Method for determining driver behavior

Abstract

The invention relates to a method for determining a driver behavior, a method for controlling a vehicle depending on the driver behavior, a computer program product and a vehicle. The method for determining a driver behavior according to the invention comprises the following steps: S1: detecting driving information of a vehicle (1) controlled by a driver; S2: extracting from the driving information a sequence specific for a first driving situation; S3: determining a first parameter by means of a preset first function depending on the first sequence extracted in step S2; S4: determining a second parameter by means of a preset first function depending on the second sequence extracted in step S2; S5: determining the driver behavior by evaluating a distribution of the first parameter and the second parameter.

Description

Technical Field

[0001] This invention relates to a method for determining driver behavior, a method for controlling a vehicle based on driver behavior, a computer program product, and a vehicle. Background Technology

[0002] Systems and methods for identifying vehicle drivers are known from DE 102016121768A1. These systems and methods include the analysis of sequences of vehicle initiation behaviors, such as when doors are opened, closed, seatbelts are fastened, and / or ignition switches are operated, as well as the analysis of long-term behavioral patterns to more appropriately examine driver identification. Longer-term behavioral patterns include acceleration and braking behaviors, behavior at stop signs, speed controller use, and various other behaviors. Summary of the Invention

[0003] The method according to the present invention for determining driver behavior includes the following steps:

[0004] S1: Detects driving information of the vehicle controlled by the driver;

[0005] S2: Extract a sequence specific to the first driving condition from the driving information;

[0006] S3: Determine the first parameter based on the first sequence extracted in step S2 using a preset first function;

[0007] S4: Determine the second parameter based on the second sequence extracted in step S2 using a preset first function;

[0008] S5: Determine driver behavior by evaluating the distribution of the first and second parameters.

[0009] Here, "driver behavior" is understood as the way a driver behaves while driving a vehicle, such as acceleration and / or braking.

[0010] Because the first and second parameters are determined by means of a preset first function based on a sequence specific to a first driving condition, the method according to the invention can realize the determination of driving condition-specific driver behavior. Driving condition-specific driving behavior can, for example, be used with appropriate speed and / or spacing adjustments to improve passenger comfort and / or assess changes in the state of charge of the energy storage device during planned driving and / or planned effective driving distance.

[0011] Preferably, the method according to the present invention includes the following steps:

[0012] S2a: Extract a sequence specific to the second driving condition from the driving information;

[0013] S3a: The third parameter is determined by using a preset second function based on the third sequence extracted in step S2a;

[0014] S4a: The fourth parameter is determined based on the fourth sequence extracted in step S2a using a preset second function.

[0015] In step S5, the distribution of the third and fourth parameters is considered when determining driver behavior. This enables the characterization of the driver's intervention behaviors and helps to more accurately determine driver behavior.

[0016] Preferably, when determining the third and fourth parameters in steps S3a and S4a, the preset second function is parameterized at least in part by means of parameters derived from the first and / or second parameters. This improves the accuracy in determining the third and fourth parameters.

[0017] Preferably, the preset first and second functions include at least partially identical function instructions. This allows for the use of the same evaluation criteria and / or the same terms in the driver model during acceleration and braking, thereby improving accuracy and / or reducing computational costs in determining parameters.

[0018] The method for controlling a vehicle based on driver behavior according to the present invention includes the following steps:

[0019] A1: Parameterize the preset vehicle control function using parameters representing driver behavior;

[0020] A2: Control the vehicle using the vehicle control function parameterized in S1.

[0021] The computer program product according to the invention causes, when run by a computing unit, the computing unit to run the method according to the invention.

[0022] The vehicle according to the invention includes

[0023] - Multiple sensors used to detect driving information;

[0024] - A computing unit, configured and arranged to run a computer program product according to the invention; and

[0025] - A control unit, configured and set up to control the vehicle based on driver behavior determined by means of a computing unit.

[0026] Because the control unit is configured and set up to control the vehicle based on driver behavior determined by means of a computing unit, driver behavior can be simulated during the operation of an autonomous or partially autonomous vehicle, thereby improving driving comfort, for example.

[0027] Other advantageous embodiments of the invention are described below. Attached Figure Description

[0028] Preferred embodiments are described in detail with reference to the accompanying drawings. They are shown here:

[0029] Figure 1 An embodiment of a vehicle according to the present invention is shown;

[0030] Figure 2 An embodiment of a method according to the invention for determining driver behavior is shown;

[0031] Figure 3 A schematic diagram illustrating driving information, including multiple sequences specific to different driving conditions; and

[0032] Figure 4 An embodiment of a method for controlling a vehicle according to the present invention is shown. Detailed Implementation

[0033] exist Figure 1 The vehicle 1 shown is a sedan and includes multiple sensors 2 for detecting driving information. In this embodiment, these are an acceleration sensor, a speed sensor, and a camera for detecting vehicles traveling ahead. Furthermore, the vehicle 1 includes a computing unit 3 and a control unit 4, configured to control the vehicle 1 based on driver behavior determined by the computing unit 3.

[0034] The computing unit 3 is configured and set up to run a computer program product, which causes the computer program product to run on Figure 2 The method for determining driver behavior is shown in the diagram. In the first step S1 of the method, the calculation unit 3 causes the sensor 2 to detect driving information during driver-controlled driving of the vehicle 1. In this embodiment, the driving information includes a time-varying curve of the vehicle acceleration G1 and optically detected distance and relative speed relative to a preceding vehicle. The time-varying curve of the vehicle acceleration G1 is shown in the diagram. Figure 3 It is illustrated in the diagram.

[0035] In the second step S2 of the method, the calculation unit 3 extracts a sequence specific to the first driving situation from the driving information. In this embodiment, this is an acceleration sequence G2. Each acceleration sequence G2 here includes acceleration data, vehicle speed data, distance data relative to a preceding vehicle, and relative speed data relative to a preceding vehicle during the acceleration process of vehicle 1. In another step S2a, the calculation unit 3 extracts a sequence specific to the second driving situation from the driving information. In this embodiment, this is a braking sequence G3. Each braking sequence G3 here includes braking delay data, vehicle speed data, distance data relative to a preceding vehicle, and relative speed data relative to a preceding vehicle during the braking process of vehicle 1.

[0036] In additional steps S2b and S2c, the calculation unit 3 selects a sequence from the sequences extracted in steps S2 and S2a according to a preset selection criterion. In this embodiment, according to the selection criterion, only sequences in which braking or acceleration of vehicle 1 causes a speed change of at least 10 km / h are selected. In this embodiment, this results in a reduction in the computational cost of subsequent steps of the method.

[0037] In the third step S3 of the method, the calculation unit 3 determines a first parameter based on the first sequence extracted in step S2 and selected in step S2b using a preset first function. In this embodiment, the calculation unit 3 performs a compensation calculation, in which the calculation unit matches the first function to the selected first acceleration sequence G2. In this embodiment, the first parameter is the maximum acceleration, the target velocity, and the acceleration exponent.

[0038] In another step S3a, the calculation unit 3 determines a third parameter based on the third sequence extracted in step S2a and selected in step S2c using a preset second function. Here, to improve accuracy and reduce computational cost, the preset second function is parameterized using parameters derived from the first and second parameters. In this embodiment, the calculation unit 3 extracts the third parameter from the selected braking sequence G3 using the second function. The third parameter includes a time interval parameter relative to the preceding vehicle and a braking delay for driver comfort.

[0039] Here, the first and second functions applied in steps S3 and S3a include partially identical function instructions, such as parameter correlations preset through the same mathematical expressions. This allows the same driver model and / or evaluation criteria to be applied during acceleration and braking, and reduces computational costs.

[0040] In the fourth step S4 of the method, calculation unit 3 determines the second parameter based on the second sequence extracted in step S2 and selected in step S2b using a preset first function. In another step S4a, calculation unit 3 determines the fourth parameter based on the fourth sequence extracted in step S2a and selected in step S2c using a preset second function. The execution of steps S4 and S4a occurs here in a manner similar to steps S3 and S3a.

[0041] In the embodiment, the calculation unit 3 extracts multiple additional parameters from multiple additional selected acceleration sequences and braking sequences in multiple additional steps S3n, S4n (not shown).

[0042] In the fifth step S5 of the method, the computation unit 3 determines driver behavior by evaluating the distribution of parameters extracted in steps S3, S3a, S3n, S4, S4a, and S4n. In this embodiment, this occurs through the formation of parameters of the same type, such as the median of maximum acceleration. Parameters characterizing driver behavior are obtained from the median formation, which are suitable for describing and replicating driving behavior.

[0043] With the help of Figure 4 The control shown in Figure 1 The method for applying this determined driver behavior to vehicle 1 is shown in the diagram. To this end, in the first step A1, calculation unit 3 parameterizes a preset vehicle control function using parameters representing the driver behavior. Then, control unit 4 controls vehicle 1 using the vehicle control function parameterized in step A1.

Claims

1. A method for determining driver behavior, comprising the following steps: S1: Detect driving information of the vehicle (1) controlled by the driver; S2: Extract a sequence specific to the first driving condition from the driving information; S3: Determine the first parameter based on the first sequence extracted in step S2 using a preset first function; S4: Determine the second parameter based on the second sequence extracted in step S2 using a preset first function; S5: Determine driver behavior by evaluating the distribution of the first and second parameters.

2. The method according to claim 1, comprising the following steps: S2a: Extract a sequence specific to the second driving condition from the driving information; S3a: The third parameter is determined by using a preset second function based on the third sequence extracted in step S2a; S4a: The fourth parameter is determined based on the fourth sequence extracted in step S2a using a preset second function. In step S5, the distribution of the third and fourth parameters is considered when determining the driver's behavior.

3. The method according to claim 2, wherein when determining the third parameter and / or the fourth parameter in steps S3a and / or S4a, the preset second function is parameterized at least in part by means of parameters derived from the first parameter and / or the second parameter.

4. The method according to any one of the preceding claims, comprising the following steps: S2b: Select a sequence from the sequence extracted in step S2 according to a preset selection criterion, wherein the first parameter and the second parameter are determined according to the selected sequence in steps S3 and S4.

5. The method according to claim 2, wherein the preset first function and the preset second function comprise at least partially identical function instructions.

6. The method according to any one of claims 1 to 3, wherein the driving information includes a curve of vehicle speed and / or vehicle acceleration (G1) with respect to time.

7. The method according to any one of claims 1 to 3, wherein the driving information includes relative speed and / or distance relative to a vehicle traveling ahead.

8. A method for controlling a vehicle (1) based on driver behavior, said driver behavior being determined according to any one of claims 1 to 7, comprising the following steps: A1: Parameterize the preset vehicle control function using parameters representing driver behavior; A2: The vehicle is controlled by means of the vehicle control function parameterized in A1 (1).

9. A computer program product, when run by a computing unit (3), wherein the computing unit (3) causes to perform the method according to any one of claims 1 to 7.

10. A vehicle (1), comprising: - Multiple sensors used to detect driving information (2); - A computing unit (3), which is configured and set up to run the computer program product according to claim 9; and - Control unit (4), which is configured and set to control the vehicle (1) based on driver behavior determined by means of the computing unit (3).

Images