Travel road determination device and method and travel road determination computer program

Abstract

A travel road determination device, method, and computer program are provided. The travel road determination device includes a collating section (32) that detects, as a candidate for a road on which a vehicle is traveling, an interval closest to a current position of the vehicle included in a road that is most consistent with a travel track in a predetermined interval closest to the vehicle, by collating the travel track and a first map indicating the road; a lane detection section (33) that detects a lane in which the vehicle is traveling, by collating a sensor signal indicating an environment around the vehicle obtained by a sensor mounted on the vehicle and a second map indicating each lane of each road; and a road determination section (34) that determines the candidate for the road as the road on which the vehicle is traveling when the detected lane is included in the candidate for the road, and determines a road including the detected lane as the road on which the vehicle is traveling when the detected lane is not included in the candidate for the road.

Description

TECHNICAL FIELD

[0001] The present application relates to a travel road determination device, a travel road determination method, and a travel road determination computer program that determine a road on which a vehicle is traveling. BACKGROUND

[0002] In order to appropriately perform automatic driving control of a vehicle, it is required to accurately detect a road on which the vehicle is traveling. Thus, a technique has been proposed in which a road on which a vehicle is traveling is determined by collating a travel trajectory of the vehicle and map information (see Japanese Patent Application Publication No. 2020-126048).

[0003] In the method of determining a position of a vehicle in a digital map described in Japanese Patent Application Publication No. 2020-126048, path information characteristic of a path on which the vehicle has traveled is decided using movement information related to movement of the vehicle. Then, the method compares the path information and map information characteristic of a path on a road saved in the digital map. SUMMARY

[0004] Depending on the accuracy of information used in calculation of a travel trajectory of a vehicle, or the road on which the vehicle is traveling and the environment around the road, in collation of the travel trajectory and a map, a road different from the road on which the vehicle is actually traveling is sometimes erroneously detected as the road on which the vehicle is traveling. In such a case, a vehicle control device that performs automatic driving control of the vehicle can not be able to use correct information related to the road on which the vehicle is traveling, and it can be possible that a failure occurs in the automatic driving control.

[0005] Thus, an object of the present application is to provide a travel road determination device capable of accurately determining a road on which a vehicle is traveling.

[0006] According to one embodiment, a travel road determination device is provided. The travel road determination device includes a collating section that detects, as a candidate of a road on which a vehicle is traveling, an interval closest to a current position of the vehicle included in a road on the first map that is most consistent with a travel trajectory in a predetermined interval closest to the vehicle, by collating the travel trajectory and the first map that represents the road; a lane detection section that detects a lane on which the vehicle is traveling, by collating a sensor signal representing an environment around the vehicle obtained by a sensor mounted on the vehicle and a second map that represents each lane of each road; and a road determination section that determines the candidate of the road as the road on which the vehicle is traveling in a case where the detected lane is included in the candidate of the road, and determines a road including the detected lane as the road on which the vehicle is traveling in a case where the detected lane is not included in the candidate of the road.

[0007] In the travel road determination device, it is preferable that the collating section calculate a first certainty degree indicating reliability of the candidate of the road, the lane detection section calculate a second certainty degree indicating reliability of the detected lane, and the road determination section determine the road including the detected lane as the road in which the vehicle is traveling only when the second certainty degree is higher than the first certainty degree.

[0008] In addition, in the travel road determination device, it is preferable that the collating section detect, as the candidate of the road in which the vehicle is traveling, the road in the road of the first map that is consistent with the travel trajectory to a degree that is equal to or higher than a predetermined consistency threshold, and the road determination section determine, when there are a plurality of the candidates of the detected road, the road including the detected lane in which the vehicle is traveling among the plurality of the candidates of the detected road as the road in which the vehicle is traveling.

[0009] Alternatively, in the travel road determination device, it is preferable that the road determination section determine, when there is no candidate of the detected road, the road including the detected lane as the road in which the vehicle is traveling.

[0010] According to another embodiment, a travel road determination method is provided. The travel road determination method includes detecting, as a candidate of a road in which a vehicle is traveling, an interval closest to a current position of the vehicle included in a road of a first map that is most consistent with a travel trajectory in a predetermined interval closest to the vehicle by collating the travel trajectory and the first map indicating the road, detecting a lane in which the vehicle is traveling by collating a sensor signal indicating an environment around the vehicle obtained by a sensor mounted on the vehicle and a second map indicating each lane of each road, determining the candidate of the road as the road in which the vehicle is traveling when the detected lane is included in the candidate of the road, and determining a road including the detected lane as the road in which the vehicle is traveling when the detected lane is not included in the candidate of the road.

[0011] According to still another embodiment, a travel road determination computer program is provided. The travel road determination computer program includes commands for causing a processor mounted on a vehicle to execute: detecting, as a candidate of a road on which the vehicle is traveling, an interval closest to a current position of the vehicle included in a road most consistent with a travel track in a predetermined interval closest to the vehicle, by collating the travel track and a first map representing roads, detecting a lane on which the vehicle is traveling, by collating a sensor signal representing an environment around the vehicle obtained by a sensor mounted on the vehicle and a second map representing each lane of each road, in a case where the detected lane is included in the candidate of the road, determining the candidate of the road as the road on which the vehicle is traveling, and in a case where the detected lane is not included in the candidate of the road, determining a road including the detected lane as the road on which the vehicle is traveling.

[0012] The travel road determination device according to the present embodiment achieves an effect of being able to determine a road on which a vehicle is traveling with good precision. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 is a schematic configuration diagram of a vehicle control system in which the travel road determination device is installed.

[0014] Figure 2 is a hardware configuration diagram of an electronic control device as one embodiment of the travel road determination device.

[0015] Figure 3 is a functional block diagram of a processor of the electronic control device relating to the travel road determination processing.

[0016] Figure 4 is a diagram representing an outline of travel road determination according to the present embodiment.

[0017] Figure 5 is an action flowchart of the travel road determination processing. DETAILED DESCRIPTION

[0018] The following describes a travel road determination device, a travel road determination method implemented in the travel road determination device, and a travel road determination computer program with reference to the drawings. The travel road determination device determines a travel trajectory of a vehicle in a predetermined section closest to the travel trajectory based on a vehicle motion signal obtained by a sensor that acquires information related to a motion of the vehicle, such as a wheel speed sensor or a gyro sensor. Further, the travel road determination device determines a road that is most consistent with the travel trajectory among roads represented in a first map by comparing the travel trajectory and the first map. Moreover, the travel road determination device determines a section included in the determined road that is closest to a current position of the vehicle as a candidate of a road on which the vehicle is traveling (hereinafter, sometimes referred to simply as a travel road). Still further, the travel road determination device detects a lane on which the vehicle is traveling (hereinafter, sometimes referred to simply as a travel lane) by comparing a sensor signal obtained by a sensor mounted on the vehicle, which represents an environment around the vehicle, and a second map that represents each lane of each road. Moreover, the travel road determination device determines the candidate as the travel road when the detected travel lane is included in the candidate, and determines a road including the detected travel lane as the travel road when the detected travel lane is not included in the candidate. In this way, the travel road determination device improves the detection accuracy of the road on which the vehicle is traveling by using the detection result of the travel lane in the determination of the travel road.

[0019] Figure 1 is a schematic configuration diagram of a vehicle control system in which the travel road determination device is installed. In addition, Figure 2 is a hardware configuration diagram of an electronic control device as one embodiment of the travel road determination device. In the present embodiment, a vehicle control system 1 mounted on a vehicle 10 and controlling the vehicle 10 has at least one vehicle motion sensor 2, a camera 3, a distance sensor 4, a storage device 5, and an electronic control device (ECU) 6 as one example of the travel road determination device. The vehicle motion sensor 2, the camera 3, the distance sensor 4, and the storage device 5 are communicably connected to the ECU 6 via an in-vehicle network that complies with a standard such as a controller area network. Furthermore, the vehicle control system 1 can also have a navigation device (not illustrated) for searching for a predetermined travel route to a destination. Further, the vehicle control system 1 can also have a wireless communicator (not illustrated) for wirelessly communicating with other devices. Still further, the vehicle control system 1 can also have a receiver (not illustrated) for positioning a position of the vehicle 10 based on a positioning signal from a satellite positioning system such as a GPS.

[0020] The vehicle motion sensor 2 is one example of a motion measuring unit that acquires information related to the motion of the vehicle 10 and generates a vehicle motion signal representing the information. The information related to the motion of the vehicle 10 is, for example, a wheel speed, angular velocities of three mutually orthogonal axes of the vehicle 10 respectively, or an acceleration of the vehicle 10. The vehicle motion sensor 2 includes, for example, at least one of a wheel speed sensor that measures a wheel speed of the vehicle 10, a gyro sensor that measures angular velocities of three mutually orthogonal axes of the vehicle 10 respectively, and an acceleration sensor that measures an acceleration of the vehicle 10. The vehicle motion sensor 2 generates the vehicle motion signal at a predetermined cycle and outputs the generated vehicle motion signal to the ECU 6 via the in-vehicle network.

[0021] The camera 3 is one example of a sensor that generates a sensor signal representing the environment around the vehicle 10 and has a two-dimensional detector composed of an array of photoelectric conversion elements having sensitivity to visible light, such as a CCD or a C-MOS, and an imaging optical system that images a region of the vehicle 10 to be a subject on the two-dimensional detector. Also, the camera 3 is mounted, for example, in the vehicle cabin of the vehicle 10 in a manner facing the front of the vehicle 10. Also, the camera 3 captures a region in front of the vehicle 10 at a predetermined capturing cycle (for example, 1 / 30 to 1 / 10 seconds) and generates an image representing the region. The image obtained by the camera 3 is one example of a sensor signal and can be either a color image or a gray scale image. In addition, a plurality of cameras having different capturing directions or focal distances can be provided in the vehicle 10.

[0022] The camera 3 outputs the generated image to the ECU 6 via the in-vehicle network each time the image is generated.

[0023] The distance sensor 4 is another example of a sensor that generates a sensor signal representing the environment around the vehicle 10, such as a LiDAR or a radar. The distance sensor 4 measures a distance from the vehicle 10 to an object existing around the vehicle 10 in each direction within a measurement range at a predetermined cycle and generates a distance measuring signal representing the measurement result. The distance measuring signal obtained by the distance sensor 4 is another example of a sensor signal.

[0024] The distance sensor 4 outputs the generated distance measuring signal to the ECU 6 via the in-vehicle network each time the distance measuring signal is generated.

[0025] Storage device 5 is an example of a storage unit, such as having at least one of a hard disk drive, a non-volatile semiconductor memory, or an optical recording medium and its access device. Furthermore, storage device 5 stores a high-precision map, which is an example of a second map representing the lanes of a road. The spatial information in the high-precision map includes information about features affecting vehicle traffic regarding each section of the road represented in a predetermined area of ​​the high-precision map. Features affecting vehicle traffic include, for example, road markings such as lane lines that delineate lanes, road signs, and roadside noise barriers. Thus, the high-precision map includes information such as lane lines for determining each lane, and therefore, the high-precision map can represent the lanes of a road. Additionally, the high-precision map may also include spatial information only about specific types of roads, such as dedicated car lanes.

[0026] When the storage device 5 receives a read request for a high-precision map from the ECU 6, it reads the driving road at the current position of the vehicle 10 and the spatial information of other roads within a predetermined range from the stored high-precision map. Furthermore, the storage device 5 outputs the read spatial information to the ECU 6 via the in-vehicle network.

[0027] ECU6 controls the driving of vehicle 10 to enable vehicle 10 to drive autonomously. Furthermore, in order to obtain spatial information related to the driving road used in the autonomous driving control of vehicle 10 from storage device 5, ECU6 performs driving road determination processing.

[0028] like Figure 2 As shown, ECU6 has a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 can be configured as separate circuits or as a single integrated circuit.

[0029] The communication interface 21 has an interface circuit for connecting the ECU 6 to the in-vehicle network. Furthermore, whenever the communication interface 21 receives a vehicle motion signal from the vehicle motion sensor 2, it delivers that vehicle motion signal to the processor 23. Additionally, whenever the communication interface 21 receives an image from the camera 3, it delivers the received image to the processor 23. Further, whenever the communication interface 21 receives a distance measurement signal from the distance sensor 4, it delivers the received distance measurement signal to the processor 23. Still further, the communication interface 21 delivers spatial information read from the storage device 5 to the processor 23.

[0030] The memory 22 is another example of a storage unit, such as a volatile semiconductor memory and a non-volatile semiconductor memory. Also, the memory 22 stores various data used in vehicle control processing including travel road determination processing executed by the processor 23 of the ECU 6. For example, the memory 22 stores a map representing a road (hereinafter referred to as a road map). The road map is an example of the first map, such as a map used for route search in a navigation device, including identification information (link ID) of each road section, position, shape, category (such as an exclusive lane for automobiles or a general lane), and information representing a connection relationship. In addition, the memory 22 stores vehicle motion signals received from the vehicle motion sensor 2 within a predetermined period closest to the present time, images of the surroundings of the vehicle 10 received from the camera 3, ranging signals received from the distance sensor 4, and spatial information read from the storage device 5. Further, the memory 22 stores parameters representing the focal length, angle of view, photographing direction, and mounting position of the camera 3, and the like, and a parameter set for determining an identifier used in detection of a lane demarcation line or the like. Further, the memory 22 temporarily stores various data generated in the middle of the vehicle control processing.

[0031] The processor 23 has one or a plurality of CPUs (Central Processing Units) and peripheral circuits thereof. The processor 23 can also have other arithmetic circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. Also, the processor 23 executes vehicle control processing including travel road determination processing for the vehicle 10 at a predetermined cycle.

[0032] Figure 3 is a functional block diagram of the processor 23 related to vehicle control processing including travel road determination processing. The processor 23 has a trajectory estimation section 31, a comparison section 32, a lane detection section 33, a road determination section 34, a spatial information acquisition section 35, and a control section 36. These sections of the processor 23 are functional modules realized by, for example, a computer program operating on the processor 23. Alternatively, these sections of the processor 23 can be dedicated arithmetic circuits provided separately. Further, the trajectory estimation section 31, the comparison section 32, the lane detection section 33, and the road determination section 34 of these sections of the processor 23 are related to travel road determination processing.

[0033] The trajectory estimation section 31 estimates the travel trajectory of the vehicle 10 in the closest predetermined period on the basis of the vehicle motion signals acquired from the vehicle motion sensor 2 at predetermined periods. For example, the trajectory estimation section 31 can estimate the travel trajectory of the vehicle 10 by integrating the wheel speeds and the angular velocities of the respective axes indicated by the vehicle motion signals in each predetermined period. Alternatively, in the case where the vehicle 10 has a receiver of a satellite positioning system, the trajectory estimation section 31 can estimate the travel trajectory of the vehicle 10 by arranging the positions of the vehicle 10 indicated by the positioning signals of the receiver in the closest predetermined period in chronological order. The trajectory estimation section 31 outputs the estimated travel trajectory to the collating section 32.

[0034] The collating section 32 detects a candidate of the travel road of the vehicle 10 by collating the travel trajectory of the vehicle 10 and the road map each time the travel trajectory is received from the trajectory estimation section 31. For example, the collating section 32 calculates the degree of coincidence of the road on the road map with the travel trajectory while changing the relative position and direction of the travel trajectory with respect to the road map. Then, the collating section 32 detects the road section in each road section included in the road on the map at which the degree of coincidence becomes the maximum as the candidate of the travel road of the vehicle 10.

[0035] The collating section 32 divides the travel trajectory into a plurality of sections, for example, when calculating the degree of coincidence. Then, the collating section 32 calculates the distance from each section in the travel trajectory to the closest road section in the road map. The collating section 32 calculates the reciprocal of the sum of the distances calculated for the sections in the travel trajectory as the degree of coincidence. Alternatively, the collating section 32 can calculate the reciprocal of the sum of the squares of the distances calculated for the sections in the travel trajectory as the degree of coincidence. Further alternatively, the collating section 32 can calculate the reciprocal of the value obtained by adding a predetermined constant having a positive value to the sum of the distances or the sum of the squares of the distances described above as the degree of coincidence.

[0036] Further, each section in the travel trajectory of the vehicle 10 should be continuous, and therefore, the collating section 32 can be configured to limit each road section on the road map which becomes the calculation target of the degree of coincidence to be continuous with each other. Alternatively, the collating section 32 can limit the range in which the degree of coincidence with the travel trajectory is calculated on the road map to include the current position of the vehicle 10 indicated by the positioning signal received from the receiver of the satellite positioning system mounted on the vehicle 10 or the travel road detected at the previous collation. Thus, the amount of calculation required for the detection of the travel road can be reduced.

[0037] Alternatively, in the case where the maximum value of the degree of coincidence is smaller than a predetermined threshold value, the collating section 32 can determine that the candidate of the travel road cannot be detected.

[0038] The control section 32 notifies the road determination section 34 of information indicating the candidate of the detected travel road. Further, the information indicating the candidate of the detected travel road includes the link ID of the road section corresponding to the candidate of the travel road and the category of the road of the road section.

[0039] The lane detection section 33 detects the travel lane of the vehicle 10 by collating the image and the high-precision map each time the image is accepted from the camera 3. At the time of the collation, the lane detection section 33 can use the spatial information read in at the previous travel road determination.

[0040] The lane detection section 33 detects the ground object indicating on or around the road of the image by inputting the image to the recognizer. As such a recognizer, the lane detection section 33 can use, for example, a deep neural network (DNN) having an architecture of a convolutional neural network type (CNN) such as Single Shot MultiBox Detector (SSD) or Faster R-CNN. Such a recognizer is previously learned so that the ground object to be detected is detected from the image. Also, the lane detection section 33 assumes the position and posture of the vehicle 10, and projects the ground object detected from the image onto the high-precision map or projects the ground object on or around the road of the vehicle 10 on the high-precision map onto the image with reference to the parameters of the camera 3. The lane detection section 33 estimates the position and posture of the vehicle 10 at the time when the ground object detected from the image and the ground object indicated by the spatial information of the high-precision map are most consistent as the current position and posture of the vehicle 10. Also, the lane detection section 33 detects the lane indicating in each lane of the high-precision map, which contains the estimated current position of the vehicle 10, as the travel lane. In addition, the lane detection section 33 calculates the reciprocal of the sum of the distances of the respective ground objects detected from the image and the corresponding ground objects on the high-precision map as the degree of consistency. Alternatively, the lane detection section 33 can calculate the reciprocal of the sum of the squares of the distances of the respective ground objects detected from the image and the corresponding ground objects on the high-precision map as the degree of consistency. Further alternatively, the lane detection section 33 can calculate the reciprocal of the value obtained by adding a predetermined constant having a positive value to the sum of the distances or the sum of the squares of the distances described above as the degree of consistency.

[0041] The lane detection section 33 refers to the high-precision map to determine the road section containing the detected travel lane. Also, the lane detection section 33 notifies the road determination section 34 of the link ID of the road section containing the travel lane and the degree of consistency calculated with respect to the travel section. In addition, the lane detection section 33 notifies the control section 36 of the detected travel lane and the position of the vehicle 10.

[0042] The road determination section 34 determines the travel road of the vehicle 10 based on whether the travel lane detected by the lane detection section 33 is included in the candidate of the travel road determined by the collation section 32. In the present embodiment, the road determination section 34 determines the candidate of the travel road as the travel road when the detected travel lane is included in the candidate of the travel road. On the other hand, when the detected travel lane is not included in the candidate of the travel road, the road determination section 34 determines a road section including the detected travel lane as the travel road of the vehicle 10. Further, the road determination section 34 can determine that the detected travel lane is included in the candidate of the travel road when the link ID of the road section including the detected travel lane coincides with the link ID of the candidate of the travel road. On the other hand, the road determination section 34 can determine that the detected travel lane is not included in the candidate of the travel road when the link ID of the road section including the detected travel lane is different from the link ID of the candidate of the travel road.

[0043] Figure 4 Fig. 1 is a diagram showing an outline of travel road determination according to the present embodiment. In the example shown in Fig. 1, a road 400 branches into two at a branch point 401. In the road 400, the vehicle 10 travels on a lane 421 included in a section 411, which is one of two road sections passing the branch point 401 in the traveling direction of the vehicle 10. Therefore, the lane 421 is detected as the travel lane. Further, a section 412, which is the other of the two road sections passing the branch point 401, is detected as the candidate of the travel road. In this case, the lane 421 is not included in the section 412 as the candidate of the travel road, and therefore the section 412 is not determined as the travel road. Further, the section 411 including the lane 421 is determined as the travel road. On the other hand, when the section 411 is detected as the candidate of the travel road, the section 411 includes the lane 421 detected as the travel lane, and therefore the section 411 is directly determined as the travel road. Figure 4

[0044] The road determination section 34 notifies the space information acquisition section 35 of information indicating the determined travel road, such as the link ID of the travel road.

[0045] ​The spatial information acquisition unit 35 acquires spatial information including a predetermined range of the travel road indicated by the information notified from the road determination unit 34 each time the information is notified. The predetermined range can be, for example, a range of several hundred meters to several kilometers centered on the travel road, which is sufficient for self-position estimation of the vehicle 10 and setting a trajectory (hereinafter referred to as a predetermined travel trajectory) through which the vehicle 10 is scheduled to pass in an interval from the current position to a predetermined distance ahead. The spatial information acquisition unit 35 temporarily stores the acquired spatial information in the memory 22 each time the spatial information is acquired.

[0046] The control unit 36 performs automatic driving control of the vehicle 10 with reference to the spatial information in a case where an operation of instructing application of the automatic driving control is performed by the driver via an operation switch (not shown) provided in the vehicle cabin of the vehicle 10.

[0047] In the present embodiment, the control unit 36 sets the predetermined travel trajectory so that the vehicle 10 travels along the travel lane detected by the lane detection unit 33 with reference to the spatial information in a case where the vehicle 10 is subjected to the automatic driving control. In addition, the control unit 36 acquires a target lane toward which the vehicle 10 is scheduled to travel with reference to the spatial information. Furthermore, the control unit 36 sets the predetermined travel trajectory so that a lane change from the travel lane to the target lane is performed in a case where the travel lane and the target lane are different.

[0048] The control unit 36 performs automatic driving control of the vehicle 10 so that the vehicle 10 travels along the predetermined travel trajectory when the predetermined travel trajectory is set. For example, the control unit 36 acquires a steering angle for the vehicle 10 to travel along the predetermined travel trajectory with reference to the current position of the vehicle 10 and the predetermined travel trajectory, and outputs a control signal corresponding to the steering angle to an actuator (not shown) that controls the steering wheel of the vehicle 10. In addition, the control unit 36 acquires a target acceleration of the vehicle 10 in accordance with a target speed of the vehicle 10 set via the operation switch in the vehicle cabin and a current vehicle speed of the vehicle 10 measured by a vehicle speed sensor (not shown), and sets an accelerator opening degree or a brake amount so as to become the target acceleration. Furthermore, the control unit 36 acquires a fuel injection amount in accordance with the set accelerator opening degree, and outputs a control signal corresponding to the fuel injection amount to a fuel injection device of an engine of the vehicle 10. Alternatively, the control unit 36 acquires electric power to be supplied to a motor of the vehicle 10 in accordance with the set accelerator opening degree, and outputs a control signal corresponding to the electric power to a drive device of the motor. Further, the control unit 36 outputs a control signal corresponding to the set brake amount to a brake of the vehicle 10.

[0049] Figure 5is a flowchart of actions of vehicle control processing including the travel road determination processing executed by the processor 23. The processor 23 can execute the vehicle control processing in accordance with the following flowchart at a predetermined cycle. The processes of steps S101 to S106 in the following flowchart are related to the travel road determination processing.

[0050] The trajectory estimation section 31 of the processor 23 estimates the travel trajectory of the vehicle 10 in the closest predetermined section (step S101). The collation section 32 of the processor 23 collates the travel trajectory and the road map, and detects the road section in the road most consistent with the travel trajectory and closest to the current position of the vehicle 10 as a candidate of the travel road of the vehicle 10 (step S102).

[0051] In addition, the lane detection section 33 of the processor 23 detects the travel lane of the vehicle 10 by collating the image received from the camera 3 and the high-precision map (step S103). Also, the road determination section 34 of the processor 23 determines whether the travel lane detected by the lane detection section 33 is included in the candidate of the travel road determined by the collation section 32 (step S104).

[0052] In a case where the detected travel lane is included in the candidate of the travel road (step S104 - Yes), the road determination section 34 determines the candidate of the travel road as the travel road (step S105). On the other hand, in a case where the detected travel lane is not included in the candidate of the travel road (step S104 - No), the road determination section 34 determines the road section including the detected travel lane as the travel road of the vehicle 10 (step S106).

[0053] When the travel road is determined, the space information acquisition section 35 of the processor 23 acquires the space information of a predetermined range including the travel road from the storage device 5 (step S107). Also, the control section 36 of the processor 23 performs automatic driving control of the vehicle 10 with reference to the space information (step S108). Also, the processor 23 ends the vehicle control processing.

[0054] As explained above, the travel road determination device detects a candidate of the travel road in which the vehicle is traveling by collating the travel trajectory of the vehicle in the closest predetermined section with the road map. In addition, the travel road determination device detects the travel lane of the vehicle by collating the sensor signal representing the environment around the vehicle obtained by the sensor mounted on the vehicle with the high-precision map. Furthermore, the travel road determination device determines the candidate as the travel road in a case where the detected travel lane is included in the candidate of the travel road, and determines the road including the detected travel lane as the travel road in a case where the detected travel lane is not included in the candidate of the travel road. In this way, by using the result of the detection of the travel lane by referring to the high-precision map including the lane unit in the determination of the travel road, the travel road determination device can improve the detection accuracy of the travel road.

[0055] According to the modification, the road determination section 34 can be limited to determining the road including the travel lane as the travel road only in a case where the degree of agreement with respect to the travel lane calculated by the lane detection section 33 is higher than the degree of agreement with respect to the candidate of the travel road calculated by the collating section 32. In addition, it is considered that the higher the degree of agreement calculated with respect to the candidate of the travel road, the higher the possibility that the candidate is the travel road, and thus the degree of agreement is one example of the first confidence indicating the reliability of the candidate of the road. Similarly, it is considered that the higher the degree of agreement calculated with respect to the detected travel lane, the higher the possibility that the detected travel lane is the lane in which the vehicle 10 is actually traveling, and thus the degree of agreement is one example of the second confidence indicating the reliability of the detected travel lane. Thus, the road determination section 34 can suppress the erroneous determination of the travel road due to the false detection of the travel lane in a case where the detection accuracy of the travel lane is lower than the detection accuracy of the candidate of the travel road. In addition, in a case where the degree of agreement with respect to the travel lane is lower than the degree of agreement with respect to the candidate of the travel road and the travel lane is not included in the candidate of the travel road, the road determination section 34 can determine that the travel road cannot be determined.

[0056] According to another modification, the collating section 32 can detect, as the candidate of the travel road, the road section included in the road closest to the current position of the vehicle 10 with respect to each road of the roads in the road map in which the degree of agreement with the travel trajectory is equal to or higher than a predetermined degree of agreement threshold. In addition, the road determination section 34 can determine, as the travel road, the candidate including the detected travel lane among a plurality of detected candidates of the travel road in a case where there are a plurality of detected candidates of the travel road. Thus, even in a case where it is difficult to determine the travel road in the collation of the travel trajectory with the road map, the road determination section 34 can determine the travel road.

[0057] Further, according to another modification, the road determination unit 34 can determine the road including the travel lane detected by the lane detection unit 33 as the travel road, in a case where the travel road is not detected by the collation unit 32. In this case, even in the collation of the travel trajectory with the road map, the road determination unit 34 can determine the travel road, even in a case where it is difficult to determine the travel road.

[0058] Further, according to another modification, the lane detection unit 33 can determine the reliability of the detected travel lane, based on the image obtained by the camera 3 or the ranging signal obtained by the distance sensor 4. Also, the road determination unit 34 can determine the travel road based on the travel lane, according to the above-described embodiment or modification, only in a case where it is determined that the detected travel lane is reliable. Thus, the road determination unit 34 can suppress erroneous determination of the travel road due to erroneous detection of the travel lane. Further, the lane detection unit 33 determines the reliability of the detected travel lane according to any one of the methods described below.

[0059] The lane detection unit 33 compares the number of lanes located on either side of the travel lane detected from the image obtained by the camera 3 with the number of lanes located on the same side of the travel lane on the high-precision map. Also, the lane detection unit 33 determines that the detected travel lane is reliable in a case where both are identical. In this case, the lane detection unit 33 can count the number of lanes located on the side of the travel lane by counting the number of lane division lines located on the side of the travel lane detected from the image. Further, the lane detection unit 33 counts the number of lanes located on the side of the travel lane on the high-precision map, based on the position of the detected travel lane and the number of lanes on the high-precision map at the position.

[0060] Alternatively, the lane detection unit 33 can determine the reliability of the detected travel lane based on the distance to the ground object (e.g., a soundproof wall) around the vehicle 10 indicated by the ranging signal. In this case, the lane detection unit 33 can determine that the detected travel lane is reliable, in a case where the difference between the distance to the ground object around the vehicle 10 indicated by the ranging signal and the distance from the position of the detected travel lane to the ground object on the high-precision map is within a predetermined error range.

[0061] Further, the computer program implementing the functions of the processor 23 of the ECU 6 according to the above-described embodiment or modification can be provided in the form of a removable recording medium that can be read by a computer, such as a semiconductor memory, a magnetic recording medium, or an optical recording medium.

[0062] As described above, those skilled in the art can make various modifications within the scope of the present application to match the implemented form.

Claims

1. A driving route determining device, comprising: The comparison unit compares the vehicle's travel trajectory in the predetermined interval closest to the road with a first map representing the road, detects the interval closest to the vehicle's current position contained in the road represented in the first map that is most consistent with the travel trajectory as a candidate for the road the vehicle is traveling on, and calculates a first confidence level, which represents the reliability of the candidate road. The lane detection unit detects the lane in which the vehicle is traveling by comparing sensor signals representing the environment around the vehicle obtained by sensors mounted on the vehicle with a second map representing each lane of each road, and calculates a second confidence level, which represents the reliability of the detected lane. as well as The road determination unit determines the candidate road as the road on which the vehicle is traveling when the detected lane is included in the candidate road, and determines the road including the detected lane as the road on which the vehicle is traveling when the detected lane is not included in the candidate road and the second confidence level is higher than the first confidence level.

2. The driving route determination device according to claim 1, If no candidate road is found, the road determination unit determines the road containing the detected lane as the road on which the vehicle is traveling.

3. A method for determining a driving route, comprising: By comparing the vehicle's travel trajectory within the nearest predetermined interval with a first map representing the roads, the interval closest to the vehicle's current position within the road represented on the first map that best matches the travel trajectory is detected as a candidate road for the vehicle's travel. A first confidence level is then calculated, representing the reliability of the road candidate. By comparing sensor signals representing the environment surrounding the vehicle obtained from sensors mounted on the vehicle with a second map representing each lane of each road, the lane in which the vehicle is traveling is detected, and a second confidence level is calculated, which represents the reliability of the detected lane. If the detected lane is included in the candidate road, the candidate road is determined as the road on which the vehicle is traveling. If the detected lane is not included in the road candidate and the second confidence level is higher than the first confidence level, the road containing the detected lane is determined as the road on which the vehicle is traveling.

4. A computer program product comprising a computer program for determining a driving route, the program being executed by a processor mounted in a vehicle: By comparing the vehicle's travel trajectory within the nearest predetermined interval with a first map representing the roads, the interval closest to the vehicle's current position within the roads represented on the first map that best match the travel trajectory is detected as a candidate road for the vehicle's travel. A first confidence level is then calculated, representing the reliability of the road candidate. By comparing sensor signals representing the environment surrounding the vehicle obtained from sensors mounted on the vehicle with a second map representing each lane of each road, the lane in which the vehicle is traveling is detected, and a second confidence level is calculated, which represents the reliability of the detected lane. If the detected lane is included in the candidate road, the candidate road is determined as the road on which the vehicle is traveling. If the detected lane is not included in the road candidate and the second confidence level is higher than the first confidence level, the road containing the detected lane is determined as the road on which the vehicle is traveling.

Images