Road recognition device

Abstract

To accurately determine whether the road on which a vehicle is being driven is a two-way street or not.SOLUTION: A road recognition device 50 includes a camera 1a that detects a compartment line of a road on which a vehicle is being driven; a compartment line discrimination unit 141 that discriminates a type of a compartment line according to the color and shape of the compartment line detected by the camera 1a; and a road compartment unit 142 that determines whether or not the road on which the vehicle is being driven is a two-way road for two-way traffic based on information on the compartment line including information on the type of the compartment line determined by the compartment line determination unit 141.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a road recognition device that recognizes the type of road on which a vehicle is traveling. [Background technology]

[0002] As this type of device, a device that determines whether the road on which the vehicle is traveling is a road with oncoming traffic or not is known (see, for example, Patent Document 1). The device described in Patent Document 1 determines whether the road on which the vehicle is traveling is a road with oncoming traffic or not based on current vehicle position information and map information including road type information acquired from a navigation device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2013-190962 Summary of the Invention [Problem to be solved by the invention]

[0004] However, if the determination is made based on information from a navigation device, as in the device described in Patent Document 1, it is not possible to accurately determine whether or not a vehicle is passing in a two-way direction. [Means for solving the problem]

[0005] A road recognition device according to one aspect of the present invention comprises a detection unit that detects dividing lines on a road on which the vehicle is traveling, a dividing line discrimination unit that discriminates the type of dividing line based on the color and shape of the dividing line detected by the detection unit, and a road discrimination unit that determines whether the road on which the vehicle is traveling is a two-way traffic road on which two-way traffic occurs, based on dividing line information including information on the type of dividing line discriminated by the dividing line discrimination unit. The road determination unit determines whether or not predetermined road conditions are met based on the dividing line information, and if it determines that the predetermined road conditions are met, it determines that the road on which the vehicle is traveling is an oncoming traffic road. However, if it determines that the predetermined road conditions are not met for a first predetermined time or more after determining that the road is an oncoming traffic road, it determines that the road on which the vehicle is traveling is not an oncoming traffic road. Furthermore, if the road determination unit determines that the predetermined road conditions are met for a second predetermined time or more that is shorter than the first predetermined time after determining that the road on which the vehicle is traveling is not an oncoming traffic road, it determines that the road on which the vehicle is traveling is an oncoming traffic road. [Effects of the Invention]

[0006] According to the present invention, it is possible to accurately determine whether the road on which the vehicle is traveling is a road with oncoming traffic. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a block diagram showing an outline of the overall configuration of a vehicle control system for an autonomous driving vehicle having a road recognition device according to an embodiment of the present invention; [Figure 2] 1 is a diagram showing an example of a driving scene assumed by a road recognition device according to an embodiment of the present invention; [Figure 3A] 3 is a diagram showing an example of a lane marking between a vehicle's own lane and an adjacent lane, different from that shown in FIG. 2; [Figure 3B] 3 is a diagram showing another example of a dividing line between the current lane and an adjacent lane, different from that shown in FIG. 2; [Figure 4] 1 is a block diagram showing the configuration of a main part of a road recognition device according to an embodiment of the present invention; [Figure 5] 1 is a diagram showing an example of a road viewed from a camera provided in a road recognition device according to an embodiment of the present invention; [Figure 6] 5 is a flowchart showing an example of processing executed by the controller of FIG. 4; [Figure 7] 5A and 5B are diagrams showing an example of the transition of a determination result by the road recognition device according to the embodiment of the present invention. [Figure 8A] FIG. 1 is a diagram showing an example of a road where vehicles keep to the right. [Figure 8B] FIG. 10 is a diagram showing another example of a road where traffic keeps to the right. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, an embodiment of the present invention will be described with reference to Figs. 1 to 8B. A road recognition device according to an embodiment of the present invention is a device that recognizes road types, and can be applied to both vehicles with an automatic driving function, i.e., automatic driving vehicles, and vehicles without an automatic driving function, i.e., manually driven vehicles. Below, an example in which the road recognition device is applied to an automatic driving vehicle will be described. Note that a vehicle to which the road recognition device according to this embodiment is applied may be referred to as the subject vehicle to distinguish it from other vehicles.

[0009] The host vehicle may be an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a traction motor as a driving source, or a hybrid vehicle having an engine and a traction motor as driving sources.

[0010] The vehicle (autonomous vehicle) can travel not only in an autonomous driving mode in which no driver operation is required, but also in a manual driving mode in which the driver operates the vehicle. For example, the vehicle can switch from a state in which the vehicle is traveling in autonomous driving mode with the steering wheel not operated (hands off) to a state in which the vehicle operates the steering wheel (hands on) and travel in manual driving mode. Alternatively, the vehicle can be driven in a hands-off state at a predetermined autonomous driving level, and then driven in a hands-on state by lowering the autonomous driving level by one or more steps in response to a command from the vehicle control system.

[0011] First, a schematic configuration related to autonomous driving will be described. Fig. 1 is a block diagram showing a schematic overall configuration of a vehicle control system 100 having a road recognition device according to an embodiment of the present invention. As shown in Fig. 1, the vehicle control system 100 mainly includes a controller 10, a group of external sensors 1 and a group of internal sensors 2, each of which is communicatively connected to the controller 10 via a CAN communication line or the like, an input / output device 3, a positioning unit 4, a map database 5, a navigation device 6, a communication unit 7, and an actuator AC for driving.

[0012] The external sensor group 1 is a collective term for a plurality of sensors (external sensors) that detect the external situation, which is information about the surroundings of the vehicle. For example, the external sensor group 1 includes a lidar that detects the position (distance and direction from the vehicle) of objects around the vehicle by emitting laser light and detecting reflected light, a radar that detects the position of objects around the vehicle by emitting electromagnetic waves and detecting reflected waves, and a camera that has an imaging element such as a CCD or CMOS and captures images of the surroundings of the vehicle. Lidar and radar can detect objects within the imaging area of ​​the camera.

[0013] The internal sensor group 2 is a collective term for a plurality of sensors (internal sensors) that detect the driving state of the host vehicle. For example, the internal sensor group 2 includes a vehicle speed sensor that detects the vehicle speed of the host vehicle, an acceleration sensor that detects the acceleration in the forward / backward and left / right directions of the host vehicle, a rotation speed sensor that detects the rotation speed of the driving source, etc. The internal sensor group 2 also includes sensors that detect the driving operations of the driver in manual driving mode, such as operation of the accelerator pedal, operation of the brake pedal, operation of the steering wheel, etc.

[0014] The input / output device 3 is a general term for devices that input commands from the driver and output information to the driver. For example, the input / output device 3 includes various switches through which the driver inputs various commands by operating operating members, a microphone through which the driver inputs commands by voice, a display that provides information to the driver via displayed images, and a speaker that provides information to the driver by voice.

[0015] The positioning unit (GNSS unit) 4 has a positioning sensor that receives positioning signals transmitted from positioning satellites. The positioning sensor can also be included in the internal sensor group 2. The positioning satellite is an artificial satellite such as a GPS satellite or a quasi-zenith satellite. The positioning unit 4 measures the current position (latitude, longitude, altitude) of the vehicle using the positioning information received by the positioning sensor.

[0016] The map database 5 is a device that stores general map information used in the navigation device 6, and is configured with, for example, a hard disk or semiconductor elements. The map information includes road position information, road shape information (curvature, etc.), and position information of intersections and branch points. Note that the map information stored in the map database 5 is different from the highly accurate map information stored in the memory unit 12 of the controller 10.

[0017] The navigation device 6 is a device that searches for a target route on roads to a destination input by the driver and provides guidance along the target route. The input of the destination and guidance along the target route are performed via the input / output device 3. The target route is calculated based on the current position of the vehicle measured by the positioning unit 4 and map information stored in the map database 5. The current position of the vehicle can also be measured using detection values ​​from the external sensor group 1, and the target route can be calculated based on this current position and high-precision map information stored in the memory unit 12.

[0018] The communication unit 7 communicates with various servers (not shown) via networks including wireless communication networks such as the Internet and mobile phone networks, and acquires map information, driving history information, traffic information, and the like from the servers periodically or at any timing. Networks include not only public wireless communication networks but also closed communication networks established for each predetermined management area, such as wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like. The acquired map information is output to the map database 5 and the storage unit 12, where the map information is updated.

[0019] Actuators AC are driving actuators for controlling the driving of the host vehicle. When the driving source is an engine, actuators AC include a throttle actuator that adjusts the opening of the engine's throttle valve (throttle opening). When the driving source is a driving motor, actuators AC include the driving motor. Actuators AC also include a brake actuator that operates the host vehicle's braking device and a steering actuator that drives the steering device.

[0020] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having an arithmetic unit 11 such as a CPU (microprocessor), a storage unit 12 such as a ROM and RAM, and other peripheral circuits (not shown) such as an I / O interface. Note that although multiple ECUs with different functions, such as an engine control ECU, a traction motor control ECU, and a braking device ECU, can be provided separately, for convenience, the controller 10 is shown in FIG. 1 as a collection of these ECUs.

[0021] High-precision road map information is stored in the memory unit 12. This road map information includes road position information, road shape information (curvature, etc.), road gradient information, intersection and branch point position information, number of lanes information, lane width and position information for each lane (information on lane center positions and lane boundary lines), position information of landmarks (traffic lights, signs, buildings, etc.) as markers on the map, and road surface profile information such as road surface irregularities. The map information stored in the memory unit 12 includes map information acquired from outside the vehicle via the communication unit 7 and map information created by the vehicle itself using detection values ​​from the external sensor group 1 or detection values ​​from the external sensor group 1 and the internal sensor group 2.

[0022] The calculation unit 11 has, as functional components, a vehicle position recognition unit 13, an external environment recognition unit 14, a behavior plan generation unit 15, and a driving control unit 16.

[0023] The vehicle position recognition unit 13 recognizes the position of the vehicle on the map (own vehicle position) based on the vehicle position information obtained by the positioning unit 4 and the map information in the map database 5. The vehicle position may be recognized using the map information stored in the storage unit 12 and information about the surroundings of the vehicle detected by the external sensor group 1, thereby enabling the vehicle position to be recognized with high accuracy. Note that when the vehicle position can be measured by an external sensor installed on or beside the road, the vehicle position can also be recognized by communicating with the sensor via the communication unit 7.

[0024] The external environment recognition unit 14 recognizes the external situation around the vehicle based on signals from the external sensor group 1, such as a lidar, radar, and camera. For example, it recognizes the positions, speeds, and accelerations of surrounding vehicles (vehicles ahead and vehicles behind) traveling around the vehicle, the positions of surrounding vehicles stopped or parked around the vehicle, and the positions and states of other objects. Examples of other objects include signs, traffic lights, markings such as road dividing lines and stop lines, buildings, guardrails, utility poles, signs, pedestrians, bicycles, etc. Examples of the states of other objects include the color of traffic lights (red, green, yellow), the moving speed and direction of pedestrians and bicycles, etc.

[0025] The behavior plan generation unit 15 generates a driving trajectory (target trajectory) of the host vehicle from the current time to a predetermined time ahead based on, for example, a target route calculated by the navigation device 6, map information stored in the memory unit 12, the host vehicle position recognized by the host vehicle position recognition unit 13, and external conditions recognized by the external environment recognition unit 14. When there are multiple trajectories that are candidates for the target trajectory on the target route, the behavior plan generation unit 15 selects an optimal trajectory from among them that satisfies criteria such as compliance with laws and regulations and efficient and safe driving, and sets the selected trajectory as the target trajectory. The behavior plan generation unit 15 then generates a behavior plan according to the generated target trajectory. The behavior plan generation unit 15 generates various behavior plans corresponding to overtaking driving to overtake a preceding vehicle, lane-changing driving to change lanes, following driving to follow a preceding vehicle, lane-keeping driving to maintain the vehicle in its lane without deviating from the lane, decelerating driving, accelerating driving, etc. When generating the target trajectory, the behavior plan generation unit 15 first determines a driving mode and generates the target trajectory based on the driving mode.

[0026] In the autonomous driving mode, the driving control unit 16 controls the actuators AC so that the host vehicle travels along the target trajectory generated by the behavior plan generation unit 15. More specifically, the driving control unit 16 calculates a required driving force for achieving the target acceleration per unit time calculated by the behavior plan generation unit 15, taking into account the driving resistance determined by the road gradient and the like in the autonomous driving mode. Then, for example, the driving control unit 16 feedback-controls the actuators AC so that the actual acceleration detected by the internal sensor group 2 becomes the target acceleration. In other words, the driving control unit 16 controls the actuators AC so that the host vehicle travels at the target vehicle speed and target acceleration.

[0027] In the manual driving mode, the driving control unit 16 controls the actuators AC in response to driving commands (such as steering operations) from the driver acquired by the internal sensor group 2. Even in the manual driving mode, the vehicle is not driven completely manually, and there are cases where the vehicle can be driven autonomously under predetermined driving conditions without the driver's driving operation, with the driver being required to monitor the road ahead. For example, if the vehicle is in the same lane on a highway or the like, the driving control unit 16 controls the actuators AC in response to the distance between the vehicle and the preceding vehicle, allowing the vehicle to drive hands-off, i.e., in same-lane autonomous driving. In addition, same-lane autonomous driving can also be performed in autonomous driving mode when the autonomous driving level is lowered to a predetermined level.

[0028] Based on the above configuration, a characteristic configuration of a road recognition device according to an embodiment of the present invention will be described. The road recognition device according to this embodiment recognizes the type of road, such as whether the road on which the vehicle is traveling is a two-way traffic road. Expressways and general roads may have two-way traffic sections without a central divider. In such cases, if the vehicle is traveling in a hands-off state while maintaining a predetermined driving state (e.g., single-lane automated driving), it is difficult to quickly take action to avoid an oncoming vehicle approaching the vehicle and requiring the vehicle to avoid the oncoming vehicle. Therefore, recognizing whether the road on which the vehicle is traveling is a two-way traffic road is particularly important for vehicles capable of traveling in a hands-off state.

[0029] FIG. 2 is a diagram showing an example of a driving scene assumed by the road recognition device according to this embodiment, depicting a two-way road with one lane in each direction. In FIG. 2, a vehicle 101 is traveling in a vehicle lane (first lane) LN1 in the direction of arrow A1, and another vehicle 102 is traveling in an adjacent lane (second lane) LN2 adjacent to the vehicle lane LN1 in the direction of arrow A2, which is opposite to the direction of arrow A1. The vehicle lane LN1 is defined by a pair of left and right dividing lines L1 and L2, and the adjacent lane LN2 is defined by a pair of left and right dividing lines L3 and L4. The dividing lines L1 and L4 at the edges of the road are solid white (W) lines. The dividing lines L2 and L3 at the center of the road are solid yellow (Y) lines indicating that overtaking is prohibited. The dividing line L5 in the center of the road, inside the dividing lines L2 and L3, is a dashed white (W) line. Note that the yellow dividing lines may be orange.

[0030] The dividing line between the current lane LN1 and the adjacent lane LN2, i.e., the boundary between the current lane LN1 and the adjacent lane LN2, is not limited to the example shown in FIG. 2, and there are various other types. FIGS. 3A and 3B are diagrams showing examples. In FIG. 3A, the boundary line between the current lane LN1 and the adjacent lane LN2 is indicated by a single dividing line L2 (center line). The dividing line L2 is marked by a white (W) dashed line. In FIG. 3B, the boundary line between the current lane LN1 and the adjacent lane LN2 is indicated by a pair of dividing lines L2 and L3 on the left and right. The dividing line L2 on the current lane side is marked by a white (W) dashed line, and the dividing line L3 on the adjacent lane side is marked by a yellow (Y) solid line.

[0031] In this embodiment, a road that satisfies certain lane marking conditions is treated as a road for oncoming traffic. The lane marking conditions include, as shown in FIG. 2, that the lane marking L2 on the center line side (the adjacent lane side) of the lane markings L1 and L2 that define the current lane LN1 is yellow. Therefore, the road shown in FIGS. 3A and 3B does not satisfy the lane marking conditions and is therefore not treated as a road for oncoming traffic. Although not shown, on oncoming traffic roads, there are various lane marking patterns in addition to those shown in FIG. 2, such as a single solid yellow line marking the boundary between the current lane and the adjacent lane, or a single solid yellow line and a single solid or broken white line marking side by side.

[0032] 4 is a block diagram showing the configuration of the main parts of a road recognition device 50 according to an embodiment of the present invention. As shown in FIG. 4, the road recognition device 50 mainly includes a camera 1a, a controller 10, an actuator AC, and a notification unit 3a.

[0033] Camera 1a is a monocular camera having an imaging element (image sensor) such as a CCD or CMOS, capable of color recognition of an object, and constitutes part of the external sensor group 1 in FIG. 1. Camera 1a may be a stereo camera. Camera 1a is attached, for example, to a predetermined position in front of the host vehicle 101, and continuously captures images of the object (camera images) by capturing images of the object in front of the host vehicle 101. The object includes another vehicle 102 and lane markings on the road (for example, lane markings L1 to L5 in FIG. 2). Note that instead of or in addition to camera 1a, a lidar or the like may be used to detect the object.

[0034] The notification unit 3a prompts the driver to perform a predetermined driving operation, and constitutes part of the input / output device 3 in Fig. 1. Specifically, when the vehicle 101 is in autonomous driving in the same lane, the notification unit 3a notifies the driver who has their hands off to put their hands on, and is constituted by a monitor in front of the driver's seat, a speaker provided in the vehicle cabin, etc.

[0035] The controller 10 in FIG. 4 has, as functional components performed by the calculation unit 11 (FIG. 1), a lane marking discrimination unit 141 and a road determination unit 142 in addition to the driving control unit 16. The lane marking discrimination unit 141 and the road determination unit 142 are used to determine the type of lane marking and the type of road, respectively, and are included in the external environment recognition unit 14 in FIG. 1.

[0036] The lane marking discrimination unit 141 recognizes multiple lane markings on the road based on the camera image acquired by the camera 1a and discriminates the type of each lane marking. That is, it discriminates whether the lane marking is white or yellow, whether the lane marking is solid or dashed, etc. The information on the type of lane marking thus discriminated becomes lane marking information.

[0037] The road determination unit 142 determines whether the road on which the vehicle is traveling is a road with oncoming traffic based on the lane marking information, including information on the type of lane marking determined by the lane marking determination unit 141, and information on other vehicles detected by the camera 1a. Specifically, the road determination unit 142 determines whether the road on which the vehicle is traveling satisfies predetermined lane marking conditions, and if the lane marking conditions are satisfied, determines that the road is a road with oncoming traffic. In the following description, a road with one lane in each direction and a road with oncoming traffic are assumed, and determines whether the road is a road with oncoming traffic.

[0038] As shown in Figure 2, the lane marking conditions include that the lane marking L2 on the side of the center line (right side) that defines the current lane LN1 is a yellow lane marking L2 (called the R lane marking). Furthermore, the lane marking conditions include that the lane marking L1 on the opposite side of the center line (left side) that defines the current lane LN1 is a solid white lane marking L1 (called the L lane marking). If the R lane marking L2 is not recognized, it is impossible to determine whether the lane is an oncoming road.

[0039] When recognizing the type of lane marking based on a camera image, if the L lane marking L1 is faded, the L lane marking L1 may not be recognized as a solid white line. Taking this into consideration, the lane marking conditions also include the absence of sufficient area outside (to the left of) the L lane marking L1. Figure 5 shows an example of a road viewed from camera 1a when the L lane marking L1 is faded and not recognized as a solid white line. As shown in Figure 5, a side wall 103 is erected outside the L lane marking L1 along the direction in which the road extends to divide the road. The boundary line L10 at the edge of the road, which is the base end of the side wall 103, extends approximately parallel to the R lane marking L2.

[0040] At this time, the road determination unit 142 sequentially calculates the distance D from the R lane marking L2 to the boundary line L10, i.e., the distance D from the characteristic point Pa on the R lane marking L2 recognized in the camera image to the characteristic point Pb on the boundary line L10, along the direction of travel. Then, by determining whether the distance D is less than a predetermined value D1, it determines that there is not enough space to the left of the L lane marking L1, i.e., that there is one lane in each direction. The predetermined value D1 is set to the width of two lanes (e.g., 2 × 3.5 m). This allows the road determination unit 142 to accurately determine whether the L lane marking L1 is a road with oncoming traffic, even if it is not recognized as a solid white line.

[0041] Even if the distance D is equal to or greater than the predetermined value D1 (D≧D1), it does not necessarily mean that there is another lane to the left of the L lane line L1. Therefore, the lane line condition also includes the absence of another lane line (called an LL lane line) outside (to the left of) the L lane line L1. When D≧D1 and an LL lane line exists, the road determination unit 142 determines that the lane is not a two-way traffic road (a road with no two-way traffic).

[0042] To improve the accuracy of on-coming traffic determination, in this embodiment, the lane marking conditions also include the recognition of a predetermined situation based on a camera image to the right of the R lane marking L2. Specifically, as shown in Figure 2, the lane marking conditions include the recognition of a white lane marking (referred to as the RR lane marking) L5 to the outside (right side) of the R lane marking L2 based on a camera image.

[0043] If the RR lane marking L5 is recognized, the road determination unit 142 further determines, based on the camera image, whether or not there is an oncoming vehicle (another vehicle 102) traveling in the adjacent lane LN2 and approaching the host vehicle 101 from the front. The road determination unit 142 then sets the determination result level of the oncoming traffic road (the reliability of the determination result) to different values ​​depending on whether or not an oncoming vehicle is recognized. That is, when an oncoming vehicle is present, the probability that the road is a oncoming traffic road is high, so the determination result level is set high (oncoming traffic (high)), and when there is no oncoming vehicle, the determination result level is set lower than when there is no oncoming vehicle (oncoming traffic (low)).

[0044] There are cases where the RR lane marking L5 is not detected in the camera image on the oncoming traffic road, for example, because the RR lane marking L5 does not exist. In this case, the road determination unit 142 determines whether or not the road is a oncoming traffic road based on the presence or absence of an oncoming vehicle. Specifically, when an oncoming vehicle is recognized, the probability that the road is a oncoming traffic road is high, and therefore the road determination unit 142 determines that the road is a oncoming traffic road (oncoming traffic (yes)).

[0045] On the other hand, when an oncoming vehicle is not recognized, the road determination unit 142 determines that the road is a non-oncoming traffic road (not a two-way traffic road). However, even when an oncoming vehicle is not recognized, there is still a possibility that the road is a two-way traffic road. Therefore, when an oncoming vehicle is not recognized, the road determination unit 142 lowers the determination result level of the non-oncoming traffic road (non-oncoming traffic (low)). Note that, as described above, when D≧D1 and an LL division line exists, the road determination unit 142 raises the determination result level of the non-oncoming traffic road (non-oncoming traffic (high)).

[0046] When the road determination unit 142 determines that the road is an oncoming traffic road (oncoming traffic (high) or oncoming traffic (low)) during same-lane automated driving, the driving control unit 16 controls the notification unit 3a to output a sound or a display urging the driver to grip the steering wheel. Furthermore, the driving control unit 16 controls the actuator AC to cancel same-lane automated driving on oncoming traffic roads. In this case, the notification mode (content of the notification) and the actuator control mode (for example, timing of canceling same-lane automated driving) may be different for oncoming traffic (high) and oncoming traffic (low). Note that even if the road determination unit 142 cannot determine that the R lane marking L2 is yellow because the R lane marking L2 is faded, for example, the driving control unit 16 also urges the driver to keep their hands on the road and outputs a control signal to the actuator AC to cancel same-lane automated driving.

[0047] On the other hand, if the road determination unit 142 determines that the road is a non-oncoming traffic road (non-oncoming traffic (high) or non-oncoming traffic (low)) while driving in the same lane automatic driving mode, the driving control unit 16 controls the actuator AC to continue the same lane automatic driving. Also, after determining that the road is a non-oncoming traffic road and issuing a hands-on command, if the road determination unit 142 determines that the road is a non-oncoming traffic road, the driving control unit 16 outputs a control signal to the notification unit 3a to notify the driver that hands-off is possible.

[0048] Fig. 6 is a flowchart showing an example of processing executed by the controller of Fig. 4. Fig. 6 is processing mainly related to determining oncoming traffic roads, and is started, for example, while the vehicle is traveling in the same lane under automated driving and is repeated at a predetermined interval.

[0049] As shown in Figure 6, first, in step S1, an image signal from camera 1a is read. Next, in step S2, the type of lane marking (R lane marking, L lane marking, RR lane marking, LL lane marking, etc.) contained in the camera image is identified. That is, the type of lane marking is identified by determining whether the lane marking is white or yellow, and whether the lane marking is solid or dashed. Next, in step S3, it is determined whether the R lane marking L2 on the right side of the current lane LN1 is yellow. If the result in step S3 is negative, the process proceeds to step S4; if the result in step S3 is positive, the process proceeds to step S5. In step S4, it is determined that oncoming traffic cannot be determined, and the process ends.

[0050] In step S5, it is determined whether the L lane marking L1 on the left side of the current lane LN1 is a solid white line. If the result of step S5 is affirmative, the process proceeds to step S6, where it is determined whether the RR lane marking L5 on the right side of the R lane marking L2 is white. If the result of step S6 is affirmative, the process proceeds to step S7, where it is determined whether an oncoming vehicle is present. If the result of step S7 is affirmative, the process proceeds to step S8, and if the result of step S7 is negative, the process proceeds to step S9. In step S8, it is determined that the road is a two-way traffic road (two-way traffic (high)) based on the high determination result level, and the process ends. In step S9, it is determined that the road is a two-way traffic road (two-way traffic (low)) based on the low determination result level, and the process ends.

[0051] If it is determined in step S6 that the RR lane marking L5 is not white, the result in step S6 is negative and the process proceeds to step S10. In step S10, as in step S7, it is determined whether or not an oncoming vehicle is present. If the result in step S10 is positive, the process proceeds to step S8, and if the result in step S10 is negative, the process proceeds to step S11. In step S11, it is determined that the road is a non-oncoming traffic road (non-oncoming traffic (low)) based on the low determination result level, and the process ends.

[0052] If it is determined in step S5 that the L lane marking L1 is not a solid white line, the result is negative and the process proceeds to step S12. In step S12, it is determined whether there is sufficient space in the adjacent lane to the left of the current lane LN1. That is, as shown in FIG. 5, the distance D from the R lane marking L2 to the road boundary line L10 is calculated based on the camera image, and it is determined whether the distance D is equal to or greater than a predetermined value D1. If the result in step S12 is positive, the process proceeds to step S13; if the result is negative, the process proceeds to step S6. In step S13, it is determined whether there is another lane marking (LL lane marking) to the left of the L lane marking L1. If the result in step S13 is positive, the process proceeds to step S14; if the result is negative, the process proceeds to step S6. In step S14, it is determined that the road is a non-oncoming traffic road (non-oncoming traffic (high)) at a high determination result level, and the process ends.

[0053] The operation of the road recognition device 50 according to this embodiment will be described in more detail. As shown in FIG. 2, if the R lane marking L2 on the right side of the host vehicle lane LN1 is yellow (e.g., a solid yellow line), the L lane marking L1 on the left side is a solid white line, the RR lane marking L5 on the right side of the R lane marking L2 is white (e.g., a dashed white line), and an oncoming vehicle (another vehicle 102) is recognized in the adjacent lane LN2, all of the lane marking conditions are satisfied, and the road is determined to be a two-way traffic road (two-way traffic (high)) (step S8). In this way, not only the types of the lane marks L1 and L2 that define the host vehicle lane LN1 but also the type of the RR lane marking L5 and the presence or absence of an oncoming vehicle are taken into consideration, so that it is possible to more accurately determine whether the road is a two-way traffic road. If the host vehicle 101 is traveling in the same lane autonomous driving mode and it is determined to be a two-way traffic road, a hands-on command is issued to the driver via the notification unit 3a, and the same lane autonomous driving is stopped. This allows the driver to issue a hands-on command at the appropriate time and cancel autonomous driving in the same lane, improving the driving safety of autonomous vehicles.

[0054] Even if a road is a two-way traffic road, it may not meet the lane marking conditions of the RR lane marking L5 being white and the presence of an oncoming vehicle (other vehicle) 102. In this case, if the lane marking conditions of the R lane marking L2 being yellow and the L lane marking L1 being a solid white line are met, the road is determined to be a two-way traffic road (two-way traffic (low)) (step S11). As a result, if some of the required lane marking conditions are met, the road is determined to be a two-way traffic road even if all of the lane marking conditions are not met, making it possible to determine two-way traffic roads that correspond to various road structures. In this case, the determination result level is lower than when all of the lane marking conditions are met, allowing for appropriate determination of two-way traffic roads.

[0055] The white solid L lane line L1 may not be recognized based on the camera image due to blurring of the L lane line L1, etc. In this case, if the distance D from the R lane line L2 to the boundary line L10 at the left edge of the road (Figure 5) is less than a predetermined value D1 (step S12 → step S6), it is determined that there is no adjacent lane to the left of the current lane LN1, and that the road is a road for oncoming traffic (steps S8, S11). Also, even if the distance D is equal to or greater than the predetermined value D1, if an LL lane line is not recognized to the left of the L lane line L1 (step S13 → step S6), it is determined that there is no adjacent lane to the left of the current lane LN1, and that the road is a road for oncoming traffic (steps S8, S11). This allows accurate determination of whether the road is a road for oncoming traffic, even if the L lane line L1 is not recognized.

[0056] In the above description, if it is determined that the lane marking condition is met, the road is determined to be a road for oncoming traffic. However, backlighting or the like can cause the camera 1a to erroneously detect a lane marking (e.g., the R lane marking L2), which can result in an erroneous determination of oncoming traffic. Therefore, if the lane marking condition is met for a predetermined period of time or longer when the road has been determined to be a road for oncoming traffic, the road determination unit 142 may determine that the road is a road for oncoming traffic. Also, if the lane marking condition is not met for a predetermined period of time or longer when the road has been determined to be a road for oncoming traffic, the road determination unit 142 may determine that the road is not a road for oncoming traffic. In other words, the continuation of a predetermined condition for a predetermined period of time may be added to the conditions for determining a road for oncoming traffic.

[0057] Fig. 7 is a diagram showing an example of changes over time in the determination result of an oncoming traffic road by the road recognition device 50 configured with this point in mind. Fig. 7 shows an example (Example 1) of changes in the determination result after the road determination unit 142 determines that the road is an oncoming traffic road, and a comparative example (Comparative Example 1), as well as an example (Example 2) of changes in the determination result after the road is determined to be a non-oncoming traffic road, and a comparative example (Comparative Example 2). In the figure, cases where the road is determined to be an oncoming traffic road are indicated by hatching.

[0058] As shown in FIG. 7, in Example 1, even if the lane line condition is met at time t1, the road determination unit 142 does not immediately determine that the road is a road for oncoming traffic, but at time t2, when a predetermined time Δt1 (e.g., 2 seconds) has elapsed since the lane line condition was met, the road is determined to be a road for oncoming traffic. Thereafter, when the lane line condition is not met at time t3, in Comparative Example 1, the road is immediately determined to be a road for non-oncoming traffic. In contrast, in Example 1, even if the lane line condition is not met, the road is not immediately determined to be a road for non-oncoming traffic, but when the state in which the lane line condition is not met continues until time t4, which is a predetermined time Δt2 (e.g., 20 seconds), the road is determined to be a road for non-oncoming traffic by the road determination unit 142. Therefore, in FIG. 7 As shown in the first embodiment, if the duration is less than the predetermined time Δt2, the road remains determined to be a road for oncoming traffic.

[0059] This prevents the vehicle 101 from erroneously detecting a yellow lane marking as a white lane marking and erroneously determining that the road is a non-oncoming road, for example, when the vehicle 101 is traveling in a backlit situation. In other words, since the possibility of erroneous detection due to backlight continuing for a predetermined time Δt2 or more is low, by setting the non-establishment of the lane marking condition for a predetermined time Δt2 or more as the determination condition, the road determination unit 142 can accurately determine the change from a oncoming road to a non-oncoming road.

[0060] In Comparative Example 2, when the lane marking condition is determined to be met at time t5 while traveling on a road determined to be non-oncoming traffic, it is immediately determined to be a road for oncoming traffic. In contrast, in Example 2, even if the road determination unit 142 determines that the lane marking condition is met, it is not immediately determined to be a road for oncoming traffic, and if the state in which the lane marking condition is met continues until time t6 after a predetermined time Δt1, it is determined to be a road for oncoming traffic. Therefore, 7 As shown in the second embodiment, if the duration is less than the predetermined time Δt1, the road remains determined to be a non-oncoming traffic road.

[0061] This prevents the road determination unit 142 from erroneously determining that the road is a two-way traffic road when the lane marking condition is temporarily met due to erroneous detection by the camera 1a, and enables accurate determination of a change from a non-oncoming traffic road to a two-way traffic road. Here, the predetermined time Δt2 is set longer than the predetermined time Δt1, so a determination that the road is a non-oncoming traffic road is less likely than a determination that the road is a two-way traffic road. This prevents automated driving that assumes a non-oncoming traffic road, such as same-lane automated driving, from being performed on a two-way traffic road, thereby improving safety.

[0062] According to this embodiment, the following effects can be achieved. (1) The road recognition device 50 includes a camera 1a that detects the lane markings on the road on which the vehicle 101 is traveling, a lane marking discrimination unit 141 that discriminates the type of lane markings based on the color and shape of the lane markings detected by the camera 1a, and a road determination unit 142 that determines whether the road on which the vehicle is traveling is a road with oncoming traffic, based on lane marking information including information on the type of lane markings discriminated by the lane marking discrimination unit 141 (FIG. 4). On a road with oncoming traffic, the color and shape of the lane markings around the vehicle's lane LN1 are predetermined. Therefore, determining whether the road is a road with oncoming traffic based on the color and shape of the lane markings detected by the camera 1a enables accurate determination.

[0063] (2) The camera 1a is further configured to be able to detect another vehicle 102, which is an oncoming vehicle traveling in the oncoming lane (adjacent lane) LN2. The road determination unit 142 further determines whether the road on which the vehicle is traveling is a two-way traffic road based on whether the oncoming vehicle 102 is detected by the camera 1a (FIG. 6). In this way, by taking into consideration whether the oncoming vehicle 102 has actually been detected, it is possible to more accurately determine whether the road is a two-way traffic road.

[0064] (3) The road determination unit 142 determines whether the road on which the vehicle 101 is traveling is a road with oncoming traffic based on information about the types of the pair of left and right lane markings L1, L2 that define the lane LN1 on which the vehicle 101 is traveling (FIG. 6). That is, the lane marking conditions include the fact that the R lane marking L2 is yellow and the L lane marking L1 is a solid white line, and determines whether the road is a road with oncoming traffic based on whether the lane marking conditions are met. This allows for accurate determination of whether the road is a road with oncoming traffic by taking into account the color and shape of the lane markings on the road with oncoming traffic.

[0065] (4) The road determination unit 142 further determines whether the road on which the vehicle is traveling is a road for oncoming traffic based on the length (distance D) of the area outside the current lane LN1 in the vehicle width direction (FIG. 6). That is, the lane marking condition includes the distance D being less than a predetermined value D1, and determines whether the road is a road for oncoming traffic based on whether the lane marking condition is met. This allows for accurate determination of whether the road is a road for oncoming traffic even when the L lane marking L1 is blurred and is not determined to be a solid white line.

[0066] (5) The road determination unit 142 further determines whether the road on which the vehicle is traveling is a road with oncoming traffic based on information about the outer demarcation lines L1 and L2 that define the vehicle's own lane LN1, such as the LL demarcation line and the RR demarcation line L5 (FIG. 6). This allows the determination of whether the road on which the vehicle is traveling is a road with oncoming traffic to be made with greater accuracy.

[0067] (6) The road determination unit 142 determines whether the lane line condition is met based on the lane line information, and if it determines that the lane line condition is met, it determines that the road on which the vehicle is traveling is a road with oncoming traffic. On the other hand, if it determines that the lane line condition is not met for a predetermined time (first predetermined time) Δt2 or more after determining that the road is a road with oncoming traffic, it determines that the road on which the vehicle is traveling is not a road with oncoming traffic (FIG. 7). This allows the determination of an oncoming traffic road to be made with high accuracy even if the camera 1a erroneously detects the type of lane line due to backlighting or the like.

[0068] (7) After determining that the road on which the vehicle is traveling is not a road for oncoming traffic, if the road determination unit 142 determines that the lane marking condition continues to be satisfied for a predetermined time (second predetermined time) Δt1 or more that is shorter than the predetermined time Δt2, the road determination unit 142 determines that the road on which the vehicle is traveling is a road for oncoming traffic ( FIG. 7 ). This allows the road determination unit 142 to accurately and quickly determine that the road is a road for oncoming traffic.

[0069] The above embodiment can be modified in various ways. Some modifications are described below. In the above embodiment, the camera 1a detects the lane markings and oncoming vehicles on the road where the vehicle is traveling. However, the lane markings and oncoming vehicles may be detected by different detection units. In the above embodiment, the lane marking conditions include the R lane marking L2 being yellow and the L lane marking L1 being a solid white line, and the road is determined to be a road with oncoming traffic. However, on roads with oncoming traffic, the types of the pair of left and right lane marks L1, L2 that define the vehicle's own lane LN1 may differ from country to country. Therefore, the road may be determined to be a road with oncoming traffic by taking into account the standards for oncoming traffic roads in each country. Therefore, the manner in which the road determination unit determines a road with oncoming traffic based on information on the type of the pair of left and right lane marks is not limited to the above.

[0070] Although the above embodiment illustrates an example of a road with left-hand traffic, the present invention can also be applied to roads with right-hand traffic. FIGS. 8A and 8B are diagrams showing an example of a road with no opposing traffic and right-hand traffic, an example of a road in the United States. In FIG. 8A, yellow dividing lines L11 and L12 are present on the left side of the current lane LN1. The fact that the L and LL dividing lines are yellow may be included in the dividing line conditions, and the road determination unit may determine whether the road is a road with no opposing traffic. In FIG. 8B, the left side of the current lane LN1 is marked with a yellow dividing line L11, and the right side is marked with a dashed white dividing line L13. In the above embodiment, it is determined whether the road is a single-lane road with two-way traffic, but it may also be determined whether the road is a multi-lane road with two-way traffic in the same manner as described above.

[0071] In the above embodiment, the road determination unit 142 determines whether the road on which the vehicle is traveling is a road for oncoming traffic based on the length (distance D) of the area outside the vehicle's own lane LN1 and on information about the type of outer lane markings of the pair of left and right lane markings L1, L2. However, the road determination unit may be configured in any way as long as it determines whether the road on which the vehicle is traveling is a road for oncoming traffic based on lane marking information including information about the type of lane markings determined by the lane marking determination unit. In the above embodiment, if the road determination unit 142 determines that the road on which the vehicle is traveling is a road for oncoming traffic and then determines that a predetermined road condition is not met for a predetermined time period Δt2 or more, the road determination unit 142 determines that the road on which the vehicle is traveling is not a road for oncoming traffic. However, the condition of a predetermined time period need not be present.

[0072] In the above embodiment, an example has been described in which the road recognition device 50 is applied to an autonomous driving vehicle, but the present invention can also be applied to a manually driven vehicle having a driving assistance function.

[0073] The above description is merely an example, and the present invention is not limited to the above-described embodiment and modifications as long as the features of the present invention are not impaired. One or more of the above-described embodiment and modifications can be arbitrarily combined, and modifications can also be combined with each other. [Explanation of symbols]

[0074] 1a camera, 10 controller, 50 road recognition device, 141 lane marking discrimination unit, 142 road determination unit, L1 L lane marking, L2 R lane marking, L5 RR lane marking, L10 LL lane marking, LN1 own lane, LN2 adjacent lane

Claims

1. a detection unit that detects lane markings on a road on which the vehicle is traveling; a lane marking discrimination unit that discriminates the type of lane marking based on the color and shape of the lane marking detected by the detection unit; a road determination unit that determines whether the road on which the vehicle is traveling is a two-way traffic road on which two vehicles are traveling, based on lane marking information including information on the type of lane marking determined by the lane marking determination unit, the road determination unit determines whether or not a predetermined road condition is met based on the lane marking information, and if it determines that the predetermined road condition is met, determines that the road on which the vehicle is traveling is a road with oncoming traffic, whereas if it determines that the predetermined road condition is not met for a first predetermined time or more after determining that the road is a road with oncoming traffic, it determines that the road on which the vehicle is traveling is not a road with oncoming traffic; Furthermore, the road determination unit determines that the road on which the vehicle is traveling is a road with oncoming traffic, if the road determination unit determines that the specified road condition continues to be met for a second predetermined time period or more that is shorter than the first predetermined time period, after determining that the road on which the vehicle is traveling is not a road with oncoming traffic.

2. 2. The road recognition device according to claim 1, The detection unit is further configured to detect an oncoming vehicle, The road recognition device is characterized in that the road determination unit further determines whether the road on which the vehicle is traveling is a two-way traffic road based on whether an oncoming vehicle is detected by the detection unit.

3. 3. The road recognition device according to claim 1, The road recognition device is characterized in that the road determination unit determines whether the road on which the vehicle is traveling is a two-way traffic road based on information on the type of a pair of left and right dividing lines that define the lane on which the vehicle is traveling.

4. 4. The road recognition device according to claim 3, The road recognition device is characterized in that the road determination unit further determines whether the road on which the vehicle is traveling is a road with oncoming traffic based on the length of the area outside the own lane in the vehicle width direction.

5. 5. The road recognition device according to claim 3, The road recognition device is characterized in that the road determination unit further determines whether the road on which the vehicle is traveling is a two-way traffic road based on information on the type of the outer demarcation lines of the pair of left and right demarcation lines.

Images