EP-4063220-B1 - METHOD FOR DETERMINING DRIVING PARAMETERS AND VEHICLE CONTROL APPARATUS

Inventors

• ZHOU, PING

Dates

Publication Date

20260506

Application Date

20220317

Claims (13)

1. A method for determining driving parameters, comprising: a) acquiring (S10) driving data of a driver; b) extracting (S12) driving features of the driver based on the driving data, wherein the driving features comprise first operation frequency of a first component of a vehicle and second operation frequency of a second component of the vehicle; c) determining (S14), based on the driving features, a first probability that the driver has a first driving style and a second probability that the driver has a second driving style; and d) determining (S16) the driving parameters based on the first probability and the second probability, wherein the driving parameters comprise at least longitudinal acceleration and longitudinal deceleration, wherein step d) comprises: determining a driving style corresponding to a larger probability in the first probability and the second probability; characterized in that step d) further comprises determining the longitudinal acceleration and the longitudinal deceleration respectively as linear functions of an index number D corresponding to the determined driving style, wherein step d) further comprises: determining lane changing duration during automated lane changing of the vehicle as (c2-c3*D) / V t , where V t is a vehicle speed during lane changing of the vehicle, and c2 and c3 are adjustment coefficients.
2. The method according to claim 1, wherein the method further comprises: performing an automated driving operation of the vehicle based on the driving parameters.
3. The method according to claim 1 or 2, wherein the first component is an accelerator pedal, and the second component is a brake pedal.
4. The method according to claim 1, 2 or 3, wherein the driving features further comprise third operation frequency of a steering wheel.
5. The method according to any one claims 1 to 4, wherein the driving features further comprise an expected time for the vehicle to move to a recognizable target ahead.
6. The method according to any one of claims 1 to 5, wherein step c) comprises: calculating the first probability and the second probability by using a logistic regression model, wherein the logistic regression model is trained by using at least part of the driving features.
7. The method according to claim 1, wherein step d) further comprises: determining a constant speed during automated driving of the vehicle as (k1*D + c1)*V max , where V max is a maximum speed limit on a current road section, and k1 and c1 are adjustment coefficients.
8. A vehicle control apparatus, comprising: a data acquisition module (202) configured to acquire driving data of a driver; a feature extraction module (204) configured to extract driving features of the driver based on the driving data, wherein the driving features comprise at least first operation frequency of a first component of a vehicle and second operation frequency of a second component of the vehicle; and a parameter setting module (206) coupled with the feature extraction module and configured to determine, based on the driving features, a first probability that the driver has a first driving style and a second probability that the driver has a second driving style and determine the driving parameters based on the first probability and the second probability, wherein the driving parameters comprise at least longitudinal acceleration and longitudinal deceleration; wherein, the vehicle control apparatus is adapted to perform the method of any one claims 1 to 7.
9. The apparatus according to claim 8, wherein the first component is an accelerator pedal, and the second component is a brake pedal.
10. The apparatus according to claim 8 or 9, wherein the feature extraction module (204) is further configured to: acquire third operation frequency of a steering wheel; and determine an expected time for the vehicle to move to a recognizable target ahead.
11. The apparatus according to any one of claims 8 to 10, wherein the parameter setting module is configured to: train a logistic regression model by using at least part of the driving features; and calculate the first probability and the second probability by using the logistic regression model.
12. The apparatus according to any one of claims 8 to 11, wherein the apparatus is deployed based on a cloud computing system.
13. A non-transitory readable storage medium, storing a group of machine executable instructions, wherein when the machine executable instructions are executed by a processor, a method for determining driving parameters according to any of claims 1 - 7 is implemented.

Description

Technical Field The invention relates to the field of automated driving technologies, and more particularly, to a method for determining driving parameters and a vehicle control apparatus. Background Art With the development of artificial intelligence technologies, automobile manufacturers add an automated driving function as an important module to their products. However, in an existing automated driving function, drivers usually determine automated driving parameters through manual setting. With such a parameter setting method, it is difficult to dynamically adjust automated driving parameters based on driving styles and driving environments of drivers. US 2010/023223 A1 discloses an adaptive vehicle control system that classifies a driver's driving style based on characteristic curve-handling maneuvers and road and traffic conditions. The system includes a plurality of vehicle sensors that detect various vehicle parameters. A maneuver identification processor receives the sensor signals to identify a characteristic maneuver of the vehicle and provides a maneuver identifier signal of the maneuver. The system also includes a traffic and road condition recognition processor that receives the sensor signals, and provides traffic condition signals identifying traffic conditions and road condition signals identifying road conditions. US 2021/107495 A1 discloses methods and systems for determining users' driving habits and pushing service information. The methods may include: obtaining a historical driving record of a user; extracting a driving feature of the user from the historical driving record; determining the driving habit of the user based on the driving feature of the user. Summary of the Invention The subject-matter of the present invention is defined in the independent claims. Further preferred embodiments of the present invention are defined in the dependent claims. According to an aspect of the invention, a method for determining driving parameters is provided, which can dynamically adjust automated driving parameters. For this purpose, the invention provides a technical solution as follows: A method for determining driving parameters includes: acquiring driving data of a driver; extracting driving features of the driver based on the driving data, where the driving features include first operation frequency of a first component of a vehicle and second operation frequency of a second component of the vehicle; determining, based on the driving features, a first probability that the driver has a first driving style and a second probability that the driver has a second driving style; and determining the driving parameters based on the first probability and the second probability, where the driving parameters include at least longitudinal acceleration and longitudinal deceleration. The method further comprises determining the driving parameters based on comparison between the first probability and the second probability: determining a driving style corresponding to a larger probability in the first probability and the second probability; and determining the longitudinal acceleration and the longitudinal deceleration respectively as linear functions of an index number D corresponding to the determined driving style. The determining the driving parameters further includes: determining lane changing duration during automated lane changing of the vehicle as (c2-c3*D)lVt, where Vt is a vehicle speed during lane changing of the vehicle, and c2 and c3 are adjustment coefficients. Optionally, the method further includes: performing an automated driving operation of the vehicle based on the driving parameters. Optionally, the driving features of the driver further include third operation frequency of a steering wheel. Optionally, the driving features of the driver further include an expected time for the vehicle to move to a recognizable target ahead. Optionally, determining a style of the driver based on the driving features includes: calculating the first probability and the second probability by using a logistic regression model, where the logistic regression model is trained by using at least part of the driving features. Optionally, the determining the driving parameters further includes: determining a constant speed during automated driving of the vehicle as (k1*D + c1)*Vmax, where Vmax is a maximum speed limit on a current road section, and k1 and c1 are adjustment coefficients. According to another aspect of the invention, a vehicle control apparatus as defined by claim 8 is provided. Optionally, the first component is an accelerator pedal, and the second component is a brake pedal. Optionally, the feature extraction module is further configured to: acquire third operation frequency of a steering wheel; and determine an expected time for the vehicle to move to a recognizable target ahead. The method for determining driving parameters provided in the invention can dynamically adjust, based on the driving d