Bicycle position estimation device

Abstract

To provide a vehicle position estimation device that is excellent in accuracy of estimating a travel lane.SOLUTION: When a vehicle 200 is located on a road having a plurality of lanes, a vehicle position estimation device 100 calculates reliability for each lane. The reliability for each lane is not a value depending on a position in the lane. Even when position estimation accuracy based on a quantity of state of the vehicle is not good, the reliability is thus calculated for each lane on the basis of sensing information and map data, and thereby a lane on which the vehicle is located can be specified by using the reliability. Consequently, the accuracy in estimating a travel lane can be improved.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The disclosure in this specification relates to a vehicle position estimation device that estimates the driving position of a vehicle on a road.

Background Art

[0002] Patent Document 1 discloses a self-position estimation device that discriminates which lane among lanes specified by lane information the in-lane position corresponds to based on the correlation between the in-lane position, the absolute position, and the error thereof, and estimates the driving lane based on the discrimination result.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technique described in the above-mentioned Patent Document 1, when the error of the estimation result of the in-lane position by the gyro sensor is larger than the lane width, there is a problem that the estimation accuracy of the lane candidates deteriorates.

[0005] Therefore, the disclosed object is made in view of the above problems, and an object is to provide a vehicle position estimation device excellent in the estimation accuracy of the driving lane.

Means for Solving the Problems

[0006] The present disclosure employs the following technical means to achieve the above object.

[0007] The vehicle position estimation device disclosed herein is a vehicle position estimation device (100) mounted on an automobile (200) and used, and includes an external information acquisition unit (110) that acquires external information regarding objects around the automobile and road markings around it, a vehicle state quantity acquisition unit (110) that acquires state quantities related to the running of the automobile, a satellite positioning acquisition unit (110) that acquires the latitude and longitude at which the automobile is located by a satellite positioning system, a map data acquisition unit (110) that acquires map data having road information regarding lanes, and a position estimation unit (120) that estimates the position of the vehicle on the map of the automobile based on the external information, state quantities, latitude and longitude, and map data. A lane change determination unit (123) that determines a lane change of an automobile based on external information, state quantities, latitude and longitude, and map data It is provided with, and when the vehicle is located on a road having a plurality of lanes, the position estimation unit uses the external information and the map data to calculate, for each lane, a reliability indicating the probability of which lane the vehicle is located in among the plurality of lanes, and has a reliability calculation unit (121) and a lane estimation unit (122) that estimates the lane in which the vehicle is located using the reliability calculated by the reliability calculation unit. When the lane change determination unit determines that a lane change has occurred, the reliability calculation unit sets the reliability of the lane located at the end opposite to the direction of the lane change to be lower than that of other lanes. The external information acquisition unit acquires the distances to the road edges on both sides of the automobile respectively. The lane change determination unit determines a lane change to one side using a change in which the distance from the automobile to the road edge on one side decreases, or a change in which the distance to the road edge on the other side increases It does.

[0008] According to such a vehicle position estimation device, when the vehicle is located on a road having a plurality of lanes, the reliability indicating the probability of which lane the vehicle is located in among the plurality of lanes is calculated for each lane. Since it is the reliability for each lane, it is not a value that depends on the position within the lane. Therefore, even when the position estimation accuracy based on the state quantity of the vehicle is poor, the reliability is calculated for each lane based on the external information and the map data, so the lane in which the vehicle is located can be specified using the reliability. As a result, the estimation accuracy of the driving lane can be improved.

[0009] Note that the reference numerals in parentheses of the above-described respective means are an example showing the correspondence relationship with the specific means described in the embodiments described later.

Brief Description of the Drawings

[0010]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Embodiments for Carrying Out the Invention

[0011] (First Embodiment) Regarding the first embodiment of the present disclosure, it will be described with reference to FIGS. 1 to 7. The own vehicle position estimation device 100 of the present embodiment is mounted, for example, as part of a vehicle system 10 of a vehicle provided with a navigation system or a vehicle having an automatic driving function. While the own vehicle 200 is actually traveling, the own vehicle position estimation device 100 estimates the own vehicle position, that is, which position on the map, specifically which lane of which road it is traveling on, based on various data described later. The own vehicle position estimation device 100 outputs the own vehicle position including the estimated lane to other devices.

[0012] By the own vehicle position estimation device 100 estimating the position of the own vehicle 200, for example, assistance for safe driving and assistance for automatic driving are provided to the driver. The own vehicle 200 corresponds to an automobile. As shown in FIG. 1, the vehicle system 10 includes a surrounding monitoring sensor 20, an own vehicle state quantity sensor unit 30, a GNSS receiver 40, a map data storage unit 50, and an own vehicle position estimation device 100.

[0013] As shown in FIG. 2, the surrounding monitoring sensor 20 is a sensor that monitors the surrounding environment of the host vehicle 200. The surrounding monitoring sensor 20 can detect moving objects such as pedestrians, cyclists, animals other than humans, and other vehicles, as well as stationary objects such as fallen objects on the road, guardrails, curbs, road signs, road markings, and structures on the roadside, from the detection range around the host vehicle. The surrounding monitoring sensor 20 outputs sensing information, which is external information obtained by detecting objects around the host vehicle 200, to the host vehicle position estimating device 100.

[0014] The surrounding monitoring sensor 20 acquires external information regarding objects around the host vehicle 200 and surrounding road markings. Specifically, the surrounding monitoring sensor 20 detects information on the dividing lines adjacent to both sides of the host vehicle 200, the total number of vehicle lanes on the road, and the number of lanes located on both sides of the host vehicle 200. In addition, the surrounding monitoring sensor 20 acquires mark information such as road markings in front of the driving lane of the host vehicle 200 and the distances to the road edges on both sides of the vehicle, respectively.

[0015] As a detection configuration for object detection, the surrounding monitoring sensor 20 has, for example, a front camera and a millimeter-wave radar. The front camera outputs at least one of imaging data obtained by photographing the front range of the host vehicle 200 and the analysis result of the imaging data as sensing information. A plurality of millimeter-wave radars are arranged at intervals on each of the front and rear bumpers of the host vehicle 200, for example. The millimeter-wave radar irradiates millimeter waves or quasi-millimeter waves toward the surroundings of the host vehicle 200. The millimeter-wave radar generates sensing information by receiving reflected waves reflected by moving objects, stationary objects, etc.

[0016] The host vehicle state quantity sensor unit 30 detects state quantities related to the running of the host vehicle 200, such as vehicle speed, acceleration, and yaw rate. The host vehicle state quantity sensor unit 30 outputs data of the detected state quantities to the host vehicle position estimating device 100.

[0017] As shown in FIG. 2, the GNSS (Global Navigation Satellite System) receiver 40 receives positioning signals transmitted from a plurality of artificial satellites, which are also referred to as positioning satellites. The GNSS receiver 40 can receive positioning signals from each positioning satellite of at least one satellite positioning system among the GPS, GLONASS, Galileo, IRNSS, QZSS, and Beidou satellite positioning systems. The GNSS receiver 40 outputs the received positioning signals as GPS information to the host vehicle position estimation device 100.

[0018] The map data storage unit 50 is a part that holds map data. The map data storage unit 50 is connected to the host vehicle position estimation device 100, and the map data can be read by the host vehicle position estimation device 100. The map data defines, for example, a map representing a road using links and nodes. Specifically, the map data is formed by sequentially connecting links formed as line segments of a predetermined length along the road by nodes.

[0019] The map data includes road information regarding the road. The road information includes the number of lanes, lane position, lane shape, and mark information. The mark information is information such as symbols, arrows, and figures formed on the road surface, and includes information on road markings. The mark information includes information on figures used specifically in that area, etc., as information other than road markings defined by laws such as the Road Traffic Law. The information on road markings includes information on lane lines and road signs.

[0020] The lane lines include the outside lane line and the lane boundary line. The outside lane line is a lane line indicating the boundary between the lane and the road shoulder, and is shown as a solid line. The lane boundary line is a lane line indicating the boundary between lanes, and is shown as a solid line or a broken line. The information on the lane lines also includes information on the color of the line, such as yellow and white. The road signs are, for example, paints drawn on the road surface for traffic control and regulation, such as a no-turn sign, traffic separation by driving direction, and maximum speed.

[0021] In addition, the map data includes information on a section without lane markings, which is a section where lanes are not demarcated. In a section without lane markings, lane boundary lines are not shown, and only the outer lane line is shown. The information on the section without lane markings includes information indicating the distance and the position of the section without lane markings.

[0022] Instead of being provided in the host vehicle position estimation device 100, the map data storage unit 50 may utilize, for example, a server on the cloud. By transmitting the map data from the cloud server to the host vehicle position estimation device 100, a similar function can be provided.

[0023] The host vehicle position estimation device 100 generates highly accurate position information and the like of the host vehicle 200 by combining a plurality of acquired information through integrated positioning. Also, in a road including multiple lanes, the host vehicle position estimation device 100 estimates one lane in which the host vehicle 200 is traveling.

[0024] The host vehicle position estimation device 100 is a control device that executes a program stored in a storage medium and controls each part. The host vehicle position estimation device 100 includes at least one arithmetic processing unit (CPU) and a storage medium that stores programs and data. The host vehicle position estimation device 100 is realized, for example, by a microcomputer equipped with a storage medium readable by a computer. The storage medium is a non-transitory physical storage medium that stores programs and data readable by a computer non-temporarily. The storage medium is realized by a semiconductor memory, a magnetic disk, or the like.

[0025] As functional blocks, the host vehicle position estimation device 100 includes an information acquisition unit 110 and a position estimation unit 120. The information acquisition unit 110 acquires sensing information from the surrounding monitoring sensor 20, state quantity data from the host vehicle state quantity sensor unit 30, GPS information from the GNSS receiver 40, and map data from the map data storage unit 50. Therefore, the information acquisition unit 110 functions as an external information acquisition unit, a host vehicle state quantity acquisition unit, a satellite positioning acquisition unit, and a map data acquisition unit. The information acquisition unit 110 provides the acquired information to the position estimation unit 120.

[0026] Based on the sensing information, state quantity data, GPS information, map data, etc., the position estimation unit 120 estimates the position of the host vehicle 200 on the map. For example, the position estimation unit 120 estimates the latitude and longitude indicating the current position of the host vehicle 200 from the GPS information acquired by the GNSS receiver 40. Also, the position estimation unit 120 estimates from the state quantity data detected by the host vehicle state quantity sensor unit 30 whether the host vehicle 200 is traveling on a straight road, on a curve road with what degree of curvature, or is traveling in a way that deviates from the lane, etc.

[0027] The position estimation unit 120 has, as sub - function blocks, a reliability calculation unit 121, a lane estimation unit 122, and a lane change determination unit 123. When the host vehicle 200 is located on a road having a plurality of lanes, the reliability calculation unit 121 calculates, for each lane, a reliability indicating the probability of the host vehicle 200 being located in which lane among the plurality of lanes.

[0028] The lane estimation unit 122 estimates the lane in which the host vehicle 200 is located using the reliability calculated by the reliability calculation unit 121. For example, the lane estimation unit 122 estimates the lane with the highest reliability as the lane in which the host vehicle 200 is located. Also, for example, when there are a plurality of lanes with the highest reliability, the lane estimation unit 122 does not estimate the lane in which the host vehicle 200 is located as one lane.

[0029] The lane change determination unit 123 determines the lane change of the host vehicle 200 based on the sensing information, state quantity data, GPS information, and map data. A lane change means moving from the currently traveling lane to an adjacent lane on the right or left side and changing the traveling lane.

[0030] Next, an explanation will be given regarding the calculation of reliability. In the example shown in FIG. 3, the position estimation unit 120 currently estimates that it is traveling on the first lane L1 among the four-lane roads on one side. However, in reality, it is traveling on the second lane L2. And in the sensing information, the information of the lane lines adjacent to both sides of the vehicle is a broken line on both sides. In the map data, there are five lane lines as the information of the lane lines during driving, and the line types are solid lines on the left and right sides, and the information that the three in the center are broken lines is stored. Therefore, the lanes with broken lines on both sides are the second lane L2 and the third lane L3. When traveling on the first lane L1, the left lane line should be a solid line and the right lane line should be a broken line detected.

[0031] When comparing the lane line information between the sensing information and the map data, the information of the second lane L2 and the third lane L3 matches, and the information of the first lane L1 and the fourth lane L4 does not match. Therefore, in this case, the probability of being in the second lane L2 and the third lane L3 is higher than the probability of being in the first lane L1 and the fourth lane L4. Therefore, as shown in FIG. 3, the reliability indicating the probability is set to be higher for the second lane L2 and the third lane L3 than for the first lane L1 and the fourth lane L4. As a result, the position estimation unit 120 uses the reliability to determine that it is not in the first lane L1 and re-estimates that it is located in the second lane L2 or the third lane L3.

[0032] In this way, the reliability calculation unit 121 compares the information of the lane lines adjacent to both sides based on the sensing information with the information of the lane lines included in the map data, and makes the reliability of the lane where the obtained lane lines adjacent to both sides match the lane lines in the map data higher than the reliability of the lanes that do not match. For example, it can also be judged using the color of the lane lines. Whether the lane lines adjacent to both sides are white or yellow, etc., is used to judge whether the information included in the map data matches, and the reliability is set.

[0033] Next, a method for calculating the reliability using the number of lanes will be described. As shown in FIG. 4, the host vehicle 200 is traveling in the second lane L2 with three lanes on one side. The sensing information includes the total number of lanes on the road on which the vehicle is traveling, the number of lanes located on the left side of the host vehicle 200, and the number of lanes located on the right side of the host vehicle 200. Since the sensing information includes the lane line information, the number of lanes is obtained using the number of lane lines. In the example shown in FIG. 4, if the sensing information is appropriate, the number of lanes on the left side is 1 and the number of lanes on the right side is 1.

[0034] And since it is known from the map data that the number of lanes during travel is 3, the lane in which the host vehicle is traveling can be estimated using the number of lanes located on both sides indicated by the sensing information. Specifically, when traveling in the first lane L1 with three lanes on one side, the number of lanes on the left side is 0 and the number of lanes on the right side is 2. When traveling in the second lane L2 with three lanes on one side, the number of lanes on the left side is 1 and the number of lanes on the right side is 1. Further, when traveling in the third lane L3 with three lanes on one side, the number of lanes on the left side is 2 and the number of lanes on the right side is 0. Therefore, the reliability calculation unit 121 increases the reliability of the traveling lane and decreases the reliability of other lanes using the detected number of lanes.

[0035] However, there may be cases where the peripheral monitoring sensor 20 cannot detect the number of lanes. For example, when another peripheral vehicle 201 is traveling in the lane adjacent to the right side, the right lane cannot be recognized, and using the sensing information, the number of lanes on the left side may be 1 and the number of lanes on the right side may be 0. Therefore, since it is different from the number of lanes in the map data, it is difficult for the reliability calculation unit 121 to assign high and low levels to the reliability of each lane.

[0036] Therefore, when the number of lanes in the map data matches the total number of lanes in the sensing information, the reliability of the lane position corresponding to the number of lanes on both sides is calculated to be higher than that of the lanes that do not match, as described above. Conversely, when the number of lanes in the map data does not match the total number of lanes in the sensing information, there may be an error in the sensing information, so the reliability of each lane is calculated to be the same.

[0037] In this way, the reliability calculation unit 121 compares the total number of lanes in the sensing information with the number of lanes included in the map data. When the obtained total number of lanes matches the number of lanes in the map data, the reliability of the lane in which the vehicle identified using the number of lanes located on both sides is located is made higher than the reliability of other lanes.

[0038] Next, a method for calculating the reliability using road markings will be described. In the example shown in FIG. 5, the position estimation unit 120 currently estimates that the host vehicle 200 is in the second lane L2 in the center of three lanes on one side. However, in reality, it is traveling in the first lane L1. In the sensing information, the road marking in front of the host vehicle 200 is a straight-ahead left-turn arrow. In the map data, it is stored that the lane with the road marking being a straight-ahead left-turn arrow is located in the first lane L1. Therefore, the road marking in front in the sensing information does not match the road marking included in the map data. If it were traveling in the second lane L2, the road marking in front of the host vehicle 200 would be a straight-ahead arrow. Therefore, in this case, as shown in FIG. 5, the reliability of the first lane L1 that matches the straight-ahead left-turn arrow is set to be higher than that of the second lane L2 and the third lane L3 that do not match.

[0039] In this way, the reliability calculation unit 121 compares the road marking in the sensing information with the road marking included in the map data. When the obtained road marking matches the road marking in the map data, the reliability of the matching lane is made higher than the reliability of the non-matching lanes. As a result, the position estimation unit 120 re-estimates that it is located in the first lane L1 using the reliability.

[0040] Next, a method for calculating the reliability using lane changes will be described. As shown in FIG. 6, the position estimation unit 120 currently estimates that the host vehicle 200 is traveling in the center of three lanes on one side. And in reality, it is also traveling in the second lane L2. A case will be described where the lane change determination unit 123 determines that the traveling lane has been changed to the lane on the right side.

[0041] When it is determined that a lane change has been made to the right, the probability of being in the first lane L1 becomes lower than the probabilities of being in the second lane L2 and the third lane L3. Conversely, when it is determined that a lane change has been made to the left, the probability of being in the third lane L3 becomes lower than the probabilities of being in the first lane L1 and the second lane L2. Therefore, in the example shown in FIG. 6, since a lane change has been made to the right, the probabilities of being in the second lane L2 and the third lane L3 are calculated to be higher than that of the first lane L1.

[0042] In the case of two lanes on one side, when it is determined that a lane change has been made to the right, the probability of being in the first lane L1 becomes lower than the probability of being in the second lane L2. Conversely, when it is determined that a lane change has been made to the left, the probability of being in the second lane L2 becomes lower than the probability of being in the first lane L1.

[0043] In this way, when the lane change determination unit 123 determines that a lane change has occurred, the reliability calculation unit 121 makes the reliability of the lane located at the end opposite to the direction of the lane change lower than that of the other lanes.

[0044] In this way, the reliability calculation unit 121 calculates the reliability of each lane using the number of lanes, road markings, lane changes, etc. Then, the reliability calculation unit 121 calculates a combined reliability by integrating each reliability using a weighting coefficient for each reliability calculated using different features. For example, the reliability using road markings is set to be more important than the reliability using lane changes, and the weight is increased. As a result, the position estimation unit 120 can estimate the lane on which the vehicle is traveling using the combined reliability.

[0045] Next, the method for determining lane changes by the lane change determination unit 123 will be described. As a first determination method, when the lane change determination unit 123 detects a dividing line, it determines that a lane change has occurred when crossing the dividing line. Also, as a second determination method, when the host vehicle 200 is traveling near the center line of the lane, if the distance between the center line of the lane and the center position of the host vehicle 200 has a tendency to increase and exceeds a predetermined threshold value, it is determined that a lane change has occurred.

[0046] In addition, as a third determination method, the lane change determination unit 123 determines a lane change to one side by using a change in which the distance from the vehicle to one side road edge decreases or a change in which the distance to the other side road edge increases. This is an effective method when the surrounding monitoring sensor 20 can recognize the road edge but cannot recognize the lane marking. The lane marking may be difficult to detect due to deterioration, puddles, etc., but the road edge is often easy to detect due to steps, etc.

[0047] Specifically, as shown in FIG. 7, as the distances to the road edges, the left end distance W2 from the center of the host vehicle to the left side road edge and the right end distance W1 to the right side road edge are detected. When changing lanes to the left lane as shown in FIG. 7, the left end distance W2 decreases, and as it decreases, the right end distance W1 increases. When the decrease width or increase width exceeds the threshold value, it is determined that a lane change has occurred.

[0048] In addition, as a fourth determination method, the lane change determination unit 123 determines that a lane change has occurred when the lane with the highest reliability calculated by the reliability calculation unit 121 changes to another lane. The reliability is calculated for each lane. When there is a lane with a high reliability, the host vehicle is likely to be located in that lane. Therefore, when the lane with a high reliability changes to another lane, it is determined that a lane change has occurred.

[0049] In this way, the lane change determination unit 123 determines a lane change using four determination methods. The lane change determination unit 123 may determine a lane change using only any one of the four determination methods, or may determine a lane change by comprehensively considering the determination results of two or more determination methods.

[0050] As described above, according to the own vehicle position estimation device 100 of the present embodiment, when the own vehicle 200 is located on a road having a plurality of lanes, the reliability is calculated for each lane. Since it is the reliability for each lane, it is not a value that depends on the position within the lane. Therefore, even when the position estimation accuracy based on the state quantity of the vehicle is poor, the reliability is calculated for each lane based on the sensing information and the map data, so that the lane in which the vehicle is located can be specified using the reliability. As a result, the estimation accuracy of the traveling lane can be improved.

[0051] Also, in the present embodiment, the reliability calculation unit 121 compares the information on the lane lines adjacent to both sides indicated by the sensing information with the information on the lane lines included in the map data, and sets the reliability of the lane in which the lane lines adjacent to both sides obtained match the lane lines in the map data to be higher than the reliability of the lanes that do not match. Since the lane lines are used, the accuracy of the reliability can be calculated.

[0052] Furthermore, in the present embodiment, the reliability calculation unit 121 compares the total number of lanes indicated by the sensing information with the number of lanes included in the map data. When the obtained total number of lanes matches the number of lanes in the map data, the reliability of the lane in which the own vehicle 200 located and specified using the number of lanes on both sides is made higher than the reliability of the other lanes. Since the number of lanes on both sides is used, the accuracy of the reliability can be further improved.

[0053] Also, in the present embodiment, the reliability calculation unit 121 compares the mark information in the sensing information with the mark information included in the map data. When the obtained mark information matches the mark information in the map data, the reliability of the matching lane is made higher than the reliability of the lanes that do not match. Since the mark information is used, the accuracy of the reliability can be further improved.

[0054] Furthermore, in the present embodiment, when the lane change determination unit 123 determines that a lane change has occurred, the reliability calculation unit 121 makes the reliability of the lane located at the end on the side opposite to the direction of the lane change lower than that of the other lanes. By using the lane change, the estimation accuracy of the lane with low reliability can be improved.

[0055] Also, in the present embodiment, the lane change determination unit 123 determines a lane change to one side by using a change in which the distance from the host vehicle 200 to one side road edge decreases or a change in which the distance to the other side road edge increases. Since the presence or absence of a lane change is determined using the distance to the road edge, a lane change can be determined even when the lane marking cannot be detected.

[0056] Furthermore, in the present embodiment, the lane change determination unit 123 determines that a lane change has occurred when the lane with the highest reliability calculated by the reliability calculation unit 121 changes to another lane. Thus, a lane change can be determined using the reliability.

[0057] Also, in the present embodiment, the reliability calculation unit 121 calculates a reliability obtained by integrating each reliability using a weight coefficient for each reliability calculated using different features. By integrating the reliabilities, the accuracy of the reliability can be further improved.

[0058] (Other Embodiments) As described above, the preferred embodiments of the present disclosure have been described. However, the present disclosure is not limited to the above-described embodiments at all, and various modifications can be made without departing from the gist of the present disclosure.

[0059] The structures of the above-described embodiments are merely examples, and the scope of the present disclosure is not limited to the scope of these descriptions. The scope of the present disclosure is indicated by the description of the claims, and further includes all modifications within the meaning and scope equivalent to the description of the claims.

[0060] In the above-described first embodiment, the information acquisition unit 110 has the functions of an external information acquisition unit, a host vehicle state quantity acquisition unit, a satellite positioning acquisition unit, and a map data acquisition unit. However, the present disclosure is not limited to a configuration in which these are integrated, and each function may be realized at different locations.

[0061] In the foregoing first embodiment, the functions realized by the host vehicle position estimation device 100 may be realized by hardware and software different from those described above, or a combination thereof. The host vehicle position estimation device 100 may communicate with other control devices, for example, and other control devices may execute part or all of the processing. When the host vehicle position estimation device 100 is realized by an electronic circuit, it can be realized by a digital circuit including a number of logic circuits or an analog circuit.

[0062] In the foregoing first embodiment, the host vehicle position estimation device 100 is used in a vehicle, but is not limited to being mounted on the vehicle, and at least a part thereof may not be mounted on the vehicle.

Description of Reference Numerals

[0063] 10…Vehicle system 20…Peripheral monitoring sensor 30…Host vehicle state quantity sensor unit 40…GNSS receiver 50…Map data storage unit 100…Host vehicle position estimation device 110…Information acquisition unit (external information acquisition unit, host vehicle state quantity acquisition unit, satellite positioning acquisition unit) (map data acquisition unit) 120…Position estimation unit 121…Reliability calculation unit 122…Lane estimation unit 123…Lane change determination unit 200…Host vehicle (automobile) L1…First lane L2…Second lane L3…Third lane L4…Fourth lane

Claims

1. In a vehicle position estimating device (100) mounted on a vehicle (200) and used, An external information acquisition unit (110) that acquires external information regarding objects around the vehicle and road markings around the vehicle; A vehicle state quantity acquisition unit (110) that acquires state quantities related to the running of the vehicle; A satellite positioning acquisition unit (110) that acquires the latitude and longitude at which the vehicle is located by a satellite positioning system; A map data acquisition unit (110) that acquires map data having road information regarding lanes; A position estimation unit (120) that estimates the position of the vehicle on the map based on the external information, the state quantity, the latitude and longitude, and the map data; A lane change determination unit (123) that determines a lane change of the vehicle based on the external information, the state quantity, the latitude and longitude, and the map data, comprising: The position estimation unit includes: When the vehicle is located on a road having a plurality of lanes, a reliability calculation unit (121) that calculates, for each lane, a reliability indicating the probability of the vehicle being located in which lane among the plurality of lanes using the external information and the map data; A lane estimation unit (122) that estimates the lane in which the vehicle is located using the reliability calculated by the reliability calculation unit; When the lane change determination unit determines that a lane change has occurred, the reliability calculation unit sets the reliability of the lane located at the end opposite to the direction of the lane change to be lower than that of other lanes; The external information acquisition unit acquires the distances to the road edges on both sides of the vehicle respectively; The lane change determination unit determines a lane change to one side of the vehicle using a change in which the distance to the road edge on one side from the vehicle decreases or a change in which the distance to the road edge on the other side increases. A vehicle position estimating device.

2. The external information acquisition unit acquires information on the dividing lines adjacent to both sides of the vehicle; The road information of the map data includes information on lane lines. The reliability calculation unit compares the information on the lane lines adjacent to both sides acquired by the external information acquisition unit with the information on the lane lines included in the map data, and makes the reliability of the lane in which the acquired lane lines adjacent to both sides match the lane lines in the map data higher than the reliability of the lanes that do not match. The vehicle position estimation device according to claim 1.

3. The external information acquisition unit acquires the total number of lanes on the road, the number of lanes located on the left side of the automobile, and the number of lanes located on the right side of the automobile, respectively. The road information of the map data includes information on the number of lanes. The reliability calculation unit compares the total number of lanes acquired by the external information acquisition unit with the number of lanes included in the map data. When the acquired total number of lanes matches the number of lanes in the map data, the reliability of the lane in which the automobile located by using the number of lanes located on both sides is higher than the reliability of other lanes. The vehicle position estimation device according to claim 1 or 2.

4. The external information acquisition unit acquires mark information formed on the road surface in front of the driving lane of the automobile. The road information of the map data includes the mark information. The reliability calculation unit compares the mark information acquired by the external information acquisition unit with the mark information included in the map data. When the acquired mark information matches the mark information in the map data, the reliability of the matching lane is higher than the reliability of the lanes that do not match. The vehicle position estimation device according to any one of claims 1 to 3.

5. When the lane with the highest reliability calculated by the reliability calculation unit changes to another lane, the lane change determination unit determines that a lane change has occurred. The vehicle position estimation device according to any one of claims 1 to 4.

6. The vehicle position estimation device according to any one of claims 1 to 5, wherein the reliability calculation unit calculates a reliability obtained by integrating each reliability using a weight coefficient for each reliability calculated using different features.

Images