KR102176834B1 - Environment feature based position recognition apparatus and method for autonomous vehicles - Google Patents

Abstract

The present invention relates to a location recognition device based on environmental characteristics of an autonomous vehicle, a road map receiving unit that receives a road map with driving lane information, a specific height reference and a specific reflectance reference among at least one object received through a lidar sensor A road object determination unit that determines an object having an abnormality, a driving environment map generation unit that generates a driving environment map by reflecting the determined object on the road map, and determines the driving lane position of the vehicle based on the determined reflection angle pattern of the object And a driving lane positioning unit. Therefore, the present invention can recognize the position of the autonomous vehicle by recognizing an object having a high reflectance on the ground through the lidar information.

Description

Location recognition device and method based on environmental characteristics of autonomous vehicles {ENVIRONMENT FEATURE BASED POSITION RECOGNITION APPARATUS AND METHOD FOR AUTONOMOUS VEHICLES}

The present invention relates to a location recognition technology based on the environmental characteristics of a vehicle, and more particularly, the location based on environmental characteristics of an autonomous vehicle that recognizes the location of the autonomous vehicle by recognizing an object with high reflectance on the ground through LiDAR information. It relates to a recognition device and method.

An autonomous vehicle refers to a vehicle that can operate by itself without driver or passenger manipulation. The autonomous vehicle recognizes the location of its own vehicle through GNSS (Global Navigation Satellite Sysrem) like a navigation system and drives accordingly. Here, among autonomous driving technologies, position recognition is a technology that indicates one's own position, and is an essential technology that determines the precision of autonomous driving according to the robustness of position recognition. Location recognition technology in autonomous driving includes a satellite-based positioning system (GNSS) and a location recognition method using sensors mounted on autonomous vehicles. However, in shaded areas where satellite reception is difficult, such as tunnels and urban areas of high-rise buildings, location recognition errors are large, making outdoor autonomous driving difficult. In addition, the location recognition technique using a camera sensor is highly affected by the weather environment, and there is a problem in that outdoor features are not measured depending on the surrounding environment. Therefore, there is a need for a location recognition method through detection of an object that is not affected by shaded areas and is robust to the environment.

Korean Patent Publication No. 10-2007-0090426 (2007.09.06)

An embodiment of the present invention is to provide a location recognition apparatus and method based on environmental characteristics of an autonomous vehicle that recognizes an object having a high reflectance on the ground through LiDAR information to recognize the location of the autonomous vehicle.

An embodiment of the present invention is an autonomous vehicle that recognizes the location of an autonomous vehicle through detection of an object (object) that is robust to the environment without being affected by a shadowed area where satellites are difficult to receive, such as a tunnel or a high-rise building. To provide a location recognition device and method based on environmental characteristics of

An embodiment of the present invention is an environment and location recognition technology required for autonomous driving. An apparatus and method for recognizing a location based on environmental characteristics of an autonomous vehicle that can be used throughout autonomous driving means such as automobiles and outdoor robots related to autonomous driving. I want to provide.

Among the embodiments, the apparatus for recognizing a location based on environmental characteristics of an autonomous vehicle is a road map receiving unit that receives a road map with driving lane information, and a specific height reference and a specific reflectance reference among at least one object received through a lidar sensor. A road object determination unit that determines an object having a, a driving environment map generation unit that generates a driving environment map by reflecting the determined object on the road map, and determines a driving lane position of the vehicle based on the determined reflection angle pattern of the object. It includes a driving lane positioning unit.

The road map receiver may receive a location of a road sign disposed on an upper portion of a driving road and map it to the road map.

The road object determination unit may detect the road sign as the determined object through the lidar sensor when the position of the road sign is located within a specific distance during the driving process of the vehicle.

The road object determination unit may calculate the specific height reference and the specific reflectance reference based on the remaining distance to the road sign.

The road object determination unit may verify whether the determined object corresponds to the road sign based on the driving speed of the vehicle.

The driving lane position determining unit may determine a position of the vehicle between both lanes by detecting a ground object having a specific pattern among the at least one object.

The driving lane position determining unit may update the driving lane position of the vehicle by detecting reflection angle patterns of the signs.

The driving lane position determining unit may update the driving lane position of the vehicle by detecting the intention to change the lane of the vehicle based on the rate of change of the gap between the vehicles of the two lanes.

The driving lane position determining unit may determine the position of the driving lane of the vehicle by determining a center of the determined object and calculating angular deviations of both ends deviated from the center.

Among embodiments, the method for recognizing a location based on environmental characteristics of an autonomous vehicle includes receiving a road map having information on a driving lane, and having a specific height reference and a specific reflectance reference or higher among at least one object received through a lidar sensor. Determining an object, generating a driving environment map by reflecting the determined object on the road map, and determining a driving lane position of the vehicle based on the determined reflection angle pattern of the object.

The disclosed technology can have the following effects. However, since it does not mean that a specific embodiment should include all of the following effects or only the following effects, it should not be understood that the scope of the rights of the disclosed technology is limited thereby.

The apparatus and method for recognizing a location based on environmental characteristics of an autonomous vehicle according to an embodiment of the present invention may recognize an object having a high reflectance on the ground through LiDAR information to recognize the location of the autonomous vehicle.

The apparatus and method for recognizing a location based on environmental features of an autonomous vehicle according to an embodiment of the present invention are not affected by shadowed areas where satellites are difficult to receive, such as tunnels or high-rise buildings, through detection of objects that are robust to the environment. It can recognize the location of an autonomous vehicle. That is, the present invention enables robust location recognition required for autonomous driving outdoors, even in adverse weather conditions such as various and complex environments and heavy rain, and accordingly, the scope of application related to future autonomous driving is wide.

The device and method for location recognition based on environmental characteristics of an autonomous vehicle according to an embodiment of the present invention is a technology for recognizing the environment and location required for autonomous driving, and can be used throughout autonomous driving vehicles such as vehicles and outdoor robots related to autonomous driving. have.

FIG. 1 is a diagram illustrating a location recognition system based on environmental features of an autonomous vehicle according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a location recognition device based on environmental features of the autonomous vehicle of FIG. 1.
FIG. 3 is a block diagram showing a functional configuration of a location recognition device based on environmental features of the autonomous vehicle shown in FIG. 1.
4 is a flowchart illustrating a method of recognizing a location based on environmental features of an autonomous vehicle according to an embodiment of the present invention.

Since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, since the embodiments can be variously changed and have various forms, the scope of the present invention should be understood to include equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only those effects, the scope of the present invention should not be understood as being limited thereto.

Meanwhile, the meaning of terms described in the present application should be understood as follows.

Terms such as "first" and "second" are used to distinguish one component from other components, and the scope of rights is not limited by these terms. For example, a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component.

When a component is referred to as being "connected" to another component, it should be understood that although it may be directly connected to the other component, another component may exist in the middle. On the other hand, when it is mentioned that a certain component is "directly connected" to another component, it should be understood that no other component exists in the middle. On the other hand, other expressions describing the relationship between the constituent elements, that is, "between" and "just between" or "neighboring to" and "directly neighboring to" should be interpreted as well.

Singular expressions are to be understood as including plural expressions unless the context clearly indicates otherwise, and terms such as “comprise” or “have” refer to implemented features, numbers, steps, actions, components, parts, or It is to be understood that it is intended to designate that a combination exists and does not preclude the presence or addition of one or more other features or numbers, steps, actions, components, parts, or combinations thereof.

In each step, the identification code (for example, a, b, c, etc.) is used for convenience of explanation, and the identification code does not describe the order of each step, and each step has a specific sequence clearly in context. Unless otherwise stated, it may occur differently from the stated order. That is, each of the steps may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the field to which the present invention belongs, unless otherwise defined. Terms defined in commonly used dictionaries should be construed as having meanings in the context of related technologies, and cannot be construed as having an ideal or excessive formal meaning unless explicitly defined in the present application.

FIG. 1 is a diagram illustrating a location recognition system based on environmental features of an autonomous vehicle according to an embodiment of the present invention.

Referring to FIG. 1, a location recognition system based on environmental features of an autonomous vehicle 100 includes a location recognition device based on environmental features (110, hereinafter, a location recognition device based on environmental features), a lidar sensor 120, and Includes database 130.

The environment feature-based location recognition device 110 may correspond to a computing device that is connected to the lidar sensor 120 through a wired or wireless network to receive lidar information. In an embodiment, the environment feature-based location recognition device 110 may detect a specific object (road object) having high reflectivity based on LiDAR information to recognize the location of the autonomous vehicle. More specifically, the environment feature-based location recognition device 110 may estimate the location of the autonomous vehicle by generating a driving environment map by extracting environmental features for a specific object on the road and comparing it with the road map. For example, the environment feature-based location recognition device 110 can accurately recognize the location of an autonomous vehicle even in a place where satellite signals cannot be received, such as a tunnel.

The lidar sensor (Light Detection And Ranging, LIDAR) 120 may be mounted on the autonomous vehicle to provide point cloud information including reflectance and location information of a target to the autonomous vehicle. More specifically, the lidar sensor 120 emits light to a nearby target (object) of the autonomous vehicle and measures the time and intensity it takes for the light to return to the target object's distance, reflectance, direction, speed, temperature, and material. Distribution and concentration characteristics can be detected. The lidar sensor 120 may collect the detected lidar information as a point cloud and use it to generate a 3D map in real time. The lidar sensor 120 may be connected to the environment feature-based location recognition device 110 through a network to transmit and receive information including various kinds of lidar information.

The database 130 may store information necessary for the environment feature-based location recognition device 110 to perform location recognition of various types of autonomous vehicles including lidar information received from the lidar sensor 120. For example, the database 130 may store point cloud data, reflectance information of environmental objects on a road, and information on features such as the size and height of a specific object having a high extracted reflectance, but is not limited thereto, In the process of generating a driving environment map through objects on the road in the driving environment and recognizing the location of the autonomous vehicle by comparing it with the road map, information collected or processed in various forms may be stored. For example, the database 130 may receive and store a road map, and may generate and store an environment map. In one embodiment, the database 130 may correspond to a cloud-based map database of various methods for storing and storing maps.

FIG. 2 is a block diagram illustrating a location recognition device based on environmental features of the autonomous vehicle in FIG. 1.

Referring to FIG. 2, the environment feature-based location recognition device 110 may include a processor 210, a memory 220, a user input/output unit 230, and a network input/output unit 240.

The processor 210 receives LiDAR information, extracts specific objects in the environment, generates a driving environment map, and executes each procedure for recognizing (estimating) the location of the autonomous vehicle through comparison with the road map. , It is possible to manage the memory 220 that is read or written throughout the process, and a synchronization time between the volatile memory and the nonvolatile memory in the memory 220 can be scheduled. The processor 210 can control the overall operation of the environmental feature-based location recognition device 110, and is electrically connected to the memory 220, the user input/output unit 230, and the network input/output unit 240 to flow data between them. Can be controlled. The processor 210 may be implemented with a CPU (Central Processing Unit) and a GPU (Graphic Processing Unit) of the location recognition apparatus 110 based on environmental features.

The memory 220 is implemented as a non-volatile memory such as a solid state disk (SSD) or a hard disk drive (HDD), and includes an auxiliary storage device used to store all data required for the location recognition device 110 based on environmental characteristics. In addition, a main memory device implemented as a volatile memory such as random access memory (RAM) may be included.

The user input/output unit 230 may include an environment for receiving a user input and an environment for outputting specific information to a user. For example, the user input/output unit 230 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In one embodiment, the user input/output unit 230 may correspond to a computing device accessed through a remote connection, and in such a case, the environment feature-based location recognition device 110 may be performed as a server.

The network input/output unit 240 includes an environment for connecting to an external device or system through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN ( Value Added Network) may include an adapter for communication.

FIG. 3 is a block diagram showing a functional configuration of a location recognition device based on environmental characteristics of the autonomous vehicle shown in FIG. 1.

Referring to FIG. 3, the environment feature-based location recognition device 110 includes a road map receiving unit 310, a road object determining unit 320, a driving environment map generating unit 330, a driving lane position determining unit 340, and a control unit. 350 may be included.

The road map receiving unit 310 may receive a road map. Here, the road map may correspond to a map having various information about a road including information on a driving lane of the road. In an embodiment, the road map receiving unit 310 may receive a location of a road sign disposed on an upper portion of a driving road of a vehicle and map it to a road map. More specifically, the road map receiving unit 310 may receive a specific map or data having location information of a road sign of a driving road in a process of receiving a road map having only driving lane information and map it to a road map. For example, the road map receiving unit 310 may receive a specific precision map indicating in detail the location of a road sign on a driving road and map it to a road map. As a result, the road map receiving unit 310 may receive a road map including both driving lane information and location information of a road sign.

The road object determination unit 320 may determine an object having a specific height reference and a specific reflectance reference or higher among at least one object received through the lidar sensor 120. Here, the at least one object may correspond to a road sign, a curb, a center divider, a speed bump, etc. existing on a road, and may mean a road environment. More specifically, the road object determination unit 320 may determine one type of object having a specific height criterion and a specific reflectance criterion among at least one object such as a road sign and a center separator on the driving path of the vehicle. For example, the road object determination unit 320 may determine a road sign as an object by setting a specific height reference and a specific reflectance reference. In one embodiment, the road object determination unit 320 may detect the road sign as the determined object through the lidar sensor 120 when the position of the road sign is located within a specific distance during the driving process of the vehicle. More specifically, in the case of an autonomous vehicle, the road object determination unit 320 has already determined the positions of the vehicle and the road sign on a preset driving path, so if the position of the road sign is located within a specific distance from the vehicle, the lidar sensor Through this, road signs can be detected as objects. For example, when the position of the road sign is located within 10 meters in front of the vehicle, the road object determination unit 320 may detect the road sign using a lidar sensor.

In an embodiment, the road object determination unit 320 may calculate a specific height reference and a specific reflectance reference based on the remaining distance to the road sign. More specifically, the road object determination unit 320 may calculate a specific height reference and a specific reflectance reference smaller as the remaining distance to the road sign is smaller. For example, the road object determination unit 320 may determine to reduce a predetermined height reference and a specific reflectance reference to a predetermined ratio as the remaining distance to the road sign is reduced by a predetermined ratio. In an embodiment, the road object determination unit 320 may verify whether the determined object corresponds to a road sign based on the driving speed of the vehicle. For example, when the driving speed of the vehicle detected through the lidar sensor 120 decreases or increases, the road object determination unit 320 determines that the object corresponds to a road sign as a static object. If the driving speed of is not constant and fluctuates up and down, the object can be determined as another vehicle as a dynamic object. More specifically, the road object determination unit 320 may verify the road sign as an object by distinguishing it from other vehicles based on a constant decrease or increasing driving speed of the vehicle.

The driving environment map generation unit 330 may generate a driving environment map by reflecting the determined object on the road map. In an embodiment, the driving environment map generation unit 330 may generate a driving environment map by reflecting the road sign on the road map. More specifically, the driving environment map generation unit 330 extracts features such as the size, center point, reflectance, and height of the road sign using a road sign having high reflectivity on the ground as an object, and reflects it on the road map to create a driving environment map. Can be generated.

The driving lane position determining unit 340 may determine a driving lane position of the vehicle based on the determined reflection angle pattern of the object. More specifically, the driving lane positioning unit 340 may determine in which lane the vehicle is driving according to a pattern of reflection angles reflected from the object of the beam emitted through the lidar sensor 120. For example, the driving lane position determining unit 340 reflects the reflection angle pattern of the beam emitted from the lidar sensor 120 of the vehicle based on the number of lanes determined on the road map and the position of the road sign as the determined object. It is possible to determine the location of the driving lane of the vehicle through a specific reflection angle pattern for the road sign at a specific location by detecting. That is, the driving lane position determining unit 340 detects the number of lanes on the road from the road map, detects the location of the determined object on the road, reflects it on the road map, generates a driving environment map, and creates a road sign based on the driving environment map. By detecting the reflection angle pattern of, the driving lane position of the vehicle may be determined according to the reflection angle pattern. For example, the driving lane positioning unit 340 may determine how many (some) lanes a vehicle is in through a difference between the reflection angle of a specific road sign for a vehicle located in one lane and a reflection angle of the same road sign for a vehicle located in three lanes. You can decide if it is located. For example, on a road with three lanes, the reflection angle of a vehicle traveling in one lane and a vehicle traveling in three lanes is opposite to the road sign located at the top over one to three lanes. As it appears, it is possible to determine whether the vehicle is traveling in one lane or three lanes, respectively.

In an embodiment, the driving lane position determining unit 340 may determine a position of a vehicle between two lanes by detecting a ground object having a specific pattern among at least one object. For example, the driving lane positioning unit 340 may detect both lanes as a ground object having a specific pattern. The driving lane position determining unit 340 may determine the position of the vehicle between the detected lanes by detecting both lanes on the ground having a specific pattern such as a color of the lane, a solid line or a dotted line. More specifically, the driving lane position determining unit 340 may accurately detect the relative position of the vehicle between the two lanes by detecting the positions of both lanes of the lane on which the vehicle is running through the lidar sensor 120. That is, the driving lane position determining unit 340 may determine whether the vehicle is driving in the center between the two lanes or is skewed toward one lane. In an embodiment, the driving lane position determining unit 340 may update the driving lane position of the vehicle by detecting the intention to change the lane of the vehicle based on the rate of change of the distance between the two lanes and the vehicle. The driving lane position determining unit 340 may detect a lane change intention of the vehicle by calculating a rate of change according to a change in the distance between the two lanes detected through the lidar sensor 120 and the vehicle. For example, the driving lane position determining unit 340 determines that the vehicle has an intention to change the lane to the right lane when the distance between the right lane among the two lanes of the vehicle decreases by more than a certain standard, and the driving lane position of the vehicle Can be updated to the right lane after a certain period of time.

In an embodiment, the driving lane position determining unit 340 may determine the location of the driving lane of the vehicle by determining the center of the determined object and calculating angular deviations of both ends deviated from the center. For example, the driving lane position determination unit 340 may determine the center of the road sign through the lidar sensor 120 and calculate the angle deviation from the center of both ends of the road sign to determine the driving lane position of the vehicle. have. The driving lane position determining unit 340 may determine how many lanes the vehicle is driving based on the angular deviation of both ends from the center of a road sign that varies according to each lane in which the vehicle is located. For example, the driving lane positioning unit 340 detects the angular deviation of both ends at the center of the road sign located above the first lane, and if the angular deviation of both ends is the same, the vehicle travels in the first lane. It can be detected as being present.

The control unit 350 performs overall control of the environment feature-based location recognition device 110, and a road map receiving unit 310, a road object determining unit 320, a driving environment map generating unit 330, and a driving lane position determining unit Control flow and data flow between 340 can be managed.

4 is a flow chart illustrating a method for recognizing a location based on environmental features of an autonomous vehicle according to an embodiment of the present invention.

In FIG. 4, the environment feature-based location recognition apparatus 110 may receive a road map having driving lane information through the road map receiving unit 310 (step S410). In an embodiment, the road map receiving unit 310 may periodically download a road map having driving lane information or road sign information updated in real time in connection with a cloud-based map database. In an embodiment, the road map receiving unit 310 may detect a specific area in which the vehicle is located based on the lidar information received from the lidar sensor 120 and selectively receive a road map for the corresponding region.

The environment feature-based location recognition device 110 may determine, through the road object determination unit 320, an object having a specific height reference and a specific reflectance reference or higher among at least one object received from the lidar sensor 120 ( Step S420). In an embodiment, the road object determination unit 320 may determine a road sign having a predetermined height reference and a specific reflectance reference or higher as the object.

The environment feature-based location recognition device 110 may generate a driving environment map by reflecting the determined object on the road map through the driving environment map generator 330 (step S430).

The environment feature-based location recognition device 110 may determine the location of the vehicle's driving lane based on the determined reflection angle pattern of the object through the driving lane position determining unit 340 (step S440).

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art will variously modify and change the present invention within the scope not departing from the spirit and scope of the present invention described in the following claims. You will understand that you can do it.

100: Location recognition system based on environmental characteristics of autonomous vehicles
110: Location recognition device based on environmental characteristics of an autonomous vehicle
120: lidar sensor
130: database
210: processor 220: memory
230: user input/output unit
240: network input/output unit
310: road map receiving unit 320: road object determining unit
330: driving environment map generation unit 340: driving lane position determination unit
350: control unit

Claims (9)

A road map receiving unit for receiving a road map having driving lane information;
A road object determination unit that determines an object having a specific height reference and a specific reflectance reference or higher among at least one object received through the lidar sensor;
A driving environment map generation unit configured to generate a driving environment map by reflecting the determined object having a specific height reference and a specific reflectance standard or higher on the road map; And
A driving lane position determining unit for determining a driving lane position of the vehicle based on the determined reflection angle pattern of the object and the number of lanes determined in the road map,
The road map receiver
Receiving the position of the road sign disposed on the top of the driving road and mapping it to the road map,
The road object determination unit
The location recognition device based on environmental characteristics of an autonomous vehicle, characterized in that calculating the specific height reference and the specific reflectance reference based on the remaining distance to the road sign.
delete The method of claim 1, wherein the road object determination unit
When the position of the road sign is located within a specific distance during the driving process of the vehicle, the road sign is detected as the determined object through the lidar sensor.
delete The method of claim 1, wherein the road object determination unit
An apparatus for recognizing a location based on environmental characteristics of an autonomous vehicle, characterized in that it verifies whether the determined object corresponds to the road sign based on the driving speed of the vehicle.
The method of claim 1, wherein the driving lane positioning unit
An apparatus for recognizing a location based on environmental features of an autonomous vehicle, comprising detecting a ground object having a specific pattern among the at least one object to determine the location of the vehicle between both lanes.
The method of claim 6, wherein the driving lane positioning unit
An environmental feature-based location recognition apparatus for an autonomous vehicle, characterized in that, based on a rate of change of the distance between the two lanes and the vehicle, the vehicle's intention to change lanes is detected to update the location of the vehicle's driving lane.
The method of claim 1, wherein the driving lane positioning unit
A position recognition device based on environmental characteristics of an autonomous vehicle, characterized in that the determined center of the object is determined and angle deviations of both ends deviated from the center are calculated to determine the location of the driving lane of the vehicle.
A road map receiving step of receiving a road map having driving lane information;
A road object determining step of determining an object having a specific height reference and a specific reflectance reference or more among at least one object received through the lidar sensor;
A driving environment map generating step of generating a driving environment map by reflecting the determined object having the specific height criterion and the specific reflectance criterion or higher on the road map; And
A driving lane position determining step of determining a driving lane position of the vehicle based on the determined reflection angle pattern of the object and the number of lanes determined in the road map,
The step of receiving the road map
Receiving the position of the road sign disposed on the top of the driving road and mapping it to the road map,
The step of determining the road object is
And calculating the specific height reference and the specific reflectance reference based on the remaining distance to the road sign.

Images