US-12623719-B2 - Method and apparatus with vehicle control

US12623719B2US 12623719 B2US12623719 B2US 12623719B2US-12623719-B2

Abstract

A method of controlling a vehicle includes: receiving pieces of data related to steering of the vehicle; detecting, among the pieces of data, target pieces of data determined to satisfy predetermined conditions; based on the target pieces of data and an optimization model, obtaining optimized model parameters that minimize a cumulative error between a predicted yaw rate of a yaw rate model of the vehicle and a measured yaw rate of the vehicle; and updating the yaw rate model of the vehicle by using the optimized model parameters.

Inventors

Hyunsoo CHA
Seho SHIN
Jaehwa Lee

Assignees

SAMSUNG ELECTRONICS CO., LTD.

Dates

Publication Date: 20260512
Application Date: 20240501
Priority Date: 20231019

Claims (20)

1 . A method of controlling a vehicle, the method comprising: receiving pieces of data related to steering of the vehicle; selecting, from among the pieces of data, a subset of the pieces of data, which are target pieces of data selected based on determining that they to satisfy predetermined conditions; based on the target pieces of data and an optimization model, optimizing model parameters that-determined, based on a cumulative error, to minimize the cumulative error between a predicted yaw rate of a yaw rate model of the vehicle and a measured yaw rate of the vehicle, wherein the cumulative error is determined based on multiple pieces of yaw rate error of respective different times; and updating the yaw rate model of the vehicle by using the optimized model parameters.
2 . The method of claim 1 , wherein the obtaining the optimized model parameters comprises applying learning-based optimization to the yaw rate model of the vehicle to determine the optimized model parameters.
3 . The method of claim 1 , further comprising determining whether to execute a calibration optimization system, the determining based on the cumulative error between the predicted yaw rate of the vehicle and the measured yaw rate value of the vehicle.
4 . The method of claim 3 , wherein the determining whether to execute the calibration optimization system is based on a user input indicating that the calibration optimization system is to be executed, the user input received through a user interface of the vehicle.
5 . The method of claim 1 , further comprising updating a control model of the vehicle based on the updated yaw rate model of the vehicle.
6 . The method of claim 5 , wherein the updating the control model of the vehicle comprises applying the updated yaw rate model to a steering wheel controller of the vehicle.
7 . The method of claim 1 , wherein the predetermined conditions comprise a lateral acceleration threshold of the vehicle and a yaw rate change threshold of the vehicle.
8 . The method of claim 1 , wherein the pieces of data related to the steering of the vehicle comprise a lateral acceleration of the vehicle, a yaw rate of the vehicle, a velocity of the vehicle, and a steering angle.
9 . The method of claim 1 , wherein the yaw rate model comprises a dynamics model or a kinematic model, either of which are used for performing calibration corresponding to the steering of the vehicle.
10 . The method of claim 9 , wherein the calibration increases accuracy of predicted yaw rates used to control the steering of the vehicle.
11 . An apparatus for controlling a vehicle, the apparatus comprising: one or more processors configured to: receive pieces of data related to steering of the vehicle, select, from among the pieces of data, a subset of the pieces of data, which are target pieces of data selected based on determining that they to satisfy predetermined conditions, based on the target pieces of data and an optimization model, optimizing model parameters determined, based on a cumulative error to minimize the cumulative error wherein the cumulative error is an error between a predicted yaw rate of a yaw rate model of the vehicle and a measured yaw rate of the vehicle, and wherein the cumulative error is determined based on multiple pieces of yaw error of respective different times, and update the yaw rate model of the vehicle by using the optimized model parameters.
12 . The apparatus of claim 11 , wherein the one or more processors are further configured to apply learning-based optimization to the yaw rate model of the vehicle to determine the optimized model parameters.
13 . The apparatus of claim 11 , wherein the one or more processors are configured to execute an error detector configured to determine whether to execute a calibration optimization system, based on the cumulative error between the predicted yaw rate value of the vehicle and the measured yaw rate value of the vehicle.
14 . The apparatus of claim 13 , wherein the one or more processors are further configured to receive, through a user interface of the vehicle, a user input indicating that the calibration optimization system is to be executed.
15 . The apparatus of claim 11 , wherein the one or more processors are further configured to update a control model of the vehicle based on the updated yaw rate model of the vehicle.
16 . The apparatus of claim 15 , wherein the control model comprises a steering wheel controller of the vehicle.
17 . The apparatus of claim 11 , wherein the predetermined conditions comprise a lateral acceleration threshold of the vehicle and a yaw rate change threshold of the vehicle.
18 . The apparatus of claim 11 , wherein the pieces of data related to the steering of the vehicle comprise a lateral acceleration of the vehicle, a yaw rate of the vehicle, a velocity of the vehicle, and a driver steering angle.
19 . The apparatus of claim 11 , wherein the yaw rate model comprises a dynamics model or a kinematic model, either of which are used for performing calibration corresponding to the steering of the vehicle.
20 . An electronic device of a vehicle, the electronic device comprising: one or more processors; memory storing instructions configured to, when executed by the one or more processors: set a target yaw rate of the vehicle for rotational driving of the vehicle, control a yaw rate of the vehicle by using a yaw rate model of the vehicle to achieve the target yaw rate, acquire data related to autonomous steering of the vehicle, based on data related to steering the vehicle satisfying a predetermined condition, determine whether to update the yaw rate model, wherein the determination is based on a cumulative error between a predicted yaw rate of the yaw rate model and a measured yaw rate of the autonomous vehicle, and based on the determining, update the yaw rate model based on the data; a display configured to display a user interface according to the instructions; wherein the instructions are further configured to cause the one or more processors to: receive pieces of data related to the steering of the vehicle, based on determining that target pieces of data, among the pieces data, satisfy predetermined conditions, optimize model parameters that are determined, based on the cumulative error to, minimize the cumulative error between the predicted yaw rate and the measured yaw rate, wherein the cumulative error comprises a statistic computed from yaw rate errors of respective different times, and update the yaw rate model of the autonomous vehicle by using the optimized model parameters.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit under 35 USC § 119 (a) of Korean Patent Application No. 10-2023-0140714, filed on Oct. 19, 2023, in the Korean Intellectual Property Office, the entire disclosure of which is incorporated herein by reference for all purposes. BACKGROUND 1. Field The following description relates to a method and apparatus with vehicle control. 2. Description of Related Art When designing and applying steering control for a vehicle, accurate prediction of a yaw rate for a steering angle can be beneficial. Movement of the vehicle may be mostly meticulously predicted and controlled when the actual movement of the vehicle, according to a control command, is accurately predicted in terms of designing a controller. With respect to accuracy of the steering control of the vehicle by a control command, calibration may be performed on a preset steering control model in situations such as tire replacement, vehicle modification, road environment change, and so forth. SUMMARY This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. In one general aspect, a method of controlling a vehicle includes: receiving pieces of data related to steering of the vehicle; detecting, among the pieces of data, target pieces of data determined to satisfy predetermined conditions; based on the target pieces of data and an optimization model, obtaining optimized model parameters that minimize a cumulative error between a predicted yaw rate of a yaw rate model of the vehicle and a measured yaw rate of the vehicle; and updating the yaw rate model of the vehicle by using the optimized model parameters. The obtaining the optimized model parameters may include applying learning-based optimization to the yaw rate model of the vehicle to determine the optimized model parameters. The method may further include determining whether to execute a calibration optimization system, and the determining may be based on the cumulative error between the predicted yaw rate of the vehicle and the measured yaw rate value of the vehicle. The determining whether to execute the calibration optimization system may be based on a user input indicating that the calibration optimization system is to be executed, and the user input may be received through a user interface of the vehicle. The method may further include updating a control model of the vehicle based on the updated yaw rate model of the vehicle. The updating of the control model of the vehicle may include applying the updated yaw rate model to a steering wheel controller of the vehicle. The predetermined conditions may include a lateral acceleration threshold of the vehicle and a yaw rate change threshold of the vehicle. The pieces of data related to the steering of the vehicle may include a lateral acceleration of the vehicle, a yaw rate of the vehicle, a velocity of the vehicle, and a steering angle. The yaw rate model may include a dynamics model or a kinematic model, either of which may be used for performing calibration corresponding to the steering of the vehicle. The calibration may increase accuracy of predicted yaw rates used to control the steering of the vehicle. In another general aspect, an apparatus for controlling a vehicle includes one or more processors configured to: receive pieces of data related to steering of the vehicle; detect, among the pieces of data, target pieces of data determined to satisfy predetermined conditions; based on the target pieces of data and an optimization model, obtain optimized model parameters that minimize a cumulative error between a predicted yaw rate of a yaw rate model of the vehicle and a measured yaw rate of the vehicle; and update the yaw rate model of the vehicle by using the optimized model parameters. The one or more processors may be further configured to apply learning-based optimization to the yaw rate model of the vehicle to determine the optimized model parameters. The one or more processors may be configured to execute an error detector configured to determine whether to execute a calibration optimization system, based on the cumulative error between the predicted yaw rate value of the vehicle and the measured yaw rate value of the vehicle. The one or more processors may be further configured to receive, through a user interface of the vehicle, a user input indicating that the calibration optimization system is to be executed. The one or more processors may be further configured to update a control model of the vehicle based on the updated yaw rate model of the vehicle. The control model may include a steering wheel controller of the vehicle. The predetermined conditions may include a lateral accelerati