Map generation apparatus

Abstract

To increase the accuracy of map data every time it is updated.SOLUTION: A map generation apparatus 50 comprises: an exterior environment recognition portion 14 that recognizes an exterior environment situation around a subject vehicle ; a map generation portion 111 that generates a map including position information indicating a position of a predetermined feature on the basis of recognition information acquired by the exterior environment recognition portion 14; a calculation portion 112 that calculates the reliability of the generated map for each piece of position information; a storage portion 12 that stores the map and the reliability information indicating the reliability as map information; and an update portion 113 that updates, when at least part of a new map newly generated by the map generation portion 111 is included in an existing map stored in the storage portion 12 as the map information, data of a corresponding section of the existing map corresponding to a generation section of the new map on the basis of the data and the reliability of the new map in the generation section and the data and the reliability of the existing map in the corresponding section.SELECTED DRAWING: Figure 2

Description

[Technical field]

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

[0002] As one example of this type of technology, a map generating device is known that collects information acquired by an on-board sensor mounted on a vehicle and generates a map based on the collected information (see Patent Document 1). In such a map generating device, when updating an existing map that has already been created using newly collected information, it is desirable to not only prevent a decrease in the accuracy of the map data, but also to improve the map data through the update. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2021 / 002190 Summary of the Invention [Problem to be solved by the invention]

[0004] In the conventional technology, difference data is obtained by comparing integrated probe map data obtained by integrating newly collected probe data with existing base map data, and the existing base map data is updated based on average difference data obtained by averaging multiple difference data. Therefore, if there is difference data that contains a lot of errors and is not excluded as temporary difference data, it will have a large effect and the accuracy of the existing base map data will decrease. Preventing degradation of map data accuracy will enable smoother vehicle movement, improving the convenience and safety of transportation, and thereby contributing to the development of a sustainable transportation system. [Means for solving the problem]

[0005] A map generating device according to one aspect of the present invention includes an external environment recognition unit that recognizes the external environment surrounding a vehicle, a map generating unit that generates a map including position information indicating the position of a specified feature based on the recognition information acquired by the external environment recognition unit, a calculation unit that calculates the reliability of the generated map for each piece of position information, a memory unit that stores the map and reliability information indicating the reliability as map information, and an update unit that, when at least a portion of a new map newly generated by the map generating unit is included in an existing map stored in the memory unit as map information, updates data of a corresponding section of an existing map that corresponds to a generated section of the new map based on the data and reliability of the new map of the generated section and the data and reliability of the existing map of the corresponding section. Effect of the Invention

[0006] According to the present invention, it is possible to increase the accuracy of map data with each update. [Brief description of the drawings]

[0007] [Figure 1] 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 2] FIG. 1 is a block diagram illustrating a configuration of a main part of a map generating device according to an embodiment. [Figure 3A] Schematic diagram illustrating the distribution of estimated values ​​of feature positions on a map. [Figure 3B] FIG. 2 is a schematic diagram illustrating an example of the relationship between an existing map, a new map, and an updated map. [Figure 4A] FIG. 2 is a diagram illustrating a scene in which the host vehicle is traveling on a road. [Figure 4B] Schematic diagram of point cloud data displayed on a 2D map. [Diagram 5] 3 is a flowchart showing an example of processing executed by the controller of FIG. 2; [Figure 6A] FIG. 1 is a schematic diagram illustrating a fusion process. [Figure 6B] FIG. 13 is another schematic diagram illustrating the fusion process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Hereinafter, an embodiment of the invention will be described with reference to the drawings. 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] <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. 1 is a block diagram illustrating a schematic configuration of a vehicle control system 100 having a map generating device according to an embodiment.

[0012] As shown in FIG. 1, 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.

[0013] 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.

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having a calculation unit 11 such as a CPU (microprocessor), a storage unit 12 such as a ROM, 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. 1 as a collection of these ECUs for the sake of convenience.

[0022] 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 driving history information indicating a driving trajectory based on the detection values ​​of the external sensor group 1 and the internal sensor group 2.

[0023] 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.

[0024] 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.

[0025] 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 111 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] <Map Generation Device> Fig. 2 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. 1. In Fig. 2, the map generating device 50 has a camera 1a, a lidar 1b, a sensor 2a, and a controller 10.

[0030] 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. 1. 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.

[0031] 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.

[0032] 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.

[0033] The controller 10 in FIG. 2 has a map generating unit 111, a reliability calculating unit 112, and a map updating unit 113 in addition to the memory unit 12 and the external environment recognizing unit 14 as functional components carried out by the calculation unit 11 (FIG. 1).

[0034] 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 111 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 may store information regarding various control programs, thresholds used in the programs, and the like.

[0035] The map generating unit 111 generates an environmental map including position information indicating the positions of features such as dividing lines on the road surface while driving in manual driving mode. Specifically, it generates an internal environmental map consisting of three-dimensional point cloud data. For example, the map generating unit 111 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 111 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 111 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.

[0036] The reliability calculation unit 112 calculates the reliability of the environmental map. For example, the position of the same feature (e.g., a division line, etc.) is measured multiple times, and the reliability of the environmental map is calculated based on the distribution of the measurement positions obtained in each measurement. This reliability calculation method is based on the assumption that "the population from which the sample is extracted has a mean μ and a variance σ 2In the case of , as the number of samples n increases, the distribution of the sample mean changes to mean μ and variance σ 2 / n normal distribution N(μ,σ 2 / n). This is based on the central limit theorem. 3A is a schematic diagram illustrating the distribution of estimated values ​​of the position of a feature on a map. In the embodiment, among detection values ​​of multiple frames acquired by the camera 1a at a predetermined frame rate, position coordinates of the same feature acquired in each frame based on detection values ​​of n frames acquired close in time correspond to n samples, and the average value (sample mean) μ of the n samples corresponds to the estimated position of the feature on the environmental map. The reliability calculation unit 112 calculates the variance σ of the normal distribution N. 2 / n is calculated as reliability information indicating the reliability of the environmental map. 2 The smaller the / n, the higher the reliability, and the variance σ 2 The larger the / n, the lower the reliability.

[0037] The map update unit 113 updates the existing environmental map when an environmental map different from the existing environmental map stored in the storage unit 12 is generated. Specifically, when at least a part of a new environmental map newly generated by the map generation unit 111 is included in the existing environmental map stored in the storage unit 12, the map update unit 113 updates data of a corresponding section of the existing environmental map corresponding to the generation section of the new map, based on data and reliability of the generation section of the new environmental map and data and reliability of the corresponding section of the existing environmental map. In other words, when generating an updated environmental map by fusing the existing environmental map with the new environmental map, priority is given to data of the environmental map with higher reliability (in other words, with smaller variance of the estimated value distribution). In the embodiment, the environmental map generated by the map generation unit 111 and before being used in the update process by the map update unit 113 is called a new map. Moreover, the environmental map stored in the storage unit 12 is called an existing map. The update process refers to merging the new map with the existing map to obtain a new environmental map (called an updated map). Furthermore, when the update map is stored in the storage unit 12, the stored update map is called an existing map.

[0038] FIG. 3B is a schematic diagram illustrating the relationship between an existing map, a new map, and an updated map with respect to the positions of features on the maps. The solid curve, the fine dashed curve, and the coarse dashed curve indicate the distribution of estimated values ​​of the positions of features on the updated map, the existing map, and the new map, respectively. The X bar corresponds to the average value of the position coordinates of the features on the updated map (in other words, the estimated positions of the features). The X1 bar corresponds to the average value of the position coordinates of the features on the existing map (in other words, the estimated positions of the features). The X2 bar corresponds to the average value of the position coordinates of the features on the new map (in other words, the estimated positions of the features).

[0039] During updating, the map update unit 113 obtains updated map data by fusing the data of the existing map and the new map using the following equations (1) to (3).

number

number

[0040] The map update unit 113 calculates the inverse of the variance of the normal distribution N of the existing map, n1 / σ1, as shown in formula (2). 2 The weight w1 for the data of the existing map is used. Also, as shown in equation (3), the inverse of the variance of the normal distribution N of the new map is n2 / σ2 2 Let w2 be the weight for the new map data. The symbols n1 and σ1 respectively indicate the number of samples and the standard deviation of the existing map, and the symbols n2 and σ2 respectively indicate the number of samples and the standard deviation of the new map. As an example, the embodiment illustrates a case where the number of samples of the new map is n2=5. Therefore, the value of the number of samples n1 of the existing map is increased by 5 every time it is updated. The value of the number of samples n2 is not limited to 5 and may be changed as appropriate.

[0041] In the example of Figure 3B, the waveform spread of the normal distribution N of the existing map is narrower than the waveform spread of the normal distribution N of the new map, so the variance σ1 of the normal distribution N of the existing map 2 / n1 is the variance σ2 of the normal distribution N of the new map 2 / n2. Therefore, the weight w1 of the existing map is greater than the weight w2 of the new map, so the update map is more influenced by the existing map than the new map. Conversely, the influence of the new map on the update map is smaller than the influence of the existing map.

[0042] If none of the above-mentioned generated sections of the new environmental map newly generated by the map generation unit 111 is included in the existing environmental map stored in the storage unit 12, the map update unit 113 updates the existing environmental map by adding the data (sample number n2=5) and reliability of the above-mentioned generated sections of the new environmental map to the existing environmental map as is. In this case, since the weight w1 of the existing map corresponds to 0 and the weight w2 of the new map corresponds to 1, the data of the new map is newly added to the updated map. When the updated map is stored in the storage unit 12, it becomes the existing map, and the value of the sample number n1 of the existing map in the newly added section remains 5 until the data of that section is next updated.

[0043] 4A is a diagram illustrating a scene in which the vehicle 101 travels on a road RD. In the scene illustrated in FIG. 4A, the map generation unit 111 generates an environmental map on which position information of the lane markings L1, L2, etc. that define the driving lane traveled by the vehicle 101 is recorded, and the reliability calculation unit 112 calculates the reliability of the environmental map based on the position information of the lane markings L1, L2, etc.

[0044] The external environment recognition unit 14 recognizes curbs, walls, ditches, guardrails or dividing lines indicating the boundaries of the road RD as road boundary lines RL and RB based on, for example, a camera image acquired by the camera 1a, and recognizes the road structure indicated by the boundary lines RL and RB. As described above, the dividing lines L1, L2, etc. include white lines (including lines of different colors), curb lines, road studs, etc., and the driving lanes of the road RD are defined by the markings of these dividing lines L1, L2, etc.

[0045] Although an example has been disclosed in which the external environment recognition unit 14 recognizes the area between the borders RL and RB as an area corresponding to the road RD, the method of recognizing the road RD is not limited to this, and other methods may be used for recognition.

[0046] 4B is a schematic diagram showing a camera image captured by camera 1a on a two-dimensional map as if the road RD were viewed from above. The up-down direction in FIG. 4B corresponds to the depth direction as seen from the vehicle 101, and the left-right direction in FIG. 4B corresponds to the road width direction as seen from the vehicle 101. The vehicle position recognition unit 13 acquires position information of features (feature points) from the environmental map stored in the storage unit 12, and estimates the position of the vehicle 101 from the moving speed and moving direction (e.g., azimuth) of the vehicle 101. Every time a camera image is acquired by the camera 1a by measurement during traveling, the map generation unit 111 acquires the relative positions of the features based on the acquired camera image by performing coordinate conversion with the position of the vehicle 101 as the center.

[0047] Here, the angle of view of camera 1a is set so that there are no blank sections of data in the direction of travel along the road RD between the camera image of the previous frame acquired in the previous image capture and the camera image of the next frame acquired in the current image capture, and is set so that at least a predetermined number of consecutive frames (for example, five frames corresponding to the above-mentioned sample number n2) commonly include features at the same position on the road RD.

[0048] As an example, the map generating unit 111 is configured to acquire position information of features (e.g., demarcation lines) based on position information commonly included in five frames from the most recent frame F1 to frame F5. As a result, for example, the demarcation lines L1 and L2 are observed as five demarcation lines L1 and L2 due to a shift in the angle of view of the camera 1a that occurs between frames due to shaking of the traveling vehicle 101. The external environment recognizing unit 14 calculates approximate curves based on the demarcation lines L1 and L2 observed in each frame for five frames. As a result, five approximate curves (for five frames) corresponding to the demarcation lines L1 and L2 are obtained. When the circled area of ​​the demarcation line L2 in FIG. 4B is focused on and enlarged, it is as shown on the right side. As shown in FIG. 4B, by configuring the lane markings at the same position on the road RD to be commonly included in five consecutive frames, five position coordinates (sample number n=5) are obtained for the lane markings at the same position on the road RD in one drive. The map generating unit 111 sets the estimated position of the lane markings on the new map obtained in one drive to the average value of the five position coordinates. That is, the sample number n2 of the new map in the embodiment is set to 5. At this time, the sample number n of the updated map is n1+5, which is the sum of the sample number n2 and the sample number n1 of the existing map. 4B, points P1, P2, P3, ... indicated by white circles indicate the average of predetermined position coordinates of the lane line L2 acquired in each frame from frame F1 to frame F5, and correspond to positions calculated by the reliability calculation unit 112. Points P1, P2, P3, ... also correspond to positions calculated by the map update unit 113 for data for fusing the existing map and the new map.

[0049] <Explanation of the flow chart> Fig. 5 is a flowchart showing an example of a process executed by the controller 10 of Fig. 2 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.

[0050] In step S10 of FIG. 5, 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 generates a new map by the map generating unit 111, and proceeds to step S30.

[0051] In step S30, the controller 10 calculates the reliability of the new map generated in step S20 by the reliability calculation unit 112, and proceeds to step S40. The reliability calculation unit 112 performs the reliability calculation process for each piece of position information included in the new map. The reliability calculation unit 112 calculates the estimated value distribution (normal distribution) of the position information of the feature as the reliability of the new map.

[0052] In step S40, the controller 10 judges whether or not the new map is included in the existing map. If at least a part of the created section of the new map newly generated by the map generating unit 111 is included in the existing map stored in the storage unit 12, the controller 10 makes an affirmative judgment in step S40 and proceeds to step S50. If the created section of the new map is not included in the existing map, the controller 10 makes a negative judgment in step S40 and proceeds to step S90.

[0053] In step S50, the controller 10 judges whether the new map is a created lane in the existing map. If the new map is a created map of the driving lane, the controller 10 makes an affirmative judgment in step S50 and proceeds to step S60. If the new map is a map of the driving lane that has not been created, the controller 10 makes a negative judgment in step S50 and proceeds to step S90.

[0054] In step S60, the controller 10 merges the new map with the existing map by the map update unit 113. Specifically, data of a corresponding section of the existing map corresponding to the generated section of the new map is merged based on the data and reliability of the generated section of the new map and the data and reliability of the corresponding section of the existing map. The merging process is based on the above formulas (1) to (3). The map update unit 113 performs the merging process for each piece of position information included in the environmental map.

[0055] FIG. 6A is a schematic diagram illustrating the merging process of the section corresponding to the enlarged view shown on the right side of FIG. 4B. Points R1, R2, R3, ... shown by white circles in FIG. 6A each indicate the average value (X bar) of a plurality of predetermined position coordinates of the division line L2 constituting the data of the update map, and correspond to the calculation position of the reliability of the update map by the reliability calculation unit 112. Points Q1, Q2, Q3, ... shown by finely dashed white circles in FIG. 6A each indicate the average value (X1 bar) of a plurality of predetermined position coordinates of the division line L2 constituting the data of the existing map, and correspond to the calculation position of the reliability of the existing map by the reliability calculation unit 112. Points P1, P2, P3, ... shown by coarsely dashed white circles in FIG. 6A each indicate the average value (X2 bar) of a plurality of predetermined position coordinates of the division line L2 constituting the data of the new map, and correspond to the calculation position of the reliability of the new map by the reliability calculation unit 112.

[0056] In the example of Figure 6A, the updated map (X bar) is more heavily influenced by the existing map (X1 bar) than the new map (X2 bar), and the estimated position of the demarcation line L2 on the updated map (X bar) is closer to the estimated position of the demarcation line L2 on the existing map (X1 bar) than the estimated position of the demarcation line L2 on the new map (X2 bar). After the controller 10 has performed the above merging process as the update process, the process proceeds to step S70.

[0057] In step S70, the controller 10 uses the reliability calculation unit 112 to calculate the reliability of the updated map fused in step S60, and proceeds to step S80. The reliability calculation unit 112 performs the reliability calculation process for each piece of position information included in the updated map (the updated existing map). The reliability calculation unit 112 calculates the estimated value distribution (normal distribution) of the position information of the feature as the reliability of the updated map.

[0058] In step S80, the controller 10 records the update map (environmental map) and reliability information indicating the reliability of the update map as environmental map information in the storage unit 12, and then ends the processing in FIG. It should be noted that when a new map is added to an existing map in step S90 described later, the controller 10 additionally records the new map (environmental map) and reliability information indicating the reliability of the new map as environmental map information in the memory unit 12, and then terminates the processing in FIG. 5.

[0059] In step S90, which is reached after a negative decision is made in step S40 or step S50, the controller 10 adds the new map to the existing map by the map update unit 113. Specifically, the data and reliability of the generated section of the new map are added directly to the existing environmental map information. The map update unit 113 performs the addition process of the new map for each piece of position information included in the new map. After the controller 10 has performed the above addition process, the controller 10 proceeds to step S80.

[0060] When calculating the reliability in the above steps S30 and S70, the reliability calculation unit 112 may set at least one of the position coordinates of the vehicle 101 on the environmental map, the number of samples n of the recognition information recognized by the external environment recognition unit 14, and the position information of the driving lane (in other words, the dividing lines L1, L2, etc. that define the driving lane) recognized by the external environment recognition unit 14 as a parameter, and calculate an estimated value distribution (normal distribution) of the position information based on this parameter.

[0061] In addition, the reliability calculation unit 112 may calculate an estimated value distribution with different variance values ​​based on at least one of the position information of the driving lane acquired by the external environment recognition unit 14, the recognition result by the external environment recognition unit 14, the frequency of updates to the existing map, the presence or absence of a past driving history corresponding to the generation section of the new map, and the driving frequency.

[0062] Fig. 6B is another schematic diagram illustrating the merging process. When merging a new map with an existing map in step S60, as shown in Fig. 6B, the depth positions of points P1, P2, P3, ... indicating the average value (X2 bar) of multiple predetermined position coordinates of demarcation line L2 constituting the data of the new map may not necessarily correspond to the depth positions of points Q1, Q2, Q3, ... indicating the average value (X1 bar) of multiple predetermined position coordinates of demarcation line L2 constituting the data of the existing map. In such a case, the map update unit 113 may calculate predetermined position information of points R1, R2, R3, ... on the updated map based on a map shape estimated by polynomial approximation using data of the new map and data of the existing map. Specifically, the map update unit 113 calculates the position information of points R1, R2, R3, ... on the updated map estimated using a weighted least squares method using the following equation (4).

number

[0063] According to the embodiment described above, the following advantageous effects are achieved. (1) The map generating device 50 includes an external environment recognition unit 14 that recognizes the external environment situation around the vehicle 101, a map generating unit 111 that generates an environmental map including position information indicating the position of a specific feature based on the recognition information acquired by the external environment recognition unit 14, a reliability calculation unit 112 that calculates the reliability of the generated environmental map for each piece of position information, a memory unit 12 that stores the environmental map and reliability information indicating the reliability as environmental map information, and a map update unit 113 that updates data of a corresponding section of the existing map corresponding to the generation section of the new map based on the data and reliability of the new map of the generation section and the data and reliability of the existing map of the corresponding section when at least a portion of a new map newly generated by the map generating unit 111 is included in an existing map stored in the memory unit 12 as environmental map information. With this configuration, when the vehicle 101 travels on the same road RD, the existing map that has already been created is updated using newly obtained recognition information each time the vehicle travels. During updating, data on the corresponding section of the existing map that corresponds to the generation section of the new map is updated based on the data and reliability of the new map for the generation section and the data and reliability of the existing map for the corresponding section, so that not only is it possible to suppress a decrease in accuracy of the map data due to updating, but it is also possible to increase the accuracy of the map data each time the existing map is updated by traveling on a road included in the existing map (in other words, the same road as the road traveled in the past). The reason for this is that, according to the central limit theorem, the more the number of samples increases, the closer the average value (estimated value) becomes to the true value.

[0064] (2) In the map generating device 50 described in (1) above, the reliability calculation unit 112 sets at least one of the position coordinates of the vehicle 101 in the map information, the number of samples n of the recognition information recognized by the external environment recognition unit 14, and the position information of the driving lane recognized by the external environment recognition unit 14 as a parameter, and calculates a distribution of estimated values ​​of the position information of the feature as reliability information based on the parameter. With this configuration, the probability distribution of the population is estimated using parameters based on the location information shown on the map, thereby improving the accuracy of the estimated value distribution as reliability information.

[0065] (3) In the map generating device 50 described in (2) above, the reliability calculation unit 112 calculates an estimated value distribution in the generated section when a new map is generated, and calculates an estimated value distribution in the corresponding section when the existing map is updated. The map update unit 113 updates the location information of the existing map by prioritizing the data of the map with the smaller variance between the estimated value distribution calculated in the corresponding section of the existing map and the estimated value distribution calculated in the generated section of the new map, and fusing the existing map of the corresponding section with the new map of the generated section. With this configuration, when updating a map, it is possible to prioritize and combine map information from either the existing map or the new map, whichever is more reliable, thereby suppressing a decrease in accuracy of map data due to updates.

[0066] (4) In the map generating device 50 described above in (3), the reliability calculation unit 112 sets weights for the data of the existing map and the new map based on at least one of the position information of the driving lane acquired by the external environment recognition unit 14, the recognition result by the external environment recognition unit 14, the update frequency of the existing map, the presence or absence of past driving history, and the driving frequency. With this configuration, the weight that determines the priority of the existing map and the new map in the fusion at the time of map update can be set taking into consideration the recognition information of the external environment recognition unit 14, the frequency of map updates, and the driving frequency, thereby making it possible to appropriately update the map.

[0067] (5) In the map generating device 50 described above in (3), if the depth positions of points P1, P2, P3, ... as the first position information of the feature in the generation section of the new map do not correspond to the depth positions of points Q1, Q2, Q3, ... as the second position information of the feature in the corresponding section of the existing map, the map update unit 113 updates the position information of the existing map by merging the existing map of the corresponding section and the new map of the generation section based on the map shape of the updated map estimated by polynomial approximation using the data of the new map of the generation section and the data of the existing map of the corresponding section. With this configuration, if the corresponding points to be merged between the new map and the existing map cannot be uniquely determined, the shape of the updated map is estimated by polynomial approximation, making it possible to update the map with little error.

[0068] (6) In the map generating device 50 described in (1) above, the external environment recognition unit 14 recognizes the external environment at a predetermined frame rate, and when calculating the reliability for a new map, the reliability calculation unit 112 calculates it for each piece of position information of the same feature recognized in multiple frames acquired close to each other, and when calculating the reliability for an existing map, the reliability calculation unit 112 calculates it for each piece of position information of the same feature included in the existing map after it has been updated by the map update unit 113. With this configuration, the reliability calculation unit 112 is able to calculate the reliability of the environmental map generated by the map generation unit 111 for each piece of location information in just one drive, even if the vehicle 101 does not drive multiple times along the same road RD. In addition, since the reliability calculation unit 112 calculates the reliability for each piece of location information of the same feature included in the existing map after it has been updated by the map update unit 113, the map update unit 113 can appropriately perform the next update based on the data and reliability of the new map for the generated section and the data and reliability of the existing map for the corresponding section.

[0069] 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, when the host vehicle 101 travels on the road RD and the map generation unit 111 newly generates a new map, the existing map is always updated if there is a past travel history for the generated section, in other words, if the generated section of the new map is included in the existing map. Instead of this, for example, the opportunity to update the existing map may be limited so that the map update unit 113 updates the existing map only when the driver intervenes in the driving operation of the host vehicle 101 due to the host vehicle 101 traveling too close to the edge of the driving lane while automatically driving using existing map information. By configuring in this manner, it becomes possible to appropriately determine the timing to update existing maps, such as omitting updates to existing maps that do not interfere with autonomous driving, while updating existing maps that are not suitable for autonomous driving.

[0070] (Variation 2) In the embodiment, the weight w used when fusing data of the existing map and the new map is determined by the variance (σ 2 The inverse of (n / n) is used as the weighting factor w for the distribution of the estimated values ​​(the smaller the variance, the larger the weighting factor w, and the larger the variance, the smaller the weighting factor w). T (For example, the more frequently the existing map is updated, the larger the product w × w T may be adopted as the weights to be used when fusing data from the existing map and the new map. By configuring in this way, it becomes possible to make existing maps that have not been updated recently less susceptible to the influence of new maps when updating. In other words, it becomes possible to make old existing maps that have been updated a long time ago more susceptible to the influence of new maps when updating.

[0071] 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]

[0072] REFERENCE SIGNS LIST 1 external sensor group, 2 internal sensor group, 10 controller, 11 calculation unit, 12 storage unit, 14 external environment recognition unit, 50 map generation device, 100 vehicle control system, 101 host vehicle, 111 map generation unit, 112 reliability calculation unit, 113 map update unit

Claims

1. An external environment recognition unit that recognizes an external environment around the vehicle; A map generating unit that generates a map including position information indicating a position of a predetermined feature based on the recognition information acquired by the external environment recognition unit; a calculation unit that calculates a reliability of the generated map for each piece of location information; a storage unit that stores the map and reliability information indicating the reliability as map information; an update unit that updates data of a corresponding section of the existing map corresponding to a generated section of the new map, based on data and reliability of the new map of the generated section and data and reliability of the existing map of the corresponding section, when at least a part of the new map newly generated by the map generation unit is included in the existing map stored in the storage unit as the map information; A map generating device comprising:

2. 2. The map generating device according to claim 1, the calculation unit sets at least one of the position coordinates of the vehicle in the map information, the number of samples of the recognition information recognized by the external environment recognition unit, and position information of the driving lane recognized by the external environment recognition unit as a parameter, and calculates a distribution of estimated values ​​of the position information of the feature as the reliability information based on the parameter.

3. 3. The map generating device according to claim 2, the calculation unit calculates the estimated value distribution in the generated section when the new map is generated, and calculates the estimated value distribution in the corresponding section when the existing map is updated; The update unit updates the location information of the existing map by prioritizing the data of the map with the smaller variance between the estimated value distribution calculated for the corresponding section of the existing map and the estimated value distribution calculated for the generated section of the new map, and merging the existing map of the corresponding section with the new map of the generated section.

4. 4. The map generating device according to claim 3, The calculation unit sets weights for the data of the existing map and the new map based on at least one of position information of the driving lane acquired by the external environment recognition unit, a recognition result by the external environment recognition unit, a frequency of updates to the existing map, presence or absence of a past driving history, and a driving frequency.

5. 4. The map generating device according to claim 3, A map generating device characterized in that, when the first position information of a feature in the generation section of the new map does not correspond to the second position information of the feature in the corresponding section of the existing map, the update unit updates the position information of the existing map by merging the existing map of the corresponding section and the new map of the generation section based on a map shape estimated by polynomial approximation using the data of the new map of the generation section and the data of the existing map of the corresponding section.

6. 2. The map generating device according to claim 1, The external environment recognition unit recognizes the external environment at a predetermined frame rate, The map generating device is characterized in that, when calculating the reliability of the new map, the calculation unit calculates it for each piece of position information of the same feature recognized in multiple frames acquired close to each other, and, when calculating the reliability of the existing map, the calculation unit calculates it for each piece of position information of the same feature included in the existing map after it has been updated by the update unit.

Images