KR20240080313A - Electronic device and method for tracking lane information of vehicle - Google Patents

Abstract

In embodiments, a vehicle device for tracking lane information includes a memory including a map, at least one sensor including LiDAR (laser image detection and ranging), at least one transceiver, and at least May include one processor. The at least one processor obtains lane information based on the map, identifies whether the vehicle is driving in a straight section or a curved section based on the lane information, and determines whether the vehicle is traveling in the curved section. When driving, navigation information of the vehicle is estimated based on the first parameter set, and when the vehicle is traveling in the straight section, a second parameter set that is a subset of the first parameter set is used. Based on this, it may be configured to estimate navigation information of the vehicle.

Description

Device and method for tracking lane information of a vehicle {ELECTRONIC DEVICE AND METHOD FOR TRACKING LANE INFORMATION OF VEHICLE}

The descriptions below relate to an apparatus and method for tracking lane information of a vehicle.

A vehicle precision navigation system for autonomous vehicles may be used. To control autonomous vehicles and determine driving routes, the vehicle can estimate the vehicle's navigation information using INS (Inertial Navigation System) and GNSS (Global Navigation Satellite System).

In embodiments, a vehicle device for tracking lane information includes a memory including a map, at least one sensor including LiDAR (laser image detection and ranging), at least one transceiver, and at least May include one processor. The at least one processor obtains lane information based on the map, identifies whether the vehicle is driving in a straight section or a curved section based on the lane information, and determines whether the vehicle is traveling in the curved section. When driving, navigation information of the vehicle is estimated based on the first parameter set, and when the vehicle is traveling in the straight section, a second parameter set that is a subset of the first parameter set is used. Based on this, it may be configured to estimate navigation information of the vehicle.

1A shows an example of a moving environment of an autonomous vehicle according to embodiments.
1B shows examples of operations for estimating vehicle navigation information according to embodiments.
2 shows examples of operations for estimating correction information according to embodiments.
Figure 3 shows an example of lane tracking using correction information, according to one embodiment.
Figure 4 shows the functional configuration of a vehicle device for performing lane tracking according to one embodiment.

Terms used in the present disclosure are merely used to describe specific embodiments and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions, unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by a person of ordinary skill in the technical field described in this disclosure. Among the terms used in this disclosure, terms defined in general dictionaries may be interpreted to have the same or similar meaning as the meaning they have in the context of related technology, and unless clearly defined in this disclosure, have an ideal or excessively formal meaning. It is not interpreted as In some cases, even terms defined in the present disclosure cannot be interpreted to exclude embodiments of the present disclosure.

In various embodiments of the present disclosure described below, a hardware approach method is explained as an example. However, since various embodiments of the present disclosure include technology using both hardware and software, the various embodiments of the present disclosure do not exclude software-based approaches.

Terms for operation states used in the following description (e.g., step, operation, procedure, block), terms referring to data (e.g., parameter, information) ), bit, symbol, codeword), terms referring to network entities, terms referring to device components, etc. are exemplified for convenience of explanation. Accordingly, the present disclosure is not limited to the terms described below, and other terms having equivalent technical meaning may be used.

In addition, in the present disclosure, the expressions greater than or less than may be used to determine whether a specific condition is satisfied or fulfilled, but this is only a description for expressing an example, and the description of more or less may be used. It's not exclusion. Conditions written as ‘more than’ can be replaced with ‘more than’, conditions written as ‘less than’ can be replaced with ‘less than’, and conditions written as ‘more than and less than’ can be replaced with ‘greater than and less than’. In addition, hereinafter, 'A' to 'B' means at least one of the elements from A to (including A) and B (including B).

Now, a method for estimating navigation information of a vehicle according to an embodiment of the present invention will be described with reference to the drawings. In the present disclosure, the vehicle's navigation information may include the vehicle's location, vehicle's speed, and vehicle's attitude information.

1A shows an example of a moving environment of an autonomous vehicle according to embodiments.

Referring to FIG. 1A, a vehicle can move along a lane. A vehicle performing autonomous driving service is between a lane located on one side of the vehicle (e.g., left) (hereinafter referred to as first lane) and a lane located on the other side of the vehicle (e.g., right) (hereinafter referred to as second lane). You can drive in . The space between the first lane and the second lane may be referred to as a road. The vehicle can drive on the lane. The vehicle navigates the first lane, the second lane, or the second lane through various systems (e.g., global navigation system (GNSS), inertial navigation system (INS), laser image detection and ranging (LiDAR)) disposed in the vehicle. Information about the lane can be estimated.

GNSS frequently suffers from signal blocking and distortion in urban environments, and in this case, the accuracy of INS used alone gradually decreases over time. To solve the above-described problems, embodiments of the present disclosure propose a technology for estimating accurate navigation information of a vehicle based on LiDAR and precision maps. Navigation information for autonomous vehicles can be estimated based on INS, GNSS, LiDAR, and precise maps. In the present disclosure, an area of interest is set based on location information estimated by INS and/or GNSS, and the vehicle's navigation information is corrected by using lane information detected through LiDAR and precision map lane information within the area of interest together. The technology used is described.

1B shows examples of operations for estimating vehicle navigation information according to embodiments.

Referring to FIG. 1B, the system for estimating vehicle navigation information according to the present embodiments includes an inertial navigation system (INS) 101, a global navigation system (GNSS) 102, a vehicle navigation information estimation block 103, LiDAR (laser image detection and ranging) (104), precision map (105), region of interest (106), LiDAR-based lane detection block (107), lane information extraction block of precision map (108), straight ahead and turn judgment block ( 109), and may include a matching and correction information estimation block 110. Each block may be implemented in the form of software or a combination of hardware and software, and hereinafter used '... part', '... device', '... thing', '... Terms such as 'body' may refer to at least one shape structure or a unit that processes a function.

The INS (101) can be used to estimate the vehicle's navigation information using the linear acceleration and rotational angular velocity values according to the vehicle's 6-degree of freedom movement measured by the IMU (Inertial Measurement Unit) mounted on the vehicle. there is.

The GNSS 102 is a satellite navigation system such as GPS and Galileo, and can acquire vehicle navigation information through a receiver that receives satellite signals.

The vehicle navigation information estimation block 103 may basically have the function of estimating the attitude, speed, and position of the vehicle by combining the INS 101 and GNSS 102 information. As the LiDAR 104 and the precision map 105 are matched, the vehicle navigation information estimation block 103 has a function of estimating corrected navigation information by additionally using the estimated correction information.

LiDAR 104 mounted on a vehicle is a device that can recognize surrounding objects through signals reflected from objects within a range within which the transmitted signal can be reached. In this disclosure, LiDAR 104 may be used to detect lanes.

The precision map (105) is an accurate map capable of distinguishing between lanes, and must be built into the navigation computer mounted on the vehicle.

The area of interest 106 is used to detect lanes among signals obtained through LiDAR, and the vehicle can set the road between the center line and the curb among the areas in front of the vehicle as the area of interest.

The LiDAR-based lane detection block 107 uses reflection intensity among signals acquired through LiDAR. By taking advantage of the fact that lanes have a higher reflection intensity than regular roads, the LiDAR-based lane detection block 107 can detect lanes.

The lane information extraction block 108 of the precision map may separately extract lane information of an area corresponding to an area of interest in the precision map.

The straight ahead and turn determination block 109 can extract center line information (or may be referred to as lane information) from lane information of the extracted precision map. The straight ahead and turn determination block 109 can identify whether the corresponding lane is a straight section or a curved section based on center line information. For example, the straight ahead and turn determination block 109 uses the center line information of the lane as a quadratic function. After regression, if a is close to 0 (e.g., whether a is less than a specified threshold (e.g., 0.1)), the lane can be identified as a straight section. Meanwhile, the straight ahead and turn determination block 109 may determine that the lane is a curved section if a is not close to 0.

The matching and correction information estimation block 110 estimates information corresponding to INS/GNSS or INS navigation error (hereinafter, error information) through matching LiDAR lanes and precision map lanes. The error information is fed back to the vehicle navigation information estimation block 103 and can be used as a measurement value for the complex navigation filter.

2 shows examples of operations for estimating correction information according to embodiments. In Figure 2, specific operations of the matching and correction information estimation block 110 of Figure 1 are described.

Referring to Figure 2, the vehicle can match lane information acquired through LiDAR and lane information extracted from a precision map through the Point-to-Plane ICP (Iterative Closest Point) algorithm.

In order to perform the matching, in operation 201, the vehicle can identify whether the front of the vehicle is a straight section or a turning section, that is, whether the lane in which the vehicle is traveling is a straight section or a turning section. . When the lane is a turning section, the vehicle may perform operation 202. If the lane is a straight section, the vehicle can perform operation 203.

In the turning section, the vehicle can obtain a first set of parameters. As parameters used for registration, the vehicle selects the x parameter, y parameter, and z parameter corresponding to the relative position of LiDAR information compared to the precision map, and the roll parameter, pitch parameter, and yaw parameter corresponding to the relative posture. By matching the two pieces of information to estimate the relative position and relative speed of the LiDAR compared to the precision map, the vehicle can estimate the position error and speed error included in the vehicle navigation information. Here, the y-axis refers to the forward direction of the vehicle in the precision map, the x-axis refers to the right side direction, and the z-axis refers to the vertical upward direction, and the roll parameter, pitch parameter, and yaw parameter refer to the precision map and the precision map based on the y-axis, x-axis, and z-axis, respectively. This refers to the Euler angle of LiDAR information.

In the straight section, the vehicle can obtain a second set of parameters. As parameters used for registration, the vehicle can only select the x and yaw parameters that correspond to the relative position of the LiDAR information compared to the precision map. The x parameter and yaw parameter may represent the difference between LiDAR information and a precision map on a plane perpendicular to the z-axis, which is the central axis of yaw. In the straight section, other parameters (e.g., y value, z value, roll parameter, pitch parameter) may not be used because the possibility of accurate estimation is low.

As depicted in FIG. 2, navigation estimation is performed by distinguishing whether the road in the forward direction of the vehicle is a straight section or a turning section and running a matching algorithm (e.g., point-to-plane ICP algorithm) using different parameters. Not only can accuracy be improved, but the amount of unnecessary calculations in autonomous vehicles can be reduced. By performing registration of precision maps and LiDAR information using different parameter sets depending on road conditions, the parameters estimated for correction can be fed back to the vehicle navigation information estimation block 103 and used as measurements of the complex navigation filter.

Figure 3 shows an example of lane tracking using correction information, according to one embodiment.

Referring to FIG. 3, forward lane information 302 extracted based on the vehicle's position on the precision map indicates the forward direction as the y-axis and the right side direction as the x-axis. The navigation information of the vehicle 301 is acquired through INS and/or GNSS and INS and includes errors, and based on this, the lane information 303 acquired through LiDAR is separated from the lane information 302 on the precision map. and there is a difference in direction. The vehicle can determine whether it is a straight road or a turning road using the forward direction lane information on the precision map and then set parameters (or parameter sets) to match the lane information on the precision map with the lane information on the LiDAR.

According to one embodiment, when the vehicle's lane is a turning road, the vehicle may set parameters other than the 3-axis position error and parameters according to the 3-axis attitude error as a parameter set for lane matching.

According to one embodiment, when the vehicle's lane is a straight road, the vehicle may set only the x-axis position error and yaw attitude error as a parameter set for lane matching. The vehicle can perform registration between precision maps and LiDAR through the Point-to-Point ICP algorithm. Through the above matching, the LiDAR-based lane information 304 can be matched to the precision map lane information 302. Parameters selected in this process can be estimated by the vehicle. This estimated information (e.g., parameters) is fed back to the vehicle navigation information estimation 103 and can be used as a measurement value of the navigation filter to estimate and correct the error of the INS. By repeating the series of operations described above, the vehicle's systems can track the correct lane while the vehicle is driving. By correctly tracking lanes, more effective autonomous driving services can be provided.

Figure 4 shows the functional configuration of a vehicle device for performing lane tracking according to one embodiment. The vehicle device can perform autonomous driving through the lane tracking. Terms such as '... unit' and '... unit' used hereinafter refer to a unit that processes at least one function or operation, which can be implemented through hardware, software, or a combination of hardware and software. there is.

Referring to FIG. 4, the vehicle device is a component for performing lane tracking according to embodiments of the present disclosure and may include a processor 410, a sensor 420, a transceiver 430, and a memory 440. You can.

The processor 410 controls overall operations of the vehicle device. The processor 410 may be referred to as a control unit of the vehicle device. For example, processor 410 transmits and receives signals through a vehicle device (or through a backhaul communication unit). Additionally, the processor 410 writes and reads data into the memory 440. Additionally, the processor 410 can perform protocol stack functions required by communication standards. Although only the processor 410 is shown in FIG. 4, according to another implementation example, the vehicle device may include two or more processors.

The sensor 420 may include at least one sensor for detecting movement of the vehicle device, state changes around the vehicle device, and state changes inside the vehicle device. For example, sensor 420 may include a GNSS sensor. GNSS sensors can receive signals from one or more satellites. Also, for example, sensor 420 may include an IMU sensor. Through the IMU sensor, the vehicle device can acquire the tilt angle or movement state of the vehicle device. Also, for example, sensor 420 may include a LiDAR sensor. LiDAR sensors can measure the distance, position, and shape of objects around a vehicle device through reflected light.

The transceiver 430 may perform functions for transmitting and receiving signals in a wireless communication environment. For example, the transceiver 430 may perform a conversion function between a baseband signal and a bit string according to the physical layer standard of the system. For example, when transmitting data, the transceiver 430 generates complex symbols by encoding and modulating the transmission bit stream. Additionally, when receiving data, the transceiver 430 restores the received bit stream by demodulating and decoding the baseband signal. Additionally, the transceiver 430 may include multiple transmission and reception paths. Although only the transceiver 430 is shown in FIG. 4, according to another implementation example, the vehicle device may include two or more transceivers. According to one embodiment, the transceiver 430 may communicate with an external server. For example, the vehicle device may obtain information about a precise map of the area where the vehicle device is located through the transceiver 430. Additionally, for example, the vehicle device may provide data or parameter values requiring analysis to an external server through the transceiver 430.

The transceiver 430 transmits and receives signals as described above. Accordingly, all or part of the transceiver 430 may be referred to as a 'communication unit', a 'transmission unit', a 'reception unit', or a 'transmission/reception unit'. Additionally, in the following description, transmission and reception performed through a wireless channel are used to mean that the processing as described above is performed by the transceiver 430.

The memory 440 stores data such as basic programs, application programs, and setting information for operating vehicle devices. Memory 440 may be referred to as a storage unit. The memory 440 may be comprised of volatile memory, non-volatile memory, or a combination of volatile memory and non-volatile memory. And, the memory 440 provides stored data according to the request of the processor 410. For example, the memory 440 may store information about a precise map according to the movement of the vehicle device. The memory 440 may output information about a precision map according to a request from the processor 410.

In embodiments, a vehicle device for tracking lane information includes a memory including a map, at least one sensor including LiDAR (laser image detection and ranging), at least one transceiver, and at least May include one processor. The at least one processor obtains lane information based on the map, identifies whether the vehicle is driving in a straight section or a curved section based on the lane information, and determines whether the vehicle is traveling in the curved section. When driving, navigation information of the vehicle is estimated based on the first parameter set, and when the vehicle is traveling in the straight section, a second parameter set that is a subset of the first parameter set is used. Based on this, it may be configured to estimate navigation information of the vehicle.

According to one embodiment, the first parameter set includes x parameters, y parameters, and z parameters corresponding to the relative positions of the detected lane information obtained through LiDAR compared to the lane information of the map, and the detected lane information compared to the lane information. It may include roll parameters, pitch parameters, and yaw parameters corresponding to the relative posture of the lane information. The second parameter set may include the x parameter and the yaw parameter, and may not include the y parameter, the z parameter, the roll parameter, and the pitch parameter.

According to one embodiment, the at least one processor may be additionally configured to set an area of interest based on at least one of a global navigation system (GNSS) or an inertial navigation system (INS). The lane information may be obtained based on the area of interest. Detected lane information obtained through the LiDAR may be obtained based on the area of interest.

According to one embodiment, the navigation information of the vehicle may include at least one of the location of the vehicle, the speed of the vehicle, and the attitude information of the vehicle.

According to one embodiment, the values of the first parameter set or the values of the second parameter set are, for a point-to-plane ICP algorithm, the sensed lane information obtained through the LiDAR compared to the lane information of the map. It can be decided based on the difference.

For autonomous driving, parameters for correcting the position or posture of the vehicle (e.g., x, y, z in the xyz coordinate system, roll, pitch, yaw in the direction coordinate system) can be variably adjusted. At this time, the vehicle can identify a parameter set that needs to be adjusted by determining whether the lane on which the vehicle is traveling is a straight section or a curved section. The vehicle can match LiDAR information with lane information of a precision map by variably adjusting the estimated parameters of the ICP (Point-to-Plane) algorithm through the identified parameter set. Additionally, the vehicle may correct navigation information of the vehicle.

Methods according to embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

When implemented as software, a computer-readable storage medium that stores one or more programs (software modules) may be provided. One or more programs stored in a computer-readable storage medium are configured to be executable by one or more processors in a vehicle device (configured for execution). One or more programs include instructions that cause the vehicle device to execute methods according to embodiments described in the claims or specification of the present disclosure.

These programs (software modules, software) may include random access memory, non-volatile memory, including flash memory, read only memory (ROM), and electrically erasable programmable ROM. (electrically erasable programmable read only memory, EEPROM), magnetic disc storage device, compact disc-ROM (CD-ROM), digital versatile discs (DVDs), or other types of disk storage. It can be stored in an optical storage device or magnetic cassette. Alternatively, it may be stored in a memory consisting of a combination of some or all of these. Additionally, multiple configuration memories may be included.

In addition, the program may be distributed through a communication network such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), or a storage area network (SAN), or a combination thereof. It may be stored on an attachable storage device that is accessible. This storage device can be connected to a device performing an embodiment of the present disclosure through an external port. Additionally, a separate storage device on a communications network may be connected to the device performing embodiments of the present disclosure.

In the specific embodiments of the present disclosure described above, elements included in the disclosure are expressed in singular or plural numbers depending on the specific embodiment presented. However, singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components, and even components expressed in plural may be composed of singular or singular. Even expressed components may be composed of plural elements.

Meanwhile, in the detailed description of the present disclosure, specific embodiments have been described, but of course, various modifications are possible without departing from the scope of the present disclosure.

Claims (5)

In a vehicle device for tracking lane information,
memory containing a map;
At least one sensor including laser image detection and ranging (LiDAR);
at least one transceiver; and
Contains at least one processor,
The at least one processor,
Obtain lane information based on the map,
Based on the lane information, identify whether the vehicle is driving in a straight section or a curved section,
When the vehicle is driving in the curved section, estimate navigation information of the vehicle based on a first parameter set,
When the vehicle is traveling in the straight section, configured to estimate navigation information of the vehicle based on a second parameter set, which is a subset of the first parameter set,
Device.
The method according to claim 1, wherein the first parameter set includes x parameters, y parameters, and z parameters corresponding to the relative positions of the detected lane information obtained through the LiDAR compared to the lane information of the map, and the detected lane compared to the lane information. Includes roll parameters, pitch parameters, and yaw parameters corresponding to the relative posture of the information,
wherein the second parameter set includes the x parameter and the yaw parameter and does not include the y parameter, the z parameter, the roll parameter, and the pitch parameter.
Device.
In claim 1,
The at least one processor,
It is further configured to set an area of interest based on at least one of a global navigation system (GNSS) or an inertial navigation system (INS),
The lane information is obtained based on the area of interest,
The detection lane information obtained through the LiDAR is obtained based on the area of interest,
Device.
In claim 1,
The navigation information of the vehicle includes at least one of the location of the vehicle, the speed of the vehicle, and the attitude information of the vehicle.
Device.
In claim 1,
The values of the first parameter set or the values of the second parameter set are determined based on the difference between the detected lane information obtained through the LiDAR compared to the lane information of the map for the point-to-plane ICP algorithm. ,
Device.