Autonomous traveling vehicle and control method thereof

Abstract

A method of controlling an autonomous driving vehicle according to an embodiment of the present disclosure may be under control of a processor and may include: determining whether an actual lane line of a driving road is recognized by receiving sensing information from a plurality of sensors on the autonomous driving vehicle; based on a result of the determination, initially identifying a target vehicle traveling behind the autonomous traveling vehicle and on another lane; the target vehicle is secondarily recognized by changing the priorities of the plurality of sensors on the basis of the environment of the traveling road on which the target vehicle which has been initially recognized is traveling.

Description

Technical Field

[0001] The present disclosure relates to an autonomous driving vehicle and a control method thereof. Background Art

[0002] Recently, autonomous vehicles that can reduce driver fatigue by performing driving, braking, and steering on behalf of the driver are required to have the ability to adaptively cope with surrounding environments that change in real time during driving.

[0003] An autonomous vehicle has at least one autonomous driving function.

[0004] For example, an autonomous driving function that recognizes vehicles behind other lanes (or in blind spots) to avoid collisions requires high target recognition accuracy of side and rear radar sensors (or blind spot radar sensors).

[0005] A typical autonomous vehicle utilizes an autonomous driving function and uses only a blind spot radar sensor to identify vehicles in the blind spot, but there may be a limited situation where intermittent diffuse reflections of the radar sensor depending on the driving / parking environment and obstacle status prevent recognition of a target vehicle among multiple vehicles in the blind spot.

[0006] Furthermore, even when a typical autonomous vehicle identifies a target vehicle, the exact position and heading angle of the target vehicle may be in error. Summary of the invention

[0007] The present disclosure relates to an autonomous driving vehicle and a control method thereof, and more particularly, to an autonomous driving vehicle and a control method thereof, which ensures the robustness of the autonomous driving function by controlling at least one sensor to complement each other to identify a target vehicle behind other lanes.

[0008] Some embodiments of the present disclosure may provide an autonomous driving vehicle and a control method thereof, which may ensure the robustness of the autonomous driving function by using a camera configured to identify the side rear (also referred to as a blind spot herein) and a side rear radar sensor (or a blind spot radar sensor) and changing their priority according to the driving environment when using them.

[0009] The embodiments and advantages of the present disclosure are not limited to the above embodiments and advantages, and those skilled in the art can also clearly understand other technical features not described above from the following description.

[0010] In order to solve the above technical problems, according to an embodiment of the present disclosure, a method for controlling an autonomous vehicle may include: for example, under the control of a processor, determining whether a lane line of a driving road is identified by receiving sensing information from multiple sensors; based on the result of the determination, initially identifying a target vehicle driving behind another lane; and based on the environment of the road on which the initially identified target vehicle is driving, secondary identifying the target vehicle by changing the priorities of multiple sensors.

[0011] According to an embodiment of the present disclosure, secondarily recognizing the target vehicle may include: under control of a processor, differently setting a determination weight based on an error rate of each of a plurality of sensors.

[0012] In an embodiment of the present disclosure, the method may further include: in response to not identifying a lane line of the driving road, generating at least one virtual lane line based on the driving trajectory of the autonomous vehicle, wherein the at least one virtual lane line may include the line of the lane in which the autonomous vehicle is driving and the line of the adjacent lane.

[0013] In an embodiment of the present disclosure, the method may further include: determining the lateral position and heading angle of the target vehicle based on the outer side of the front / rear tires of the target vehicle, and the distance between the target vehicle and the lane line of the road or the distance between the target vehicle and the virtual lane line, and identifying the target vehicle based on the calculation results.

[0014] In the embodiments of the present disclosure, the road environment may include: a first environment, namely a normal road environment; a second environment, namely a dark road environment; and a third environment, namely a heavy rain / heavy snow or diffuse reflection road environment.

[0015] In an embodiment of the present disclosure, secondarily identifying the target vehicle may include: under the control of the processor, in the case of the first environment, secondarily identifying the target vehicle by operating a plurality of sensors with the same priority.

[0016] In an embodiment of the present disclosure, secondarily identifying the target vehicle may include: under control of the processor, in case of the second environment, secondarily identifying the target vehicle by operating a radar among the plurality of sensors with a first priority.

[0017] In an embodiment of the present disclosure, secondarily recognizing the target vehicle may include: under the control of the processor, in case of the third environment, secondarily recognizing the target vehicle by operating a camera among the plurality of sensors with a first priority.

[0018] In an embodiment of the present disclosure, the method may further include: under the control of the processor, calculating the position of the target vehicle based on the set determination weight.

[0019] According to an embodiment of the present disclosure, there may be a non-transitory computer-readable storage medium storing instructions, which, when executed by a processor, may cause the processor to execute a method of controlling an autonomous driving vehicle.

[0020] In order to solve the above technical problems, according to an embodiment of the present disclosure, an autonomous vehicle may include a processor, wherein the processor may be configured to: determine whether a lane line of a driving road is identified by receiving sensing information from multiple sensors; based on the result of the determination, initially identify a target vehicle driving behind another lane; and based on the environment of the road on which the initially identified target vehicle is driving, secondary identify the target vehicle by changing the priority of multiple sensors.

[0021] In the vehicle of the embodiment of the present disclosure, the processor may be configured to differently set the determination weight based on an error rate of each of the plurality of sensors in order to secondarily identify the target vehicle.

[0022] In the vehicle of the embodiment of the present disclosure, the processor may be further configured to, in response to failure to identify a lane line of the driving road, generate at least one virtual lane line based on the driving trajectory of the autonomous vehicle, wherein the at least one virtual lane includes the line of the lane in which the autonomous vehicle is driving and the line of the adjacent lane.

[0023] In the vehicle of the embodiment of the present disclosure, the processor may be further configured to calculate the lateral position of the target vehicle and the heading angle of the target vehicle based on the outer sides of the front / rear tires of the target vehicle and the distance between the target vehicle and the lane line of the road or the distance between the target vehicle and the virtual lane line, and identify the target vehicle based on the calculation results.

[0024] In the vehicle of the embodiment of the present disclosure, the road environment may include: a first environment, namely a normal road environment; a second environment, namely a dark road environment; and a third environment, namely a heavy rain / heavy snow or diffuse reflection road environment.

[0025] In the vehicle of the embodiment of the present disclosure, the processor may be further configured to: in the case of the first environment, secondarily identify the target vehicle by operating the plurality of sensors with the same priority.

[0026] In the vehicle of the embodiment of the present disclosure, the processor may be further configured to, in case of the second environment, secondarily identify the target vehicle by operating the radar among the plurality of sensors with the first priority.

[0027] In the vehicle of the embodiment of the present disclosure, the processor may be further configured to: in case of the third environment, secondarily identify the target vehicle by operating a camera among the plurality of sensors with the first priority.

[0028] In the vehicle of the embodiment of the present disclosure, the processor may be further configured to calculate the position of the target vehicle based on the set determination weight.

[0029] According to an embodiment of the present disclosure, an autonomous driving vehicle and a control method thereof can ensure the robustness of an autonomous driving function by using a camera configured to identify blind spots and a blind spot radar sensor and changing their priorities according to the driving environment when using them.

[0030] According to an embodiment of the present disclosure, an autonomous vehicle and a control method thereof may use a rear camera and a digital side-view mirror (DSM) having a recognition method different from that of a radar sensor to identify the presence or absence of a target vehicle behind other lanes, so as to improve the performance of identifying the target vehicle, and supplement the recognition of the position, heading angle, etc. of the target vehicle, so as to improve the performance of recognition and control.

[0031] According to an embodiment of the present disclosure, an autonomous vehicle and a control method thereof can improve recognition performance by changing priorities according to the driving environment while using a camera and a blind spot radar sensor configured to identify blind spots, thereby improving unnecessary warnings to misidentified false target vehicles and the risk of not identifying target vehicles.

[0032] According to an embodiment of the present disclosure, an autonomous vehicle and a control method thereof can use a camera to generate virtual lane lines, and based on the generated virtual lane lines, improve the positioning accuracy of target vehicles traveling behind other lanes, suppress unnecessary operations, and improve the restricted conditions for using radar sensors.

[0033] According to an embodiment of the present disclosure, an autonomous vehicle and a control method thereof may additionally use a camera having a different recognition method from a radar sensor to supplement their different limitations and advantages and disadvantages, thereby improving the performance of recognition, warning, and control.

[0034] According to an embodiment of the present disclosure, an autonomous vehicle and a control method thereof may additionally use a camera having a different recognition method from a radar sensor to complement their different limitations and advantages and disadvantages, thereby preventing erroneous warnings and controls due to false recognition or misidentification of targets.

[0035] According to an embodiment of the present disclosure, an autonomous driving vehicle and a control method thereof can alleviate the limitation of the driving environment by using sensors with different recognition methods when the operation of the sensor is restricted by the driving environment, thereby using the autonomous driving function more accurately.

[0036] The advantages that can be achieved by some embodiments of the present disclosure are not limited to the above advantages. Some embodiments of the present disclosure can also achieve other advantages not described above, as those skilled in the art can understand from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a block diagram illustrating an autonomous driving vehicle according to an embodiment of the present disclosure.

[0038] Figure 2A and Figure 2B is a diagram showing an example of generating a virtual lane line under the control of a processor according to an embodiment of the present disclosure.

[0039] Figure 3 is a diagram illustrating an example of determining a position of a target vehicle using a virtual lane line under the control of a processor according to an embodiment of the present disclosure.

[0040] Figure 4 is a diagram illustrating an example of identifying a target vehicle by changing priorities of a plurality of sensors under the control of a processor according to an embodiment of the present disclosure.

[0041] Figure 5A and Figure 5B is a diagram illustrating a warning area according to an embodiment of the present disclosure.

[0042] Figure 6 is a diagram illustrating an example of differently setting a determination weight based on an error rate of each of a plurality of sensors under the control of a processor according to an embodiment of the present disclosure.

[0043] Figures 7 to 9 is a flow chart illustrating a method of controlling an autonomous vehicle according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] Some example embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings, and the same or similar elements may be given the same reference numerals regardless of the reference symbols, and repeated descriptions thereof may be omitted. In addition, when describing an embodiment, when it is determined that a detailed description of a related well-known technology may obscure the subject matter of the embodiment described herein, a detailed description thereof may be omitted.

[0045] As used herein, the terms "include", "comprising", and "having" indicate the presence of stated elements, components, and / or combinations thereof, but do not preclude the presence or addition of one or more other elements, components, and / or combinations thereof. In addition, when describing example embodiments in conjunction with the accompanying drawings, the same reference numerals may refer to the same components, and repeated descriptions thereof may be omitted.

[0046] In addition, the terms "unit" and "control unit" included in names such as a vehicle control unit (VCU) may be terms widely used to name control devices or controllers configured to control specific functions of a vehicle, and may not be terms representing general functional units. For example, each controller or control unit may include a communication device that communicates with other controllers or sensors to control corresponding functions, a memory that stores an operating system (OS) or logic commands and input / output information, and at least one processor that performs determinations, calculations, selections, etc. required to perform control functions.

[0047] Figure 1 is a block diagram illustrating an autonomous driving vehicle according to an embodiment of the present disclosure.

[0048] Reference Figure 1 The autonomous driving vehicle 100 according to the embodiment of the present disclosure may include a processor 110 and a plurality of sensors 130 .

[0049] The plurality of sensors 130 may be provided in the autonomous vehicle 100, or may be installed at the front, rear, and sides of the autonomous vehicle 100. The plurality of sensors 130 may sense the periphery of the autonomous vehicle 100 in real time when the autonomous vehicle 100 is parked or driving, and provide sensing information to the processor 110.

[0050] For example, the sensor 130 may include a radar 131, a camera 132, and a light detection and ranging sensor or a lidar 133. The radar 131 may also be referred to herein as a first sensor, the camera 132 may also be referred to herein as a second sensor, and the lidar 133 may also be referred to herein as a third sensor.

[0051] The radar 131 may be provided as one or more radars in the autonomous vehicle 100. The radar 131 may measure the relative speed and relative distance relative to the identified object together with the wheel speed sensor (not shown) installed on the autonomous vehicle 100. For example, the radar 131 may be installed at the rear and / or side of the autonomous vehicle 100 to identify the rear object (also referred to as the rear object in this article). The rear object described in this article may include a rear vehicle, a rear target vehicle, a target vehicle, etc.

[0052] The camera 132 may be provided as one or more cameras in the autonomous vehicle 100. The camera 132 may include, for example, a wide-angle camera. The camera 132 may capture images of objects and their states around the autonomous vehicle 100, and output image data based on the captured information. For example, the camera 132 may be installed at the rear or side of the autonomous vehicle 100 to identify objects behind the side of the autonomous vehicle 100. This will be described in detail below.

[0053] The laser radar 133 may be configured as one or more laser radars in the autonomous vehicle 100. The laser radar 133 may irradiate a laser pulse to an object, measure the time it takes for the laser pulse reflected from an object within the measurement range to return, sense information such as the distance to the object, the direction and speed of the object, and output laser radar data based on the sensed information. The object described herein may be an obstacle, a vehicle, a person, an object, etc. outside the autonomous vehicle 100.

[0054] The processor 110 may receive sensing information from the plurality of sensors 130 , determine whether a lane line of a road on which the autonomous vehicle 100 is traveling is recognized, and initially recognize a target vehicle traveling to the side or rear based on the determination result.

[0055] The processor 110 can perform a second recognition of the target vehicle identified initially based on the road environment on which the target vehicle is traveling by changing the priorities of the plurality of sensors 130, and set the determination weight differently based on the target vehicle identified twice. For example, the processor 110 can perform sensing using the first sensor 131 and the second sensor 132 with substantially the same priority according to the environment of the road.

[0056] Alternatively, the processor 110 may perform sensing using the first sensor 131 in preference to the second sensor 132 according to the environment of the road. Alternatively, the processor 110 may perform sensing using the second sensor 132 in preference to the first sensor 131 according to the environment of the road. This will be described in detail below.

[0057] Figure 2A and Figure 2B is a diagram showing an example of generating a virtual lane line under the control of a processor according to an embodiment of the present disclosure.

[0058] Reference Figure 2A and Figure 2B The processor 110 of the embodiment of the present disclosure can determine whether the lane line of the driving road is recognized based on the sensing information provided by the multiple sensors 130.

[0059] The processor 110 may determine whether a lane line of a road on which the host vehicle (eg, the autonomous vehicle 100 ) is traveling is recognized based on the sensing information provided by the first sensor 131 and the second sensor 132 .

[0060] Reference Figure 2AWhen it is determined that the lane line of the road is recognized, the processor 110 can recognize one or more rear vehicles 10a, 10b, and 10c traveling behind or to the side of the host vehicle 100 based on the recognized lane line. The processor 110 can recognize the rear vehicles 10a, 10b, and 10c for the first time, and set one of the initially recognized vehicles 10a, 10b, and 10c as the target vehicle (e.g., 10a).

[0061] In comparison, reference Figure 2B When it is determined that no lane line of the road is identified, the processor 110 may generate a virtual lane line VL based on the driving lane. For example, when no lane line of the driving road is identified, the processor 110 may generate a virtual lane line VL based on the driving trajectory of the vehicle 100.

[0062] For example, when the lane line L does not exist or is not recognized, the processor 110 can receive the sensing information recognized by the rear / side camera and generate a virtual lane line VL to improve the accuracy of the position of the target vehicle 10a behind or on the side. In this example, the sensing information can include lane line information.

[0063] Because the target vehicle 10a is located behind or to the side due to the nature of the blind spot collision avoidance assist (BCA) function, the processor 110 can generate a virtual lane line VL by storing and calculating the lane line behind the host vehicle 100 or the trajectory that the host vehicle 100 has traveled.

[0064] In this example, the virtual lane line VL may include the line of the lane (host lane) in which the host vehicle 100 is traveling and the line of the adjacent lane adjacent to the host lane. The line of the adjacent lane may include all lines adjacent to both sides of the host lane.

[0065] As described above, when no lane line is identified, the processor 110 can define and store the trajectory that the vehicle 100 has traveled as the center of the lane, and can determine the virtual lane line VL from the vehicle 100 to the two side lanes of the vehicle 100 by default.

[0066] The processor 110 can set the lane width W of the virtual lane line VL generated based on the host vehicle 100 or the target vehicle 10a to be about 2.7 meters (m) or more and 3.3 meters or less, which is usually the minimum width of the lane of a general road (in some countries and / or for certain types of roads). When the width of the virtual lane is about 2.7 meters or less, large vehicles (e.g., large sports utility vehicles (SUVs), trucks, and public vehicles) may encounter great inconvenience when traveling within the width of the virtual lane. In addition, when the width of the virtual lane is about 3.3 meters or more, there may be no inconvenience for vehicle driving, but for general roads with limited width, the number of lanes may be relatively small. Based on this, it may be desirable to set the width of the virtual lane to about 3 meters.

[0067] In this example case, the curvature of the lane line can follow the driving trajectory of the vehicle 100 under the control of the processor 110 .

[0068] Figure 3 is a diagram showing an example of determining the position of a target vehicle using a virtual lane line VL under the control of a processor according to an embodiment of the present disclosure.

[0069] Reference Figure 3 According to an embodiment of the present disclosure, the processor 110 may initially identify the target vehicle 10 a based on sensing information provided by the plurality of sensors 130 .

[0070] The processor 110 can calculate the lateral position of the target vehicle 10a and the heading angle of the target vehicle 10a based on the outer sides of the front / rear tires of the target vehicle 10a identified based on the sensing information, and the distance between the target vehicle 10a and the lane line of the road or the distance between the target vehicle 10a and the virtual lane line VL.

[0071] Therefore, the autonomous vehicle 100 can more accurately identify the target vehicle 10a under the control of the processor 110. The autonomous vehicle 100 may also be referred to as the host vehicle 100 in this document.

[0072] For example, the processor 110 can calculate the lateral position of the target vehicle 10a and the heading angle of the target vehicle 10a by receiving sensing information and analyzing the distance W1 between the host vehicle 100 and the virtual lane line VL, the distances W2 and W3 between the outer sides of the front / rear tires of the target vehicle 10a and the virtual lane line VL, the distance between the host vehicle 100 and the lane line, the distance between the outer sides of the front / rear tires of the target vehicle 10a and the lane line, etc.

[0073] The lateral position of the target vehicle 10 a and the heading angle of the target vehicle 10 a may need to be calculated because the position of the target vehicle 10 a in the sensing information provided by the camera may have errors.

[0074] Therefore, the processor 110 can generate a virtual lane line VL, analyze the distance between the generated virtual lane line VL and the identified target vehicle 10a, and based on the analysis results, calculate the lateral position of the target vehicle 10a and the heading angle of the target vehicle 10a, thereby more accurately identifying the position of the target vehicle 10a.

[0075] Figure 4 is a diagram illustrating an example of identifying a target vehicle by changing priorities of a plurality of sensors under the control of a processor according to an embodiment of the present disclosure.

[0076] Reference Figure 4 The processor 110 may control the environment of the road on which the target vehicle 10 a is traveling based on the initial recognition, and may re-recognize the target vehicle 10 a by changing the priorities of the plurality of sensors 130 .

[0077] In this example case, the environment of the road (also referred to herein as the road environment) may include a first environment, a second environment, and a third environment.

[0078] The first environment may be a normal road environment. The first environment may refer to an environment where the driving road is in a normal state. In the case of the first environment, the processor 110 may control the operation of the plurality of sensors 130 with the same priority to secondary identify the target vehicle 10a.

[0079] For example, in a normal driving road environment where all sensors have no problem recognizing, when the side rear radar and camera meet the requirements for recognizing the target vehicle 10a or lane line, the processor 110 can determine the existence of the target vehicle 10a or lane line.

[0080] In the case of the first environment, the processor 110 may analyze the sensing information provided by the first sensor 131 to calculate the longitudinal position of the target vehicle 10a and the speed of the target vehicle 10a. The first sensor 131 may be a radar.

[0081] With respect to the longitudinal position and speed of the target vehicle 10 a , under the control of the processor 110 , the recognition value of the side rear radar having a relatively high accuracy in recognizing a moving object may be set as the first priority.

[0082] In the first environment, the processor 110 may analyze the sensing information provided by the second sensor 132 to calculate the lateral position of the target vehicle 10a and the heading angle of the target vehicle 10a. The second sensor 132 may be a camera.

[0083] For the lateral position and heading angle of the target vehicle 10a, under the control of the processor 110, the recognition value of the camera calculated by the camera based on the distance between the target vehicle 10a and the lane line can be set as the first priority.

[0084] The second environment may be a dark road environment. The second environment may refer to an environment where the road is in a dark state at night. In the case of the second environment, the processor 110 may control the radar (which is the first sensor 131 among the multiple sensors 130) to operate with a first priority to identify the target vehicle 10a for the second time. In this example, the camera (which is the second sensor 132) may not be able to identify the target vehicle 10a and the lane line in the dark road environment as the second environment, or even if the camera recognizes the target vehicle 10a and the lane line, its sensing accuracy may also be significantly reduced. Therefore, the processor 110 may control the first sensor 131 to operate in the second environment in priority to the second sensor 132. When the camera's recognition of both the target vehicle 10a and the lane line is limited (as in the dark road state at night), the processor 110 may use the side rear radar to operate this function.

[0085] In the case of the second environment, the processor 110 may analyze the sensing information provided by the first sensor 131 to calculate the longitudinal position of the target vehicle 10a, the speed of the target vehicle 10a, the lateral position of the target vehicle 10a, and the heading angle of the target vehicle 10a.

[0086] When the lane line recognition of the camera is limited, for example, when there are no lane lines or the lane lines cannot be seen normally, the processor 110 can preferentially use the recognition value of the side rear radar to determine the lateral position and heading angle of the target vehicle 10a.

[0087] The third environment may be a heavy rain / heavy snow or diffuse reflection road environment. The third environment may refer to an environment where there is diffuse reflection on the road or heavy rain / heavy snow on the road.

[0088] In the case of the third environment, the processor 110 can control the camera (which is the second sensor 132 among the multiple sensors 130) to operate with the first priority to secondary identify the target vehicle 10a. In this example, the radar as the first sensor 131 may not be able to identify the target vehicle 10a and the lane line in the heavy rain / heavy snow or diffuse reflection road environment as the third environment, or even if the radar identifies the target vehicle 10a and the lane line, its sensing accuracy may be significantly reduced. Therefore, the processor 110 can control the second sensor 132 to operate in the third environment in priority to the first sensor 131. When the recognition of the side rear radar is limited due to heavy rain, heavy snow, etc., the processor 110 can use the camera to operate this function.

[0089] In the case of the third environment, the processor 110 can analyze the sensing information provided by the second sensor 132 to calculate the longitudinal position of the target vehicle 10a, the speed of the target vehicle 10a, the lateral position of the target vehicle 10a, and the heading angle of the target vehicle 10a. When the recognition of the side rear radar is limited due to heavy rain, heavy snow, etc., the processor 110 can determine the longitudinal position of the target vehicle 10a and the speed of the target vehicle 10a by preferentially using the recognition value of the camera.

[0090] Figure 5A and Figure 5B is a diagram illustrating a warning area according to an embodiment of the present disclosure.

[0091] Reference Figure 5A and Figure 5B , the processor 110 may generate a virtual lane line VL using sensing information provided by the plurality of sensors 130. The virtual lane line VL may include a line of a lane in which the autonomous vehicle 100 is traveling, a line of an adjacent lane, and a line of a lane next to the adjacent lane.

[0092] Reference Figure 5A , when the outer side of the tire of the target vehicle 10a enters the adjacent lane on the side, a typical autonomous vehicle may determine the entry and may operate based on the warning area A1 regardless of the lane, thereby activating unnecessary warning / control.

[0093] In comparison, reference Figure 5B Under the control of the processor 110, the autonomous vehicle 100 according to an embodiment of the present disclosure may, during a lane change to an adjacent lane, not activate unnecessary warnings / controls due to the target vehicle 10a in the lane next to the adjacent lane before the target vehicle 10a completely enters the lateral adjacent lane.

[0094] The processor 110 can divide the warning area A2 into a first area A21 and a second area A22 based on the line of the adjacent lane (which is the generated virtual lane line VL), and when the target vehicle 10a changes lanes to the adjacent lane, before the target vehicle 10a completely enters the adjacent lane, unnecessary warnings / controls will not be activated due to the target vehicle 10a in the lane next to the adjacent lane.

[0095] In this example case, the first area A21 may be a warning area where a warning is to be activated, and the second area A22 may be a non-warning area where a warning is not to be activated.

[0096] Figure 6 is a diagram illustrating an example of differently setting a determination weight based on an error rate of each of a plurality of sensors under the control of a processor according to an embodiment of the present disclosure.

[0097] Reference Figure 6 During the secondary recognition of the target vehicle 10 a , the processor 110 may control to differently set the determination weight based on the error rate of each of the plurality of sensors 130 .

[0098] The processor 110 may calculate the position of the target vehicle 10 a based on the set determination weight.

[0099] For example, the processor 110 may assign different weights to the position of the target vehicle 10a during sensor fusion based on the longitudinal and lateral error rates of each of the plurality of sensors 130. In this example case, the error rate may also be referred to as accuracy, accuracy ratio, or error rate ratio.

[0100] like Figure 6 As shown, each of the multiple sensors 130 can be divided according to the accuracy and measured distance based on the longitudinal direction and the accuracy and measured distance based on the transverse direction. Based on this, the processor 110 can assign different determination weights based on the sensor accuracy. For example, as shown in the figure, when the accuracy of the radar is 90% in the longitudinal direction and 60% in the transverse direction, and the accuracy of the camera is 70% in the longitudinal direction and 90% in the transverse direction, the processor 110 can calculate and determine the position of the target vehicle 10a as follows. In this example case, the accuracy a of the radar is 90% in the longitudinal direction, the accuracy b of the camera is 70% in the longitudinal direction, the accuracy c of the radar is 60% in the transverse direction, and the accuracy d of the camera is 90% in the transverse direction.

[0101] For example, when the radar measures the longitudinal position of the target vehicle 10a as 10m and the camera measures the longitudinal position of the target vehicle 10a as 15m, the processor 110 can calculate [(radar 10m*(90 / (90+70))%+camera 15m*(70 / (90+70))%)]=12.2m.

[0102] In addition, when the radar measures the lateral position of the target vehicle 10a as 4m and the camera measures the lateral position of the target vehicle 10a as 3m, the processor 110 can calculate [(radar 4m*(60 / (60+90))%+camera 3m*(90 / (60+90))%)]=3.4m.

[0103] Figures 7 to 9 is a flowchart illustrating a method of controlling an autonomous driving vehicle according to an embodiment of the present disclosure.

[0104] Reference Figures 7 to 9 , a method for controlling an autonomous driving vehicle according to an embodiment of the present disclosure is as follows.

[0105] In operation S11 , the processor 110 may receive sensing information from the plurality of sensors 130 and determine whether a lane line of a driving road is recognized.

[0106] In operation S12, when a lane line of a driving road or a line of a lane is recognized, the processor 110 may store the recognized lane of the road or the recognized line of the lane.

[0107] In operation S13 , when a lane or a lane line of a driving road is not recognized, the processor 110 may set a virtual lane line VL including a driving lane and an adjacent lane next to the driving lane.

[0108] In operation S14 , the processor 110 may generate a virtual lane line VL based on the driving trajectory of the host vehicle 100 .

[0109] When the lane line of the driving road cannot be identified, the processor 110 can generate a virtual lane line VL based on the driving trajectory that the host vehicle 100 has already driven. In this example case, the virtual lane line VL may include the line of the host lane where the host vehicle 100 is driving and the line of the adjacent lane adjacent to the host lane. This has been described in detail above, and a more detailed description thereof will be omitted here.

[0110] In operation S15 , the processor 110 may initially recognize the target vehicle 10 a traveling laterally and rearwardly based on the generated virtual lane line VL.

[0111] The processor 110 can identify the outer sides of the front / rear tires of the target vehicle 10a in operation S16, calculate the lateral position of the target vehicle 10a and the heading angle of the target vehicle 10a based on the distance between the target vehicle 10a and the lane line of the road or the distance between the target vehicle 10a and the virtual lane line VL in operation S17, and determine the position of the target vehicle 10a based on this in operation S18.

[0112] The processor 110 may re-identify the target vehicle 10 a by changing the priorities of the plurality of sensors 130 based on the road environment in which the target vehicle 10 a is traveling, which is identified initially.

[0113] When the processor 110 is in a normal driving road environment where all sensors have no problem recognizing in operation S19, the processor 110 can calculate the longitudinal position of the target vehicle 10a and the speed of the target vehicle 10a by analyzing the sensing information provided by the first sensor 131 in operation S20, and calculate the lateral position of the target vehicle 10a and the heading angle of the target vehicle 10a by analyzing the sensing information provided by the second sensor 132 in operation S21.

[0114] When in operation S22, the camera's recognition of the target vehicle 10a and the lane line is limited in a dark road environment at night (which is not in a normal road environment), the processor 110 can calculate the longitudinal position of the target vehicle 10a, the speed of the target vehicle 10a, the lateral position of the target vehicle 10a, and the heading angle of the target vehicle 10a by analyzing the sensing information provided by the side rear radar in operation S23.

[0115] When the recognition of the side rear radar is limited in a diffuse reflection road environment or a heavy rain / heavy snow environment in operation S24, the processor 110 can determine the longitudinal position of the target vehicle 10a, the speed of the target vehicle 10a, the lateral position of the target vehicle 10a and the heading angle of the target vehicle 10a by analyzing the sensing information provided by the camera in operation S25.

[0116] Subsequently, in operation S26, the processor 110 may assign weights differently to the position of the target vehicle 10a during sensor fusion based on the error rate of each of the longitudinal and lateral directions of each of the plurality of sensors 130. This has been described above with reference to Figure 6 It has been described in detail, and a more detailed description thereof will be omitted here.

[0117] In operation S27 , the processor 110 may determine whether the host vehicle 100 has changed to a side adjacent lane.

[0118] In operation S33 , when the host vehicle 100 does not change to the adjacent lane as a result of the determination, the processor 110 may operate control of a warning and behavior capability assessment (BCA) function.

[0119] When the host vehicle 100 has changed to the adjacent lane and completed the entry in operation S28 , the processor 110 may activate a warning based on the lane in operation S31 .

[0120] When the host vehicle 100 has changed to the adjacent lane but has not completed the entry, the processor 110 may determine whether the target vehicle 10 a traveling on a lane next to the adjacent lane merges into the adjacent lane in operation S29 .

[0121] When it is determined that the target vehicle 10a traveling in the lane next to the adjacent lane has merged into the adjacent lane, the processor 110 may activate a warning based on the area in operation S32. In this example case, the processor 110 may warn the target vehicle 10a regardless of the lane.

[0122] When it is determined that the target vehicle 10a traveling in the lane beside the adjacent lane does not merge into the adjacent lane, the processor 110 may activate a warning based on the lane in operation S30. Therefore, issuing a warning to the target vehicle 10a traveling in the lane beside the adjacent lane may be suppressed.

[0123] The embodiments of the present disclosure described herein can be implemented as computer readable codes on a medium of a recording program. Computer readable media may include all types of recording devices storing data to be read by a computer system. Computer readable media may include, for example, hard disk drives (HDDs), solid state drives (SSDs), silicon disk drives (SDDs), read-only memories (ROMs), random access memories (RAMs), optical disk ROMs (CD-ROMs), magnetic tapes, floppy disks, optical data storage devices, etc.

[0124] Therefore, the foregoing detailed description should not be interpreted as limiting, but should be interpreted as illustrative in all aspects. The scope of possible embodiments of the present disclosure should be determined by reasonable interpretation of the appended claims, and all changes and modifications within the equivalent scope of the present disclosure may be included in the scope of the present disclosure.

Claims

1. A method for controlling an autonomous vehicle, the method comprising: Determine whether an actual lane line of the driving road is recognized by receiving sensing information from a plurality of sensors on the autonomous driving vehicle; Based on the result of the determination, initially identifying a target vehicle behind the autonomous vehicle and traveling in another lane; as well as The target vehicle is secondarily identified by changing priorities of the plurality of sensors based on the environment of the driving road.

2. The method according to claim 1, wherein: Secondary identification of the target vehicle includes: A weight is determined for each of the plurality of sensors based on an error rate of each of the plurality of sensors.

3. The method according to claim 2, further comprising: In response to not identifying an actual lane line of the driving road, generating at least one virtual lane line based on the driving trajectory of the autonomous vehicle, The at least one virtual lane line includes a first line of a first lane in which the autonomous vehicle is traveling and a second line of an adjacent lane.

4. The method according to claim 3, further comprising: The lateral position and heading angle of the target vehicle are determined based on the outer sides of the front and rear tires of the target vehicle and the distance between the target vehicle and the actual lane line of the driving road or the distance between the target vehicle and the at least one virtual lane line.

5. The method according to claim 4, wherein: The driving road environment includes one of a first environment, a second environment and a third environment, the first environment is a normal road environment, the second environment is a dark road environment, and the third environment is a heavy rain / heavy snow or diffuse reflection road environment.

6. The method according to claim 5, wherein: Secondary identification of the target vehicle includes: In the case of the first environment, the target vehicle is secondarily identified by operating the plurality of sensors at the same priority.

7. The method according to claim 5, wherein: Secondary identification of the target vehicle includes: In case of the second environment, the target vehicle is secondarily identified by operating the radar among the plurality of sensors with a first priority.

8. The method according to claim 5, wherein: Secondary identification of the target vehicle includes: In case of the third environment, the target vehicle is secondarily recognized by operating a camera among the plurality of sensors with a first priority.

9. The method according to claim 2, further comprising: Based on the setting of the determination weights, the position of the target vehicle is calculated.

10. A non-transitory computer-readable storage medium storing instructions, wherein the instructions are executed by a processor to cause the processor to perform the method according to any one of claims 1 to 9.

11. An autonomous vehicle, comprising: one or more processors; and A storage medium storing computer-readable instructions, which, when executed by the one or more processors, enable the one or more processors to: Determine whether an actual lane line of the driving road is recognized by receiving sensing information from a plurality of sensors on the autonomous driving vehicle; Based on the result of the determination, initially identifying a target vehicle behind the autonomous vehicle and traveling in another lane; as well as The target vehicle is secondarily identified by changing priorities of the plurality of sensors based on the environment of the driving road.

12. The autonomous vehicle according to claim 11, wherein: The instructions further enable the one or more processors to: In order to secondarily identify the target vehicle, a weight is set for each of the plurality of sensors based on an error rate of each of the plurality of sensors.

13. The autonomous vehicle according to claim 12, wherein: The instructions further enable the one or more processors to: In response to not identifying an actual lane line of the driving road, at least one virtual lane line is generated based on the driving trajectory of the autonomous vehicle.

14. The autonomous driving vehicle according to claim 13, wherein: The at least one virtual lane includes a first line of a first lane in which the autonomous vehicle is traveling and a second line of an adjacent lane.

15. The autonomous vehicle according to claim 13, wherein: The instructions further enable the one or more processors to: Based on the outer sides of the front and rear tires of the target vehicle and the distance between the target vehicle and the actual lane line of the driving road or the distance between the target vehicle and the at least one virtual lane line, the lateral position of the target vehicle and the heading angle of the target vehicle are calculated, and the target vehicle is identified based on the calculation results.

16. The autonomous vehicle according to claim 15, wherein: The driving road environment includes one of a first environment, a second environment and a third environment, the first environment is a normal road environment, the second environment is a dark road environment, and the third environment is a heavy rain / heavy snow or diffuse reflection road environment.

17. The autonomous vehicle according to claim 16, wherein: The instructions further enable the one or more processors to: In the case of the first environment, the target vehicle is secondarily identified by operating the plurality of sensors at the same priority.

18. The autonomous vehicle according to claim 16, wherein: The instructions further enable the one or more processors to: In case of the second environment, the target vehicle is secondarily identified by operating the radar among the plurality of sensors with a first priority.

19. The autonomous vehicle of claim 16, wherein: The instructions further enable the one or more processors to: In case of the third environment, the target vehicle is secondarily recognized by operating a camera among the plurality of sensors with a first priority.

20. The autonomous vehicle of claim 12, wherein: The instructions further enable the one or more processors to: Based on the setting of the determination weights, the position of the target vehicle is calculated.

Images