JP6982430B2 - Vehicle lane identification device - Google Patents

Description

The present invention relates to a vehicle traveling lane specifying device that specifies whether or not the traveling lane of the own vehicle position acquired based on the position information from the positioning satellite is the traveling lane in which the own vehicle is actually traveling.

Conventionally, in the car navigation system mounted on the own vehicle, the position (own vehicle position) and the traveling direction of the own vehicle are based on the position information received from the positioning satellite (GNSS (Global Navigation Satellite System) satellite including the GPS satellite). And by matching with the road map information, the position information of the center of the lane closest to the direction of travel and the road azimuth angle are acquired. And radio navigation that performs steering control of automatic driving so that the own vehicle travels along the center of the lane is known.

However, in the above-mentioned radio navigation, when the reception accuracy from the positioning satellite deteriorates due to buildings around the road, weather conditions, etc., the error included in the vehicle position information increases, and steering control by stable automatic driving is performed. It can be difficult to continue. To deal with this, for example, Patent Document 1 (Japanese Unexamined Patent Publication No. 2011-2324) discloses a technique for estimating the error variance included in the position information of a vehicle by using a Kalman filter.

That is, in the same document, map matching is performed for each road data around the vehicle position by using the vehicle position, error variance, and map data obtained based on the information from the positioning receiver, the angular speed sensor, the vehicle speed sensor, and the like. Then, among the candidate points, the candidate point with the highest probability is selected as the position of the own vehicle on the map, and the error ellipse for determining the reliability from the error covariance matrix around this point is set as the existence probability (95 [ %], 99.7 [%], etc.). Then, when this error ellipse is within the traveling lane, it is determined that the own vehicle exists in the traveling lane with the above-mentioned existence probability.

Japanese Unexamined Patent Publication No. 2011-2324

By the way, the error ellipse generated by the Kalman filter estimates the range of the own vehicle position where the estimation error is minimized according to the normal distribution (Gaussian distribution), and the candidate point with the highest likelihood is the center of the own vehicle position. Estimate as a value. Therefore, if the radius of the error ellipse is small, the position of the own vehicle can be estimated with high probability.

However, since the position information from the positioning satellite contains an error, it is possible that the candidate point with the highest likelihood is offset from the actual vehicle position. Therefore, even if the radius of the error ellipse generated around the candidate point with the highest probability is small and it is within the driving lane, that driving lane is the driving lane set by the own vehicle as the target traveling lane. It is not possible to determine if it is.

Therefore, when trying to maintain stable steering control in automatic driving, it is always determined whether or not the driving lane in which the error ellipse is contained is the driving lane set as the target traveling path of the own vehicle. It needs to be verified and identified.

In view of the above circumstances, the present invention allows the traveling lane to be the target traveling path of the own vehicle even when the error range of the own vehicle position set based on the position information from the positioning satellite is within the traveling lane. It is an object of the present invention to provide a vehicle lane identification device capable of reliably specifying the vehicle lane set as the vehicle and capable of continuing automatic driving in a stable state.

The present invention includes a vehicle position acquisition means for receiving a positioning signal from a positioning satellite to acquire the vehicle position of the vehicle, a storage unit for storing road map information, and the vehicle acquired by the vehicle position acquisition means. The traveling lane estimation means for estimating the traveling lane by referring to the road map information stored in the storage means based on the vehicle position, the traveling state detecting means for detecting the traveling state of the own vehicle, and the own vehicle position acquisition. An error range calculation means for setting an error range of the position information of the own vehicle acquired by the own vehicle position acquisition means by filtering the own vehicle position acquired by the means and the running state detected by the running state detecting means. When the error range calculated by the error range calculation means is within the driving lane estimated by the traveling lane estimation means, the reliability determination means for determining that the information of the own vehicle position is highly reliable. When the reliability determination means determines that the information on the position of the own vehicle has high reliability, the lane marking type of the lane that divides the left and right of the lane in which the own vehicle travels. A lane marking type recognizing means for recognizing, and a lane marking type comparing means for comparing the lane marking type recognized by the lane marking means with the lane marking type stored in the road map information of the traveling lane. , The traveling direction calculating means for obtaining the traveling direction of the own vehicle position from the time change of the own vehicle position, and the traveling direction obtained by the traveling direction calculating means and the road map information of the own vehicle position are stored. The azimuth comparison means for comparing the lane orientation, the lane marking type recognized by the lane marking means by the lane marking comparison means, and the lane marking type stored in the road map information of the traveling lane. When it is determined that the two are in agreement and the traveling direction and the lane direction are determined by the direction comparison means, the traveling lane set based on the own vehicle position is the own vehicle. It further has a traveling lane specifying means for identifying the traveling lane of the vehicle.

According to the present invention, the line type of the lane marking that divides the left and right of the traveling lane recognized by the lane marking type recognition means matches the lane marking type stored in the road map information of the traveling lane, and positioning is performed. When the traveling direction of the own vehicle position obtained from the time change of the own vehicle position set based on the positioning signal from the satellite and the lane direction stored in the road map information of the own vehicle position match. Since the driving lane set based on the own vehicle position is specified as the driving lane of the own vehicle, even if the error range of the own vehicle position is within the driving lane, the driving lane is specified. It is possible to more reliably determine that the vehicle is in the driving lane set as the target travel path of the own vehicle, and it is possible to continue automatic driving in a stable state.

Schematic configuration of the navigation device Flow chart showing the vehicle position error calculation routine Flowchart showing Kalman filter operation subroutine Flowchart showing the own vehicle lane identification routine (Part 1) Flowchart showing the own vehicle lane identification routine (Part 2) (A) is an explanatory diagram showing an error ellipse of the position of the own vehicle that has been positioned, (b) is an explanatory diagram showing a state in which the major axis of the error ellipse protrudes from the traveling lane, and (c) is an explanatory diagram showing the error ellipse in the traveling lane. Explanatory diagram showing the state Explanatory drawing showing the state where the center of the error ellipse is detected in the adjacent lane with respect to the lane in which the own vehicle is traveling. Explanatory drawing showing a state in which the center of the error ellipse is detected in the oncoming lane with respect to the lane in which the own vehicle is traveling. Explanatory diagram showing a state of determining whether or not the center of the error ellipse is on the traveling lane from the curve curvature when the own vehicle is traveling.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Reference numeral 1 in FIG. 1 is a navigation device mounted on a vehicle (own vehicle, see FIG. 6) M, and has a navigation control unit (navigation_ECU) 11. The navigation_ECU 11 is mainly composed of a microcomputer and has a well-known CPU, ROM, RAM, non-volatile memory and the like, and various programs and fixed data executed by the CPU are stored in the ROM.

Further, the navigation_ECU 11 is provided with a Kalman filter calculation unit 11a as an error range calculation means and a own vehicle traveling lane specific calculation unit 11b as a locator function. In addition to the locator function, the navigation_ECU 11 has a guidance function for guiding the own vehicle M to the destination, but since this guidance function is well known, the description thereof is omitted here.

On the input side of the navigation_ECU 11, it acts on the camera unit 12 as a forward recognition means and the own vehicle M as sensors for acquiring the parameters necessary for identifying the traveling lane in which the own vehicle M is actually traveling. Acceleration sensor 13 that detects acceleration G, wheel speed sensor 14 that detects wheel speed from the number of rotations of each wheel, gyro sensor 15 that detects angular speed acting on own vehicle M, GNSS (Global Navigation) represented by GPS satellite Satellite System) A GNSS receiver 16 or the like as a vehicle position acquisition means for receiving a positioning signal from a satellite and acquiring position information of the vehicle M is connected. Each of the sensors 13 to 15 corresponds to the traveling state detecting means of the present invention.

Further, the camera unit 12 has a stereo camera including a main camera 12a and a sub camera 12b, and an image processing unit (IPU) 12c, and the driving environment information in front of the own vehicle M captured by both cameras 12a and 12b is the IPU 12c. Image processing is performed in a predetermined manner and output to the navigation_ECU 11.

Further, a high-precision road map database 17 is connected to this navigation_ECU 11. The high-precision road map database 17 is provided in a large-capacity storage means such as an HDD, and high-precision road map information (dynamic map) is stored. The high-precision road map information includes a lane width database that stores lane width data, a lane center database that stores lane center position coordinate data, a lane direction angle database that stores lane travel direction angle data, and the like.

Further, the steering control unit 21 is connected to the output side of the navigation_ECU 11. In the steering control of automatic driving, the steering control unit 21 drives the own vehicle M along the target traveling path set to guide the own vehicle M to the destination based on the own vehicle position information from the navigation_ECU 11. It controls the steering torque for the electric power steering (EPS) motor.

By the way, the own vehicle position information received by the GNSS receiver 16 includes a predetermined error, and the navigation_ECU 11 checks whether or not this error range is within the traveling lane, and if it is within the traveling lane, It is presumed that the own vehicle M is traveling without protruding into the traveling lane. Therefore, at the time of steering control of automatic operation, the Kalman filter calculation unit 11a of the navigation_ECU 11 has the acceleration detected by the acceleration sensor 13, the wheel speed detected by the wheel speed sensor 14, the angular velocity and the azimuth angle detected by the gyro sensor 15, and the azimuth angle. The candidate points of the own vehicle position information acquired by the GNSS receiver 16 are taken in.

Then, the error information contained therein is integrated by using a Kalman filter which is a filtering process, and the most probable candidate point is estimated to be the own vehicle position P (FIG. 6) based on the position information received by the GNSS receiver 16. (Refer to), and with this estimated vehicle position P as the center, according to the normal distribution (Gaussian distribution), the average of the candidate points of the vehicle position information and the predetermined existence probability (predetermined existence probability) as the error range represented by the variance-covariance matrix. For example, an error ellipse R showing 95 [%]) is generated.

Further, the own vehicle lane identification calculation unit 11b determines whether or not the error ellipse R centered on the estimated own vehicle position P is within the travel lane, and the own vehicle M sets this travel lane as the target travel path. It is determined whether or not the vehicle is in the driving lane.

The error ellipse R centered on the estimated vehicle position P calculated by the Kalman filter calculation unit 11a is specifically generated in the vehicle position error calculation routine shown in FIG. In this routine, first, in step S1, the acceleration of the own vehicle M detected by the acceleration sensor 13 is read, the process proceeds to step S2, and the wheel speed which is the rotation speed of each wheel detected by the wheel speed sensor 14 is read, and further, a step is performed. In S3, the angular velocity of the own vehicle M detected by the gyro sensor 15 is read.

Then, the process proceeds to step S4, a plurality of candidate points indicating the position of the own vehicle acquired by the GNSS receiver 16 are read, and in step S5, a Kalman filter operation is executed based on these parameters to exit the routine.

This Kalman filter operation is executed according to the Kalman filter operation subroutine shown in FIG. In this subroutine, first, in step S11, a well-known Kalman filter is used to calculate the most likely candidate point and the error variance from the candidate points indicating the positioning values having discrete errors received by the GNSS receiver 16. ..

Then, the process proceeds to step S12, the most probable candidate point calculated in step S11 is set as the estimated own vehicle position (latitude, longitude) P, and the process proceeds to step S13, and the error distribution centered on the estimated own vehicle position P. Set the ellipse (error ellipse) R of and exit the routine. This error ellipse R indicates a range in which the own vehicle position exists with a predetermined probability (for example, 95 [%]), and as shown in FIG. 6A, the error distance (error diameter) A in the longitudinal direction and the latitude direction It is represented by the error distance (error diameter) B of, and it is shown that the positioning error is large in the major axis direction of the ellipse and the error is small in the minor axis direction of the ellipse. In the figure, the state in which the own vehicle M is traveling from south to north or from north to south (hereinafter referred to as "north-south direction") is shown.

The estimated own vehicle position and the error ellipse R are read by the own vehicle traveling lane specifying calculation unit 11b. In the own vehicle traveling lane specific calculation unit 11b, whether or not the error ellipse R obtained by the above-mentioned Kalman filter calculation unit 11a is within the traveling lane, and whether or not the traveling lane is actually set as the target traveling path of the own vehicle M. Performs processing to identify whether or not the vehicle is in the driving lane.

The identification of the own vehicle traveling lane is specifically executed according to the own vehicle traveling lane identification routine shown in FIGS. 4 to 5. In this subroutine, first, from each database stored in the high-precision road map database 17 in step S21, the attributes of road information near the estimated own vehicle position P (number of lanes, lane width, type of left and right lane markings (lane markings). Seed), lane orientation angle, curve curvature, etc.) are read. Next, the process proceeds to step S22, and the estimated own vehicle position P is matched with the read road map to estimate the traveling lane. The processing in steps S21 and S22 corresponds to the traveling lane estimation means of the present invention.

Then, the process proceeds to step S23, and the reliability of the estimated own vehicle position P is checked depending on whether or not the error ellipse R indicating the existence probability generated around the estimated own vehicle position P is within the traveling lane. The process in this step corresponds to the reliability determination means of the present invention.

For example, as shown in FIG. 6B, even if the error distance B in the latitude direction of the error elliptical R set in the own vehicle M traveling in the north-south direction is a minor axis, the error distance A in the longitudinal direction A. If has a major axis and extends beyond the width direction of the traveling lane, the probability of being present in the traveling lane of the own vehicle M is less than or equal to a preset existence probability (for example, 95 [%]), and is out of the traveling lane. It is determined that there is.

On the contrary, for example, as shown in FIG. 6 (c), even if the error distance B in the latitude direction of the error ellipse R is the major axis, when the error distance in the longitude direction is the minor axis and it is in the traveling lane, it is self. It is determined that the vehicle M exists in the traveling lane with an existence probability (for example, 95 [%]) or more. Therefore, the determination of whether or not the own vehicle M is within the traveling lane based on the error ellipse R is determined by whether or not the error ellipse R is out of the lane width Lw.

Then, when the error ellipse R protrudes from the lane width Lw (state in FIG. 6B), the information of the estimated own vehicle position P has low reliability, so that the information branches to step S29. On the other hand, when the error ellipse R is within the lane width Lw (state in FIG. 6C), the probability that the error ellipse R exists in the traveling lane of the own vehicle M is higher than the predetermined existence probability, and it certainly exists. The determination is made, and the process proceeds to step S24.

In step S24, the image information as the front road information in front of the own vehicle M captured by the camera unit 12 is read, and the type of the lane marking (section line type) that divides the left and right of the traveling lane is recognized. Therefore, the camera unit 12 has a function as a division line type recognition means of the present invention.

Then, the process proceeds to step S25, and the left and right division line types of the traveling lane in which the estimated own vehicle position P exists are compared with the left and right division line types recognized by the camera unit 12. The processing in this step corresponds to the division line type comparison means of the present invention.

For example, as shown in FIG. 7, when the road has three lanes on each side and the own vehicle M is traveling in the left lane, the left section line is a solid line and the right section line is a broken line. When traveling in the central lane, both the left and right section lines are broken lines. Further, when traveling in the right lane, the left lane is a broken line and the right lane is a solid line. The arrow in the error ellipse R indicates the traveling direction of the estimated own vehicle position P.

Therefore, when the left and right lane markings recognized by the camera unit 12 and the left and right lane markings of the traveling lane in which the estimated own vehicle position P exists obtained from the road map information do not match, for example, as shown in FIG. If the lane in which the own vehicle M is actually traveling is the left lane, but the estimated own vehicle position P is in the adjacent central lane, the left lane is the solid line in the left lane and the right lane. The line type is a broken line, and the left and right lane markings are both broken lines in the center lane. Therefore, on a road having two lanes on each side and three lanes on each side, it is possible to determine whether or not the traveling lanes match by examining the left and right lane marking types.

Then, if the left and right lanes match, the process proceeds to step S26, and if they do not match, the process proceeds to step S30. In step S26, the traveling direction of the estimated vehicle position P is obtained from the temporal change of the estimated vehicle position P. The processing in this step corresponds to the traveling direction calculation means of the present invention.

Next, the process proceeds to step S27, and the estimated own vehicle position P is compared with the lane direction of the traveling lane stored in the matched road map information, and it is checked whether or not both positions match. Both of these positions do not have to be exactly the same, and if they are within the allowable range in the direction of travel, they are judged to be the same. The process in step S27 corresponds to the directional comparison means of the present invention.

As a result, for example, as shown in FIG. 8, on the one-sided one-lane two-way road, both the left and right lane markings are drawn as solid lines in the traveling lane and the oncoming lane of the own vehicle M. In, even though the estimated own vehicle position P is matched to the oncoming lane side, since the left and right division line types match, it is erroneously determined that the traveling lanes are the same. However, in step S27, erroneous determination can be prevented by comparing the traveling direction of the estimated own vehicle position P (upward on the paper in the figure) with the lane direction on the road map (downward on the paper in the figure). ..

Then, in step S27, when the traveling direction of the estimated own vehicle position P and the lane direction on the road map match, it is determined that the estimated own vehicle position P exists on the traveling lane of the own vehicle M. Then, the process proceeds to step S28. If the traveling directions do not match, it is determined that the estimated own vehicle position P is matched to the oncoming lane side, and the vehicle branches to step S29.

On the other hand, when branching from step S25 to step S30, in steps S30 to S32, the estimated own vehicle position P is offset from the lane in which the own vehicle M is traveling, but the own vehicle M itself is the target traveling path. It is verified whether or not the vehicle is driving correctly in the driving lane set as.

That is, first, in step S30, the road shape is calculated from the travel locus generated based on the angular velocity detected by the gyro sensor 15 and the mileage detected by the wheel speed sensor 14, and the process proceeds to step S31. Map matching (comparison) is performed with the road information in the vicinity of the estimated own vehicle position P read in step S21. The process in step S30 described above corresponds to the road shape acquisition means of the present invention.

For example, as shown in FIG. 9, when the own vehicle M is traveling on a curved road, the curve curvature χ, which is the shape of the road, is calculated based on the traveling locus. On the other hand, from the road map information, the lane width of the traveling lane and the curve curvature in the center of the lane are read, the curve curvature in the traveling lane is calculated, and the curve curvature χ calculated based on the traveling locus is compared. The figure shows a state in which the own vehicle M is driven along the center of the lane by lane keeping control.

Next, in step S32, it is checked whether or not there is a matching road shape (for example, curve curvature), and if there is a matching road shape, the process proceeds to step S33, and the current own vehicle position is obtained as road map information based on the traveling locus. And, the vehicle position information on the road map is acquired, and the process returns to step S28. If there is no matching road shape, the process returns to step S29. The process in step S32 corresponds to the road shape comparison means of the present invention.

Then, when the process proceeds from step S27 to step S28, the traveling lane on the road map of the estimated own vehicle position P is specified as the traveling lane in which the own vehicle M is traveling, and the routine is exited. Further, when returning from step S33 to step S28, the lane to which the own vehicle position information acquired in step S33 is mapped is specified as the traveling lane of the own vehicle M, and the routine is exited. The process in step S28 corresponds to the traveling lane specifying means of the present invention.

On the other hand, when the vehicle branches from steps S23, S27, or S32 to step S29, it is determined that the position information of the estimated vehicle position P or the vehicle position information acquired in step S31 described above has low reliability, and the information is cleared. And exit the routine.

When the traveling lane of the own vehicle M is specified in step S28 described above, the steering control unit 21 sets the position information (latitude, longitude, lane azimuth angle, etc.) on the road map on which the own vehicle M exists and the target traveling path. Based on the above, steering control by automatic operation is continued. On the other hand, when the own vehicle position information is cleared in step S29, the steering control by the automatic driving is interrupted, and the steering control operation is switched to the driver.

As described above, in the present embodiment, the most probable candidate point from the candidate points of the own vehicle position acquired based on the position information from the positioning satellite received by the GNSS receiver 16 is set as the estimated own vehicle position P. At the same time, even if the error elliptical R set around the estimated own vehicle position P is within the traveling lane, the traveling lane and the traveling lane set as the target traveling path of the own vehicle M are one. Since it is checked whether or not the vehicle is doing so, it is necessary to surely specify that the driving lane on the estimated own vehicle position P matching the road map information is the driving lane set as the target traveling path of the own vehicle M. Can be done. As a result, when the traveling lanes match, the automatic driving can be continued in a stable state.

Further, even if the traveling lane in which the estimated own vehicle position P exists and the traveling lane set as the target traveling path of the own vehicle M do not match, the curve curvature is based on the forward image captured by the camera unit 12. Since the driving lane is specified by recognizing the road shape such as, etc. and matching with the road map information, even if the estimated own vehicle position P is offset to the oncoming lane side, automatic driving is performed. It will be possible to continue in a stable state.

The present invention is not limited to the above-described embodiment, and the front recognition means is not limited to the camera unit 12 as long as it can recognize the division line type that divides the left and right sides of the traveling lane. It may be another forward recognition means using a laser radar or the like.

1 ... Navigation device,
11 ... Navigation control unit,
11a ... Kalman filter calculation unit,
11b ... Own vehicle lane identification calculation unit,
12 ... Camera unit,
13 ... Accelerometer,
14 ... Wheel speed sensor,
15 ... Gyro sensor,
16 ... GNSS receiver,
17 ... High-precision road map database,
21 ... Steering control unit,
A ... Error distance in the latitude direction,
B ... Error distance in the longitude direction,
G ... Acceleration,
Lw ... Lane width,
M ... own vehicle,
P ... Estimated own vehicle position,
R ... Error ellipse

Claims (2)

A vehicle position acquisition means that receives a positioning signal from a positioning satellite to acquire the vehicle position of the vehicle,
A storage means for storing road map information,
A traveling lane estimation means that estimates a traveling lane by referring to road map information stored in the storage means based on the own vehicle position acquired by the own vehicle position acquisition means.
The traveling state detecting means for detecting the traveling state of the own vehicle and the traveling state detecting means.
The error range of the position information of the own vehicle acquired by the own vehicle position acquisition means is set by filtering the own vehicle position acquired by the own vehicle position acquisition means and the running state detected by the traveling state detecting means. Error range calculation means and
When the error range calculated by the error range calculating means is within the traveling lane estimated by the traveling lane estimation means, the reliability determination means for determining that the information of the own vehicle position is highly reliable is used. In the driving lane identification device of the vehicle to be equipped
When the reliability determination means determines that the information on the position of the own vehicle has high reliability, the division line type recognition means for recognizing the division line type of the division line that divides the left and right of the lane in which the own vehicle travels.
A lane marking type comparing means for comparing the lane marking type recognized by the lane marking means with the lane marking type stored in the road map information of the traveling lane, and a lane marking comparison means.
A traveling direction calculation means for obtaining the traveling direction of the own vehicle position from the time change of the own vehicle position, and
A direction comparison means for comparing the traveling direction obtained by the traveling direction calculating means with the lane direction stored in the road map information of the own vehicle position, and
It is determined by the division line type comparison means that the division line type recognized by the division line type recognition means matches the division line type stored in the road map information of the traveling lane, and the above-mentioned When it is determined by the direction comparison means that the traveling direction and the lane direction match, the traveling lane set based on the own vehicle position is specified as the traveling lane of the own vehicle. A vehicle traveling lane identification device, which further comprises means. A road shape acquiring means for acquiring a road shape from the traveling locus of the own vehicle calculated based on the traveling state detected by the traveling state detecting means, and a road shape acquiring means.
Further, it has a road shape comparing means for checking whether or not there is a matching road shape by matching the road shape acquired by the road shape acquiring means with the road map information around the own vehicle position.
In the traveling lane specifying means, the division line type recognized by the division line type recognition means by the division line type comparison means does not match the division line type stored in the road map information of the traveling lane. The vehicle according to claim 1, wherein when the road shape is determined to be the same and a matching road shape is detected by the road shape comparison means, the lane having the road shape is specified as the traveling lane of the own vehicle. Driving lane identification device.

Images