Device and method for estimating vehicle position

Abstract

The present invention relates to an apparatus and method for estimating a vehicle position, wherein the apparatus for estimating a vehicle position comprises: a position information detector configured to detect the position information of the vehicle; an image information detector configured to detect image information around the vehicle; a storage device configured to store an accurate map; and a processor configured to: determine a search range of the accurate map according to the reliability of the position information; search for a candidate object in the search range; match the candidate object with the image information; and estimate the current position of the vehicle according to the matching result.

Description

[0001] CROSS REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the priority of Korean Patent Application No. 10-2018-0142015 filed on November 16, 2018, in the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The invention relates to a device and a method for estimating a vehicle position. Background Art

[0004] The autonomous driving system needs to accurately identify the current position of the vehicle, so it needs accurate vehicle position estimation technology (which uses accurate maps). Accurate maps include information such as lane information, road information, road facility information, and also include data such as sensor data, three-dimensional (3D) data, etc.

[0005] Therefore, as the amount of accurate map data increases, the time required to identify the vehicle position increases due to the heavy search operation load of the system in the accurate map search. Therefore, as the time required for the accurate map search increases, the performance of the conventional vehicle position estimation technology in identifying the vehicle position in real time may be poor. Summary of the invention

[0006] The present invention is dedicated to solving the above-mentioned problems existing in the prior art while still completely retaining the advantages of the prior art.

[0007] An aspect of the present invention provides an apparatus and method for estimating a vehicle position, which optimizes a precise map search area based on global positioning system (GPS) signal characteristics.

[0008] The technical problems to be solved by the present invention are not limited to the above problems, and those skilled in the art to which the present invention belongs will clearly understand any other technical problems not mentioned in the present invention from the following description.

[0009] According to one aspect of the present invention, a device for estimating the position of a vehicle includes: a position information detector configured to detect the position information of the vehicle; an image information detector configured to detect image information around the vehicle; a storage device configured to store an accurate map; and a processor configured to: determine a search range of the accurate map based on the reliability of the position information; search for candidate objects in the search range; match the candidate objects with the image information; and estimate the current position of the vehicle based on the matching results.

[0010] In one embodiment, the location information detector acquires the location information using a Global Positioning System (GPS) receiver.

[0011] In one embodiment, the processor is configured to generate reference coordinates using the position information and previous compensation values ​​stored in the storage device.

[0012] In one embodiment, the previous compensation value is defined as the difference between the position information detected in the previous vehicle position estimation cycle and the current estimated position information.

[0013] In one embodiment, the processor is configured to determine a search area of ​​a predetermined shape centered at the reference coordinates.

[0014] In one embodiment, the processor is configured to determine the size of the search area based on the reliability of the location information.

[0015] In one embodiment, the processor is configured to determine the reliability of the location information based on a horizontal dilution of precision (HDOP), the horizontal dilution of precision calculated based on data measured by the global positioning system receiver.

[0016] In one embodiment, the processor is configured to determine the size of the search area based on the previous compensation value.

[0017] In one embodiment, the processor is configured to: identify objects contained in the image information; extract candidate objects that match the identified objects from the candidate objects; calculate the current position of the vehicle based on the extracted candidate objects; and define the calculated current position as the final position.

[0018] In one embodiment, the processor is configured to calculate a difference between the final position and the position information, and update the previous compensation value according to the difference.

[0019] According to one aspect of the present invention, a method for estimating a vehicle position includes: a first operation of detecting position information of the vehicle and image information around the vehicle; a second operation of generating reference coordinates based on the position information; a third operation of determining a search area of ​​a precise map with reference to the reference coordinates; a fourth operation of selecting a candidate object in the search area; and a fifth operation of matching the candidate object with the image information and estimating the current position of the vehicle based on the matching result.

[0020] In one embodiment, the first operation includes the following steps: detecting the location information using a global positioning system (GPS) module; and detecting the image information via a camera.

[0021] In one embodiment, the second operation includes generating the reference coordinates by adding a previous compensation value stored in a storage device to the position information.

[0022] In one embodiment, the previous compensation value is defined as the difference between the position information detected in the previous vehicle position estimation cycle and the current estimated position information.

[0023] In one embodiment, the third operation includes: determining a search area having a predetermined shape centered at the reference coordinates.

[0024] In one embodiment, the third operation includes the following steps: determining the size of the search area according to the signal quality of the global positioning system receiver; and determining the size of the search area according to a previous compensation value.

[0025] In one embodiment, the signal quality of the GPS receiver is determined based on a horizontal dilution of precision (HDOP) calculated based on data measured by the GPS receiver.

[0026] In one embodiment, the step of determining the size of the search area according to the previous compensation value includes: determining an enlargement or reduction ratio of the search area according to the previous compensation value.

[0027] In one embodiment, the fourth operation includes the following steps: identifying objects contained in the image information; extracting candidate objects that match the identified objects from the candidate objects; calculating the current position of the vehicle based on the extracted candidate objects; and defining the calculated current position as the final position.

[0028] In one embodiment, after the fifth operation, the method further comprises: calculating a difference between the estimated position and the position information; and updating the previous compensation value according to the difference. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0030] Figure 1 is a block diagram illustrating an apparatus for estimating a vehicle position according to an embodiment of the present invention;

[0031] Figure 2 and Figure 3 is a schematic diagram for explaining a method for determining an accurate map search area according to the present invention;

[0032] Figure 4 is a flow chart illustrating a method for estimating a vehicle position according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The exemplary embodiments of the present invention will be described in detail below with reference to the exemplary drawings. It should be noted that when adding reference numerals to the elements in each figure, the same or equivalent elements are marked with the same reference numerals, even if these elements are shown in other figures. Further, when describing the embodiments of the present invention, when it is determined that the detailed description of the relevant known configurations or functions interferes with the understanding of the embodiments of the present invention, the detailed description of the relevant known configurations or functions will be omitted.

[0034] When describing the elements according to the embodiments of the present invention, words such as first, second, A, B, (a), (b) may be used. These words are only used to distinguish an element from other elements without limiting the properties, order or sequence of these elements. Unless otherwise defined, the meanings of all words (including technical and scientific terms) used herein are the same as those commonly understood by those of ordinary skill in the art to which the present invention belongs. It will be further understood that words defined in common dictionaries, for example, should be interpreted as having meanings consistent with them in the context of the relevant field, and unless clearly defined herein, shall not be interpreted in an idealized or overly literal sense.

[0035] The present invention relates to a vehicle position estimation (recognition) technology applicable to an autonomous driving system. The present invention uses the reliability of a global positioning system (GPS) signal to set an optimal accurate map search area, thereby achieving efficient accurate map search in an autonomous driving system.

[0036] Figure 1 is a block diagram illustrating an apparatus 100 for estimating a vehicle position according to an embodiment of the present invention.

[0037] refer to Figure 1 The device 100 includes a vehicle information detector 110 , an image information detector 120 , a position information detector 130 , a storage device 140 and a processor 150 .

[0038] The vehicle information detector 110 includes one or more sensors for detecting vehicle information and an electronic control unit (ECU) installed on the vehicle via an in-vehicle network (IVN). The IVN in the vehicle can be implemented as a controller area network (CAN), a multimedia oriented system transmission (MOST) network, a local interconnect network (LIN) and / or a wire control (Flexray), etc. The vehicle information includes control information related to vehicle driving, such as vehicle speed, steering angle, steering angular velocity, etc.

[0039] The image information detector 120 acquires image information around the vehicle through a camera installed on the vehicle. For example, the image information detector 120 includes a camera capable of acquiring an image in front of the vehicle. The image information includes objects located in front of, behind, and / or to the side of the vehicle, the type and distance to the vehicle of the left and right lanes, the curvature of the road, and the like.

[0040] The camera may be installed at the front, rear and side of the vehicle, respectively. The camera may be implemented as at least one of an image sensor, such as a charge coupled device (CCD) image sensor, a complementary metal oxide semiconductor (CMOS) image sensor, a charge activated device (CPD) image sensor, a charge injection device (CID) image sensor, etc. The camera may include an image processor configured to perform image processing (such as noise removal, color reproduction, file compression, image quality adjustment, saturation adjustment, etc.) on an image acquired by the image sensor.

[0041] The position information detector 130 measures the current position of the vehicle. The position information detector 130 may be implemented as a global positioning system (GPS) receiver. The GPS receiver receives signals transmitted from three or more GPS satellites and calculates the current position of the vehicle using the received GPS signals.

[0042] In addition, the position information detector 130 calculates the horizontal dilution of precision (HDOP) based on the data (position coordinates) measured by the GPS receiver. The horizontal dilution of precision (HDOP) is a coefficient indicating the degree of degradation depending on the distribution state of GPS satellites in the celestial sphere. The HDOP refers to the accuracy of the horizontal positioning result.

[0043] The storage device 140 stores accurate map data (accurate map information, hereinafter referred to as accurate map). The accurate map includes lane information required for autonomous driving (e.g., the number of lanes, lane positions (coordinates), road types, appropriate speeds for the roads, etc.), road information, road facility information, and surrounding environment information.

[0044] The storage device 140 may store software programmed to be embedded in the processor 150 and to perform predetermined operations. The storage device 140 may also store input and output data of the processor 150.

[0045] The storage device 140 may store image processing logic, precise map search logic, position estimation logic, etc. The storage device 140 may also store vehicle information, position information, image information, reference search area size, previous compensation values, etc. In addition, the storage device 140 may also store a lookup table containing information such as a search area size (range) depending on the HDOP, a search area size depending on previous compensation values, and the like.

[0046] The storage device 140 can be implemented as at least one of the storage media (recording media), such as a flash memory, a hard disk, an SD card (secure digital card), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an electrically erasable programmable ROM (EEPROM), an erasable programmable ROM (EPROM), a register, a removable disk, a network storage, and the like.

[0047] The processor 150 controls the overall operation of the apparatus 100 for estimating the position of a vehicle. The processor 150 may be implemented as at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGAs), a central processing unit (CPU), a microcontroller, and a microprocessor.

[0048] Processor 150 executes vehicle position estimation logic using information detected by detectors 110-130 and a precise map stored in storage device 140 as input. That is, processor 150 performs position compensation and estimates the current position of the vehicle using position information, image information, and precise map information.

[0049] The processor 150 compiles the precise map provided by the storage device 140 and the vehicle information, position information and image information input from the detectors 110-130 into a data form that can be processed at the logic. That is, the processor 150 pre-processes the data input to the logic.

[0050] The processor 150 generates the reference coordinates using the position information detected by the position information detector 130 and the previous compensation value stored in the storage device 140. For example, the processor 150 calculates the reference coordinates by adding the previous compensation value to the detected position information.

[0051] In this regard, the previous compensation value is a value calculated in a previous vehicle position estimation cycle (process). The previous compensation value refers to the difference between the position information (measured position information) output by the position information detector 130 and the final estimated position information. That is, the compensation value is the estimated final position minus the position measured by the GPS receiver.

[0052] The processor 150 controls the execution of the position compensation function by optimizing the precise map search area according to the position accuracy measured by the GPS receiver, i.e., GPS signal reliability (quality). The processor 150 determines the GPS signal reliability, i.e., the reliability of the detected position information based on the horizontal positioning result accuracy (horizontal dilution of precision, HDOP) calculated at the position information detector 130.

[0053] For example, when HDOP is less than 1, or HDOP is equal to or greater than 1 but less than 10, the processor 150 determines that the GPS signal reliability is good; when HDOP is greater than 10, the processor 150 determines that the GPS signal reliability is poor.

[0054] In addition, the processor 150 may determine the GPS signal reliability based on the previous compensation value. For example, when the previous compensation value is less than 3 meters, or the previous compensation value is equal to or greater than 3 meters but less than 9 meters, the processor 150 determines that the GPS signal reliability is good; when the previous compensation value is greater than 9 meters, the processor 150 determines that the GPS signal reliability is poor.

[0055] The processor 150 determines a precise map search area (hereinafter referred to as search area) centered on the reference coordinates according to GPS signal reliability. The processor 150 reflects the reference coordinates on a precise map and sets a search area of ​​a predetermined shape (e.g., circular, square, polygonal, etc.) centered on the reference coordinates.

[0056] In addition, the processor 150 determines the size of the search area according to the GPS signal reliability. As the GPS signal reliability decreases, the processor 150 increases the size of the search area, and as the GPS signal reliability increases, the processor 150 decreases the size of the search area. For example, the processor 150 determines the radius of the search area according to the GPS signal reliability.

[0057] That is, the processor 150 increases or decreases the size of the search area according to the HDOP and / or the previous compensation value.

[0058] After determining the search area, the processor 150 searches for objects in the corresponding area in the accurate map. At this time, the processor 150 selects one or more objects in the search area as candidate objects according to the search condition. In this regard, the search condition refers to a predetermined search object (e.g., a road sign, a lane, a subway station, etc.).

[0059] The processor 150 matches the selected candidate object with the object in the image information. That is, the processor 150 identifies the object in the image information and extracts the candidate object that matches the identified object from the selected candidate objects. The processor 150 calculates the current position of the vehicle using the extracted candidate object as a reference and defines the calculated current position as the final position.

[0060] The processor 150 calculates the difference between the estimated position information (final position) and the position information detected by the position information detector 130 as a compensation value (i.e., final position detection position). The processor 150 updates the previous compensation value stored in the storage device 140 with the calculated compensation value. That is, the compensation value calculated in the current cycle is used as the previous compensation value in the next cycle.

[0061] Figure 2 and Figure 3 is a schematic diagram for explaining a method for determining a precise map search area according to the present invention.

[0062] The processor 150 may determine the size of the search area according to the GPS signal reliability (quality). The processor 150 may increase the size of the search area when the GPS signal reliability is low, and may decrease the size of the search area when the GPS signal reliability is high.

[0063] In this regard, the processor 150 evaluates GPS signal reliability (reliability of detected location information) using the HDOP calculated at the location information detector 130. The processor 150 determines the size R of the search area according to the HDOP h. g (h). Figure 2 As shown in FIG. 1 , when the HDOP is less than 1, the processor 150 determines the radius R of the search area. g When the HDOP is equal to or greater than 1 but less than 10, the processor 150 determines the radius R of the search area. g is 20 meters, and when the HDOP is equal to or greater than 10, the processor 150 determines the radius R of the search area g is 30 meters.

[0064] The processor 150 may determine the size of the search area according to the previous compensation value. In this regard, when the previous compensation value is large, it means that the difference between the position measured by the GPS receiver and the actual position is large. That is, when the previous compensation value is large, the positioning accuracy measured by the GPS receiver is low. Therefore, when the previous compensation value d is large, the processor 150 increases the size R of the search area. d (d), and when the previous compensation value d is smaller, the processor 150 reduces the size of the search area R d (d) In this regard, the size of the search area Rd (d) refers to the ratio between the current size of the search area and the reference size (reference radius) of the search area (indicating expansion or reduction).

[0065] Reference Figure 3 When the previous compensation value d is less than 3 meters, the processor 150 determines the enlargement / reduction ratio R of the search area. d (d) is 1. When the previous compensation value d is equal to or greater than 3 meters but less than 9 meters, the processor 150 determines the enlargement / reduction ratio R of the search area d (d) is 1.2, and when the previous compensation value d is equal to or greater than 9 meters, the processor 150 determines the enlargement / reduction ratio R of the search area d (d) is 1.6.

[0066] Figure 4 is a flow chart illustrating a method for estimating a vehicle position according to an embodiment of the present invention.

[0067] The processor 150 of the apparatus 100 for estimating a vehicle position generates reference coordinates using the position information detected by the position information detector 130 and a previous compensation value stored in the storage device 140 (S110). The processor 150 calculates the reference coordinates by adding the previous compensation value to the detected position information.

[0068] The processor 150 determines an accurate map search area (hereinafter referred to as "search area") according to the reference coordinates (S120). The processor 150 reflects the reference coordinates on the accurate map and sets the search area centered on the reference coordinates.

[0069] The processor 150 determines the size of the search area according to the reliability of the detected location information (GPS signal reliability) (S121). The processor 150 determines the reliability of the detected location information according to the HDOP. As the HDOP increases, the processor 150 increases the size of the search area, and as the HDOP decreases, the processor 150 decreases the size of the search area.

[0070] The processor 150 determines the size of the search area according to the previous compensation value (S122). When the previous compensation value is large, the processor 150 increases the size of the search area, and when the previous compensation value is small, the processor 150 decreases the size of the search area.

[0071] The processor 150 selects candidate objects in the precise map based on the determined search area (S130). The processor 150 selects (divides) predetermined search objects in the determined search area and defines them as candidate objects.

[0072] The processor 150 estimates the current position of the vehicle by matching the selected candidate objects with the image information detected by the image information detector 120 (S140). The processor 150 identifies the objects contained in the detected image information and extracts the candidate objects that match the identified objects from the selected candidate objects. The processor 150 calculates the current position of the vehicle using the extracted candidate objects as a reference and estimates it as the final position.

[0073] For example, when the vehicle is traveling, in view of the good condition of the GPS signal of about 1 HDOP, the processor 150 searches for objects in a small radius area and calculates the current position. Then, when the GPS signal condition deteriorates (HDOP is greater than 10), the processor 150 increases the radius of the search area to 30 meters using the operation logic. Then, the processor 150 checks the compensation value of the previous operation. When the previous compensation value is 10 meters, the processor 150 determines that the reliability of the GPS signal is low, and then increases the search area by 60% according to the operation logic. Thereafter, the processor 150 finally adjusts the search radius to 40 meters.

[0074] In one example, when the HDOP is greater than 10 and the previous compensation value is greater than 9 meters, the processor 150 sets the search area to the maximum search radius and searches for objects in the precise map to calculate the current position. Thereafter, when the vehicle deviates from the city and enters a highway on a flat land without buildings, the quality of the GPS signal improves, so the difference between the position measured by the GPS receiver and the estimated position is almost 0. Then, the processor 150 reduces the precise map search area to a minimum according to the operation logic.

[0075] The above description is merely an explanation of the technical concept of the present invention, and those skilled in the art can make various modifications and changes without departing from the basic features of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical concept of the present invention, but to illustrate the present invention, and the scope of the technical concept of the present invention is not limited by the embodiments. The scope of the present invention should be interpreted as being included in the scope of the attached claims, and all technical concepts belonging to the scope of the claims should be interpreted as being included in the scope of the present invention.

[0076] According to the present invention, the size of the precise map search area can be changed according to the GPS (Global Positioning System) signal characteristics, so the precise map search area can be optimized according to the environment. Thus, the time required to identify the position can be optimized and the accuracy of the vehicle position estimation can be improved.

[0077] Although the present invention has been described above with reference to exemplary embodiments and the accompanying drawings, the present invention is not limited thereto, but various modifications and changes may be made by those skilled in the art without departing from the spirit and scope of the claims of the present invention.

Claims

1. A device for estimating a vehicle position, the device comprising: a position information detection sensor configured to detect position information of a vehicle; an image information detection sensor configured to detect image information around the vehicle; a storage device configured to store a precise map and a previous compensation value defined as a difference between previously detected position information and currently estimated position information in a previous vehicle position estimation cycle; as well as Processor, which is configured as: determining a size of a search area of ​​the accurate map according to the reliability of the position information, and determining an enlargement or reduction ratio of the search area according to the previous compensation value to adjust the size of the search area; searching for candidate objects in the search area; matching the candidate object with the image information; Estimate the current position of the vehicle based on the matching results, wherein the processor is configured to generate a reference coordinate using the position information and the previous compensation value and determine a search area centered on the reference coordinate; The processor is configured to increase the ratio between the current size of the search area and the reference size of the search area when the previous compensation value is equal to or greater than a predetermined value, and decrease the ratio between the current size of the search area and the reference size of the search area when the previous compensation value is less than the predetermined value.

2. The device for estimating the position of a vehicle according to claim 1, wherein: The position information detection sensor acquires position information using a global positioning system receiver.

3. The device for estimating the position of a vehicle according to claim 1, wherein: The processor is configured to determine a search area of ​​a predetermined shape centered at the reference coordinates.

4. The device for estimating the position of a vehicle according to claim 2, wherein: The processor is configured to determine the reliability of the position information based on a horizontal dilution of precision calculated based on data measured by the global positioning system receiver.

5. The device for estimating the position of a vehicle according to claim 1, wherein: The processor is configured as follows: identifying an object contained in the image information; Extracting candidate objects that match the identified object from the candidate objects; Calculating the current position of the vehicle based on the extracted candidate objects; The calculated current position is defined as the final position.

6. The device for estimating the position of a vehicle according to claim 5, wherein: The processor is configured to calculate a difference between the final position and the position information, and update the previous compensation value according to the difference.

7. A method for estimating a vehicle position, the method comprising: The first operation is to detect the position information of the vehicle and the image information around the vehicle; a second operation of generating a reference coordinate based on the position information and a previous compensation value, wherein the previous compensation value is defined as a difference between the position information detected in a previous vehicle position estimation cycle and the current estimated position information; A third operation is to determine a search area of ​​the accurate map with reference to the reference coordinates; A fourth operation is to select a candidate object in the search area; as well as The fifth operation is to match the candidate object with the image information and estimate the current position of the vehicle according to the matching result. The second operation includes: generating the reference coordinates by adding the previous compensation value to the position information, The third operation comprises the following steps: Determine a search area with the reference coordinates as the center; Determining the size of the search area based on the signal quality of the GPS receiver; and An enlargement or reduction ratio of the search area is determined according to the previous compensation value to adjust the size of the search area, when the previous compensation value is equal to or greater than a predetermined value, the ratio between the current size of the search area and the reference size of the search area is increased, and when the previous compensation value is less than the predetermined value, the ratio between the current size of the search area and the reference size of the search area is reduced.

8. The method for estimating the position of a vehicle according to claim 7, wherein: The first operation comprises the following steps: Detecting the location information using a global positioning system module; and The image information is detected via a camera.

9. The method for estimating the position of a vehicle according to claim 7, wherein: The third operation includes determining a search area having a predetermined shape centered at the reference coordinates.

10. The method for estimating the position of a vehicle according to claim 7, wherein: The signal quality of the GPS receiver is determined based on a horizontal DOP calculated based on data measured by the GPS receiver.

11. The method for estimating vehicle position according to claim 7, wherein: The fourth operation comprises the following steps: identifying an object contained in the image information; Extracting candidate objects that match the identified object from the candidate objects; calculating the current position of the vehicle based on the extracted candidate objects; and The calculated current position is defined as the final position.

12. The method for estimating a vehicle position according to claim 7, further comprising after the fifth operation: calculating a difference between the estimated position and the position information; as well as The previous compensation value is updated according to the difference.

Images