KR20180138477A - Apparatus and method for detecting object in vehicle - Google Patents

Abstract

According to the present invention, a method for detecting a target vehicle in front of a vehicle comprises the following steps of: calculating a longitudinal position error value with respect to the position of the target vehicle; compensating for a longitudinal position value with respect to the position of the target vehicle based on the longitudinal position error value; calculating a transverse position error value with respect to the target vehicle; and compensating for a transverse position value with respect to the position of the target vehicle based on the transverse position error value.

Description

[0001] APPARATUS AND METHOD FOR DETECTING OBJECT IN VEHICLE [0002]

The present invention relates to an apparatus and method for recognizing an object in a vehicle.

With the development of electronic technology, the strengthening of traffic safety regulations, and the demand of consumers, the application of intelligent systems to vehicles is rapidly increasing. ADAS (advanced driver assistance system) for driver's safety / convenience is applied such as front-and-rear monitoring camera system that simply keeps the driving clock, a system that warns of lane departure, and a system that automatically secures the safety distance from the front car. it started. An active type safety system that prevents the collision or mitigates the collision damage by applying the braking device automatically in the front collision danger situation is applied, which can be attributed to the rapid development of the sensor recognition technology. In addition, interest in recognition technology is increasing due to autonomous driving, which has recently become a focus of attention in the field of automobiles. Prior arts for autonomous driving include forward safety, driving safety, and driving convenience. Here, techniques for fusing sensors such as a camera, a radar, and a lidar are being studied in relation to the environmental perception of autonomous navigation technologies. In order to improve the stability of the autonomous driving, it is important to track the position of the object being tracked.

U.S. Published Patent US 2017-0057494, published on March 02, 2017 entitled " APPARATUS AND METHOD FOR CONTROLLING VEHICLE ". Korean Patent No. 10-1481134, published on November 19, 2014 entitled " System and method for estimating radius of curvature through sensor fusion of autonomous vehicle ".

It is an object of the present invention to provide an object recognition apparatus and method thereof that improves the accuracy of object tracking in a vehicle.

A method for recognizing a target vehicle ahead in a vehicle according to an embodiment of the present invention includes: calculating a longitudinal position error value for the position of the target vehicle; Compensating a longitudinal position value for the position of the target vehicle based on the longitudinal position error value; Calculating a lateral position error value for the position of the target vehicle; And compensating a lateral position value for the position of the target vehicle based on the lateral position error value.

In an embodiment, the longitudinal position error value is the difference between the longitudinal position value in the current cycle and the lateral position value in the previous cycle.

In an embodiment, the compensated longitudinal position value may be proportional to the longitudinal position error value.

In an embodiment, the lateral position error value may be calculated using the longitudinal position value of the target vehicle, the heading angle to the lateral position value of the target vehicle, and the side slip angle of the target vehicle.

In an embodiment, the method may further include calculating the difference between the side slip angle of the target vehicle in the current cycle and the side slip angle of the target vehicle in the previous cycle.

In an embodiment, the lateral position error value may be calculated using steering angles of the tires of the target vehicle, distances from the center of the target vehicle to the axle, and a difference value of the side slip angles.

In an embodiment, compensating for the longitudinal position value may comprise calculating a longitudinal position compensation value using a normalized linear interpolation function.

In an embodiment, compensating for the lateral position value may comprise calculating a lateral position compensation value using a normalized linear interpolation function.

An object recognition apparatus in a vehicle according to an embodiment of the present invention includes: a target position detection unit that detects a value of a longitudinal position of a target vehicle and a value of a lateral position of the target vehicle; And calculating a longitudinal position error value by comparing the longitudinal position value of the target vehicle in the current cycle with the longitudinal position value of the target vehicle in the previous cycle, Calculating a lateral position error value by comparing the lateral position values of the target vehicle in a previous cycle and calculating the lateral position error value and the lateral position error value according to the longitudinal position error value and the lateral position error value using a linear interpolation function, And a target position compensation unit for compensating the lateral position value.

In an embodiment, the target position detection unit may include an ultrasonic sensor, a radar, or an ultrasonic sensor.

In an embodiment, the lateral position error value may include a variation amount of the side slip angle of the target vehicle.

In an embodiment, the lateral position error value may be calculated using steering angles of the tires of the target vehicle, distances to the axle from the center of the target vehicle, and difference values of the side slip angles.

The object recognition apparatus and method thereof according to the embodiment of the present invention can improve the position accuracy by ensuring the position of the detected object.

BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention. However, the technical features of the present embodiment are not limited to the specific drawings, and the features disclosed in the drawings may be combined with each other to constitute a new embodiment.
FIG. 1 is an exemplary view showing a general autonomous-travelable vehicle.
2 is a block diagram illustrating an example of an object recognition apparatus 100 according to an embodiment of the present invention.
3 is a view for explaining a general slip angle.
4 is a flowchart illustrating an exemplary method for compensating a target position of an object recognition apparatus according to an exemplary embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: FIG.

The present invention is capable of various modifications and various forms, and specific embodiments are illustrated in the drawings and described in detail in the text. It is to be understood, however, that the invention is not intended to be limited to the particular forms disclosed, but on the contrary, is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms.

The terms may be used for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

Other expressions that describe the relationship between components, such as "between" and "between" or "neighboring to" and "directly adjacent to" should be interpreted as well. The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, the terms "comprises" or "having" are intended to specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, wherein one or more other features, , Steps, operations, components, parts, or combinations thereof, as a matter of course. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be construed as meaning consistent with meaning in the context of the relevant art and are not to be construed as ideal or overly formal in meaning unless expressly defined in the present application .

FIG. 1 is an exemplary view showing a general autonomous-travelable vehicle. 1, the vehicle 10 includes various object recognition devices, for example, at least one ultrasonic sensor 12, at least one ultrasonic sensor 12 for detecting a surrounding object, for example, a target vehicle 20 in front, Purpose radar 14, at least one long-range radar 16, or at least one multi-purpose camera 18. The multi-

The ultrasonic sensor 12 may be implemented to recognize objects within a maximum range of 4.5 m. For example, the ultrasonic sensor 12 may be used as a wave assist or the like.

The multipurpose radar 14 may be implemented to recognize the wheel to detect accident risk situations within 40 m. The multipurpose radar 14 may be used to operate an airbag, seat belt, etc. in an emergency.

The long-range radar 16 may be implemented to detect an object within 70 degrees ahead of 90 degrees. The long-range radar 16 can assist the camera when the visibility is bad, such as in bad weather.

The multipurpose camera 18 can be implemented to detect an object within 50 m, 500 m ahead. The multipurpose camera 18 can be used to detect movement of other cars and pedestrians.

Generally, the self-propelled vehicle 10 is equipped with various object recognition devices 12, 14, 16, 18 to track the position of an object. In order to improve the stability of autonomous driving, the position accuracy of the object being tracked is important. An object recognition apparatus according to an embodiment of the present invention can perform compensation for a position value in a longitudinal direction / lateral direction to increase positional accuracy with respect to an object .

2 is a block diagram illustrating an example of an object recognition apparatus 100 according to an embodiment of the present invention. Referring to FIG. 2, the object recognition apparatus 100 may include a target position detection unit 110, and a target position compensation unit 120.

The target position detection unit 110 may be configured to sense the target and to detect the detected target position. The target position detection unit 110 can detect the target position using at least one detection sensor. That is, the target position detection unit 110 can detect the target position by at least one of at least one ultrasonic sensor, at least one multipurpose radar, at least one long-range radar, or at least one multi-purpose camera. In an embodiment, the target position may be expressed by a longitudinal position coordinate value LONGPV and a lateral position coordinate value LATPV.

The target position compensation unit 120 receives the longitudinal position coordinate value LONGPV and the lateral position coordinate value LATPV from the target position detection unit 110 and detects the corrected longitudinal direction To generate the position coordinate value LONGPV 'and the corrected lateral position coordinate value LATPV'.

In an embodiment, the target position compensation unit 120 may include a longitudinal position compensation function and a lateral position compensation function to compensate for the lateral and longitudinal position coordinate values LONGPV, LATPV. In an embodiment, at least one of the longitudinal position compensation function and the lateral position compensation function may comprise a linear interpolation function.

In an embodiment, the longitudinal position compensation function may calculate a longitudinal position compensation value LONGPV 'proportional to the longitudinal position error value LONGV ERR. Here, the longitudinal position error value (LONG ERR) can satisfy the following expression (1).

Where t represents the current cycle and t-1 represents the previous cycle. Hereinafter, for convenience of explanation, it is assumed that the target object is a forward vehicle.

 In order to calculate the longitudinal position error value, the longitudinal position value of the target vehicle outputted from the logic for tracking the target vehicle ahead is used, as shown in equation (1). For example, the difference value of the longitudinal position value LONGPV (t-1) in the previous cycle in the longitudinal position value LONGPV (t) in the current cycle becomes the longitudinal position error value LONG ERR . That is, the longitudinal position error value LONGPV ERR is the longitudinal positional variation of the target vehicle.

In addition, the lateral position compensation function for calculating the lateral position error value (LATPV ERR) may satisfy the following equation (2).

Here,? Is the steering angle of the front / rear tires of the target vehicle, and W is the distance from the center of the target vehicle to the front and rear axles (rear axle).

In an embodiment, the lateral position compensation function may calculate the lateral position compensation value (LATPV ') using the longitudinal position error value LONGV ERR.

In the embodiment, the target position compensation unit 120 calculates a heading angle for the lateral position value and the longitudinal position value of the final target vehicle to calculate the lateral position error value LATPV ERR, The side slip angle of the target vehicle can be calculated and the difference value between the value of the previous cycle and the value of the current cycle with respect to the side slip angle can be calculated. That is, the lateral position error is a change amount of the side slip angle of the target. As shown in Fig. 3, the slip angle is related to the steering of the vehicle wheel.

에 적용된 게인(gain)은, 타겟 차량의 후륜의 미끄러짐이 거의 없다고 가정할 경우 0에 가까운 값을 적용할 수 있다. 또한, 타겟 차량의 전류의 조향 각도

는 전방의 타겟 차량의 위치값으로부터 계산된 헤딩 값이라 가정한다.In Equation 2,

A value close to 0 can be applied when the rear wheel of the target vehicle is assumed to have almost no slippage. Further, the steering angle of the current of the target vehicle

Is a heading value calculated from the position value of the target vehicle ahead.

In order to calculate the position compensation value proportional to the thus obtained longitudinal / lateral position error value, a normalized linear interpolation function can be used as shown in Equation (3).

Where min and max are the physical maximum and minimum values of the position error, and new_max and new_min are the range of values to be normalized.

The object recognition apparatus according to an embodiment of the present invention can be variously applied to the field of environment recognition technology such as a radar, a camera, and an ultrasonic sensor.

4 is a flowchart illustrating an exemplary method for compensating a target position of an object recognition apparatus according to an exemplary embodiment of the present invention. 2 to 4, a method of compensating a target position of the object recognition apparatus 100 may be performed as follows.

The longitudinal position error value LONGPV ERR may be calculated (S110) as shown in Equation (1). The longitudinal position compensation value LONGPV'1 may be calculated using the longitudinal position error value LONGPV ERR (S120). The lateral position error value (LATPV ERR) may be calculated (S130) as shown in Equation (2). The lateral position compensation value LATPV'1 may be calculated using the lateral position error value LATPV ERR (S140). The error value in the lateral direction can be determined by the amount of change in the side slip angle of the front object. To calculate the output values proportional to the error values of the longitudinal and transverse coordinates, a normalized linear interpolation function may be used. Here, if the normalization interval is set large, the output value can be increased.

The object recognition apparatus and method thereof according to the embodiment of the present invention can more precisely correct the position of an object after detecting an object (obstacle) in the front.

In the embodiment, the object recognition apparatus can be applied to a radar, a camera, a sensor, or the like for autonomous travel as shown in Fig.

The steps and / or operations in accordance with the present invention may occur in different orders, in parallel, or concurrently in other embodiments for other epochs or the like, as may be understood by one of ordinary skill in the art .

Depending on the embodiment, some or all of the steps and / or operations may be performed on one or more non-transitory computer-readable media, including instructions, programs, interactive data structures, At least some of which may be implemented or performed using one or more processors. The one or more non-transitory computer-readable media can be, by way of example, software, firmware, hardware, and / or any combination thereof. Further, the functions of the "module" discussed herein may be implemented in software, firmware, hardware, and / or any combination thereof.

One or more non-transitory computer-readable media and / or means for implementing / performing one or more operations / steps / modules of embodiments of the present invention may be implemented as application-specific integrated circuits (ASICs), standard integrated circuits, But are not limited to, controllers that perform appropriate instructions, including microcontrollers, and / or embedded controllers, field-programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs) .

The above-described contents of the present invention are only specific examples for carrying out the invention. The present invention will include not only concrete and practical means themselves, but also technical ideas which are abstract and conceptual ideas that can be utilized as future technologies.

10: Self-propelled vehicle
100: object recognition device
110: Target position detection unit
120: Target position compensation unit

Claims (12)

A method for recognizing a target vehicle ahead in a vehicle, comprising:
Calculating a longitudinal position error value for the position of the target vehicle;
Compensating a longitudinal position value for the position of the target vehicle based on the longitudinal position error value;
Calculating a lateral position error value for the position of the target vehicle; And
And compensating for a lateral position value for the position of the target vehicle based on the lateral position error value. The method according to claim 1,
Wherein the longitudinal position error value is a difference between a longitudinal position value in a current cycle and a lateral position value in a previous cycle. 3. The method of claim 2,
Wherein the compensated longitudinal position value is proportional to the longitudinal position error value. The method according to claim 1,
Wherein the lateral position error value is calculated using a longitudinal position value of the target vehicle, a heading angle to a lateral position value of the target vehicle, and a side slip angle of the target vehicle. 5. The method of claim 4,
Further comprising calculating the difference between the side slip angle of the target vehicle in the current cycle and the side slip angle of the target vehicle in the previous cycle. 6. The method of claim 5,
Wherein the lateral position error value is calculated using steering angles of tires of the target vehicle, distances from the center of the target vehicle to the axle, and a difference value of the side slip angle. The method according to claim 1,
Wherein compensating the longitudinal position value comprises calculating a longitudinal position compensation value using a normalized linear interpolation function. The method according to claim 1,
Wherein compensating the lateral position value comprises calculating a lateral position compensation value using a normalized linear interpolation function. 1. An object recognizing apparatus in a vehicle, comprising:
A target position detection unit for detecting a longitudinal position value of the target vehicle and a lateral position value of the target vehicle; And
Calculating a longitudinal position error value by comparing the longitudinal position value of the target vehicle in the current cycle with the longitudinal position value of the target vehicle in a previous cycle, Calculating a lateral position error value by comparing the lateral position value of the target vehicle in the cycle, calculating a lateral position error value by using the linear interpolation function and the longitudinal position value and the lateral position error value according to the longitudinal position error value and the lateral position error value, And a target position compensation unit for compensating a lateral position value. 10. The method of claim 9,
Wherein the target position detection unit includes an ultrasonic sensor, a radar, or an ultrasonic sensor. 10. The method of claim 9,
Wherein the lateral position error value includes a variation amount of the side slip angle of the target vehicle. 10. The method of claim 9,
Wherein the lateral position error value is calculated using steering angles of tires of the target vehicle, distances from the center of the target vehicle to the axle, and difference values of the side slip angles.

Images