KR102705940B1 - System and method for determining location of a vehicle using historical information of roads and lanes - Google Patents

Abstract

The present invention provides a vehicle position determination method using history information of roads and lanes and a system applying the same. The vehicle position determination system according to the present invention includes a sensor unit that collects road/lane information on which a vehicle is driving and inertial sensing information of the vehicle; a road/lane history information generation unit that generates road/lane shape history information by fusing the road/lane information and the inertial sensing information; and a position determination unit that determines the position of the vehicle in a precision map using a result of matching the road/lane shape history information and precision map information. The road/lane information includes at least one of a road width, a road curvature, a lane width, a lane curvature, the number of lanes, and a lane type, and the inertial sensing information includes at least one of a speed, an acceleration, a yaw angle, a yaw velocity, a pitch angle, a pitch angular velocity, a roll angle, a roll angular velocity, a gravitational acceleration, and a gravity of the vehicle.

Description

{SYSTEM AND METHOD FOR DETERMINING LOCATION OF A VEHICLE USING HISTORICAL INFORMATION OF ROADS AND LANES}

The present invention relates to a system and method for determining or correcting a vehicle's position using sensing information.

Autonomous driving uses environmental sensors such as cameras and radar to identify surrounding obstacles, lanes, and road information, and receives GNSS (Global Navigation Satellite System) information to estimate the current vehicle location, guide the future route, and perform detailed vehicle behavior control considering avoidance of accidents with surrounding obstacles.

When GNSS information reception is not smooth, route guidance is performed through dead reckoning (DR), which temporarily estimates the vehicle's location by estimating the vehicle's behavior using inertial sensor (velocity, acceleration, yaw rate) values. However, since DR through inertial sensors accumulates errors over time, there is a safety issue when using it for route guidance. In particular, when driving on a route under an overpass surrounded by surrounding buildings, such as under an overpass in Seoul, GNSS signals are not received. In this case, there is a problem that accurate route guidance using inertial sensors is not easy because the road is complex.

The present invention aims to provide a method for determining a vehicle's own position and a system applying the same, which uses lane information or road information acquired by a sensor such as a camera for environmental recognition for correction or as a substitute for GNSS in a situation where it is difficult to receive GNSS information, to enable a vehicle to move, in order to solve the above-mentioned problems.

The present invention provides a method for determining a vehicle's own position and a system applying the same, which generates road/lane shape history information including road curvature and gradient (elevation information) by fusing lane recognition information (width and curvature of roads and lanes, etc.) using a camera and vehicle sensor information (speed, acceleration, yaw angle, pitch angle, roll angle, gravitational acceleration/gravity, etc.) and uses the same to increase the reliability of GNSS-based map matching position determination, and performs a function of determining the vehicle's position by comparing the road lane shape history information with precision map information in tunnels, etc., where GNSS reception is not smooth, thereby enhancing the driving performance of autonomous vehicles.

According to one embodiment of the present invention for achieving the above object, a vehicle position determination system includes: a sensor unit for collecting road/lane information on which a vehicle is driving and inertial sensing information of the vehicle; a road/lane history information generation unit for generating road/lane shape history information by fusing the road/lane information and the inertial sensing information; and a position determination unit for determining a position of the vehicle in a precision map by using a result of matching the road/lane shape history information and precision map information. The road/lane information includes at least one of a road width, a road curvature, a lane width, a lane curvature, the number of lanes, and a lane type, and the inertial sensing information includes at least one of a speed, an acceleration, a yaw angle, a yaw velocity, a pitch angle, a pitch angular velocity, a roll angle, a roll angular velocity, a gravitational acceleration, and a gravity of the vehicle.

The above sensor unit may include a road/lane recognition unit that recognizes the road/lane information through a road/lane recognition camera; and an inertial sensor unit that obtains inertial sensing information of the vehicle.

The above road/lane history information generation unit can generate road/lane shape history information including curvature and slope information of the road on which the vehicle has driven from a predetermined time ago to the present.

In addition, the road/lane history information generation unit stores the road/lane shape history information in internal storage, and can vary the collection cycle of the road/lane shape history information based on at least one of the slope and curvature of the road.

The above position determining unit can determine the position of the vehicle in the precision map by comparing a predetermined section of the precision map and the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.

And, a vehicle position determination system according to one embodiment of the present invention includes a position detection unit that detects a global position of a vehicle based on a GNSS signal; a position recognition unit that matches a precision map to the global position to recognize the position of the vehicle in the precision map; and a position correction unit that corrects the position of the vehicle in the precision map by utilizing the result of matching the road/lane shape history information and the precision map.

The above position correction unit can generate road/lane shape history information including curvature and slope information of the road on which the vehicle has driven from a predetermined time ago to the present.

In addition, the position correction unit stores the road/lane shape history information in an internal storage, and can vary the collection cycle of the road/lane shape history information based on at least one of the slope and curvature of the road.

In addition, the position correction unit can determine the position of the vehicle in the precision map by comparing a predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.

In addition, the position correction unit can determine the position of the vehicle by matching the shape history information of the road/lane and the precision map when the position detection unit fails to receive a GNSS signal.

And, a vehicle position determination method according to one embodiment of the present invention includes a step of recognizing road/lane information on which a vehicle is driving through a sensor; a step of obtaining inertial sensing information of the vehicle; a road/lane history information generation step of generating road/lane shape history information by fusing the road/lane information and the inertial sensing information; and a step of determining a vehicle position in the precision map using a result of matching the road/lane shape history information with precision map information. The road/lane information includes at least one of a road width, a road curvature, a lane width, a lane curvature, a number of lanes, and a lane type, and the inertial sensing information includes at least one of a speed, an acceleration, a yaw angle, a yaw velocity, a pitch angle, a pitch angular velocity, a roll angle, a roll angular velocity, a gravitational acceleration, and gravity of the vehicle.

In the above road/lane history information generation step, road/lane shape history information including curvature and slope information of the road on which the vehicle has driven from a predetermined time ago to the present can be generated.

In the step of determining the position of the vehicle, the position of the vehicle in the precision map can be determined by comparing a predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.

And, a vehicle position determination method according to one embodiment of the present invention includes a position detection step for detecting a global position of a vehicle based on a GNSS signal; a position recognition step for recognizing a position of a vehicle in a precision map by matching the global position with the precision map; and a position correction step for correcting the position of the vehicle in the precision map by utilizing a result of matching the road/lane shape history information and the precision map.

In the above position correction step, road/lane shape history information including curvature and slope information of the road on which the vehicle has driven from a predetermined time ago to the present can be generated.

In the above position correction step, the position of the vehicle in the precision map can be determined by comparing a predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.

A method for determining a vehicle's own position according to one embodiment of the present invention and a system applying the same generate road/lane shape history information and use the same, thereby increasing the reliability of GNSS-based map matching position determination, and can determine a vehicle's position within a predetermined error range by comparing road/lane shape history information with precision map information in tunnels or the like where GNSS reception is not smooth.

A method for determining a vehicle's own position according to one embodiment of the present invention and a system applying the same have the effect of improving the reliability of vehicle position recognition through position correction in an area where GNSS reception is possible, and have the effect of performing a positioning function more precisely than the conventional DR method or precision map matching method even in a shadow area where GNSS reception is not smooth.

FIG. 1 is a block diagram showing the configuration of a vehicle position determination system according to the first embodiment of the present invention.
Figure 2 is a flow chart showing a vehicle position determination method according to the first embodiment of the present invention.
FIG. 3 is a block diagram showing the configuration of a vehicle position determination system according to the second embodiment of the present invention.
Figure 4 is a flowchart showing a vehicle position determination method according to a second embodiment of the present invention.

The advantages and features of the present invention, and the methods for achieving them, will become clear with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments are provided to make the disclosure of the present invention complete, and to fully inform a person having ordinary skill in the art to which the present invention belongs of the scope of the invention, and the present invention is defined only by the scope of the claims. Meanwhile, the terminology used in this specification is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated in the phrase. The terms "comprises" and/or "comprising" as used in the specification do not exclude the presence or addition of one or more other components, steps, operations, and/or elements mentioned.

In describing the present invention, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the present invention, the detailed description is omitted.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. In order to facilitate overall understanding in describing the present invention, the same reference numbers will be used for the same means regardless of the drawing numbers.

Autonomous driving systems receive GNSS signals to estimate global location. In GNSS shadow areas such as high-rise buildings or tunnels, the vehicle's location is temporarily estimated through dead reckoning (DR) using the vehicle's inertial sensor. Dead reckoning has a disadvantage in that errors accumulate over time, which reduces location estimation accuracy and makes vehicle control difficult. Therefore, autonomous driving systems typically identify the location of the vehicle and use a precision map to generate a path for autonomous driving. A precision map is a high definition map that can represent all roads, terrain, and surrounding buildings. A precision map includes information such as the location of the road (including height), the width and shape (curvature, gradient, etc.) of the road and lane, lanes, road markings, traffic lights, and signs.

For reference, GPS (Global Positioning System) is a type of GNSS, so in the present invention, GNSS is used to mean including GPS.

The main element function for autonomous driving is that functional safety application design must be considered to ensure safety in the event of a failure. In order to apply functional safety, backup devices or auxiliary technologies must be provided to enable normal vehicle driving temporarily even in situations where GNSS signals are not properly received. Currently, in the case of Level 3 autonomous driving, the driving time with a backup device is set to several seconds (e.g., 4 seconds) and temporary driving is possible through DR, but in the future, in the case of Level 4 autonomous driving, driving without accidents for several minutes (e.g., 10 minutes) should be possible even in the event of a failure. To this end, additional technology that identifies the global location is required, and among the various pieces of information recognized by the vehicle, lane and road shape information can be matched with a precision map, and most autonomous vehicles are designed to recognize lane and road end information, so road and lane history information can be utilized for global location recognition for autonomous driving.

A vehicle position determination system according to one embodiment of the present invention detects a position based on a GNSS signal for autonomous driving, and determines a position by linking the position with a precision map. However, rather than matching road and/or lane shape information at a certain point in time with the precision map, the system performs precision map matching for a predetermined section based on road/lane shape history information generated during driving, thereby performing highly reliable positioning.

In addition, the vehicle position determination system according to one embodiment of the present invention continuously collects shape information of the road and lane during driving by fusing road/lane information (width of the road/lane, number and type of lanes) recognized by a lane recognition camera for autonomous driving and yaw angle, pitch angle, roll angle, speed, and gravity information acquired by an inertial sensor of the vehicle, and generates and stores shape history information of the road and lane based on this.

In addition, a vehicle position determination system according to one embodiment of the present invention is characterized by generating road and lane shape history information in real time by fusing lane and road recognition information of a front camera and a rear camera.

In addition, a vehicle position determination system according to one embodiment of the present invention can correct lane information and road information recognized by a camera according to actual curvature and gradient information through driving of a vehicle to create a history of road and lane information by driving distance/location, and can find the current location of the vehicle by comparing this information with lane or road information of a precision map.

Additionally, the vehicle position determination system according to one embodiment of the present invention identifies or corrects the position of the vehicle by comparing road/lane shape history information and precision map information.

In addition, a vehicle position determination system according to one embodiment of the present invention is characterized by estimating a current global position by comparing a precision map and road lane shape history information within an allowable error using features such as curves, straight lines, and gradients.

In addition, a vehicle position determination system according to one embodiment of the present invention is characterized by determining the vehicle position within a precision map by fusing lane information (3 lanes, 4 lanes, etc.) of a road on which the vehicle is driving and location information of intersections, underpasses, junctions, and traffic lights with road/lane history information.

In addition, a vehicle position determination system according to one embodiment of the present invention estimates a current position using road/lane shape history information when driving in a shaded area such as a GNSS failure or tunnel, and determines a position on a precision map based on the information.

FIG. 1 is a block diagram showing the configuration of a vehicle position determination system according to the first embodiment of the present invention.

A vehicle position determination system according to a first embodiment of the present invention includes a road/lane recognition unit (110), an inertial sensor unit (120), a road/lane history information generation unit (130), and a position determination unit (140).

The vehicle position determination system according to the first embodiment determines the position of the vehicle on the precision map by utilizing the result of matching the road/lane shape history information with the precision map. The vehicle position determination system according to the first embodiment can determine the current position of the vehicle by utilizing the road/lane shape history information when driving in a shaded area such as a GNSS failure or a tunnel.

The road/lane recognition unit (110) recognizes road/lane information through a road/lane recognition camera. The road/lane recognition camera includes at least one of a front camera and a rear camera, and the road/lane information includes at least one of the width and curvature of the road/lane and the number and types of lanes. In addition, the road/lane information may include location information of road structures (intersections, underpasses, junctions, signals).

The inertial sensor unit (120) obtains inertial sensing information of the vehicle. The inertial sensing information includes at least one of the vehicle's speed, acceleration, yaw angle/yaw velocity, pitch angle/pitch angular velocity, roll angle/roll angular velocity, and gravitational acceleration/gravity.

The road/lane history information generation unit (130) generates road/lane shape history information by fusing road/lane information and inertial sensing information, and stores it in the internal storage. The road/lane shape history information includes not only the shape information of the road/lane on which the vehicle is currently located, but also the shape information of the road/lane in the past. That is, the road/lane shape history information includes the curvature and road gradient information of the road/lane on which the vehicle has driven from a predetermined time ago to the present. In addition, the road/lane shape history information includes not only the curvature of the road/lane, but also three-dimensional information about the gradient (uphill/downhill) of the road. For example, the road/lane history information generation unit (130) can derive acceleration information on the Z-axis of the vehicle by using gravity information or gravitational acceleration information among the inertial sensing information, and can calculate history information about the gradient of the road by using the acceleration information on the Z-axis of the vehicle.

Meanwhile, the road/lane history information generation unit (130) can generate both the road/lane shape history information recognized through the image captured by the front camera and the road/lane shape history information recognized through the image captured by the rear camera.

Since the internal storage space of the road/lane history information generation unit (130) is limited, a management policy for road/lane history information that takes into account the purpose of the present invention (improving the reliability of position determination) is required.

The time interval (for example, 10 seconds) during which the road/lane history information generation unit (130) maintains the road/lane shape history information may vary depending on the setting. In addition, the time interval may vary depending on the slope or curvature of the road. For example, if the time interval is set to 20 seconds on a straight road, the time interval may be set to 5 seconds on a curved road (wherein a specific curvature of the road may be used as a reference value). That is, if the road/lane shape history information is generated based on the road/lane shape information from 20 seconds ago to the present on a straight road, the road/lane shape history information may be generated based on the road/lane shape information from 5 seconds ago to the present on a curved road.

In addition, the road/lane history information generation unit (130) can manage the data size by saving at regular intervals, but can vary the collection cycle (sampling time) of the road/lane shape information depending on the slope or curvature of the road. If the absolute value or rate of change of the road slope or the absolute value or rate of change of the road curvature is greater than a predetermined standard, the collection cycle can be shortened. For example, if the vehicle's heading angle changes by 40 degrees or more as a result of the instantaneous curvature analysis of the road, the collection cycle can be changed to 0.5 seconds, which is shorter than 1 second for a straight road. This is to collect detailed information that can be compared with a precision map and increase the reliability of the location information determined by the location determination unit (140).

In addition, the road/lane history information generation unit (130) may store and manage road/lane shape history information using section information where changes are detected. For example, when the road/lane history information generation unit (130) stores road/lane shape information for a 1 km straight section, instead of storing all driving information for the section, it may store and manage road/lane shape history information by only storing information that the section is a straight line and storing the start point and the end point.

Meanwhile, the road/lane history information generation unit (130) can take a management policy of deleting the road/lane shape history information of the previous curved section after confirming the current position when the vehicle enters a straight section (for example, when the difference between the maximum and minimum values of the heading angle is within 5 degrees while the vehicle is driving 20 m). This is because, once the current position is confirmed, storing the road/lane shape history information of the past curved section has low utility.

The position determination unit (140) determines the position of the vehicle on the precision map by using the result of matching the road/lane shape history information and the precision map information. The position determination unit (140) compares a predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the road curve/straight line (curvature) and gradient, and determines the position of the vehicle on the precision map. The position determination unit (140) can determine the position of the vehicle on the precision map by using the road/lane shape history information recognized through the image captured by the front camera and the road/lane shape history information recognized through the image captured by the rear camera together.

Fig. 2 is a flowchart illustrating a vehicle position determination method according to the first embodiment of the present invention. The vehicle position determination method according to the first embodiment of the present invention includes steps S210 to S2240.

Step S210 is a step for recognizing lanes. Road/lane information is recognized through a road/lane recognition camera. The road/lane recognition camera includes at least one of a front camera and a rear camera, and the road/lane information includes at least one of the width and curvature of the road/lane and the number and types of lanes. In addition, the road/lane information may include location information of road structures (intersections, underpasses, junctions, signals).

Step S220 is a step of acquiring inertial sensing information of the vehicle. The inertial sensing information includes at least one of the vehicle's speed, acceleration, yaw angle/yaw velocity, pitch angle/pitch angular velocity, roll angle/roll angular velocity, and gravitational acceleration/gravity.

Step S230 is a step for generating road/lane history information. Road/lane information and inertial sensing information are fused to generate road/lane shape history information, which is then stored in the internal storage. The contents and management policy of the road/lane shape history information have been described above in the description of the road/lane history information generation unit (130).

Step S240 is the step of determining the location. The location of the vehicle on the precision map is determined using the result of matching the road/lane shape history information and the precision map information. Based on the characteristics of the road, such as curvature/straightness and gradient, the precision map and the road/lane shape history information are compared within the allowable error to determine the location of the vehicle on the precision map.

FIG. 3 is a block diagram showing the configuration of a vehicle position determination system according to the second embodiment of the present invention.

The vehicle position determination system according to the second embodiment of the present invention includes a position detection unit (310), a position recognition unit (320), and a position correction unit (330). In addition, the vehicle position determination system according to the second embodiment of the present invention may further include a position information output unit (340).

The position detection unit (310) detects the global position of the vehicle. The position detection unit (310) receives a GNSS signal and estimates the global position of the vehicle based on this. In addition, the position detection unit (310) can temporarily estimate the position of the vehicle through a dead reckoning (DR) using the inertial sensor of the vehicle in a GNSS shadow area such as a high-rise building or a tunnel. That is, when the position detection unit (310) cannot receive a GNSS signal, it analyzes the behavior of the vehicle using inertial sensing information and estimates the global position of the vehicle based on this.

The location recognition unit (320) matches (links) the precision map to the global location of the vehicle and recognizes the location of the vehicle in the precision map.

The position correction unit (330) corrects the position of the vehicle on the precision map by utilizing the result of matching the road/lane shape history information with the precision map. The position correction unit (330) includes a road/lane recognition module (331), an inertial sensor module (332), a road/lane history information generation module (333), and a correction module (334). When the position detection unit (310) fails to estimate the global position and the position recognition unit (320) cannot recognize the position of the vehicle, the position correction unit (330) can determine the position of the vehicle by matching the road/lane shape history information with the precision map. For example, if the position detection unit (310) cannot estimate the global position due to non-reception of GNSS signals or a communication error, and the position detection unit (310) does not use an alternative means (e.g., dead reckoning (DR)), and the position recognition unit (320) cannot recognize the position of the vehicle, the position correction unit (330) can determine the position of the vehicle by matching the shape history information of the road/lane with the precision map. In addition, if the position correction unit (330) cannot receive a GNSS signal, but estimates the global position of the vehicle through dead reckoning (DR), it can correct the position in the precision map recognized by the position recognition unit (320).

The road/lane recognition module (331) recognizes road/lane information through a road/lane recognition camera. The road/lane recognition camera includes at least one of a front camera and a rear camera. The road/lane information includes at least one of the width and curvature of the road/lane and the number and types of lanes. The road/lane information may include location information of road structures (intersections, underpasses, junctions, signals).

The inertial sensor module (332) acquires inertial sensing information of the vehicle. The inertial sensing information includes at least one of the vehicle's speed, acceleration, yaw angle/yaw velocity, pitch angle/pitch angular velocity, roll angle/roll angular velocity, and gravitational acceleration/gravity.

The road/lane history information generation module (333) generates road/lane shape history information by fusing road/lane information and inertial sensing information, and stores it in internal storage.

The road/lane shape history information includes not only the shape information of the road/lane on which the vehicle is currently located, but also the shape information of the road/lane in the past. That is, the road/lane shape history information includes the curvature and road gradient information of the road/lane on which the vehicle has driven from a predetermined time ago to the present. In addition, the road/lane shape history information includes not only the curvature of the road/lane, but also three-dimensional information about the gradient (uphill/downhill) of the road. For example, the road/lane history information generation unit (130) can derive acceleration information on the Z-axis of the vehicle by using gravity information or gravitational acceleration information among the inertial sensing information, and can calculate history information about the gradient of the road by using the acceleration information on the Z-axis of the vehicle.

Meanwhile, the road/lane history information generation module (333) can generate both the road/lane shape history information recognized through the image captured by the front camera and the road/lane shape history information recognized through the image captured by the rear camera.

The time interval (for example, 10 seconds) for which the road/lane history information generation module (333) maintains the road/lane shape history information may vary depending on the setting. In addition, the time interval may vary depending on the slope or curvature of the road. For example, if the time interval is set to 20 seconds on a straight road, the time interval may be set to 5 seconds on a curved road (wherein a specific curvature of the road may be used as a reference value). That is, if the road/lane shape history information is generated based on the road/lane shape information from 20 seconds ago to the present on a straight road, the road/lane shape history information may be generated based on the road/lane shape information from 5 seconds ago to the present on a curved road.

In addition, the road/lane history information generation module (333) can vary the collection cycle (sampling time) of the road/lane shape information according to the slope or curvature of the road. If the absolute value or rate of change of the road slope or the absolute value or rate of change of the road curvature is greater than a predetermined standard, the collection cycle can be shortened. For example, if the vehicle's heading angle changes by 40 degrees or more as a result of the instantaneous curvature analysis of the road, the collection cycle can be changed to 0.5 seconds, which is shorter than 1 second for a straight road. This is to collect detailed information that can be compared with a precision map and to increase the reliability of the location information determined by the location determination unit (140).

In addition, the road/lane history information generation module (333) can store and manage road/lane shape history information using section information where changes are detected. For example, when the road/lane history information generation module (333) stores road/lane shape information for a 1 km straight section, instead of storing all driving information for the section, it can store and manage road/lane shape history information by only storing information that the section is straight and storing the start point and the end point.

Meanwhile, the road/lane history information generation module (333) can take a management policy of deleting the road/lane shape history information of the previous curved section after confirming the current position when the vehicle enters a straight section (for example, when the difference between the maximum and minimum values of the heading angle is within 5 degrees while the vehicle is driving 20 m). This is because, once the current position is confirmed, storing the road/lane shape history information of the past curved section has low utility.

The correction module (334) corrects the position of the vehicle on the precision map by using the result of matching the road/lane shape history information and the precision map information. The correction module (334) corrects the position of the vehicle on the precision map by comparing the precision map and the road/lane shape history information within an allowable error based on at least one feature of the road's curve/straight line (curvature) and gradient.

Meanwhile, the correction module (334) can correct the vehicle's position on the precision map by using the shape history information of the road/lane recognized through the image captured by the front camera and the shape history information of the road/lane recognized through the image captured by the rear camera.

The location information output unit (340) provides the vehicle's location information to the user. For example, the providing method may use a visual/auditory method, etc. The vehicle's location information includes at least one of the vehicle's global location and location on a precision map.

Figure 4 is a flowchart illustrating a vehicle position determination method according to a second embodiment of the present invention.

A vehicle position determination method according to a second embodiment of the present invention includes steps S410 to S430, and may further include step S440.

Step S410 is a step for detecting the global position of the vehicle. It receives GNSS signals and estimates the global position of the vehicle based on them. In addition, the vehicle position can be temporarily estimated through dead reckoning (DR) using the vehicle's inertial sensor in GNSS shadow areas such as high-rise buildings or tunnels. In other words, when GNSS signals cannot be received, the vehicle's behavior is analyzed using inertial sensing information and the vehicle's global position is estimated based on this.

Step S420 is the step of recognizing the vehicle's location on the precision map by matching (linking) the precision map to the vehicle's global location.

Step S430 is the step for correcting the vehicle's position on the precision map. The vehicle's position on the precision map is corrected by using the result of matching the road/lane shape history information and the precision map.

First, road/lane information is recognized through a road/lane recognition camera. The road/lane recognition camera includes at least one of a front camera and a rear camera. The road/lane information includes at least one of the width and curvature of the road/lane and the number and types of lanes. The road/lane information may include location information of road structures (intersections, underpasses, junctions, signals).

In addition, inertial sensing information of the vehicle is acquired. The inertial sensing information includes at least one of the vehicle's speed, acceleration, yaw angle/yaw velocity, pitch angle/pitch angular velocity, roll angle/roll angular velocity, and gravitational acceleration/gravity.

And, by fusing road/lane information and inertial sensing information, road/lane shape history information is generated and stored in the internal storage. The contents and management policy of the road/lane shape history information are described above in the description of the road/lane history information generation module (333).

Afterwards, the vehicle's position on the precision map is corrected using the result of matching the road/lane shape history information and the precision map information. That is, the vehicle's position on the precision map is corrected by comparing the precision map and the road/lane shape history information within an allowable error based on the road's features such as curves/straights and gradients.

If the global position cannot be estimated at step S410 and the vehicle position recognition task is not performed at step S420, the vehicle position can be determined by matching the road/lane shape history information with the precision map at step S430. For example, if the global position cannot be estimated at step S410 due to non-reception of a GNSS signal or a communication error and the dead reckoning (DR) is not used, and the vehicle position recognition task is not performed at step S420, the vehicle position can be determined by matching the road/lane shape history information with the precision map at step S430. In addition, if the GNSS signal cannot be received at step S410 but the global position of the vehicle is estimated through dead reckoning (DR), the position recognition result in the precision map can be corrected by matching the road/lane shape history information with the precision map at step S430.

Step S440 is a step for outputting location information. That is, in this step, the location information of the vehicle is provided to the user. The providing method may use a visual/auditory method, etc. The location information of the vehicle includes at least one of the global location of the vehicle and the location on the precision map.

For reference, components according to embodiments of the present invention may be implemented in the form of software or hardware such as a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC), and may perform predetermined roles.

However, 'components' are not limited to software or hardware, and each component may be configured to be on an addressable storage medium or configured to execute one or more processors.

Thus, as an example, components include components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

Components and the functionality provided within those components may be combined into a smaller number of components or further separated into additional components.

At this time, it will be understood that each block of the flowchart drawings and combinations of the flowchart drawings can be performed by computer program instructions. These computer program instructions can be loaded onto a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment create a means for performing the functions described in the flowchart block(s). These computer program instructions can also be stored in a computer-readable memory or used to direct a computer or other programmable data processing equipment to perform the functions in a specific manner, so that the instructions used in the computer or stored in the computer-readable memory can also produce an article of manufacture including an instruction means for performing the functions described in the flowchart block(s). Since the computer program instructions may be installed on a computer or other programmable data processing apparatus, a series of operational steps may be performed on the computer or other programmable data processing apparatus to produce a computer-executable process, so that the instructions executing the computer or other programmable data processing apparatus may also provide steps for executing the functions described in the flowchart block(s).

Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a particular logical function(s). It should also be noted that in some alternative implementation examples, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may in fact be performed substantially concurrently, or the blocks may sometimes be performed in reverse order, depending on the functionality they perform.

Here, the term 'part' or 'module' used in the present embodiment means software or hardware components such as FPGAs or ASICs, and the 'part' or 'module' performs certain roles. However, the 'part' or 'module' is not limited to software or hardware. The 'part' or 'module' may be configured to be in an addressable storage medium and may be configured to cause one or more processors to be played. Accordingly, as an example, the 'part' or 'module' includes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within a plurality of components, 'parts' or 'modules' may be combined into a smaller number of components, 'parts' or modules, or further separated into additional components and 'parts' or 'modules'. In addition, the components, 'parts' and 'modules' may be implemented to regenerate one or more CPUs within the device or the secure multimedia card.

The vehicle position determination method according to the first embodiment described above and the vehicle position determination method according to the second embodiment have been described with reference to the flowcharts presented in the drawings. For simplicity, the method has been depicted and described as a series of blocks; however, the present invention is not limited to the order of the blocks, and some blocks may occur in a different order or simultaneously with other blocks than depicted and described herein, and various other branches, flow paths, and orders of blocks that achieve the same or similar results may be implemented. Furthermore, not all of the depicted blocks may be required to implement the method described herein.

Hereinafter, the configuration of the present invention has been described in detail with reference to the attached drawings, but this is only an example, and it is obvious that those with ordinary knowledge in the technical field to which the present invention pertains can make various modifications and changes within the scope of the technical idea of the present invention. Therefore, the protection scope of the present invention is determined by the claims described below rather than the detailed description above, and all changes or modified forms derived from the scope of the claims and their equivalent concepts should be interpreted as being included in the technical scope of the present invention.

100: Vehicle Positioning System
110: Road/Lane Recognition Unit
120: Inertial sensor section
130: Road/lane history information generation unit
140: Positioning Unit
300: Vehicle Positioning System
310: Position detection unit
320: Location recognition unit
330: Position correction part
331: Road/Lane Recognition Module 332: Inertial Sensor Module
333: Road/lane history information generation module 334: Correction module
340: Location information output section

Claims (16)

A sensor unit that collects road/lane information on which a vehicle is driving and inertial sensing information of the vehicle;
A road/lane history information generation unit that generates road/lane shape history information by fusing the above road/lane information and the above inertial sensing information; and
It includes a position determination unit that determines the position of the vehicle on the precision map by using the result of matching the road/lane shape history information and the precision map information;
The above road/lane information includes at least one of road width, road curvature, lane width, lane curvature, number of lanes, and lane type.
The above inertial sensing information includes at least one of the vehicle's speed, acceleration, yaw angle, yaw velocity, pitch angle, pitch angular velocity, roll angle, roll angular velocity, gravitational acceleration and gravity,
The above road/lane shape history information includes information on the curvature and slope of the road on which the vehicle has driven from a certain time ago to the present.
A vehicle positioning system. In the first paragraph, the sensor part,
A road/lane recognition unit that recognizes the road/lane information through a road/lane recognition camera; and
Including an inertial sensor unit for obtaining inertial sensing information of the above vehicle;
A vehicle positioning system. delete In the first paragraph, the road/lane history information generation unit,
The above road/lane shape history information is stored in an internal storage, and the collection cycle of the road/lane shape history information is varied based on at least one of the slope and curvature of the road.
A vehicle positioning system. In the first paragraph, the position determining unit,
Determining the position of the vehicle in the precision map by comparing a predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.
A vehicle positioning system. A position detection unit that detects the global position of the vehicle based on GNSS signals;
A location recognition unit that recognizes the location of a vehicle in the precision map by matching the precision map to the global location; and
A position correction unit that generates road/lane shape history information including curvature and slope information of a road on which the vehicle has driven from a predetermined time ago to the present, and corrects the position of the vehicle in the precision map by utilizing the result of matching the road/lane shape history information and the precision map;
A vehicle positioning system comprising: delete In the sixth paragraph, the position correction unit,
The above road/lane shape history information is stored in an internal storage, and the collection cycle of the road/lane shape history information is varied based on at least one of the slope and curvature of the road.
A vehicle positioning system. In the sixth paragraph, the position correction unit,
Determining the position of the vehicle in the precision map by comparing the predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.
A vehicle positioning system. In the sixth paragraph, the position correction unit,
If the above location detection unit fails to receive a GNSS signal, the vehicle's location is determined by matching the road/lane shape history information with the above precision map.
A vehicle positioning system. A step of recognizing road/lane information on which a vehicle is driving through a sensor;
A step of acquiring inertial sensing information of the above vehicle;
A road/lane history information generation step for generating road/lane shape history information by fusing the above road/lane information and the above inertial sensing information; and
A step of determining the location of a vehicle in the precision map by using the result of matching the road/lane shape history information and the precision map information;
The above road/lane information includes at least one of road width, road curvature, lane width, lane curvature, number of lanes, and lane type.
The above inertial sensing information includes at least one of the vehicle's speed, acceleration, yaw angle, yaw velocity, pitch angle, pitch angular velocity, roll angle, roll angular velocity, gravitational acceleration and gravity,
The above road/lane history information generation step is:
Including generating the road/lane shape history information by including the curvature and slope information of the road on which the vehicle has driven from a predetermined time ago to the present.
A method for determining the position of a vehicle. delete In the 11th paragraph, the step of determining the position of the vehicle is:
Determining the position of the vehicle in the precision map by comparing the predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.
A method for determining the position of a vehicle. A position detection step for detecting the global position of a vehicle based on GNSS signals;
A location recognition step for recognizing the location of a vehicle in the precision map by matching the precision map to the global location; and
A position correction step for generating road/lane shape history information including curvature and slope information of a road on which the vehicle has driven from a predetermined time ago to the present, and correcting the position of the vehicle in the precision map by utilizing the result of matching the road/lane shape history information and the precision map;
A method for determining a vehicle position, comprising: delete In the 14th paragraph, the position correction step,
Determining the position of the vehicle in the precision map by comparing the predetermined section of the precision map with the road/lane shape history information within an allowable error based on at least one feature of the curvature and gradient of the road.
A method for determining the position of a vehicle.

Images