KR-20260063306-A - Method And Apparatus for Path Prediction Based On Driver Intention

KR20260063306AKR 20260063306 AKR20260063306 AKR 20260063306AKR-20260063306-A

Abstract

A method and apparatus are disclosed for an autonomous driving system to perform path prediction based on a driver's driving intention. According to one aspect of the present disclosure, a method for predicting a future path of a vehicle is provided, comprising: a process of storing driving information of the vehicle—the driving information includes one or more of the vehicle's speed, acceleration, steering angle, steering angle velocity, heading angle, yaw rate, acceleration/braking pedal amount, and gear position—; a process of determining a driver's longitudinal driving intention and lateral driving intention using the driving information; a process of generating a driving speed profile and a driving curvature profile of the vehicle based on the longitudinal driving intention and the lateral driving intention; and a process of calculating a future path of the vehicle based on the driving speed profile and the driving curvature profile.

Inventors

이성욱

Assignees

현대자동차주식회사
기아 주식회사

Dates

Publication Date: 20260507
Application Date: 20241030

Claims (14)

As a method for predicting the future path of a vehicle, A process for storing driving information of the above vehicle - the above driving information includes one or more of the vehicle's speed, acceleration, steering angle, steering angle velocity, heading angle, yaw rate, acceleration/brake pedal amount, and gear position -; A process of determining the driver's longitudinal driving intention and lateral driving intention using the above driving information; A process of generating a driving speed profile and a driving curvature profile of the vehicle based on the above longitudinal driving intention and the above lateral driving intention; and A process of calculating the future path of a vehicle based on the above driving speed profile and the above driving curvature profile. A method including
In paragraph 1, The process of determining the above-mentioned longitudinal driving intention is, A process of determining the longitudinal driving intention as the first longitudinal driving intention when the magnitude of the above acceleration exceeds a preset reference acceleration. Includes, The above first longitudinal driving intention is the driver's intention to accelerate or decelerate rapidly, method
In paragraph 2, The process of determining the above-mentioned longitudinal driving intention is, A process of determining whether the speed is less than or equal to a preset reference speed when the magnitude of the acceleration is less than or equal to the reference acceleration; and A process of determining the longitudinal driving intention as a second longitudinal driving intention when the above speed is less than or equal to the above reference speed, and determining the longitudinal driving intention as a third longitudinal driving intention when the above speed exceeds the above reference speed. Including more, The above second longitudinal driving intention is the driver's intention to drive at a low speed, and The above third longitudinal driving intention is a method in which the driver intends to drive at a speed other than low speed.
In paragraph 3, The process of determining the above-mentioned longitudinal driving intention is, When the above gear position is set to D or R and there is no input from the acceleration/brake pedal, the process of determining the above longitudinal driving intention as the fourth longitudinal driving intention. Including more, The above fourth longitudinal driving intention is a method in which the driver intends to drive creep.
In paragraph 4, The process of determining the above-mentioned lateral driving intention is, A process of determining the lateral driving intention as the first lateral driving intention when the steering angle is less than or equal to a preset first reference steering angle or the steering angular velocity is less than or equal to a preset first reference steering angular velocity; A process of determining the lateral driving intention as a second lateral driving intention when the steering angle exceeds a preset second reference steering angle or the steering angular velocity exceeds a preset second reference steering angular velocity; and A process of determining the lateral driving intention as a third lateral driving intention when the above lateral driving intention does not correspond to the above first lateral driving intention or the above second lateral driving intention. Includes, The above-mentioned first lateral driving intention is an intention by the driver to change the path gradually, and The above second lateral driving intention is a method in which the driver intends to abruptly change the path.
In paragraph 5, The process of determining the above-mentioned lateral driving intention is, When the above lateral driving intention is determined to be a first lateral driving intention, a process of determining whether the sign of the yaw rate is opposite to the sign of the steering angle; and A process of determining the lateral driving intention as a fourth lateral driving intention when the sign of the yaw rate is opposite to the sign of the steering angle. A method that further includes
In paragraph 6, The process of determining the above-mentioned lateral driving intention is, A process of determining whether the sign of the steering angle is opposite to the sign of the steering angular velocity when the above lateral driving intention is determined to be a second lateral driving intention; and A process of determining the lateral driving intention as the fifth lateral driving intention when the sign of the steering angle is opposite to the sign of the steering angular velocity. A method that further includes
In Paragraph 7, The process of generating the above driving speed profile is, A process of generating a driving speed profile using the above-mentioned longitudinal driving intention; and A process of adjusting the driving speed profile using the above lateral driving intention A method including
In paragraph 8, The above driving speed profile consists of an acceleration/deceleration section and a constant speed section, and The process of generating the driving speed profile using the above longitudinal driving intention is a process of determining the length of the acceleration/deceleration section and the length of the constant speed section according to the above longitudinal driving intention.
In Paragraph 9, A method in which the process of adjusting the driving speed profile using the above-mentioned lateral driving intention is the process of adjusting the length of the acceleration/deceleration section according to the above-mentioned lateral driving intention.
In Paragraph 7, The process of generating the above driving curvature profile is, A process of generating a driving curvature profile using the above-mentioned lateral driving intention; and A process of adjusting the driving curvature profile using the above longitudinal driving intention A method including
In Paragraph 11, The above driving curvature profile is, If the above lateral driving intention is determined to be the first lateral driving intention, it is generated in the form of a linear function, and If the above lateral driving intention is determined to be a second lateral driving intention or a third lateral driving intention, it is generated in the form of a constant function, and If the above lateral driving intention is determined to be the fourth lateral driving intention, it is generated in the form of a quadratic function, and A method that is generated in the form of a step function when the above lateral driving intention is determined to be the fifth lateral driving intention.
In Paragraph 12, The process of adjusting the driving speed profile using the above longitudinal driving intention is a process of multiplying the driving curvature profile by a correction factor, A method in which the above correction factor is a value between 0 and 1, determined based on the longitudinal driving intention.
As a device for predicting the future path of a vehicle, At least one memory for storing instructions; and Includes at least one processor, The above at least one processor executes the above instructions, Storing driving information of a vehicle - the driving information includes one or more of the vehicle's speed, acceleration, steering angle, steering angle velocity, heading angle, yaw rate, acceleration/brake pedal amount, and gear position -; Using the above driving information, the driver's longitudinal driving intention and lateral driving intention are determined; Based on the above longitudinal driving intention and the above lateral driving intention, a driving speed profile and a driving curvature profile of the vehicle are generated; A device for calculating the future path of a vehicle based on the above driving speed profile and the above driving curvature profile.

Description

Method and Apparatus for Path Prediction Based on Driver Intention The present disclosure relates to a method and apparatus for path prediction based on a driver's driving intention. More specifically, the present disclosure relates to a method and apparatus for improving path prediction accuracy by performing path prediction based on a driver's driving intention in situations where a vehicle cannot acquire lane information. The following description merely provides background information related to the present embodiment and does not constitute prior art. The autonomous driving system predicts the path of the subject vehicle for path planning and collision avoidance judgments. For example, the autonomous driving system uses the predicted path to calculate the probability of collision between the autonomous vehicle and surrounding objects, and performs driver warnings and avoidance control. If an autonomous vehicle can recognize the lanes of the road it is traveling on, the autonomous driving system can improve path prediction accuracy by utilizing lane information during path prediction. On the other hand, if lanes cannot be recognized, conventional autonomous driving systems predict the vehicle's path based on a kinematic model using the vehicle's driving information (speed, acceleration, yaw rate, steering angle, etc.). In situations where lanes cannot be recognized, conventional path prediction methods calculate the lateral movement and heading angle change of the autonomous vehicle to be larger than the driver's driving intention as the distance from the current point increases when the prediction interval is long (e.g., 4 seconds). In other words, conventional path prediction methods have limitations in predicting paths over long intervals when lanes cannot be recognized. FIG. 1 is a block diagram schematically showing a path prediction device according to one embodiment of the present disclosure. FIG. 2 shows an example of a state transition diagram used by a path prediction device according to one embodiment of the present disclosure to determine a lateral driving intention. FIGS. 3a to 3c are exemplary diagrams illustrating a method in which a profile generation unit determines a vehicle's driving speed profile. FIGS. 4a to 4c are exemplary diagrams illustrating a method in which a profile generation unit determines the driving curvature profile of a vehicle. FIG. 5 is a flowchart illustrating the process of a path prediction device according to one embodiment of the present disclosure generating a future path of a vehicle. FIGS. 6a and 6b are exemplary diagrams for comparing a future path generated by a path prediction method according to one embodiment of the present disclosure with a future path generated by a conventional path prediction method. FIG. 7 is a block diagram schematically illustrating an exemplary computing device that can be used to implement a method or device according to the present disclosure. Some embodiments of the present disclosure are described in detail below with reference to exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the present disclosure, if it is determined that a detailed description of related known components or functions could obscure the essence of the present disclosure, such detailed description is omitted. In describing the components of the embodiments according to the present disclosure, symbols such as first, second, i), ii), a), b), etc., may be used. These symbols are intended only to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the symbols. When a part in the specification is described as 'comprising' or 'having' a component, this means that, unless explicitly stated otherwise, it does not exclude other components but may include additional components. The detailed description set forth below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiment in which the present disclosure can be practiced. In the present disclosure, path prediction refers to the function of an autonomous driving system predicting the future path of an autonomous vehicle (self vehicle). In the present disclosure, a prediction time window refers to a time interval from a current point in time to a future point in time that the autonomous driving system intends to predict. The length of the prediction time window may be expressed in units of time. For example, if the autonomous driving system predicts a path from a current point in time to a future point in time 4 seconds later, the length of the prediction time window is 4 seconds. FIG. 1 is a block diagram schematically showing a pa