Map generation device and map generation system

Abstract

To add a proper shape of a lane to a map for travelling in such a specific scene as the inside of a modified intersection.SOLUTION: A map generation device 50 include: a storage unit 12 for storing travel trace information showing the travel trace of a vehicle; a recognition unit 14 for recognizing situations around the vehicle; a curvature calculation unit 112 for calculating the curvature of a travel trace in a specific scene on the basis of the travel trace information read from the storage unit 12 in a case where map information for travelling in the specific scene is not acquired; an estimation unit 113 for estimating the shape of a lane in the specific scene on the basis of the curvature calculated by the curvature calculation unit 112; and a map generation unit 114 for adding the lane shape estimated by the estimation unit 113 to the map information for travelling.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a map generating device and a map generating system that generate a map based on information acquired by a vehicle. [Background technology]

[0002] As this type of technology, a map generating device that generates a map based on information acquired by an on-board sensor mounted on a vehicle is known (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2010-26326 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the conventional technology, the entrance and exit points of an intersection are connected by an S-shape or a single arc using a Bézier curve based on the direction of travel. Therefore, for example, in the case of a deformed intersection where the entrance and exit points of the intersection are offset from each other, a smooth lane shape may not be obtained. Obtaining smooth lane shapes at intersections in map data enables smooth vehicle movement, improving traffic convenience and safety, and thereby contributing to the development of a sustainable transportation system. [Means for solving the problem]

[0005] A map generating device according to a first aspect of the present invention includes a memory unit that stores driving trajectory information indicating a driving trajectory of a vehicle, a recognition unit that recognizes the situation around the vehicle, a curvature calculation unit that calculates a curvature of the driving trajectory in a specific scene based on the driving trajectory information read from the memory unit when driving map information for a specific scene has not been acquired, an estimation unit that estimates a lane shape of the specific scene based on the curvature calculated by the curvature calculation unit, and a map generating unit that adds the lane shape estimated by the estimation unit to the driving map information. A map generation system according to a second aspect of the present invention includes the map generation device of the first aspect and a server device that acquires and stores driving trajectory information from a plurality of vehicles, and a curvature calculation unit calculates a curvature of a driving trajectory in a specific scene based on the driving trajectory information of vehicles other than two-wheeled vehicles among the driving trajectory information from the plurality of vehicles stored in the server device. Effect of the Invention

[0006] According to the present invention, it is possible to add appropriate lane shapes to a driving map in a specific scene, for example, in a deformed intersection. [Brief description of the drawings]

[0007] [Figure 1] FIG. [Diagram 2] 1 is a block diagram illustrating a schematic configuration of a vehicle control system having a map generating device according to an embodiment of the invention; [Diagram 3] FIG. 1 is a block diagram illustrating a configuration of a main part of a map generating device according to an embodiment. [Figure 4A] A schematic diagram showing the driving trajectory of a driving section including an intersection on a two-dimensional map. [Figure 4B] FIG. 11 is a schematic diagram illustrating the distribution of driving trajectories with outliers removed. [Figure 5A] FIG. 2 is a schematic diagram illustrating a first example of estimation of a lane shape. [Figure 5B] FIG. 5B is a diagram showing the curvature of the travel trajectory M in FIG. 5A. [Figure 6A] FIG. 1 is a schematic diagram illustrating the method according to Estimation Example 1 in more detail. [Figure 6B] 1 is a diagram illustrating an example of a driving trajectory M from the entrance to the exit of an intersection and the distance to a virtual lane boundary line. [Figure 7A] FIG. 11 is a schematic diagram illustrating a second example of estimation of a lane shape. [Figure 7B] FIG. 11 is a schematic diagram illustrating a third example of estimation of a lane shape. [Figure 8] 4 is a flowchart showing an example of processing executed by the controller of FIG. 3; [Figure 9] FIG. 1 is a diagram illustrating a configuration of a road map generating system according to a first modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, an embodiment of the invention will be described with reference to the drawings. <Summary> The map generating device according to the embodiment is configured to generate a map (an environmental map to be described later) used when a vehicle having an automatic driving function (an automatic driving vehicle) is traveling. In the following description, the vehicle equipped with the map generating device according to the embodiment may be called the host vehicle to distinguish it from other vehicles.

[0009] The map generation device generates a map when the driver manually drives the vehicle. Therefore, the map generation device can be provided in a vehicle that does not have an automatic driving function (a manually driven vehicle).

[0010] The map generating device generates an environmental map consisting of three-dimensional point cloud data using detection values ​​detected by a group of external sensors described later while the vehicle is traveling. For example, edges showing the contours of objects as features are extracted from camera images acquired by cameras constituting the group of external sensors based on brightness and color information for each pixel, and feature points are extracted using the edge information. Feature points are, for example, points on edges or intersections of edges, and correspond to division lines on a road surface, corners of buildings, corners of road signs, etc. The map generating device obtains distances from the vehicle to the feature points using a LiDAR (Light Detection and Ranging) or a Radar (Radar) constituting the group of external sensors, records the feature points on an environmental map, and generates an environmental map of the area around the road on which the vehicle has traveled. The map generating device can be installed not only in a manually driven vehicle, but also in an autonomous vehicle that can be switched from an autonomous driving mode that does not require driving operation by the driver to a manual driving mode that requires driving operation by the driver. In the following, the map generating device will be described assuming that it is installed in an autonomous vehicle.

[0011] <Example of modified intersection> Fig. 1 is a schematic diagram illustrating an intersection where the entrance to the intersection and the exit to leave the intersection are offset, in other words, a modified intersection where the position of the driving lane toward the entrance of the intersection extended into the intersection is offset from the position of the exit of the intersection. The intersection enclosed by a rectangular dashed line does not have guide lines or the like (including road markings and cones) that guide the driving route within the intersection. The roads that run vertically across an intersection are four lanes in total, with two lanes on each side. In the example of Figure 1, when a vehicle 101 traveling upward in the first lane and another vehicle 102 traveling upward in the second lane go straight through the intersection, they should follow the routes L101 and L102 indicated by the arrows to go upward through the intersection. When a host vehicle 101 and another vehicle 102 traveling in the first and second lanes in an autonomous driving mode go straight through the intersection, the map generating device according to the embodiment estimates the lane shape within the intersection so that the host vehicle 101 and another vehicle 102 follow routes L101 and L102, respectively, within the intersection, and generates an environmental map including the estimated lane shape. Such a map generating device will be described in detail below.

[0012] <Autonomous vehicles> First, the configuration of an autonomous vehicle will be described. The vehicle may be any of an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a driving motor as a driving source, and a hybrid vehicle having an engine and a driving motor as driving sources. Fig. 2 is a block diagram illustrating a schematic configuration of a vehicle control system 100 having a map generating device according to an embodiment.

[0013] As shown in FIG. 2, the vehicle control system 100 mainly includes a controller 10, a group of external sensors 1 each communicatively connected to the controller 10 via a CAN (Controller Area Network) communication line or the like, a group of internal sensors 2, 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.

[0014] 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. The external sensor group 1 includes a camera that has an image sensor such as a CMOS sensor and captures the surroundings (front, rear, and sides) of the vehicle, a lidar that detects the positions (distance and direction from the vehicle) of objects around the vehicle by irradiating laser light and detecting reflected light, and a radar that detects the positions of objects around the vehicle by irradiating electromagnetic waves and detecting reflected waves.

[0015] The internal sensor group 2 is a collective term for a plurality of sensors (internal sensors) that detect the driving state of the vehicle. The internal sensor group 2 includes, for example, a vehicle speed sensor that detects the vehicle speed of the vehicle, an acceleration sensor that detects the acceleration in the forward / rearward and left / right directions of the 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 operation of the driver in the manual driving mode, such as the operation of the accelerator pedal, the operation of the brake pedal, the operation of the steering wheel, etc.

[0016] 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 a displayed image, a speaker that provides information to the driver by voice, and the like.

[0017] The positioning unit 4 has a positioning sensor that receives positioning signals transmitted from a positioning satellite, and measures the current position (latitude, longitude, altitude) of the vehicle using the positioning information received by the positioning sensor. The positioning satellite is an artificial satellite such as a GPS satellite or a quasi-zenith satellite. The positioning sensor may be included in the internal sensor group 2. The positioning unit 4 may also be called a GNSS (Global Navigation Satellite System) unit.

[0018] 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 a semiconductor device. The map information includes road position information, road shape (curvature, etc.) information, and intersection and branch point position information. It should be noted that the map information stored in the map database 5 is different from the map information of the highly accurate environmental map stored in the storage unit 12 of the controller 10.

[0019] 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 ​​of the external sensor group 1, and the target route may be calculated based on this current position and environmental map information stored in the memory unit 12.

[0020] The communication unit 7 communicates with various servers (not shown) via a network including a wireless communication network such as the Internet network or a mobile phone network, and acquires map information, driving history information, traffic information, and the like from the server periodically or at any timing. The network includes not only a public wireless communication network but also a closed communication network provided for each predetermined management area, such as a wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like. If the acquired map information is the above-mentioned general map information, the map in the map database 5 is updated. Also, if the acquired map information is environmental map information, the environmental map in the storage unit 12 is updated. The communication unit 7 can also communicate with other vehicles.

[0021] The actuators AC are driving actuators for controlling the driving of the host vehicle. When the driving source for driving is an engine, the actuators AC include a throttle actuator that adjusts the opening of a throttle valve (throttle opening) of the engine. When the driving source for driving is a driving motor, the actuators AC include the driving motor. The actuators AC also include a brake actuator that operates the braking device of the host vehicle and a steering actuator that drives the steering device.

[0022] 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 a RAM, and other peripheral circuits (not shown) such as an I / O interface. Note that although a plurality of ECUs with different functions, such as an engine control ECU, a travel motor control ECU, and a braking device ECU, can be provided separately, the controller 10 is shown in FIG. 2 as a collection of these ECUs for the sake of convenience.

[0023] The storage unit 12 stores highly accurate environmental map information. The environmental map includes road position information, road shape (curvature, etc.) information, road gradient information, intersection and branch point position information, number of lanes (which may be called driving lanes), lane width and position information for each lane (information on lane center positions and lane position boundary lines), position information of landmarks (traffic lights, signs, buildings, etc.) as markers on the map, road surface profile information such as road surface unevenness, etc. The storage unit 12 stores the environmental map (its data) and reliability information indicating the reliability of the environmental map as environmental map information. The storage unit 12 can further store travel trajectory information indicating a travel trajectory based on the detection values ​​of the external sensor group 1 and the internal sensor group 2.

[0024] The calculation unit 11 has, as its functional configuration, a vehicle position recognition unit 13, an external environment recognition unit 14, a behavior plan generation unit 15, and a driving control unit 16.

[0025] The vehicle position recognition unit 13 recognizes the position of the vehicle on the map (the 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 also be recognized using the environmental map information stored in the storage unit 12 and the surrounding information of the vehicle detected by the external sensor group 1, and the vehicle position can be recognized with high accuracy. When the vehicle position can be measured by a sensor installed externally on or beside the road, the vehicle position may be recognized by communicating with the sensor via the communication unit 7.

[0026] The vehicle position recognition unit 13 further performs a process of estimating the position of the vehicle in parallel with a map generation process by the map generation unit 114 described later. The position estimation estimates the position of the vehicle based on the change in the position of features (feature points) over time. The map creation process and the position estimation process are performed simultaneously according to a SLAM (Simultaneous Localization and Mapping) algorithm using signals from an external sensor group 1 (cameras and lidars), for example.

[0027] The external environment recognition unit 14 recognizes the external situation around the vehicle based on signals from the external sensor group 1. For example, it recognizes the positions, speeds, and accelerations of surrounding vehicles (vehicles in front 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, and the like. Examples of the states of other objects include the colors of traffic lights (red, green, yellow), and the moving speeds and directions of pedestrians and bicycles. The dividing lines include white lines (including lines of different colors such as yellow), curb lines, road studs, and the like, and may be called lane marks.

[0028] The action plan generating unit 15 generates a running trajectory (target trajectory) of the vehicle from the current time to a predetermined time ahead based on, for example, the target route calculated by the navigation device 6, the map information stored in the map database 5 (may be the environmental map information stored in the storage unit 12), the vehicle position recognized by the vehicle position recognition unit 13, and the external situation 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 action plan generating unit 15 selects an optimal trajectory that complies with laws and regulations and satisfies criteria such as efficient and safe running, and sets the selected trajectory as the target trajectory. Then, the action plan generating unit 15 generates an action plan according to the generated target trajectory. The action plan generating unit 15 generates various action plans corresponding to overtaking running to overtake a preceding vehicle, lane changing running to change the running lane, following running to follow a preceding vehicle, lane keeping running to maintain the lane so as not to deviate from the running lane, decelerating running or accelerating running, etc. When generating a target trajectory, the behavior plan generating unit 15 first determines a driving mode, and generates the target trajectory based on the driving mode.

[0029] In the automatic driving mode, the driving control unit 16 controls each actuator AC so that the vehicle runs along the target trajectory generated by the behavior plan generating unit 15. More specifically, the driving control unit 16 calculates a required driving force for obtaining the target acceleration per unit time calculated by the behavior plan generating unit 15, taking into account the running resistance determined by the road gradient, etc., in the automatic 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. That is, the driving control unit 16 controls the actuators AC so that the vehicle runs at the target vehicle speed and the target acceleration. When the driving mode is the manual driving mode, the driving control unit 16 controls each actuator AC in response to a driving command (such as a steering operation) from the driver acquired by the internal sensor group 2.

[0030] <Map Generation Device> Fig. 3 is a block diagram illustrating a configuration of a main part of a map generating device 50 according to an embodiment. The map generating device 50 is included in the vehicle control system 100 of Fig. 2. In Fig. 3, the map generating device 50 has a camera 1a, a lidar 1b, a sensor 2a, and a controller 10.

[0031] The camera 1a is a monocular camera having an image sensor such as a CMOS sensor, and is one of the external sensor group 1 in Fig. 2. The camera 1a may be a stereo camera. The camera 1a is attached to a predetermined position in the front of the vehicle, and continuously captures images of the space in front of the vehicle at a predetermined frame rate to obtain images (camera images) of the above-mentioned surrounding vehicles and other objects. In addition, together with the camera 1a or instead of the camera 1a, a lidar 1b or the like may be used to detect an object.

[0032] The lidar 1b is also one of the external sensor group 1. The lidar 1b is attached facing the front of the vehicle so that the field of view (hereinafter referred to as FOV) of the lidar 1b includes an area to be watched while driving. The lidar 1b intermittently irradiates a laser beam to a plurality of detection points (which may be called irradiation points) in the FOV, and acquires point information for each detection point, where the irradiated laser beam is reflected (scattered) at a certain point on the surface of the object and returns. The point information includes the distance from the laser source (the vehicle) to the point, the intensity of the reflected (scattered) laser beam, and the relative speed between the laser source and the point. In the embodiment, data consisting of point information of a plurality of detection points in the FOV is called point cloud data. The lidar 1b continuously acquires a predetermined number of point cloud data (the number of detection points in the FOV) per frame at a predetermined frame rate.

[0033] The sensor 2a is a detector used to calculate the amount of movement and the direction of movement of the vehicle. The sensor 2a is part of the internal sensor group 2, and is composed of, for example, a vehicle speed sensor and a yaw rate sensor. That is, the controller 10 (vehicle position recognition unit 13) integrates the vehicle speed detected by the vehicle speed sensor to calculate the amount of movement of the vehicle, and also integrates the yaw rate detected by the yaw rate sensor to calculate the yaw angle, and estimates the position of the vehicle by odometry when creating a map. Note that the configuration of the sensor 2a is not limited to this, and the vehicle position may be estimated using information from other sensors.

[0034] The controller 10 in FIG. 3 has, as functional components carried out by the calculation unit 11 (FIG. 2), a driving trajectory acquisition unit 111, a curvature calculation unit 112, a lane shape estimation unit 113, and a map generation unit 114 in addition to the memory unit 12 and the external environment recognition unit 14.

[0035] The storage unit 12 stores the environmental map information as described above. The environmental map stored in the storage unit 12 includes an environmental map (which may be called an external environmental map) acquired from the outside of the vehicle via the communication unit 7, and an environmental map (which may be called an internal environmental map) created by the map generation unit 114 using recognition information by the external environment recognition unit 14, the detection values ​​of the external sensor group 1, or the detection values ​​of the external sensor group 1 and the internal sensor group 2. The external environmental map is an environmental map acquired, for example, via a cloud server, and the internal environmental map is an environmental map created by mapping using a technology such as the above-mentioned SLAM. The external environmental map is shared between the vehicle and other vehicles, whereas the internal environmental map is a map that the vehicle possesses independently. The storage unit 12 can further store travel locus information indicating a travel locus. The storage unit 12 may also store information regarding various control programs, thresholds used in the programs, and the like.

[0036] The external environment recognition unit 14 recognizes curbs, walls, ditches, guardrails, or dividing lines indicating road boundaries as road boundaries based on, for example, camera images acquired by the camera 1a, and recognizes the road structure indicated by the road boundaries. As described above, dividing lines include white lines (including lines of different colors), curb lines, road studs, etc., and the driving lanes of the road are defined by the markings of these dividing lines, etc. Although an example has been disclosed in which the external environment recognition unit 14 recognizes an area enclosed by road boundary lines as an area corresponding to a road, the method of recognizing a road is not limited to this, and other methods may be used for recognition.

[0037] (Travel trajectory acquisition unit) The travel locus acquisition unit 111 acquires a travel locus traveled by the host vehicle 101. Position information (time-series position information) of the host vehicle 101 measured by the positioning unit 4 while the host vehicle 101 is traveling is temporarily recorded (may also be called accumulated) in the storage unit 12. The travel locus acquisition unit 111 acquires the travel locus of the host vehicle 101 by reading and calculating the time-series position information accumulated in the storage unit 12. The internal sensor group 2 may be configured to temporarily store time-series sensor data measured by the wheel speed sensor and steering angle sensor while the host vehicle 101 is traveling in the storage unit 12. The traveling trajectory acquisition unit 111 acquires the traveling trajectory of the host vehicle 101 by reading and calculating the time-series sensor data stored in the storage unit 12. The travel locus information indicating the travel locus acquired by the travel locus acquisition unit 111 can be stored in the storage unit 12 as described above.

[0038] When the time-series position information based on the driving trajectory information read from the memory unit 12 is arranged in time series on, for example, a two-dimensional map (with the vertical axis being the traveling direction (which may be called the depth direction) and the horizontal axis being the road width direction), the position information is discretely arranged in the traveling direction. By calculating an approximation curve based on discrete points in the traveling direction for each driving occasion, an approximation curve corresponding to the driving section can be obtained for each number of times that driving section has been driven.

[0039] Fig. 4A is a schematic diagram showing the travel trajectory of a travel section including an intersection on the above-mentioned two-dimensional map as seen from above. The up-down direction in Fig. 4A corresponds to the traveling direction as seen from the vehicle 101, and the left-right direction in Fig. 4A corresponds to the road width direction as seen from the vehicle 101. The area surrounded by a rectangular dashed line is within the intersection. The division lines L1 to L3 are division lines that respectively define the first and second lanes before entering the intersection, and the division lines L1' to L3' are division lines that respectively define the first and second lanes after exiting the intersection.

[0040] The n travel trajectories P1, P2, ..., Pn indicate n travel trajectories when the vehicle travels n times on the first lane from bottom to top in Fig. 4A. The travel trajectory M corresponds to the average value of the travel trajectories P1, P2, ..., Pn. The curvature calculation unit 112, which will be described later, determines the travel locus M as an average value of a plurality of approximation curves for the number of travels.

[0041] (curvature calculation section) The curvature calculation unit 112 calculates the curvature (lane curvature) of the travel trajectory of the vehicle 101, etc. in a specific scene, such as an intersection without travel lane markings or a merging area after passing through a gate on a highway, based on the travel trajectory information read out from the storage unit 12. To explain in more detail, the curvature calculation unit 112 calculates a travel trajectory M as the average value of the above-mentioned travel trajectories P1, P2, ..., Pn after removing statistical outliers (peculiar data) from the travel trajectory information, and calculates the curvature of the travel trajectory M. The outliers may be removed using, for example, a RANSAC (Random Sample Consensus) algorithm, and location information that is a predetermined distance or more away from other location information in a direction intersecting the traveling direction (road width direction) is removed.

[0042] 4B is a schematic diagram illustrating the distribution of travel trajectories with outliers removed. The vertical axis indicates the number of occurrences, and the horizontal axis indicates the position coordinate in the road width direction. In the embodiment, travel trajectories in the same section on the road acquired by the travel trajectory acquisition unit 111 correspond to n samples, and the average value (sample mean) μ of the n samples corresponds to travel trajectory M, which is the average value of the travel trajectories in that section.

[0043] (Lane Shape Estimation Unit) The lane shape estimation unit 113 estimates the lane shape of the specific scene as follows, based on the curvature of the travel trajectory M of the host vehicle 101 etc. in the specific scene described above. <Estimation example 1> Fig. 5A is a schematic diagram illustrating a lane shape estimation example 1. When a specific scene is within an intersection as illustrated in Fig. 5A where no driving lane markings are provided, and the curvature of the driving trajectory M calculated by the curvature calculation unit 112 is equal to or greater than a predetermined value, the lane shape estimation unit 113 estimates the lane shape within the intersection from an approximation curve calculated based on the driving trajectory M and the lane shapes at the entrance and exit of the intersection.

[0044] Fig. 5B is a diagram showing the curvature of the travel trajectory M in Fig. 5A, where the vertical axis indicates the magnitude of the curvature and the horizontal axis indicates the distance in the traveling direction. The curvature of the part surrounded by circle R1 in Fig. 5A corresponds to the part surrounded by circle C1 in Fig. 5B, and the curvature of the part surrounded by circle R2 in Fig. 5A corresponds to the part surrounded by circle C2 in Fig. 5B. Since the curvature in Fig. 5B exceeds a predetermined threshold value, lane shape estimation unit 113 estimates the lane shape in the intersection from an approximation curve calculated based on travel trajectory M and the lane shapes at the entrance and exit of the intersection.

[0045] Fig. 6A is a schematic diagram for explaining in more detail the method according to Estimation Example 1. In Fig. 6A, the distance between a dividing line L1 that defines the first lane at the entrance to the intersection and the traveling trajectory M is called the left-side distance. Also, the distance between a dividing line L2 that defines the first lane at the entrance to the intersection and the traveling trajectory M is called the right-side distance. Similarly, the distance between the marking line L1' that defines the first lane at the exit of the intersection and the driving trajectory M is called the left-side distance. Also, the distance between the marking line L2' that defines the first lane at the exit of the intersection and the driving trajectory M is called the right-side distance.

[0046] 6B is a diagram illustrating an example of the driving trajectory M from the entrance to the exit of the intersection and the distance to the virtual lane boundary line. The lane shape estimation unit 113 estimates the change in the distance from the driving trajectory M to the left and right virtual lane boundary lines in the intersection from the entrance to the exit of the intersection by linear approximation based on the distance between the driving trajectory M at the entrance and the exit of the intersection in FIG. 6A and the division lines L1, L2 and L1', L2' as the left and right lane boundary lines provided at the entrance and the exit. Then, the lane shape estimation unit 113 estimates the curved lane shape (in other words, the left and right virtual lane boundary lines) in the intersection by a nonlinear approximation curve using the discrete points of the left and right virtual lane boundary lines calculated based on the distance estimated by linear approximation. Note that Figures 5A and 5B show examples in which the curvature at two points within the intersection exceeds a predetermined threshold, but if the curvature at at least one point within the intersection exceeds a predetermined threshold, the lane shape estimation unit 113 estimates the lane shape within the intersection using the method described in estimation example 1.

[0047] <Estimation example 2> Fig. 7A is a schematic diagram illustrating a second example of lane shape estimation. When a specific scene is within an intersection as illustrated in Fig. 7A where no driving lane markings are provided, and the curvature of the driving trajectory M calculated by the curvature calculation unit 112 is less than a predetermined value, the lane shape estimation unit 113 estimates the lane shape within the intersection from an approximation curve calculated based on the lane shapes at the entrance and exit of the intersection.

[0048] For example, left and right approximate curves (shown by dashed lines within the intersection in Figure 7A) are calculated as left and right virtual lane boundary lines connecting the lane shape of the first lane defined by dividing lines L1 and L2 as left and right lane boundary lines at the entrance and the lane shape of the first lane defined by dividing lines L1' and L2' as left and right lane boundary lines at the exit, and the lane shape within the intersection is estimated from these left and right approximate curves.

[0049] <Estimation example 3> Fig. 7B is a schematic diagram illustrating a lane shape estimation example 3. When a specific scene is within an intersection where driving lane markings are provided as illustrated in Fig. 7B, the lane shape estimation unit 113 estimates the lane shape within the intersection from an approximation curve calculated based on the lane shapes and guidance markings at the entrance and exit of the intersection.

[0050] For example, left and right approximate curves (shown by dashed lines within the intersection in Figure 7A) are calculated as left and right virtual lane boundary lines that respectively connect the lane shape of the first lane defined by dividing lines L1 and L2 as left and right lane boundary lines at the entrance, left and right guide lines G1 and G2 as guidance signs provided within the intersection, and the lane shape of the first lane defined by dividing lines L1' and L2' as left and right lane boundary lines at the exit, and the lane shape within the intersection is estimated from these left and right approximate curves.

[0051] (Map Generation Section) The map generating unit 114 generates an environmental map including position information indicating the positions of features such as dividing lines on the road surface while driving in the manual driving mode. Specifically, it generates an internal environmental map consisting of three-dimensional point cloud data. For example, the map generating unit 114 extracts feature points of features recognized by the external environment recognition unit 14 from a camera image acquired by the camera 1a. The map generating unit 114 further obtains the distance from the vehicle to the feature points using a distance measurement value based on the camera image or a detection value by the lidar 1b, and sequentially plots the feature points at positions separated by the obtained distance from the position of the vehicle on the environmental map estimated by the vehicle position recognition unit 13, thereby generating an environmental map of the area around the road on which the vehicle has traveled. As described above, the map generating unit 114 may perform the map generating process not only when driving in the manual driving mode, but also when driving in the automatic driving mode in the same manner as in the manual driving mode. Furthermore, for the specific scene described above, the map generating unit 114 includes (adds) information indicating the lane shape estimated by the lane shape estimating unit 113 in the environmental map.

[0052] <Explanation of the flow chart> Fig. 8 is a flowchart showing an example of a process executed by the controller 10 of Fig. 3 in accordance with a predetermined program. The process shown in this flowchart is repeated at a predetermined interval while the vehicle is traveling in manual driving mode, for example, to generate an environmental map.

[0053] In step S10 of FIG. 8, the controller 10 acquires sensor information from the camera 1a, the lidar 1b, and the sensor 2a, and proceeds to step S20. In step S20, the controller 10 determines whether or not a guide sign is provided in the intersection. If there is no guide sign, the controller 10 makes an affirmative decision in step S20 and proceeds to step S30, and if there is a guide sign, the controller 10 makes a negative decision in step S20 and proceeds to step S100.

[0054] In step S30, the controller 10 acquires the travel locus and proceeds to step S40. As described above, the travel locus information is stored in the storage unit 12. In step S40, the controller 10 calculates the curvature of the travel locus M, which is the average value of the travel locus, by the curvature calculation unit 112, and proceeds to step S50.

[0055] In step S50, the controller 10 determines whether the curvature is equal to or greater than a predetermined threshold value. If the curvature is equal to or greater than the predetermined threshold value, the controller 10 makes an affirmative decision in step S50 and proceeds to step S60, whereas if the curvature is less than the predetermined threshold value, the controller 10 makes a negative decision in step S50 and proceeds to step S90.

[0056] In step S60, the controller 10 estimates the lane shape of the intersection based on the travel trajectory M and the shape of the entrance / exit of the intersection using the lane shape estimation unit 113, and proceeds to step S70. The estimation in step S60 corresponds to estimation example 1 described above.

[0057] In step S70, the controller 10 causes the map generating unit 114 to add information indicating the lane shape estimated in step S60 to the environmental map, and then proceeds to step S80.

[0058] In step S80, the controller 10 records the environmental map to which the information indicating the lane shape has been added in the storage unit 12 as environmental map information, and ends the processing in FIG.

[0059] In step S90, which is reached after making a negative decision in step S50, the controller 10 estimates the lane shape of the intersection based on the shape of the entrance / exit of the intersection using the lane shape estimation unit 113, and then proceeds to step S70. The estimation in step S90 corresponds to estimation example 2 described above.

[0060] In step S100, which is reached after making a negative decision in step S20, the controller 10 estimates the lane shape of the intersection based on the entrance / exit of the intersection and the guide sign of the intersection using the lane shape estimation unit 113, and proceeds to step S70. The estimation in step S100 corresponds to estimation example 3 described above.

[0061] According to the embodiment described above, the following advantageous effects are achieved. (1) The map generating device 50 includes a memory unit 12 that stores driving trajectory information indicating the driving trajectory M of the vehicle 101, an external environment recognition unit 14 that recognizes the situation around the vehicle 101, a curvature calculation unit 112 that calculates the curvature of the driving trajectory M within the intersection based on the driving trajectory information read from the memory unit 12 when an environmental map has not been acquired as driving map information within an intersection as a specific scene, a lane shape estimation unit 113 that estimates the lane shape within the intersection based on the curvature calculated by the curvature calculation unit 112, and a map generating unit 114 that adds the lane shape estimated by the lane shape estimation unit 113 to the environmental map. With this configuration, for example, when an environmental map has not been acquired as map information for driving within an intersection that does not have guide lines such as road markings or cones to guide the driving route within the intersection, it is possible to add to the environmental map an appropriate lane shape within the intersection that is estimated based on the curvature of the driving trajectory M actually traveled through the intersection.

[0062] (2) In the map generating device 50 of (1) above, the specific scene is an intersection where no guide lines or the like are installed as guide signs to guide the driving route, and the curvature calculation unit 112 calculates the curvature of the average value of the driving trajectory (driving trajectory M) within the intersection based on the driving trajectory information. If the curvature calculated by the curvature calculation unit 112 is equal to or greater than a predetermined value, the lane shape estimation unit 113 estimates the lane shape within the intersection from an approximate curve calculated based on the driving trajectory M and the lane shapes at the entrance and exit of the intersection, and the map generating unit 114 adds the lane shape within the intersection estimated by the lane shape estimation unit 113 to the environmental map. With this configuration, for example, for intersections where the entrance and exit of the intersection are misaligned in the direction intersecting with the direction of travel (this may be called an offset), and the curvature of the driving trajectory M, which is the average value of the driving trajectory within the intersection, is equal to or greater than a predetermined value, it is possible to appropriately estimate the lane shape within the intersection and add it to the environmental map.

[0063] (3) In the map generating device 50 described in (2) above, the lane shape estimation unit 113 linearly approximates the change in distance from the average value of the driving trajectory within the intersection from the entrance to the exit to the left and right virtual lane boundary lines based on the average value of the driving trajectory at the entrance and exit of the intersection based on the driving trajectory information and the distance between the left and right lane boundary lines set at the entrance and exit, and estimates the lane shape within the intersection with a nonlinear approximation curve using discrete points of the left and right virtual lane boundary lines calculated based on the distance estimated by the linear approximation, and the map generating unit 114 adds the lane shape within the intersection estimated by the lane shape estimation unit 113 to the environmental map. With this configuration, it becomes possible to appropriately estimate the lane shape within an intersection that has little deviation from the driving trajectory of the vehicle 101 and is close to the actual driving trajectory based on the curvature of the driving trajectory M, which is the average value of the driving trajectory, and add it to the environmental map.

[0064] (4) In the map generating device 50 of (1) above, the specific scene is an intersection where no guide signs are installed to guide the driving route, and the curvature calculation unit 112 calculates the curvature of the average value of the driving trajectory within the intersection based on the driving trajectory information. If the curvature calculated by the curvature calculation unit 112 is less than a predetermined value, the lane shape estimation unit 113 estimates the lane shape within the intersection from an approximate curve calculated based on the lane shapes at the entrance and exit of the intersection, and the map generating unit 114 adds the lane shape within the intersection estimated by the lane shape estimation unit 113 to the environmental map. With this configuration, for intersections where the curvature of the driving trajectory M, which is the average value of the driving trajectory within the intersection, does not exceed a predetermined value, it is possible to appropriately estimate the lane shape within the intersection and add it to the environmental map while reducing the calculation load compared to the estimation calculations in the above cases (2) and (3).

[0065] (5) In the map generating device 50 described in (2) to (4) above, the specific scene is an intersection where guidance signs (e.g., road markings and other installations such as cones) that guide the driving route are installed, and the lane shape estimation unit 113 estimates the lane shape within the intersection from an approximate curve calculated based on the lane shapes at the entrance and exit of the intersection and the guidance signs, and the map generating unit 114 adds the lane shape within the intersection estimated by the lane shape estimation unit 113 to the environmental map. With this configuration, it is possible to appropriately estimate the lane shape within an intersection and add it to the environmental map, even for intersections where road markings or guide lines such as cones are installed to guide the driving route within the intersection.

[0066] (6) In the map generating device 50 described above in (1) to (4), the curvature calculation unit 112 detects statistical outliers from a plurality of pieces of driving trajectory information, and calculates the curvature of the driving trajectory in a specific scene, such as within an intersection, based on the driving trajectory information from which the outliers have been removed. With this configuration, irregular driving trajectory information that is different from the norm (for example, obstacle avoidance behavior within an intersection, or behavior of yielding to an emergency vehicle, etc. within an intersection) that is present in the driving trajectory information can be excluded as outliers, making it possible to more appropriately estimate the lane shape within an intersection.

[0067] The above embodiment can be modified in various ways, and modifications will be described below. (Variation 1) In the embodiment, an example has been described in which the travel locus acquisition unit 111 acquires travel locus information of the vehicle 101 on its own, but in the first modification, an example will be described in which the travel locus information of a vehicle 102 or the like other than the vehicle 101 is acquired via, for example, a cloud server. That is, in the first modification, the travel locus information is shared among a plurality of vehicles.

[0068] Fig. 9 is a diagram illustrating a configuration of a road map generation system 400 according to Modification 1. In Fig. 9, the road map generation system 400 includes a server 200 connected to a communication network 300, and a vehicle control system 100a and a vehicle control system 100b configured to be communicatively connected to the communication network 300. The vehicle control system 100a is a vehicle control system 100 mounted on a host vehicle 101, and the vehicle control system 100b is a vehicle control system 100 mounted on another vehicle 102.

[0069] The server 200 is operated, for example, by a business entity that provides a travel locus information sharing service, etc. The configuration of the vehicle control systems 100a and 100b is similar to that of the vehicle control system 100 in the above-described embodiment.

[0070] The vehicle control systems 100a and 100b are each connected via a communication unit 7 to a communication network 300 such as a wireless communication network, the Internet network, or a telephone line network. Although two vehicles, the host vehicle 101 and the other vehicle 102, are shown in FIG. 9, the number of vehicles that can be connected to the communication network 300 is not limited to two and may be many.

[0071] The vehicle control systems 100a and 100b of the vehicle 101 and the other vehicle 102 each transmit the travel trajectory information of the vehicle stored in the storage unit 12 together with the vehicle type information of the vehicle to the server 200 via the communication unit 7 at a predetermined transmission time. The vehicle type information may be information that can identify at least the size of the vehicle, such as a passenger car (which may be called a general vehicle), bus, truck, or motorcycle. The transmission time may be appropriately set by the driver, for example, once a week or every predetermined distance traveled.

[0072] When the vehicle control systems 100a and 100b mounted on the host vehicle 101 and the other vehicle 102 transmit driving locus information to the server 200, the server 200 stores the driving locus information in a database (not shown) by vehicle size, for example.

[0073] In addition, when the server 200 receives a request for driving trajectory information from the vehicle control systems 100a and 100b installed in the host vehicle 101 and the other vehicle 102, the server 200 reads out from the database the driving trajectory information of the vehicle in a specific scene in the area in which the requesting vehicle is driving, the driving trajectory information corresponding to the size of the requesting vehicle, and transmits it to the requesting vehicle.

[0074] In the case of the first modification, when the controller 10 of the host vehicle 101 etc. acquires a travel trajectory in step S30 of Fig. 8, the controller 10 requests the server 200 for travel trajectory information in the area in which the host vehicle 101 etc. travels. At this time, the controller 10 notifies the server 200 of the position information of the host vehicle 101 etc. and the vehicle type information of the host vehicle 101 etc. This enables the server 200 to transmit to the requesting vehicle the travel trajectory information of the vehicle that corresponds to the size of the requesting vehicle.

[0075] The road map generation system 400 described in the above-described variant example 1 includes a server 200 as a server device that acquires driving trajectory information from multiple vehicles, such as the vehicle 101, and stores it in a database. The curvature calculation unit 112 of the vehicle 101, etc. calculates the curvature of the driving trajectory in a specific scene based on the driving trajectory information from the multiple vehicles stored in the database of the server 200. With this configuration, by acquiring the travel path information of other vehicles 102 and the like other than the subject vehicle 101, it becomes possible to estimate the lane shape within the intersection with higher reliability. In addition, since it becomes possible to capture a large amount of travel locus information, when statistical values ​​are used in calculations, statistical data close to true values ​​can be obtained. Furthermore, by acquiring the travel locus information of a vehicle corresponding to the size of the requesting vehicle, it is possible to obtain travel locus information that matches the actual travel situation of the requesting vehicle size by excluding travel locus information of other vehicles having different vehicle widths, inner wheel difference, etc. As a result, it is possible to estimate the lane shape in the intersection with higher reliability.

[0076] (Variation 2) The curvature of the travel trajectory in the specific scene may be calculated based on the travel trajectory information of a vehicle other than a two-wheeled vehicle among the travel trajectory information from a plurality of vehicles stored in the database of the server 200. That is, the curvature calculation unit 112 in the second modification calculates the curvature of the travel trajectory in the specific scene based on the travel trajectory information of a vehicle other than a two-wheeled vehicle. With this configuration, it is possible to calculate the curvature using only the travel trajectories of motorcycles, which generally travel along the roadside, and away from the roadside, making it possible to calculate the curvature of the travel trajectories of vehicles other than motorcycles that are actually traveling. As a result, it is possible to estimate the lane shape in an intersection with higher reliability.

[0077] The above description is merely an example, and the present invention is not limited to the above-mentioned embodiment and modifications, as long as the characteristics of the present invention are not impaired. One or more of the above-mentioned embodiment and modifications can be arbitrarily combined, and modifications can also be combined with each other. [Explanation of symbols]

[0078] REFERENCE SIGNS LIST 1 external sensor group, 2 internal sensor group, 10 controller, 11 calculation unit, 12 memory unit, 14 external environment recognition unit, 50 map generation device, 100 vehicle control system, 101 host vehicle, 111 travel trajectory acquisition unit, 112 curvature calculation unit, 113 lane shape estimation unit, 114 map generation unit

Claims

1. A storage unit that stores travel locus information indicating a travel locus of a vehicle; A recognition unit that recognizes a situation around the vehicle; a curvature calculation unit that calculates a curvature of a travel path in the specific scene based on the travel path information read from the storage unit when travel map information in the specific scene has not been acquired; an estimation unit that estimates a lane shape of the specific scene based on the curvature calculated by the curvature calculation unit; a map generation unit that adds the lane shape estimated by the estimation unit to the driving map information; A map generating device comprising:

2. 2. The map generating device according to claim 1, The specific scene is an intersection where no guide sign is installed to guide a driving route, The curvature calculation unit calculates an average curvature of a travel locus within the intersection based on the travel locus information, when the curvature calculated by the curvature calculation unit is equal to or greater than a predetermined value, the estimation unit estimates a lane shape within the intersection from an approximation curve calculated based on an average value of the travel locus and lane shapes at an entrance and an exit of the intersection; The map generating device, wherein the map generating unit adds the lane shape within the intersection estimated by the estimation unit to the driving map information.

3. 3. The map generating device according to claim 2, the estimation unit linearly approximates changes in distances from the average value of the travel trajectory within the intersection from the entrance to the exit to left and right virtual lane boundary lines based on an average value of the travel trajectory at the entrance and the exit of the intersection based on the travel trajectory information and distances between the left and right lane boundary lines provided at the entrance and the exit, and estimates a lane shape within the intersection with a nonlinear approximation curve using discrete points of the left and right virtual lane boundary lines calculated based on the distances estimated by the linear approximation; The map generating device, wherein the map generating unit adds the lane shape within the intersection estimated by the estimation unit to the driving map information.

4. 2. The map generating device according to claim 1, The specific scene is an intersection where no guide sign is installed to guide a driving route, The curvature calculation unit calculates an average curvature of a travel locus within the intersection based on the travel locus information, when the curvature calculated by the curvature calculation unit is less than a predetermined value, the estimation unit estimates a lane shape within the intersection from an approximation curve calculated based on lane shapes at an entrance and an exit of the intersection; The map generating device, wherein the map generating unit adds the lane shape within the intersection estimated by the estimation unit to the driving map information.

5. The map generating device according to any one of claims 2 to 4, The specific scene is an intersection where a guide sign for guiding a driving route is installed, the estimation unit estimates a lane shape within the intersection from an approximation curve calculated based on lane shapes at an entrance and an exit of the intersection and the guidance sign; The map generating device, wherein the map generating unit adds the lane shape within the intersection estimated by the estimation unit to the driving map information.

6. The map generating device according to any one of claims 1 to 4, The map generating device, characterized in that the curvature calculation unit detects statistical outliers from the plurality of pieces of driving locus information, and calculates a curvature of the driving locus in the specific scene based on the driving locus information from which the outliers have been removed.

7. A map generating device according to any one of claims 1 to 4; A server device that acquires and stores the travel locus information from a plurality of vehicles, the curvature calculation unit calculates a curvature of a travel trajectory in the specific scene based on the travel trajectory information of a vehicle other than a two-wheeled vehicle among the travel trajectory information from the plurality of vehicles stored in the server device. A map generating system comprising:

Images