Map generation device and map generation system

Abstract

A map generation device is provided with: a storage unit (12) that stores travel trajectory information indicating a travel trajectory of a vehicle; a recognition unit (14) that recognizes the situation around the vehicle; a curvature calculation unit (112) that calculates the curvature of the travel trajectory in the specific scene on the basis of the travel trajectory information read from the storage unit (12) when the travel map information in the specific scene is not acquired; an estimation unit (113) that estimates the lane shape of the specific scene on the basis of the curvature calculated by the curvature calculation unit (112); and a map generation unit (114) that adds the lane shape estimated by the estimation unit (113) to travel map information.

Description

[0001] This application claims the priority based on Japanese Application No. 2023-110507 filed on July 5, 2023, the contents of which are incorporated herein by reference. Technical Field

[0002] The present invention relates to a map generating device and a map generating system for generating a map based on information obtained from a vehicle. Background Art

[0003] As a technique of this type, a map generating device is known that generates a map based on information acquired by an on-vehicle sensor mounted on a vehicle.

[0004] For example, in the technology described in Patent Document 1, the entry point and exit point of the intersection are connected in an S-shape or a single arc using a Bezier curve based on the traveling direction. Therefore, in the case of a deformed intersection where the entry point and exit point of the intersection are offset from each other, a smooth lane shape may not be obtained.

[0005] Obtaining a smooth lane shape at an intersection in map data enables vehicles to move smoothly, thereby helping to improve traffic convenience and safety, thereby contributing to the sustainable development of the transportation system.

[0006] Prior art literature

[0007] Patent Literature

[0008] Patent Document 1: Japanese Patent Application Publication No. 2010-026326 (JP 2010-026326 A). Summary of the invention

[0009] The map generating device of the first technical solution of the present invention comprises: a storage unit, which stores driving trajectory information showing the driving trajectory of a vehicle; an identification unit, which identifies the conditions around the vehicle; a curvature calculating unit, which calculates the curvature of the driving trajectory in a specific scene based on the driving trajectory information read from the storage unit without obtaining the driving map information in the specific scene; an estimating unit, which estimates the lane shape in the specific scene based on the curvature calculated by the curvature calculating unit; and a map generating unit, which adds the lane shape estimated by the estimating unit to the driving map information.

[0010] The map generation system of the second technical solution of the present invention comprises the map generation device of the first technical solution and a server device that obtains and stores driving trajectory information from multiple vehicles, and the curvature calculation unit calculates the curvature of the 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 multiple vehicles stored in the server device. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The objects, features and advantages of the present invention will be further clarified through the following description of the embodiments in conjunction with the accompanying drawings.

[0012] Figure 1 is a schematic diagram illustrating a deformed intersection.

[0013] Figure 2 This is a block diagram illustrating a schematic configuration of a vehicle control system including a map generating device according to an embodiment of the present invention.

[0014] Figure 3 This is a block diagram illustrating a main part configuration of a map generating device according to an embodiment.

[0015] Figure 4A This is a schematic diagram showing a driving trajectory of a driving section including an intersection on a two-dimensional map.

[0016] Figure 4B This is a schematic diagram for explaining the distribution of driving trajectories from which outliers are excluded.

[0017] Figure 5A It is a schematic diagram explaining the example 1 of estimating the lane shape.

[0018] Figure 5B It is shown Figure 5A Graph of the curvature of the driving trajectory M.

[0019] Fig. 6A This is a schematic diagram for explaining the method of Estimation Example 1 in further detail.

[0020] Figure 6B 2 is a diagram illustrating a travel trajectory M from the entrance to the exit of an intersection and the distance to a virtual lane boundary line.

[0021] Fig. 7A It is a schematic diagram explaining the second example of estimating the lane shape.

[0022] Figure 7B It is a schematic diagram explaining the example 3 of estimating the lane shape.

[0023] Figure 8 It is shown by Figure 3 A flowchart of an example of a process performed by a controller.

[0024] Fig. 9 This is a diagram illustrating the configuration of a road map generating system according to Modification 1. DETAILED DESCRIPTION

[0025] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0026] <Outline>

[0027] The map generation device of the embodiment is configured to generate a map (an environmental map described later) used when a vehicle having, for example, an autonomous driving function (autonomous driving vehicle) is traveling. In the following description, a vehicle equipped with the map generation device of the embodiment is sometimes referred to as the subject vehicle, as distinguished from other vehicles.

[0028] The map generation device generates a map when the driver manually drives the vehicle. Therefore, the map generation device can also be provided in a vehicle that does not have an automatic driving function (a manually driven vehicle).

[0029] The map generation device generates an environmental map composed of three-dimensional point cloud data using the detection values ​​detected by the external sensor group described later while the vehicle is traveling. For example, from the camera image obtained by the camera constituting the external sensor group, the edge showing the outline of the object as the feature is extracted based on the brightness and color information of each pixel, and the feature point is extracted using the edge information. Feature points are, for example, points on the edge and the intersection of the edges, corresponding to road lines on the road surface, corners of buildings, corners of road signs, etc. The map generation device calculates the distance from the vehicle to the above-mentioned feature points using the laser radar (LiDAR: Light Detection and Ranging) and radar (Radar) constituting the external sensor group, records the feature points on the environmental map, and generates an environmental map of the surrounding area of ​​the road where the vehicle has traveled.

[0030] It should be noted that the map generation device can be provided not only on a manually driven vehicle, but also on an autonomous driving vehicle that can switch from an autonomous driving mode that does not require a driver's driving operation to a manual driving mode that requires a driver's driving operation. The map generation device is described below using the case where the map generation device is provided on an autonomous driving vehicle.

[0031] <Example of Deformed Intersection>

[0032] Figure 1 This is a schematic diagram illustrating an intersection where the entrance to the intersection and the exit from the intersection are offset, in other words, a deformed intersection where the position of the driving lane leading to the entrance to the intersection is extended into the intersection and the position of the exit of the intersection is offset. It is assumed that in the intersection surrounded by the rectangular dotted line, there is no guide line (including road markings and road cones) for guiding the driving path in the intersection.

[0033] The roads set up in the upper and lower directions across the intersection are roads with two lanes on each side, for a total of four lanes. Figure 1In the example, when the vehicle 101 traveling upward in the first lane and the other vehicle 102 traveling upward in the second lane are traveling straight at the intersection, it is correct for them to travel upward in the intersection along the paths L101 and L102 indicated by the arrows, respectively.

[0034] When the vehicle 101 and other vehicles 102 traveling in the first lane and the second lane in the automatic driving mode are traveling straight at the above-mentioned intersection, the map generation device of the embodiment estimates the lane shape in the intersection by traveling along the paths L101 and L102 in the intersection, and generates an environment map including the estimated lane shape. The following describes such a map generation device in detail.

[0035] <Autonomous driving vehicles>

[0036] First, the structure of the autonomous driving vehicle is described. The vehicle may be an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a driving motor as a driving source, or a hybrid vehicle having an engine and a driving motor as driving sources. Figure 2 This is a block diagram illustrating a schematic configuration of a vehicle control system 100 including a map generating device according to an embodiment.

[0037] like Figure 2 As shown, the vehicle control system 100 mainly includes a controller 10 and an external sensor group 1, an internal sensor group 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, which are respectively connected to the controller 10 for communication via CAN (Controller Area Network) communication lines.

[0038] The external sensor group 1 is a general term for a plurality of sensors (external sensors) that detect peripheral information of the vehicle, i.e., external conditions. The external sensor group 1 includes, for example, a camera having an imaging element (image sensor) such as a CMOS (complementary metal oxide semiconductor) sensor to capture the periphery (front, rear, and sides) of the vehicle, a laser radar that detects the position of an object in the periphery of the vehicle (the distance from the vehicle, direction, etc.) by irradiating a laser beam and detecting reflected light, and a radar that detects the position of an object in the periphery of the vehicle by irradiating an electromagnetic wave and detecting reflected waves.

[0039] The internal sensor group 2 is a general term for a plurality of sensors (internal sensors) for detecting the driving state of the vehicle. The internal sensor group 2 includes, for example, a vehicle speed sensor for detecting the vehicle speed, an acceleration sensor for detecting the acceleration of the vehicle in the front-rear direction and the left-right direction, a rotation speed sensor for detecting the rotation speed of the driving source, etc. The internal sensor group 2 also includes sensors for detecting 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.

[0040] The input / output device 3 is a general term for devices for inputting commands from the driver and outputting information to the driver. For example, the input / output device 3 includes various switches for the driver to input various commands by operating the operating member, a microphone for the driver to input commands by voice, a display that provides information to the driver by displaying images, a speaker that provides information to the driver by sound, etc.

[0041] The positioning unit 4 has a positioning sensor that receives a positioning signal sent from a positioning satellite, and uses the positioning information received by the positioning sensor to determine the current position (latitude, longitude, altitude) of the vehicle. The positioning satellite is an artificial satellite such as a GPS satellite or a quasi-zenith satellite. The positioning sensor may also be included in the internal sensor group 2. In addition, the positioning unit 4 may also be referred to as a GNSS (Global Navigation Satellite System) unit.

[0042] The map database 5 is a device that stores general map information used in the navigation device 6 and is composed of, for example, a hard disk or a semiconductor device. The map information includes road position information, road shape information (curvature, etc.), and intersection and fork position information.

[0043] It should be noted that the map information stored in the map database 5 is different from the map information of the high-precision environment map stored in the storage unit 12 of the controller 10 .

[0044] The navigation device 6 is a device that searches for a target path on the road leading to the destination input by the driver and guides the driver along the target path. The input of the destination and the guidance along the target path are performed through the input / output device 3. The target path is calculated based on the current position of the vehicle measured by the positioning unit 4 and the map information stored in the map database 5. The current position of the vehicle can also be measured using the detection value of the external sensor group 1, and the target path can also be calculated based on the current position and the environmental map information stored in the storage unit 12.

[0045] The communication unit 7 communicates with various servers (not shown) through a network including a wireless communication network represented by the Internet, a mobile phone network, etc., and obtains map information, driving history information of other vehicles, traffic information, etc. from the server regularly or at any time. The network includes not only a public wireless communication network, but also a closed communication network set up in each specified management area, such as a wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. When the map information obtained is the above-mentioned general map information, the map of the map database 5 is updated. In addition, when the map information obtained is environmental map information, the environmental map of the storage unit 12 is updated. The communication unit 7 can also communicate with other vehicles.

[0046] The actuator AC is a driving actuator for controlling the driving of the vehicle. When the driving source is an engine, the actuator AC includes a throttle actuator for adjusting the opening of the throttle valve of the engine (throttle opening). When the driving source is a driving motor, the driving motor is included in the actuator AC. The brake actuator that operates the braking device of the vehicle and the steering actuator that drives the steering device are also included in the actuator AC.

[0047] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having a computing unit 11 such as a CPU (microprocessor), a storage unit 12 such as a ROM (read-only memory) and a RAM (random access memory), and other peripheral circuits not shown in the figure, such as an I / O (input / output) interface. It should be noted that multiple ECUs with different functions, such as an engine control ECU, a travel motor control ECU, and a brake device ECU, can be separately set up, but for convenience, Figure 2 The controller 10 is shown in FIG. 1 as a collection of these ECUs.

[0048] The storage unit 12 stores high-precision environmental map information. The environmental map includes: road location information, road shape information (curvature, etc.), road slope information, intersection and fork location information, lane number information (also called driving lanes), lane width and each lane location information (lane center position, lane boundary information), location information of landmarks (signals, signs, buildings, etc.) as marks on the map, road surface contour information such as road surface unevenness, etc.

[0049] The storage unit 12 stores an environment map (data thereof) and reliability information indicating the reliability of the environment map as environment map information. The storage unit 12 can also store driving trajectory information indicating a driving trajectory based on detection values ​​of the external sensor group 1 and the internal sensor group 2.

[0050] The calculation unit 11 includes a vehicle position recognition unit 13 , an outside world recognition unit 14 , an action plan generation unit 15 , and a travel control unit 16 as functional components.

[0051] The vehicle position recognition unit 13 recognizes the position of the vehicle on the map (vehicle position) based on the position information of the vehicle acquired by the positioning unit 4 and the map information of the map database 5. In addition, the vehicle position can 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, so that the vehicle position can be recognized with high accuracy.

[0052] It should be noted that, when the position of the vehicle can be measured by an external sensor installed on the road or beside the road, the position of the vehicle may be identified by communicating with the sensor via the communication unit 7 .

[0053] The vehicle position recognition unit 13 also performs the position estimation processing of the vehicle in parallel with the map generation processing of the map generation unit 114 described later. Position estimation refers to estimating the position of the vehicle based on the change of the position of the ground object (feature point) over time. For example, the signal from the external sensor group 1 (camera, laser radar) is used to perform the map making processing and the position estimation processing simultaneously according to the SLAM (Simultaneous Localization and Mapping) algorithm.

[0054] The external recognition unit 14 recognizes the external conditions around the vehicle based on the signal from the external sensor group 1. For example, it recognizes the position, speed, acceleration of surrounding vehicles (front vehicles, rear vehicles) traveling around the vehicle, the position of surrounding vehicles parked or parked around the vehicle, and the position and status of other objects. Other objects include: signs, traffic lights, road markings or stop lines, buildings, guardrails, telephone poles, billboards, pedestrians, bicycles, etc. The status of other objects includes: the color of the traffic light (red, green, yellow), the moving speed and direction of pedestrians and bicycles, etc. Road markings should include white lines (including lines of different colors such as yellow), curb lines, road spikes, etc., which can also be called lane markings (Lanemark).

[0055] The action plan generation unit 15 generates a driving trajectory (target trajectory) of the vehicle from the current time point to a predetermined time based on, for example, the target path calculated by the navigation device 6, the map information stored in the map database 5 (or the environmental map information stored in the storage unit 12), the vehicle position identified by the vehicle position recognition unit 13, and the external conditions identified by the external recognition unit 14. When there are multiple trajectories as candidates for the target trajectory on the target path, the action plan generation unit 15 selects the best trajectory that complies with the law and satisfies the criteria such as efficient and safe driving, and uses the selected trajectory as the target trajectory. Then, the action plan generation unit 15 generates an action plan corresponding to the generated target trajectory. The action plan generation unit 15 generates various action plans corresponding to overtaking driving for overtaking a preceding vehicle, lane change driving for changing the driving lane, following driving for following a preceding vehicle, lane keeping driving for keeping the lane without deviating from the driving lane, deceleration driving or acceleration driving, etc. When generating the target trajectory, the action plan generation unit 15 first determines the driving mode and generates the target trajectory according to the driving mode.

[0056] In the automatic driving mode, the driving control unit 16 controls each actuator AC so that the vehicle travels along the target trajectory generated by the action plan generation unit 15. More specifically, in the automatic driving mode, the driving control unit 16 takes into account the driving resistance determined by the road slope, etc., and calculates the required driving force for obtaining the target acceleration per unit time calculated by the action plan generation unit 15. Then, for example, the actuator AC is feedback-controlled so that the actual acceleration detected by the internal sensor group 2 becomes the target acceleration. That is, the actuator AC is controlled so that the vehicle travels at the target vehicle speed and target acceleration. It should be noted that when the driving mode is the manual driving mode, the driving control unit 16 controls each actuator AC according to the driving instructions (steering operation, etc.) from the driver obtained by the internal sensor group 2.

[0057] <Map Generator>

[0058] Figure 3 1 is a block diagram showing a main part structure of a map generating device 50 according to an exemplary embodiment. The map generating device 50 includes Figure 2 In the vehicle control system 100. Figure 3 In the figure, the map generating device 50 includes a camera 1a, a laser radar 1b, a sensor 2a, and a controller 10.

[0059] Camera 1a is a single-lens reflex camera having an image sensor such as a CMOS sensor. Figure 2The camera 1a is one of the external sensor groups 1. The camera 1a may also be a stereo camera. The camera 1a is installed at a predetermined position in front of the vehicle, continuously captures the space in front of the vehicle at a predetermined frame rate, and obtains images (camera images) of the surrounding vehicles and other objects.

[0060] It should be noted that the object can also be detected by laser radar 1b or the like together with camera 1a or instead of camera 1a.

[0061] The laser radar 1b is also one of the external sensor groups 1. The laser radar 1b is installed facing the front of the vehicle so that the area to be paid attention to during driving is included in the field of view (hereinafter referred to as FOV) of the laser radar 1b. The laser radar 1b intermittently irradiates a laser beam to multiple detection points (also referred to as irradiation points) within the FOV, and obtains point information of the irradiated laser beam reflected (scattered) back at a certain point on the surface of the object for each detection point. The point information includes the distance from the laser light source (this vehicle) to the point, the intensity of the reflected (scattered) laser beam, and the relative speed between the laser light source and the point. In an embodiment, the data composed of the point information of multiple detection points within the FOV is referred to as point cloud data. The laser radar 1b continuously obtains point cloud data with a specified number of frames (the number of detection points within the FOV) at a specified frame rate.

[0062] The sensor 2a is a detector for calculating the movement amount and movement direction of the vehicle. The sensor 2a is a 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 movement amount of the vehicle, and integrates the yaw rate detected by the yaw rate sensor to calculate the yaw angle, and estimates the position of the vehicle using the odometry method when generating a map. It should be noted that the configuration of the sensor 2a is not limited to this, and the position of the vehicle can also be estimated using information from other sensors.

[0063] Figure 3 The controller 10 includes a driving track acquisition unit 111, a curvature calculation unit 112, a lane shape estimation unit 113, and a map generation unit 114 as the computing unit 11 ( Figure 2 ) is the functional structure undertaken by the

[0064] The storage unit 12 stores environmental map information as described above. The environmental map stored in the storage unit 12 includes: an environmental map obtained from the outside of the vehicle via the communication unit 7 (also referred to as an external environmental map), identification information of the external identification unit 14, and an environmental map generated by the map generation unit 114 using 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 (also referred to as an internal environmental map). The external environmental map is, for example, an environmental map obtained via a cloud server, and the internal environmental map is an environmental map generated by mapping using the above-mentioned SLAM and other technologies. The external environmental map is shared by the vehicle and other vehicles, whereas the internal environmental map is a map owned exclusively by the vehicle.

[0065] The storage unit 12 may further store driving trajectory information showing the driving trajectory.

[0066] In addition, the storage unit 12 may store information on programs of various controls, threshold values ​​used by the programs, and the like.

[0067] The external recognition unit 14 recognizes, for example, a curb, wall, ditch, guardrail, or road marking indicating a road boundary as a road boundary line based on the camera image obtained by the camera 1a, and recognizes the road structure represented by the road boundary line. As described above, the road marking line includes white lines (including lines of different colors), curb lines, road spikes, etc., and the driving lanes of the road are defined by markings such as these road marking lines.

[0068] It should be noted that an example is disclosed in which the outside world recognition unit 14 recognizes the area sandwiched by the road boundary lines as the area corresponding to the road, but the method of recognizing the road is not limited to this, and other methods may be used for recognition.

[0069] (Driving track acquisition unit)

[0070] The driving track acquisition unit 111 acquires the driving track of the host vehicle 101. The position information (time-sequential position information) of the host vehicle 101 measured by the positioning unit 4 during the driving of the host vehicle 101 is temporarily recorded (also referred to as stored) in the storage unit 12. The driving track acquisition unit 111 acquires the driving track of the host vehicle 101 by reading and calculating the time-sequential position information stored in the storage unit 12.

[0071] It should be noted that the configuration may also be such that the time-series sensor data measured by the wheel speed sensor and the steering angle sensor constituting the internal sensor group 2 during the driving of the host vehicle 101 is temporarily recorded in the storage unit 12. The driving track acquisition unit 111 acquires the driving track of the host vehicle 101 by reading and calculating the time-series sensor data stored in the storage unit 12.

[0072] The traveling track information indicating the traveling track acquired by the traveling track acquisition unit 111 can be stored in advance in the storage unit 12 as described above.

[0073] When the time-series position information based on the driving trajectory information read from the storage unit 12 is arranged in time sequence on a two-dimensional map (the vertical axis is the driving direction (also called the depth direction) and the horizontal axis is the road width direction), the position information is discretely connected in the driving direction. An approximate curve based on discrete points in the driving direction is calculated for each driving opportunity, thereby obtaining an approximate curve corresponding to the driving interval for the number of times the vehicle has traveled in the driving interval.

[0074] Figure 4A This is a schematic diagram showing a travel trajectory of a travel section including an intersection on the two-dimensional map viewed from above. Figure 4A The up and down direction in corresponds to the traveling direction observed from the vehicle 101. Figure 4A The left and right directions in correspond to the road width direction observed from the vehicle 101. The area surrounded by the dotted lines of the rectangle is within the intersection. The road marking lines L1 to L3 respectively define the first lane and the second lane before entering the intersection, and the road marking lines L1′ to L3′ respectively define the first lane and the second lane after exiting the intersection.

[0075] The n driving trajectories P1, P2, ... Pn show the Figure 4A The driving trajectory M corresponds to the average value of the driving trajectories P1, P2, ..., Pn.

[0076] The curvature calculation unit 112 described later uses the average value of a plurality of approximate curves corresponding to the number of times the travel is performed as the travel trajectory M.

[0077] (Curvature calculation unit)

[0078] The curvature calculation unit 112 calculates the curvature (lane curvature) of the driving trajectory of the host vehicle 101, etc. in a specific scene based on the driving trajectory information read from the storage unit 12. The specific scene is, for example, an intersection without a driving lane mark, a merging area after passing through a gate on a highway, etc. More specifically, the curvature calculation unit 112 calculates a driving trajectory M as an average value of the driving trajectories P1, P2, ..., Pn, and calculates the curvature of the driving trajectory M, based on excluding statistical outliers (specific data) in the driving trajectory information.

[0079] Outliers can also be eliminated using, for example, a RANSAC (Random Sample Consensus) algorithm to eliminate position information separated from other position information by a predetermined distance or more in a direction intersecting the traveling direction (road width direction).

[0080] Figure 4B This is a schematic diagram for explaining the distribution of driving trajectories with outliers excluded. The vertical axis shows the number of occurrences, and the horizontal axis shows the position coordinates in the road width direction. In the embodiment, the driving trajectory of the same section on the road obtained by the driving trajectory acquisition unit 111 corresponds to n samples, and the average value (sample average) μ of the n samples corresponds to the average value of the driving trajectory of the section, that is, the driving trajectory M.

[0081] (Lane shape estimation unit)

[0082] The lane shape estimating 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.

[0083] <Estimation Example 1>

[0084] Figure 5A 1 is a schematic diagram for explaining lane shape estimation example 1. The specific scenario is that there is no lane marking. Figure 5A In an intersection such as the one illustrated, when the curvature of the driving trajectory M calculated by the curvature calculation unit 112 is greater than a specified value, the lane shape estimation unit 113 estimates the lane shape in the intersection based on an approximate curve calculated based on the driving trajectory M and the lane shapes at the entrance and exit of the intersection.

[0085] Figure 5B It is shown Figure 5A The vertical axis shows the curvature of the driving trajectory M, and the horizontal axis shows the distance in the direction of travel. Figure 5A The curvature of the part enclosed by circle R1 corresponds to Figure 5B The part enclosed by circle C1 is Figure 5A The curvature of the part enclosed by circle R2 corresponds to Figure 5B The part of the circle C2 in Figure 5B Since the median curvature exceeds a predetermined threshold value, the lane shape estimating unit 113 estimates the lane shape in the intersection based on the approximate curve calculated based on the driving trajectory M and the lane shapes at the entrance and exit of the intersection.

[0086] Fig. 6A is a schematic diagram further illustrating the method of estimating Example 1 in detail. Fig. 6AIn the figure, the distance between the road marking line L1 defining the first lane at the entrance of the intersection and the driving track M is referred to as the left distance. In addition, the distance between the road marking line L2 defining the first lane at the entrance of the intersection and the driving track M is referred to as the right distance.

[0087] Likewise, the distance between the road marking line L1' defining the first lane at the exit of the intersection and the driving track M is called the left distance. Also, the distance between the road marking line L2' defining the first lane at the exit of the intersection and the driving track M is called the right distance.

[0088] Figure 6B : is a diagram illustrating a 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 is based on Fig. 6A The distances between the driving trajectory M at the entrance and exit of the intersection and the road marking lines L1, L2 and road marking lines L1', L2' set at the entrance and exit as the left and right lane boundaries are estimated by linear approximation from the entrance to the exit of the intersection and from the driving trajectory M in the intersection to the left and right virtual lane boundaries. Then, the curved lane shape in the intersection (in other words, the left and right virtual lane boundaries) is estimated by a nonlinear approximation curve using the discrete points of the left and right virtual lane boundaries calculated based on the distance estimated by linear approximation.

[0089] It should be noted that in Figure 5A and Figure 5B , an example is shown in which the curvatures at two locations within the intersection exceed the prescribed threshold value. However, when the curvature at least at one location within the intersection exceeds the prescribed threshold value, the lane shape estimating unit 113 estimates the lane shape within the intersection using the method described in Estimation Example 1.

[0090] <Estimation Example 2>

[0091] Fig. 7A 2 is a schematic diagram for explaining lane shape estimation example 2. The specific scenario is that there is no lane marking. Fig. 7A In the intersection as illustrated, when the curvature of the driving trajectory M calculated by the curvature calculation unit 112 is lower than a predetermined value, the lane shape estimation unit 113 estimates the lane shape in the intersection based on the approximate curve calculated based on the lane shapes at the entrance and exit of the intersection.

[0092] For example, left and right approximate curves (in Fig. 7AThe left and right virtual lane boundaries connect the lane shape of the first lane defined by the road markings L1 and L2 as the left and right lane boundaries set at the entrance and the lane shape of the first lane defined by the road markings L1′ and L2′ as the left and right lane boundaries set at the exit.

[0093] <Estimation Example 3>

[0094] Figure 7B 3 is a schematic diagram for explaining lane shape estimation example 3. Figure 7B In the case of an intersection as exemplified, the lane shape estimating unit 113 estimates the lane shape in the intersection based on the lane shapes at the entrance and exit of the intersection and the approximate curve calculated based on the guide signs.

[0095] For example, left and right approximate curves (in Fig. 7A The left and right virtual lane boundary lines respectively connect the lane shape of the first lane defined by the road marking lines L1 and L2 as left and right lane boundary lines set at the entrance and the lane shape of the first lane defined by the left and right guide lines G1 and G2 as guide signs set at the intersection and the lane shape of the first lane defined by the road marking lines L1′ and L2′ as left and right lane boundary lines set at the exit.

[0096] (Map Generation Department)

[0097] The map generation unit 114 generates an environmental map including position information showing the positions of features such as road markings on the road surface while driving in the manual driving mode. Specifically, an internal environmental map composed of three-dimensional point cloud data is generated. The map generation unit 114 extracts feature points of features, such as those recognized by the external recognition unit 14, from the camera image obtained by the camera 1a. The map generation unit 114 also uses the ranging value based on the camera image or the detection value of the laser radar 1b to calculate the distance from the vehicle to the feature point, and starting from the position of the vehicle on the environmental map estimated by the vehicle position recognition unit 13, the feature points are sequentially drawn at positions separated by the above-calculated distances, thereby generating an environmental map of the surrounding area of ​​the road on which the vehicle has traveled.

[0098] It should be noted that, as described above, the map generation unit 114 is not limited to the case where the vehicle is traveling in the manual driving mode, and can also perform the map generation process when traveling in the automatic driving mode in the same manner as in the manual driving mode.

[0099] Furthermore, the map generation unit 114 includes (adds) information indicating the lane shape estimated by the lane shape estimation unit 113 in relation to the above-mentioned specific scene in the above-mentioned environment map.

[0100] <Explanation of the flow chart>

[0101] Figure 8 It shows that according to a predetermined procedure Figure 3 Flowchart of an example of a process executed by the controller 10. The process shown in the flowchart is repeated at a predetermined cycle during driving in the manual driving mode, for example, to generate an environment map.

[0102] exist Figure 8 In S10 (S: processing step), the controller 10 obtains sensor information from the camera 1a, the laser radar 1b and the sensor 2a, and enters S20.

[0103] In S20, the controller 10 determines whether there is no guide sign in the intersection. If there is no guide sign, the controller 10 determines S20 as positive (S20: Yes) and proceeds to S30. If there is a guide sign, the controller 10 determines S20 as negative (S20: No) and proceeds to S100.

[0104] In S30, the controller 10 obtains the driving trajectory and proceeds to S40. As described above, the driving trajectory information is stored in the storage unit 12. In S40, the controller 10 calculates the average value of the driving trajectory, that is, the curvature of the driving trajectory M, through the curvature calculation unit 112 and proceeds to S50.

[0105] In S50, the controller 10 determines whether the curvature is greater than a predetermined threshold value. If the curvature is greater than the predetermined threshold value, the controller 10 determines S50 as positive (S50: Yes) and proceeds to S60. If the curvature is less than the predetermined threshold value, the controller 10 determines S50 as negative (S50: No) and proceeds to S90.

[0106] In S60, the controller 10 estimates the lane shape of the intersection based on the driving trajectory M and the shape of the entrance and exit of the intersection by the lane shape estimation unit 113, and then proceeds to S70. The estimation in S60 corresponds to the estimation example 1 described above.

[0107] In S70 , the controller 10 adds information indicating the lane shape estimated in S60 to the environment map via the map generation unit 114 , and the process proceeds to S80 .

[0108] In S80, the controller 10 records the environment map to which the information showing the lane shape is added as environment map information in the storage unit 12, and ends. Figure 8 processing.

[0109] In S90 where S50 is determined to be negative (S50: No), the controller 10 estimates the lane shape of the intersection based on the shape of the entrance and exit of the intersection by the lane shape estimation unit 113, and then proceeds to S70. The estimation in S90 corresponds to the estimation example 2 described above.

[0110] In S100 where S20 is determined to be negative (S20: No), the controller 10 estimates the lane shape of the intersection based on the entrance and exit of the intersection and the guide signs of the intersection by the lane shape estimation unit 113, and then proceeds to S70. The estimation in S100 conforms to the estimation example 3 described above.

[0111] The above-described embodiment has the following effects.

[0112] (1) The map generating device 50 includes: a storage unit 12 that stores driving trajectory information indicating a driving trajectory M of the host vehicle 101; an external environment recognition unit 14 that recognizes the surrounding conditions of the host vehicle 101; a curvature calculation unit 112 that calculates the curvature of the driving trajectory M in the intersection based on the driving trajectory information read from the storage unit 12 when an environment map as driving map information in the intersection as a specific scene is not obtained; a lane shape estimation unit 113 that estimates the lane shape in 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 environment map.

[0113] Because of this configuration, for example, in the absence of an environmental map serving as map information for driving within an intersection, an appropriate lane shape within an intersection estimated based on the curvature of a driving trajectory M actually traveled through the intersection can be added to the environmental map, where no guide lines such as road surface markings or road cones are provided within the intersection for guiding the driving path within the intersection.

[0114] (2) According to the map generating device 50 of (1) above, in a specific scenario where a guide line or the like is not provided as a guide mark for guiding the driving path, the curvature calculating unit 112 calculates the curvature of the average value (driving trajectory M) of the driving trajectory in the intersection based on the driving trajectory information, and the lane shape estimating unit 113 estimates the lane shape in the intersection based on an approximate curve calculated based on the driving trajectory M and the lane shape at the entrance and exit of the intersection when the curvature calculated by the curvature calculating unit 112 is greater than a specified value, and the map generating unit 114 adds the lane shape in the intersection estimated by the lane shape estimating unit 113 to the environment map.

[0115] Because of this structure, for example, since the entrance and exit of the intersection are misaligned (also called offset) in a direction intersecting the direction of travel, for intersections where the average value of the driving trajectory in the intersection, that is, the curvature of the driving trajectory M, becomes greater than a specified value, the lane shape in the intersection can be appropriately estimated and added to the environmental map.

[0116] (3) According to the map generating device 50 of (2) above, the lane shape estimating unit 113 linearly approximates the change in distance from the entrance to the exit and from the average value of the driving trajectory in the intersection to the left and right virtual lane boundaries, based on the average value of the driving trajectory at the entrance and exit of the intersection obtained based on the driving trajectory information and the distance between the left and right lane boundaries set at the entrance and exit, and estimates the lane shape in the intersection through a nonlinear approximation curve using discrete points of the left and right virtual lane boundaries calculated based on the distance estimated by the linear approximation. The map generating unit 114 adds the lane shape in the intersection estimated by the lane shape estimating unit 113 to the environment map.

[0117] With this configuration, the lane shape in the intersection that is less deviated from the driving trajectory of the host vehicle 101 and closer to the actual driving trajectory can be appropriately estimated based on the curvature of the driving trajectory M, which is the average value of the driving trajectory, and added to the environment map.

[0118] (4) According to the map generating device 50 of (1) above, the specific scenario is an intersection where no guide signs for guiding the driving path are set. The curvature calculation unit 112 calculates the curvature of the average value of the driving trajectory in the intersection based on the driving trajectory information. When the curvature calculated by the curvature calculation unit 112 is lower than a specified value, the lane shape estimation unit 113 estimates the lane shape in the intersection based on an approximate curve calculated based on the lane shape of the entrance and exit of the intersection. The map generating unit 114 adds the lane shape in the intersection estimated by the lane shape estimation unit 113 to the environment map.

[0119] Because of this structure, for intersections where the average value of the driving trajectory in the intersection, that is, the curvature of the driving trajectory M, does not exceed the specified value, the lane shape in the intersection can be appropriately estimated and added to the environmental map while reducing the calculation load, compared with the estimation calculation in the above cases (2) and (3).

[0120] (5) According to the map generating device 50 of (2) to (4) above, in a specific scenario, an intersection is provided with guide signs for guiding the driving path (for example, in addition to road surface signs, it also includes objects such as road cones), and the lane shape estimating unit 113 estimates the lane shape in the intersection based on the lane shape at the entrance and exit of the intersection and the approximate curve calculated by the guide signs, and the map generating unit 114 adds the lane shape in the intersection estimated by the lane shape estimating unit 113 to the environment map.

[0121] With this configuration, even at an intersection where road surface markings or guide lines such as road cones are provided to guide the travel path at the intersection, the shape of the lane in the intersection can be appropriately estimated and added to the environment map.

[0122] (6) According to the map generation device 50 of (1) to (4) above, the curvature calculation unit 112 detects statistical outliers from a plurality 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 are excluded.

[0123] Because of this structure, by excluding irregular driving trajectory information that is different from the normal ones (for example, behavior of avoiding obstacles in the intersection, behavior of giving way to emergency vehicles in the intersection, etc.) as outliers, the lane shape in the intersection can be estimated more appropriately.

[0124] The above-mentioned embodiment can be modified into various forms. Modifications will be described below.

[0125] (Variant 1)

[0126] In the embodiment, an example is described in which the driving track acquisition unit 111 independently acquires the driving track information of the host vehicle 101, but in Modification 1, an example is described in which the driving track information of other vehicles 102 other than the host vehicle 101 is acquired through a cloud server. That is, in Modification 1, the driving track information is shared among a plurality of vehicles.

[0127] Fig. 9 FIG. 4 is a diagram illustrating a configuration of a road map generation system 400 according to Modification 1. Fig. 9 In the embodiment, the road map generation system 400 includes a server 200 connected to a communication network 300, a vehicle control system 100a and a vehicle control system 100b configured to be communicably 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.

[0128] The server 200 is operated by, for example, a business providing a driving trajectory information sharing service, etc. The configuration of the vehicle control systems 100a and 100b is the same as that of the vehicle control system 100 in the above-described embodiment.

[0129] The vehicle control systems 100 a and 100 b are connected to a communication network 300 such as a wireless communication network, the Internet, and a telephone network via the communication unit 7 , respectively.

[0130] Fig. 9 Two vehicles, namely, the own vehicle 101 and the other vehicle 102 are shown in the figure, but the number of vehicles connectable to the communication network 300 is not limited to two, and a plurality of vehicles may exist.

[0131] The vehicle control systems 100a and 100b of the vehicle 101 and other vehicles 102 respectively transmit the driving track information of the vehicle stored in the storage unit 12 together with the vehicle model information of the vehicle to the server 200 via the communication unit 7 at a predetermined transmission period. The vehicle model information may be at least information capable of identifying the size of a vehicle such as a sedan (also referred to as a general vehicle), a bus, a truck, or a two-wheeled vehicle. In addition, the driver may appropriately set the transmission period, such as once a week, or in units of a specified driving distance.

[0132] When the server 200 receives the travel track information from the vehicle control systems 100 a and 100 b mounted on the host vehicle 101 and the other vehicles 102 , the server 200 stores the travel track information in a database (not shown) for example, according to the size of the vehicle.

[0133] In addition, when the server 200 receives a request for driving trajectory information from the vehicle control systems 100a, 100b mounted on the present vehicle 101 and other vehicles 102, it reads the driving trajectory information of the vehicle corresponding to the size of the requesting party's vehicle from the driving trajectory information in a specific scene of the area where the requesting party's vehicle is driving from the above-mentioned database, and sends it to the requesting party's vehicle.

[0134] The controller 10 of the vehicle 101 or the like in the case of the first modification is Figure 8 When the driving trajectory is obtained in S30, the driving trajectory information of the vehicle 101 etc. in the driving area is requested from the server 200. At this time, the position information of the vehicle 101 etc. and the vehicle model information of the vehicle 101 etc. are notified to the server 200. Thus, the server 200 can send the driving trajectory information of the vehicle corresponding to the size of the requesting vehicle to the requesting vehicle.

[0135] The road map generation system 400 described in the above-described variant example 1 includes a server 200, which is a server device that obtains 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 and the like calculates the curvature of the driving trajectory in a specific scenario based on the driving trajectory information from multiple vehicles stored in the database of the server 200.

[0136] With such a configuration, by acquiring the travel trajectory information of other vehicles 102 and the like other than the host vehicle 101 , it is possible to estimate the lane shape in the intersection with higher reliability.

[0137] Furthermore, since a large amount of driving trajectory information can be acquired, when statistical values ​​are used for calculations, statistical data close to true values ​​can be obtained.

[0138] Furthermore, by obtaining the driving trajectory information of the vehicle corresponding to the size of the requesting party's vehicle, the driving trajectory information of other vehicles with different vehicle widths, inner wheel differences, etc. can be excluded, and the driving trajectory information that matches the actual driving state of the vehicle of the requesting party's size can be obtained. As a result, the lane shape in the intersection can be estimated with higher reliability.

[0139] (Variant 2)

[0140] The curvature of the driving track in a specific scene may also be calculated based on the driving track information of vehicles other than two-wheeled vehicles among the driving track information of 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 driving track in a specific scene based on the driving track information of vehicles other than two-wheeled vehicles.

[0141] Because of this configuration, the travel trajectory of two-wheeled vehicles that generally travel on the road side can be excluded, and the curvature can be calculated using only the travel trajectory far from the road side, so the curvature of the travel trajectory that matches the actual travel state of vehicles other than two-wheeled vehicles can be calculated. As a result, the lane shape in the intersection can be estimated with higher reliability.

[0142] One or more of the above-described embodiments and modifications may be arbitrarily combined, and modifications may be combined with each other.

[0143] According to the present invention, in a specific scene such as a deformed intersection, an appropriate lane shape can be added to a driving map.

[0144] The present invention has been described above in conjunction with preferred embodiments, but it should be understood by those skilled in the art that various modifications and changes can be made without departing from the scope of the claims.

Claims

1. A map generating device, characterized in that: have: A storage unit (12) storing driving track information showing a driving track of a vehicle; an identification unit (14) for identifying the conditions around the vehicle; a curvature calculation unit (112) for calculating the curvature of the driving track in the specific scene based on the driving track information read from the storage unit (12) when the driving map information in the specific scene is not obtained; an estimating unit (113) for estimating a lane shape of the specific scene based on the curvature calculated by the curvature calculating unit (112); as well as A map generating unit (114) adds the lane shape estimated by the estimating unit (113) to the driving map information.

2. The map generating device according to claim 1, characterized in that: The specific scenario is an intersection where no guide signs for guiding the driving path are set. The curvature calculation unit (112) calculates the curvature of the average value of the driving trajectory in the intersection based on the driving trajectory information. The estimating unit (113) estimates the shape of the lane in the intersection based on an approximate curve calculated based on an average value of the driving trajectory and the shape of the lane at the entrance and exit of the intersection when the curvature calculated by the curvature calculating unit (112) is greater than a predetermined value. The map generation unit (114) adds the lane shape in the intersection estimated by the estimation unit (113) to the driving map information.

3. The map generating device according to claim 2, characterized in that: The estimating unit (113) performs linear approximation on the change in distance from the entrance to the exit and from the average value of the driving trajectory in the intersection to the left and right virtual lane boundaries, based on the average value of the driving trajectory at the entrance and the exit of the intersection obtained based on the driving trajectory information and the distance between the left and right lane boundaries set at the entrance and the exit, and estimates the lane shape in the intersection through a nonlinear approximation curve using discrete points of the left and right virtual lane boundaries calculated based on the distance estimated by the linear approximation. The map generation unit (114) adds the lane shape in the intersection estimated by the estimation unit (113) to the driving map information.

4. The map generating device according to claim 1, characterized in that: The specific scenario is an intersection where no guide signs for guiding the driving path are set. The curvature calculation unit (112) calculates the curvature of the average value of the driving trajectory in the intersection based on the driving trajectory information. The estimating unit (113) estimates the shape of the lane in the intersection based on an approximate curve calculated based on the shape of the lane at the entrance and exit of the intersection when the curvature calculated by the curvature calculating unit (112) is lower than a predetermined value. The map generation unit (114) adds the lane shape in the intersection estimated by the estimation unit (113) to the driving map information.

5. The map generating device according to any one of claims 2 to 4, characterized in that: The specific scene is an intersection with guide signs for guiding the driving path. The estimating unit (113) estimates the lane shape in the intersection based on the lane shape at the entrance and exit of the intersection and the approximate curve calculated based on the guide sign. The map generation unit (114) adds the lane shape in the intersection estimated by the estimation unit (113) to the driving map information.

6. The map generating device according to any one of claims 1 to 4, characterized in that: The curvature calculation unit (112) detects statistical outliers from the plurality of driving trajectory information, and calculates the curvature of the driving trajectory in the specific scene based on the driving trajectory information from which the outliers are excluded.

7. The map generating device according to any one of claims 1 to 4, characterized in that: The driving trajectory information indicates a driving trajectory of the vehicle in a manual driving mode that requires a driving operation by a driver.

8. The map generating device according to any one of claims 1 to 4, characterized in that: The driving map information is used in an automatic driving mode that does not require a driving operation by a driver.

9. A map generation system (400), characterized in that: have: The map generating device according to any one of claims 1 to 4; as well as A server device (200) acquires and stores the driving trajectory information from a plurality of vehicles, The curvature calculation unit (112) calculates the curvature of the driving track in the specific scene based on the driving track information of vehicles other than two-wheeled vehicles among the driving track information from the plurality of vehicles stored in the server device (200).

Images