within the vehicle 1, and processed by the control unit 2.

[0032] For example, physiological characteristic values / data such as heart rate, respiratory rate, and skin conductance can be calculated based on signals acquired from at least one vital sensor 5. Alternatively or additionally, these characteristic values / data can be calculated based on signals acquired from optical and / or electronic sensors within the vehicle 1 or in the vehicle seat.

[0033] Driver-specific characteristics / data, particularly those related to driving dynamics, can be calculated based on signals acquired from the vehicle's acceleration sensor, as well as signals acquired from other sensors, such as wheel rotation speed and / or engine speed. Based on the acquired and processed signals, lateral acceleration, longitudinal acceleration, velocity distribution, maximum engine speed, and engine speed distribution can also be calculated.

[0034] Furthermore, based on existing information (available information) from the additional control unit 3, driver-specific characteristic values / data can also be extracted. For example, information on many driver assistance interventions, such as initiated emergency braking and steering wheel intervention for lane keeping, as well as information on the lateral positioning of vehicle 1 within the lane and / or information on the distance to the preceding vehicle selected by the driver of vehicle 1, can be used.

[0035] Furthermore, the driver's emotions can be detected (identified), for example, based on facial signals, voice signals, and / or physiological signals acquired using the corresponding sensor system in the vehicle 1, particularly the in-vehicle camera 6. For example, the driver's physiological stress response can be detected.

[0036] Characteristic values / data related to a driver's unique driving style or individual driver's unique driving behavior can be identified using a variety of methods. For example, driving behavior can be classified based on acquired sensor signals.

[0037] Furthermore, emotional feedback from other road users around Vehicle 1 could be used to evaluate the individual driving style or behavior of the driver of Vehicle 1.

[0038] In this method for evaluating the driving safety of the driver of vehicle 1, characteristic values / data related to the driver's individual physiological, emotional, driver-specific driving dynamics, and driving behavior-specific information are recorded and aggregated in the vehicle's control unit 2 over a relatively long, pre-set period of time.

[0039] For the driver of Vehicle 1, driving values ​​for the driving safety evaluation FB, i.e., driving ability parameters, are calculated (ermittelt) from the driver's unique characteristic space (Merkmalsraum). These values ​​for the driving safety evaluation FB are, so to speak, an evaluation of the characteristics of the driver's driving style, and characterize or evaluate the safety of the driver's driving style.

[0040] Furthermore, individual vehicle usage and, in particular, media usage MN are identified based on signals acquired by the vehicle's sensor system. Vehicle usage includes actions such as turning on the air conditioner or opening the sliding roof. In this case, media usage characteristic values ​​are calculated.

[0041] As media usage MN, the driver's mobile terminal device, i.e., operation of a smartphone, podcast settings, operation of music and / or the infotainment system of vehicle 1, and selected volume for media playback are detected based on signals acquired by sensor systems also installed in vehicle 1.

[0042] To further differentiate media usage MN, for example, content and emotion can be analyzed using computer-aided speech analysis methods.

[0043] In a further embodiment of this method, the characteristic space described above can be extended using additional personal physiological and driver-specific characteristic values / data.

[0044] Based on vehicle usage characteristics and media usage characteristics, it is possible to create individual driver mappings for the driving safety evaluation FB as a function of vehicle usage characteristics and media usage characteristics.

[0045] For this purpose, a heuristic function approximation, such as a linear mapping of media usage characteristic values ​​to a target value of the driving safety evaluation FB, can be used. Alternatively or additionally, a machine learning method can be used to learn or train the function approximation in vehicle 1. For this purpose, vehicle usage characteristics and media usage characteristics are used as input values, and the driving safety evaluation FB is used as the target value. This allows the machine learning algorithm to identify the function approximation that best maps the characteristic values ​​to the relevant target value.

[0046] Based on function approximation, it is possible to identify vehicle usage characteristics and media usage characteristics that negatively affect individual driving safety evaluations (FB). For example, a method that can identify the characteristics that most strongly influence the function value, so-called feature analysis, can be applied to each function approximation.

[0047] If individual vehicle use and media use MN occur during the operation of vehicle 1 that negatively affect the driving safety FS, vehicle 1 can issue acoustic, visual, and / or tactile warnings to the driver. To this end, the current individual vehicle use and media use MN are analyzed in real time and mapped as values ​​of the driving safety FS using function approximation. If it is determined that the value of the driving safety FS falls below a predetermined threshold, visual, acoustic, and / or tactile warnings are output from vehicle 1.

[0048] In a further embodiment of this method, an action option may be proposed to the driver as an alternative to or addition to a warning, which does not substantially negatively impact the driver safety FS, but in some cases improves the driver safety FS.

[0049] Furthermore, in this method, individual mappings and / or basic characteristic values ​​are transmitted from vehicle 1 to a central computer unit 8, which may be a so-called cloud or a vehicle manufacturer's data center, via wireless communication K. The characteristic values ​​are aggregated and processed here to identify relevant characteristic values ​​for vehicle 1 and other vehicles in the vehicle fleet, particularly regarding driving safety FS during media usage MN.

[0050] In one embodiment, the driver is driving a relatively high-end luxury car, referred to as Vehicle 1, and switches on the infotainment system of Vehicle 1. The driver selects a podcast to play in Vehicle 1. Based on audio analysis performed on the podcast, it is identified that the podcast is the latest stock market report of a particular company.

[0051] Based on function approximation, if the driving safety FS (Feasibility Study) is predicted to be extremely poor for characteristic values ​​such as "stock market report of a specific company," "increased resting heart rate," and "increased skin conductance," then another podcast or relaxing music is suggested to the driver as an alternative.

[0052] In the embodiment shown in Figure 2, graph D shows the driving safety evaluation FB assigned to each driver during media usage MN.

[0053] For drivers whose driving safety evaluation FB is shown by a solid line, the driving safety FS reaches its highest value when the media usage MN value is zero, that is, when there is no media usage MN during the driving operation of vehicle 1. This highest value is indicated by the star S1.

[0054] In contrast, for another driver whose driving safety evaluation FB is shown by a dashed line, the driving safety FS value increases with the increase in the media usage MN value.

[0055] The media usage MN, particularly its characteristic value, may be, for example, the set volume for media playback in vehicle 1.

[0056] For drivers whose driving safety rating FB is shown by a solid line, turning on the infotainment system may lead to a decrease in the driving safety FS value. For other drivers, as shown by the additional star S2 as an example, such a situation may lead to an increase in the driving safety FS value with increasing volume, resulting in an increase in driving safety FS during the operation of vehicle 1.

Claims

1. A method for evaluating the driving safety (FB) of the driver of a vehicle (1), wherein the driver of the vehicle (1) is identified as a person inside the vehicle (1), The individual physiological characteristics and driving-specific characteristics of the driver, as well as the driver's media usage characteristics, are acquired, processed, and stored over a predetermined period of time during the driving operation. Based on the characteristic values ​​obtained, the driving safety (FS) value is calculated. Depending on the calculated value of the driving safety (FS), a recommendation or warning is output within the vehicle (1). The driver's driving safety is mapped as a function of the vehicle usage characteristic value and the media usage characteristic value. Based on the performed function approximation, the vehicle utilization characteristic value and the media utilization characteristic value that affect the value of the driving safety (FS) are identified. A method characterized by the following:

2. The physiological characteristics of the driver are calculated based on the driver's heart rate, respiratory rate, and skin conductance. The method according to claim 1, characterized in that

3. The driver's characteristic values ​​are calculated based on the vehicle's (1) acceleration, wheel rotation speed, engine speed, driver assistance intervention, the vehicle's (1) lateral position within the lane, and / or the distance to the vehicle ahead. The method according to claim 1 or claim 2, characterized in that...

4. The driver's media usage characteristics are calculated based on the operation of the mobile terminal device, the operation of the infotainment system of the vehicle (1), and / or the set volume of media playback within the vehicle (1). The method according to any one of claims 1 to 3, characterized in that

5. The driver's media usage (MN) is analyzed using computer-aided speech analysis. The method according to any one of claims 1 to 4, characterized in that

6. Based on the acquired facial signals, voice signals, and / or physiological signals, the driver's emotions are identified. The method according to any one of claims 1 to 5, characterized in that

7. Based on the predicted driving safety value using at least the media usage signal, the driver is recommended to use an alternative media in the vehicle (1). The method according to any one of claims 1 to 6, characterized in that

8. During driving operations, the individual physiological characteristics and driving-specific characteristics of the driver, as well as the driver's media usage characteristics, acquired over a predetermined period of time, are transmitted to a central computer unit (8) connected to the vehicle (1) in a data-technical manner. The method according to any one of claims 1 to 7, characterized in that

Images