KR102334039B1 - Apparatus for evalutating adaptive cruise control system for vehicle - Google Patents

Abstract

An ACC system test and evaluation apparatus is disclosed. The ACC system test and evaluation apparatus of the present invention includes: a performance evaluation unit for calculating theoretical values for a plurality of preset scenarios using sensing information of an adaptive cruise control (ACC) system; an actual vehicle test unit configured to detect an actual value according to the actual vehicle test of the ACC system for each scenario; and a test evaluation unit for evaluating the performance of the ACC system using the theoretical value calculated by the performance evaluation unit and the actual value detected by the actual vehicle testing unit, wherein the actual vehicle testing unit evaluates the front image of the own vehicle camera sensor to take pictures; and obtaining lane width information based on the lane detected from the front image captured by the camera sensor, and applying the position information of the camera sensor installed in the own vehicle and the obtained lane width information to a predefined geometric model. and a distance calculator for calculating an inter-vehicle distance from the vehicle to the vehicle in front.

Description

Vehicle ACC system test and evaluation device {APPARATUS FOR EVALUTATING ADAPTIVE CRUISE CONTROL SYSTEM FOR VEHICLE}

The present invention relates to an ACC system test and evaluation device for a vehicle, and more specifically, sets a plurality of scenarios for target vehicle identification and tracking, and compares and verifies theoretical values and actual vehicle test values according to each scenario to test and evaluate the ACC system It relates to a vehicle ACC system test and evaluation device.

An autonomous vehicle refers to a vehicle that recognizes the surrounding environment through external information detection and processing functions during driving, determines a driving route by itself, and drives independently using its own power. Autonomous vehicles can drive themselves to their destinations by preventing collisions with obstacles on the driving path and adjusting vehicle speed and driving direction according to the shape of the road without the driver operating the steering wheel, accelerator pedal, or brake. have. For example, acceleration may be performed on a straight road, and deceleration may be performed on a curved road while changing a driving direction in response to the curvature of the road.

A plurality of advanced driver assistance systems (ADAS) are applied to these autonomous vehicles to assist the driver in driving, and the driver assistance systems include ACC (Adaptive Cruise Control), LDWS (Lane Departure Warning System), There are Lane Keeping Assistance System (LKAS), High Beam Assistance (HBA), and Autonomous Emergency Braking (AEB).

In particular, the ACC system is a system that safely follows the preceding vehicle without the driver's throttle input or brake input based on active control technology. The ACC system minimizes the driver's driving load by controlling the vehicle's longitudinal speed and distance, and is useful for preventing and preventing accidents.

However, since the ACC system has a problem of causing a collision accident with a preceding vehicle when malfunctioning, a precise evaluation of the performance of the ACC system is essential. However, research and development related to the current ACC system is insufficient.

The background technology of the present invention is disclosed in 'A method and apparatus for verifying the performance of an ACC/LKS integrated controller for a vehicle, and a computer-readable recording medium therefor' of Korean Patent Application Laid-Open No. 10-2015-0057537 (2015.05.28). have.

An object of the present invention is to provide an ACC system test and evaluation device for a vehicle that tests and evaluates the ACC system by setting a plurality of scenarios for target vehicle identification and tracking, and comparing and verifying theoretical values and actual vehicle test values according to each scenario. will provide

According to an aspect of the present invention, an apparatus for test and evaluation of an ACC system for a vehicle includes: a performance evaluation unit for calculating theoretical values for a plurality of preset scenarios using sensing information of an adaptive cruise control (ACC) system; an actual vehicle test unit configured to detect an actual value according to the actual vehicle test of the ACC system for each scenario; and a test evaluation unit for evaluating the performance of the ACC system using the theoretical value calculated by the performance evaluation unit and the actual value detected by the actual vehicle testing unit, wherein the actual vehicle testing unit evaluates the front image of the own vehicle camera sensor to take pictures; and obtaining lane width information based on the lane detected from the front image captured by the camera sensor, and applying the position information of the camera sensor installed in the own vehicle and the obtained lane width information to a predefined geometric model. and a distance calculator for calculating an inter-vehicle distance from the vehicle to the vehicle in front.

The scenario of the present invention is for evaluating at least one of selecting a target vehicle for ACC control of a preceding vehicle on the same lane, and identifying and estimating a target vehicle when a target is changed due to a cut-in or lane change. do.

The lane width information of the present invention is characterized in that it includes a first lane width L1 based on the wheels of the preceding vehicle and a second lane width L2 based on the bonnet of the host vehicle.

The position information of the camera sensor of the present invention includes a first height (h1) of the camera sensor with respect to the ground, a second height (h2) of the camera sensor with respect to the bonnet of the own vehicle, and parallel to the ground A first distance (b) from the bonnet to the camera sensor in one direction, and a second distance (c) from the front end of the own vehicle to the camera sensor in a direction parallel to the ground characterized in that

The distance calculating unit of the present invention, The distance (a) from the front end of the own vehicle to the end point of the blind spot of the camera sensor formed by the bonnet of the own vehicle based on the longitudinal direction of the host vehicle; _{, after calculating the distance d image} from the end point to the wheel of the front vehicle based on the geometric model, _{the inter-vehicle distance using the calculated distance a, d image} and the specification information of the front vehicle It is characterized in that the distance from the front end of the host vehicle to the rearmost end of the front vehicle is calculated as (d _{real ).}

The distance calculating unit of the present invention is configured to calculate the distance a using the first and second heights h1 and h2 and the first and second distances b and c based on the geometric model. characterized in that

The distance calculating unit of the present invention is configured to connect the camera sensor and the wheel of the front vehicle from the ground at the termination point using the first and second lane widths L1 and L2 based on the geometric model. A second straight line connecting the camera sensor and the end point by calculating the height l to the first straight line, and using the distance a, the second distance c, and the first height h1 A first angle θ formed with a straight line perpendicular to the ground is calculated, and the first angle θ, the distance a, the second distance c, and the first height h1 are used to calculate the first angle θ. , after calculating the second angle α formed by the first straight line and the second straight line, the distance ( d _image ) is characterized in that it is calculated.

The distance calculating unit of the present invention is configured _{by subtracting a rear overhang length (d OH} ) as the specification information of the front vehicle from the sum of _{the distance (a) and the distance (d image} ) to determine the inter-vehicle distance ( d _real ) is characterized.

The camera sensor of the present invention is characterized in that it is a monocular camera sensor.

The test evaluation unit of the present invention comprises: an error rate calculator for calculating an error rate by comparing the theoretical value and the actual value for each scenario; and a system evaluation unit analyzing the performance characteristics of the ACC system using each of the error rates calculated by the error rate calculating unit.

The ACC system test and evaluation apparatus for a vehicle according to an aspect of the present invention sets a plurality of scenarios for target vehicle identification and tracking, and compares and verifies theoretical values and actual vehicle test values according to each scenario to test and evaluate the ACC system. It is possible to comprehensively evaluate the performance of the system and to actively respond to the international standard for the test and evaluation method of the ACC system.

An ACC system test and evaluation apparatus for a vehicle according to another aspect of the present invention evaluates the performance of the ACC system to prevent malfunction of an autonomous vehicle in advance, and to prevent an accident with a surrounding vehicle in advance.

An ACC system test and evaluation device for a vehicle according to another aspect of the present invention obtains a lane width in an image based on a lane and a vanishing point detected from a front image of a monocular camera, and from the own vehicle to the front vehicle based on a predetermined geometric model By calculating the inter-vehicle distance of , the distance accuracy can be improved even when a monocular camera sensor is used, and the accuracy of autonomous driving control can be improved by utilizing the calculated inter-vehicle distance for autonomous driving control.

1 is a block diagram of an ACC system test and evaluation apparatus for a vehicle according to an embodiment of the present invention.
2 is a view showing test conditions and test methods of the first to eleventh scenarios according to an embodiment of the present invention.
3 is a block diagram of an actual vehicle testing unit according to an embodiment of the present invention.
4 and 5 are exemplary views for explaining a process of calculating an inter-vehicle distance in a real vehicle test unit according to an embodiment of the present invention.

Hereinafter, an embodiment of the ACC system test and evaluation apparatus for a vehicle of the present invention will be described with reference to the accompanying drawings. In this process, the thickness of the lines or the size of the components shown in the drawings may be exaggerated for clarity and convenience of explanation. In addition, the terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of the user or operator. Therefore, definitions of these terms should be made based on the content throughout this specification.

Referring to FIG. 1 , an ACC system test and evaluation apparatus for a vehicle according to an embodiment of the present invention includes a real vehicle test unit 10 , a performance evaluation unit 20 , and a test evaluation unit 30 .

The performance evaluation unit 20 calculates a theoretical value for each of a plurality of preset scenarios using sensing information of an adaptive cruise control (ACC) system.

The scenario is for evaluating at least one of whether the ACC system selects a preceding vehicle on the same lane as a target vehicle for ACC control, and identifies and estimates the target vehicle when the target vehicle changes due to a cut-in or lane change.

On the other hand, the basic function of the ACC system is to maintain a constant vehicle distance from the target vehicle at a constant speed set by the driver, so that the speed and the inter-vehicle distance are automatically maintained. Therefore, in order to evaluate the tracking capability, which is the basic function of the ACC system, test evaluation is performed for each scenario, such as detection range, target identification, target vehicle tracking capability, and curve turning capability test.

In this embodiment, the scenarios are divided into first to eleventh scenarios. The scenario will be described with reference to FIG. 2 . Hereinafter, SV (Subject Vehicle) means a vehicle equipped with an ACC system to be evaluated, and LV (Lead Vehicle) means a preceding vehicle or target vehicle driving in front of a vehicle equipped with an ACC system to be evaluated.

In the first scenario, at the beginning of the test, the SV drives at 30, 60, 80 km/h, and two LV1 and LV2 run side by side in different lanes at the same speed as the SV. SV (Subject Vehicle) follows LV1. At this time, after the start of the test, the SV runs at the initial set speed of the ACC system, LV1 increases the speed by 10 km/h from the beginning of the test, and LV2 is the same as the initial test conditions. The test conditions and test methods of Scenario 1 are shown in Table 1 below.

Test conditions and test method for Scenario 1 scenario test initial conditions Conditions after the start of the test
One SV set speed 30, 60, 80 km/h SV set speed Early ACC
set speed LV1 set speed same speed as SV LV1 set speed Initial condition + 10 km/h LV2 set speed same speed as SV LV2 set speed Same as initial condition

In the second scenario, the initial conditions and post-test conditions are the same as those of the first scenario, and in the additional cut-in situation, LV1 changes lanes with instantaneous acceleration (cut-in). The test conditions and test methods of Scenario 2 are shown in Table 2 below.

scenario
test initial conditions Conditions after the start of the test
2 The first scenario and the initial conditions of the test and the conditions after the start of the test are the same + additional conditions below Additional conditions Lane change with instantaneous acceleration in a cut-in situation, the cut-in range is based on _{d 1}

In the third scenario, at the beginning of the test, the SV drives at 30, 60, 80 km/h, and two LV1 and LV2 (Lead Vehicles) run side by side in different lanes at the same speed as the SV. SV (Subject Vehicle) follows LV1. At this time, after the test starts, the SV runs at the initial set speed of the ACC system, and LV1 and LV2 are the same as the initial test conditions. The test conditions and test methods of Scenario 3 are shown in Table 3 below.

Test conditions and test method for Scenario 3 scenario test initial conditions Conditions after the start of the test
3 SV set speed 30, 60, 80 km/h SV set speed Early ACC
set speed LV1 set speed same speed as SV LV1 set speed Same as initial condition LV2 set speed same speed as SV LV2 set speed Same as initial condition

Scenario 4 has the same test initial conditions and test start conditions as in Scenario 3, and LV1 changes lanes with instantaneous acceleration in a cut-in situation. The test conditions and test methods of Scenario 4 are shown in Table 4 below.

scenario
test initial conditions Conditions after the start of the test
4 The 3rd scenario and the initial conditions of the test and the conditions after the start of the test are the same + additional conditions below Additional conditions Lane change with instantaneous acceleration in a cut-in situation, the cut-in range is based on d ₁ ~d _s-max

Scenario 5 has the same test initial conditions and post test start conditions as Scenario 4, and LV1 changes lanes with instantaneous acceleration in a cut-in situation. The test conditions and test methods of Scenario 5 are shown in Table 5 below.

scenario
test initial conditions Conditions after the start of the test
5 The 4th scenario and the initial conditions of the test and the conditions after the start of the test are the same + additional conditions below Additional conditions Lane change with instantaneous acceleration in a cut-in situation, the cut-in range is based on _{d 0} ~ d ₁

In the sixth scenario, at the beginning of the test, SV runs at a speed 10km/h lower than LV1, LV1 drives at 30,60,80km/h, and LV2 runs at the same speed as LV1. After the test starts, the SV runs at the initial set speed of the ACC system, and LV1 and LV2 are the same as the initial test conditions. In the 6th scenario, LV1 changes lanes with instantaneous acceleration in a cut-in situation, and the cut-in range is based on d ₁ ~d _s-max .

The test conditions and test methods of Scenario 6 are shown in Table 6 below.

scenario test initial conditions Conditions after the start of the test
6 SV set speed LV1-10km/h SV set speed Early ACC
set speed LV1 set speed 30, 60, 80 km/h LV1 set speed Same as initial condition LV2 set speed same speed as SV LV2 set speed Same as initial condition Additional conditions Lane change with instantaneous acceleration in a cut-in situation, the cut-in range is based on d ₁ ~d _s-max

In the 7th scenario, the initial conditions and post-test conditions are the same as those of the 6th scenario, and in the additional cut-in situation, LV1 changes lanes with instantaneous acceleration (cut-in). The test conditions and test methods of the 7th scenario are shown in Table 7 below.

scenario
test initial conditions Conditions after the start of the test
7 The 6th scenario and the initial conditions of the test and the conditions after the start of the test are the same + additional conditions below Additional conditions Lane change with instantaneous acceleration in a cut-in situation, the cut-in range is based on _{d 0} ~ d ₁

In the eighth scenario, at the beginning of the test, the SV drives at a speed 10km/h lower than that of LV1, and LV1 drives at 30,60,80km/h. After the start of the test, the SV runs at the initial set speed of the ACC system, and LV1 is the same as the test initial condition. LV1 changes lanes with instantaneous acceleration in a cut-in situation, and the cut-in range is based on d ₁ ~d _{s -max} . The test conditions and test methods of Scenario 8 are shown in Table 8 below.

scenario test initial conditions Conditions after the start of the test
8 SV set speed LV1-10km/h SV set speed Early ACC
set speed LV1 set speed 30, 60, 80 km/h LV1 set speed Same as initial condition Additional conditions Lane change with instantaneous acceleration in a cut-in situation, the cut-in range is based on d ₁ ~d _{s -max}

In the ninth scenario, the test initial conditions and post test conditions are the same as those of the eighth scenario, and in the additional cut-in situation, LV1 changes lanes with instantaneous acceleration (cut-in). The test conditions and test methods of Scenario 9 are shown in Table 9 below.

scenario
test initial conditions Conditions after the start of the test
9 The 9th scenario and the initial conditions of the test and the conditions after the start of the test are the same + additional conditions below Additional conditions Lane change with instantaneous acceleration in a cut-in situation, the cut-in range is based on _{d 0} ~ d ₁

In the tenth scenario, SV is 30km/h or 40km/h in the initial test condition, LV1 is the same speed as SV, and after the start of the test, SV is the initial ACC setting speed, and LV1 is the same as the initial test condition. Additionally, the deceleration during stopping is 0.1~0.3g, and the acceleration after stopping is 0.1g. The test conditions and test methods of Scenario 10 are shown in Table 10 below.

scenario test initial conditions Conditions after the start of the test

10 SV set speed 30, 40 km/h SV set speed Initial ACC set speed SV1 set speed same speed as SV SV1 set speed Same as initial condition Additional conditions The deceleration when stopping is 0.1~0.3g / the acceleration after stopping is 0.1g

Scenario 11 runs at 30, 60, 80 km/h at the beginning of the test, and LV1 runs at the same speed as SV. After the test starts, the SV runs at the initial set speed of the ACC system, and LV1 is the same as the test initial condition. Additionally, LV1 is tested at a speed of 30 km/h at a radius of curvature of 125 m, at a speed of 60 km/h at a radius of curvature of 250 m, and at a speed of 80 km/h at a radius of curvature of 500 m. The test conditions and test methods of Scenario 11 are shown in Table 11 below.

scenario test initial conditions Conditions after the start of the test

11 SV set speed 30, 60, 80 km/h SV set speed Initial ACC set speed SV1 set speed same speed as SV SV1 set speed Same as initial condition Additional conditions The speed of 30km/h is 125m in radius of curvature / 60km/h is 250m in radius of curvature, and the speed of 80km/h is 500m in radius of curvature.

Accordingly, the performance evaluation unit 20 calculates a theoretical value for each of a plurality of preset scenarios by using the sensing information of the ACC system for each scenario described above.

The actual vehicle test unit 10 detects actual values according to the actual vehicle test of the ACC system for each scenario. That is, the actual vehicle test unit 10 detects an actual measurement value for performance evaluation when the ACC system mounted on the vehicle operates for each scenario. The actual value is the actual distance between the target vehicle and the preceding vehicle measured through the ACC system. As the result of the actual vehicle test below, speed is explained as an example.

The actual vehicle testing unit 10 includes a camera sensor 11 and a distance calculating unit 12 as shown in FIG. 3 .

The camera sensor 11 may capture a front image of the own vehicle and transmit it to the distance calculating unit 12 to be described later. The camera sensor 11 may be a front camera sensor installed on the top of the windshield inside the own vehicle to capture an image of the front of the own vehicle, or a monocular camera sensor.

The distance calculator 12 may calculate the inter-vehicle distance to the vehicle in front based on the front image captured by the camera sensor 11 . Although the distance calculator 12 and the controller 300 to be described later are described as separate components to help understand the embodiment, the function of the distance calculator 12 of the present embodiment may be integrated into the controller 300 and implemented. . The distance calculator 12 and the controller 300 may be implemented as a processor or system on chip (SoC) that processes and calculates various data, and receives instructions or data received from other components. It may be designed to process by loading it into a memory, and to store various data in the memory.

A process in which the distance calculating unit 12 calculates the inter-vehicle distance from the host vehicle to the vehicle in front will be described in detail.

In this embodiment, the distance calculator 12 obtains lane width information based on the lane detected from the front image captured by the camera sensor 11, and obtains the location information and the location information of the camera sensor 11 installed in the own vehicle. By applying the obtained lane width information to a predefined geometric model, the inter-vehicle distance from the own vehicle to the vehicle in front can be calculated. Here, the lane width information may include a first lane width L1 based on a wheel of the vehicle in front and a second lane width L2 based on a bonnet of the own vehicle.

4 shows an example of a process of obtaining lane width information from a front image captured by the camera sensor 11 . A left lane and a right lane are detected from the forward image, and a point where the detected left and right lanes meet forms a vanishing point.

In the front image, the first lane width L1 means the distance between the left and right lanes based on the point where the wheels (rear wheels) of the front vehicle and the ground contact, and the second lane width L2 is the bonnet of the own vehicle It means the distance between the left and right lanes based on (B, eg: the top of the bonnet in the front image). Since the first lane width L1 and the second lane width L2 have distance values in the front image, the value of the first lane width L1 is smaller than the value of the second lane width L2. . In FIG. 4 , the height H1 means the vertical distance between the first lane width L1 and the second lane width L2, and the height H2 is the distance from the vanishing point to the straight line formed by the first lane width L1. vertical distance. An image processing algorithm for calculating the lane widths L1 and L2 and heights H1 and H2 from the front image captured by the camera sensor 11 may be predefined in the distance calculator 12 ( _{In addition, a rear overhang length (d OH} ) of a vehicle in front, which will be described later, may also be obtained through the above image processing algorithm).

When the lane width information is obtained through the above-described process, the distance calculating unit 12 applies the location information and the lane width information of the camera sensor 11 installed in the own vehicle to a predefined geometric model from the own vehicle to the vehicle in front. can calculate the inter-vehicle distance. 4 schematically shows a geometric model to help the understanding of the present embodiment, and specific equations follow Equations 2 to 6 to be described later. Referring to FIG. 4 , location information of the camera sensor 11 considered in the geometric model includes a first height h1 of the camera sensor 11 with respect to the ground and a camera sensor based on the bonnet of the own vehicle. The second height (h2) of (11), the first distance (b) from the bonnet to the camera sensor 11 based on the direction parallel to the ground, and the front end of the own vehicle based on the direction parallel to the ground The second distance c to the camera sensor 11 may be included.

As shown in FIG. 5, the inter-vehicle distance (d _real ) finally calculated in this embodiment is the distance from the front end (eg, front bumper) of the own vehicle to the rearmost end (eg, rear bumper) of the front vehicle, In order to calculate such an inter-vehicle distance (d _real ), in the present embodiment, three distance parameters, that is, a distance (a), a distance (d _image ), and a rear overhang length (d _{OH) as specification information of the vehicle in front} ) is employed.

The distance (a) is from the front end of the own vehicle, the terminal point of the blind spot of the camera sensor 11 formed by the bonnet of the own vehicle based on the longitudinal direction of the own vehicle (P in FIG. 4, the longitudinal direction of the own vehicle) refers to the distance to the front end point of the blind spot of the camera sensor 11). The distance d _image means a distance from the aforementioned termination point to a wheel (rear wheel) of the front vehicle. When following the definition of the distance (a) and the distance (d _image) as described above, in this embodiment the inter-vehicle distance is the distance (a) and the distance (d _image) the rear overhang of the front vehicle at a value adding (rear overhang) length ( d _OH ) can be calculated by subtracting. If this is expressed as an equation, it is as shown in Equation 1 below.

Now, the process of calculating the distance (a) and the distance (d _image ), which are factors of Equation 1, will be described in detail.

First, the distance calculator 12 may calculate the distance a using the first and second heights h1 and h2 and the first and second distances b and c based on the geometric model. The location information of the camera sensor 11 currently installed in the own vehicle may be previously stored in the distance calculating unit 12 . Using the proportional expression with reference to FIG. 5 , the distance a may be calculated according to Equation 2 below.

Next, _{the process of calculating the distance d image} is a process of calculating the height l in FIG. 3 , the process of calculating the first angle θ, and calculating the second angle α based on the geometric model and a process of calculating the _{distance (d image).}

Specifically, the distance calculating unit 12 uses the first and second lane widths L1 and L2, and the height from the ground point to the first straight line connecting the camera sensor 11 and the wheel of the vehicle in front. (l) can be calculated. The second lane width L2 obtained from the front image corresponds to the first height h1, and the difference between the second lane width L2 and the first lane width L1 corresponds to the height l. Considering the proportional relationship, the height l may be calculated according to Equation 3 below.

In addition, the distance calculator 12 uses the distance a, the second distance c, and the first height h1 so that the second straight line connecting the camera sensor 11 and the end point is perpendicular to the ground. The first angle θ formed with the straight line may be calculated. Referring to FIG. 5 , the first angle θ may be calculated according to Equation 4 below.

In addition, the distance calculator 12 uses the first angle θ, the distance a, the second distance c, and the first height h1 to form a second angle between the first straight line and the second straight line. (α) can be calculated. Referring to FIG. 4 , the second angle α may be calculated according to Equation 5 below.

_{Finally, the distance calculator 12 may calculate the distance d image} by using the height l, the first angle θ, and the second angle α. Referring to FIG. 5 , the distance d _image may be calculated according to Equation 6 below.

When the distance a and the distance d _image are calculated through the above-described process, the final inter-vehicle distance d _real may be calculated according to Equation 1 above.

Tables 11 and 12 below are experimental data showing the values obtained from the front image captured by the camera sensor 11 and the error rates from the measured values, respectively. From Tables 12 and 13, it can be seen that the error rate of the inter-vehicle distance detection method according to the present embodiment has high reliability in the range of 0% to 5%.

Meanwhile, in the present embodiment, as shown in FIG. 5 , the controller 300 for controlling the operation of a driver assistance system (DAS) applied to the own vehicle based on the inter-vehicle distance calculated through the distance calculator 12 . ) may be further included. The driving assistance system may refer to various systems that utilize the inter-vehicle distance as a control factor thereof, such as ACC (Adaptive Cruise Control), AEB (Autonomous Emergency Braking), LKAS (Lane Keeping Assist System), and HDA (Highway Driving Assist). may include

The test evaluation unit 30 evaluates the performance of the ACC system using the theoretical value calculated by the performance evaluation unit 20 and the actual value detected by the actual vehicle testing unit 10 .

The test evaluation unit 30 includes an error rate calculation unit 31 and a system evaluation unit 32 .

The error rate calculator 31 calculates an error rate by comparing a theoretical value and an actual measured value for each scenario.

Here, the relative distance values of the actual vehicle test are the values at which the tracking function of the ACC system is stabilized. The system evaluation unit 32 analyzes the performance characteristics of the ACC system using each of the error rates calculated by the error rate calculation unit 31 . In this case, the system evaluation unit 32 may distinguish the preceding vehicle and evaluate whether the ACC system operates and whether the ACC system follows the preceding vehicle.

The system evaluation unit 32 confirms that an error is also seen in the speed, and the ACC system is stabilized by matching the speed and distance of the vehicle in front over time, and it can be evaluated as stable regardless of the error rate.

As described above, the ACC system test and evaluation apparatus for a vehicle according to an embodiment of the present invention is set in a plurality of scenarios for target vehicle identification and tracking, and the ACC system is tested and evaluated by comparing and verifying theoretical values and actual vehicle test values according to each scenario. By doing so, it is possible to comprehensively evaluate the performance of the ACC system and to actively respond to the international standard for the test and evaluation method of the ACC system.

In addition, the ACC system test and evaluation apparatus for a vehicle according to an embodiment of the present invention evaluates the performance of the ACC system to prevent malfunctions of the autonomous vehicle in advance and to prevent accidents with surrounding vehicles in advance.

In addition, the ACC system test and evaluation apparatus for a vehicle according to an embodiment of the present invention obtains a lane width in an image based on a lane and a vanishing point detected from a front image of a monocular camera, and obtains a lane width in an image based on a predetermined geometric model. By calculating the inter-vehicle distance to the vehicle, even when a monocular camera sensor is used, the distance accuracy can be improved, and the calculated inter-vehicle distance can be used for autonomous driving control, thereby improving the accuracy of autonomous driving control.

Implementations described herein may be implemented in, for example, a method or process, an apparatus, a software program, a data stream, or a signal. Although discussed only in the context of a single form of implementation (eg, discussed only as a method), implementations of the discussed features may also be implemented in other forms (eg, as an apparatus or program). The apparatus may be implemented in suitable hardware, software and firmware, and the like. A method may be implemented in an apparatus such as, for example, a processor, which generally refers to a computer, a microprocessor, a processing device, including an integrated circuit or programmable logic device, and the like. Processors also include communication devices such as computers, cell phones, portable/personal digital assistants (“PDA”) and other devices that facilitate communication of information between end-users.

Although the present invention has been described with reference to the embodiment shown in the drawings, this is merely exemplary, and it is understood that various modifications and equivalent other embodiments are possible by those of ordinary skill in the art. will understand Accordingly, the true technical protection scope of the present invention should be defined by the following claims.

10: actual vehicle test section
11: Camera sensor
12: distance calculator
20: performance evaluation unit
30: test evaluation unit
31: error rate calculator
32: system evaluation unit

Claims (10)

a performance evaluation unit for calculating theoretical values for a plurality of preset scenarios using sensing information of an adaptive cruise control (ACC) system;
an actual vehicle test unit configured to detect an actual measured value that is an inter-vehicle distance from the own vehicle to the front vehicle according to the actual vehicle test of the ACC system for each scenario; and
a test evaluation unit for evaluating the performance of the ACC system using the theoretical value calculated by the performance evaluation unit and the actual value detected by the actual vehicle testing unit;
The actual vehicle test unit includes a camera sensor for photographing a front image of the own vehicle; and obtaining lane width information based on the lane detected from the front image captured by the camera sensor, and applying the position information of the camera sensor installed in the own vehicle and the obtained lane width information to a predefined geometric model. An ACC system test and evaluation device for a vehicle, characterized in that it comprises a distance calculator for calculating an inter-vehicle distance from the vehicle to the vehicle in front.
The method of claim 1 , wherein the scenario comprises at least one of selecting a target vehicle for ACC control of a preceding vehicle on the same lane, and identifying and estimating a target vehicle when a target vehicle is changed due to a cut-in or lane change. Vehicle ACC system test and evaluation device, characterized in that.
The method of claim 1, wherein the lane width information comprises:
An ACC system test and evaluation device for a vehicle including a first lane width (L1) based on the wheels of a preceding vehicle and a second lane width (L2) based on the bonnet of the own vehicle.
4. The method of claim 3,
The position information of the camera sensor includes a first height h1 of the camera sensor with respect to the ground, a second height h2 of the camera sensor with respect to the bonnet of the own vehicle, and a direction parallel to the ground A first distance (b) from the bonnet to the camera sensor as a reference, and a second distance (c) from the front end of the own vehicle to the camera sensor based on a direction parallel to the ground ACC system test and evaluation device for vehicles.
5. The method of claim 4,
The distance calculator,
The distance (a) from the front end of the own vehicle to the end point of the blind spot of the camera sensor formed by the bonnet of the own vehicle based on the longitudinal direction of the own vehicle, and from the end point to the front vehicle the distance (d _image) of the wheel up to then calculated based on the geometric model, the calculated distance (a, d _image) and the self-vehicle using a specification information of the preceding vehicle as the vehicle distance (d _real) ACC system test and evaluation device for a vehicle, characterized in that calculating the distance from the front end of the front end of the vehicle.
6. The method of claim 5,
The distance calculation unit, based on the geometric model,
The ACC system test and evaluation apparatus for a vehicle, characterized in that the distance (a) is calculated using the first and second heights (h1, h2) and the first and second distances (b, c).
7. The method of claim 6,
The distance calculation unit, based on the geometric model,
Using the first and second lane widths L1 and L2, a height l from the ground to a first straight line connecting the camera sensor and the wheel of the front vehicle is calculated from the terminal point,
Using the distance (a), the second distance (c), and the first height (h1), a first angle ( θ) is calculated,
A second angle α formed by the first straight line and the second straight line using the first angle θ, the distance a, the second distance c, and the first height h1 After calculating
The ACC system test and evaluation apparatus for a vehicle, characterized in that _{the distance (d image} ) is calculated using the height (l), the first angle (θ), and the second angle (α).
8. The method of claim 7,
The distance calculator,
and calculating the inter-vehicle distance d _{real by subtracting a rear overhang length d OH} as the specification information of the front vehicle from the sum of the distance a and the distance d _image ACC system test and evaluation device for vehicles.
According to claim 1,
The camera sensor is an ACC system test and evaluation device for a vehicle, characterized in that it is a monocular camera sensor.
According to claim 1, wherein the test evaluation unit
an error rate calculator for calculating an error rate by comparing the theoretical value with the actual value for each scenario; and
and a system evaluation unit analyzing performance characteristics of the ACC system using each of the error rates calculated by the error rate calculating unit.

Images