Map generation device

Abstract

A map generation device (50) is provided with: an outside world recognition unit (14) that recognizes the outside situation around a host vehicle; a map generation unit (111) that generates, on the basis of the identification information acquired by the outside world identification unit (14), position information including a position indicating a predetermined surface feature; a calculation unit (112) that calculates a degree of reliability with respect to the generated map for each piece of position information; a storage unit (12) that stores, as map information, a map and reliability information indicating reliability; and an update unit (113) that, when at least a part of a new map newly generated by the map generation unit (111) is included in an existing map stored as map information in the storage unit (12), updates the new map on the basis of 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. And updating data of a corresponding section of the existing map corresponding to the generation section of the new map.

Description

Technical Field

[0001] The present invention relates to a map generating device for generating a map based on information acquired from a vehicle. Background Art

[0002] As a technology of this kind, a map generation device is known that collects information obtained by a vehicle-mounted sensor and generates a map based on the collected information (see Patent Document 1). In such a map generation device, when updating an existing map that has already been created using newly collected information, it is desirable to suppress a decrease in the accuracy of the map data and to improve the map data through the update.

[0003] In the prior art, differential data is obtained by comparing integrated detection map data obtained by integrating newly collected detection data with existing basic map data, and the existing basic map data is updated based on average differential data obtained by averaging a plurality of differential data. Therefore, when there is differential data containing many errors that are transient differential data and have not been eliminated, the existing basic map data is greatly affected and the accuracy is reduced.

[0004] Suppressing the decrease in map data accuracy is related to enabling vehicles to move smoothly and improving traffic convenience and safety. This can contribute to the development of a sustainable transportation system.

[0005] Prior art literature

[0006] Patent Literature

[0007] Patent document 1: International Publication No. 2021 / 002190 (WO2021 / 002190A). Summary of the invention

[0008] A map generating device according to a technical solution of the present invention comprises: an external recognition unit for recognizing external conditions around a vehicle; a map generating unit for generating a map including position information indicating the position of a specified feature based on the recognition information obtained by the external recognition unit; a calculating unit for calculating the reliability of the generated map for each position information; a storing unit for storing the map and the reliability information indicating the reliability as map information; and an updating unit for updating the data of a corresponding interval of the existing map corresponding to the generated interval of the new map based on the data and reliability of the new map of the generated interval and the data and reliability of the existing map of the corresponding interval when at least a part of a new map newly generated by the map generating unit is included in an existing map stored in the storing unit as map information. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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.

[0010] Figure 1 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 invention.

[0011] Figure 2 This is a block diagram illustrating a main part configuration of a map generating device according to an embodiment.

[0012] Figure 3A This is a schematic diagram for explaining the distribution of estimated values ​​of the positions of features on a map.

[0013] Figure 3B It is a schematic diagram illustrating the relationship between the existing map, the new map, and the updated map.

[0014] Figure 4A The figure illustrates a scene in which the vehicle is traveling on a road.

[0015] Figure 4B It is a schematic diagram that represents point cloud data on a two-dimensional graph.

[0016] Figure 5 Is Figure 2 A flowchart of an example of a process performed by a controller.

[0017] Fig. 6A is a schematic diagram illustrating a fusion process.

[0018] Figure 6B is another schematic diagram illustrating the fusion process. DETAILED DESCRIPTION

[0019] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0020] The map generation device of the embodiment is configured to generate a map (an environmental map described later) for use 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.

[0021] 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 (manual driving vehicle).

[0022] 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.

[0023] 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 following describes the map generation device as a case where the map generation device is provided on an autonomous driving vehicle.

[0024] <Autonomous driving vehicles>

[0025] 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 1 1 is a block diagram illustrating a schematic configuration of a vehicle control system 100 including a map generating device according to an embodiment.

[0026] like Figure 1 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 a CAN (Controller Area Network) communication line.

[0027] 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 around 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 around the vehicle by irradiating an electromagnetic wave and detecting reflected waves.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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 .

[0033] 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.

[0034] 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, 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.

[0035] 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.

[0036] 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 1 The controller 10 is shown in FIG. 1 as a collection of these ECUs.

[0037] 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.

[0038] 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 travel history information indicating a travel trajectory based on detection values ​​of the external sensor group 1 and the internal sensor group 2.

[0039] 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.

[0040] 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.

[0041] 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 can also be recognized by communicating with the sensor via the communication unit 7 .

[0042] 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 111 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, using the signal from the external sensor group 1 (camera, laser radar), the map production processing and the position estimation processing are performed simultaneously according to the SLAM (Simultaneous Localization and Mapping) algorithm.

[0043] 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 and other markings, 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).

[0044] 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.

[0045] 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.

[0046] <Map Generator>

[0047] Figure 2 FIG. 5 is a block diagram of a main structure of a map generating device 50 according to an exemplary embodiment. The map generating device 50 includes Figure 1 In the vehicle control system 100. Figure 2 In the figure, the map generating device 50 includes a camera 1a, a laser radar 1b, a sensor 2a, and a controller 10.

[0048] Camera 1a is a single-lens reflex camera having an image sensor such as a CMOS sensor. Figure 1 The 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.

[0049] 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.

[0050] The laser radar 1b is also one of the external sensor groups 1. The laser radar 1b is installed toward 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 (the 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 a specified number of point cloud data per frame (the number of detection points within the FOV) at a specified frame rate.

[0051] 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 (the 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 making a map. It should be noted that the structure of the sensor 2a is not limited to this, and the position of the vehicle can also be estimated using information from other sensors.

[0052] Figure 2The controller 10 includes a map generating unit 111, a reliability calculating unit 112, and a map updating unit 113 as the computing unit 11 ( Figure 1 ) is the functional structure undertaken by the

[0053] 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 produced by the map generation unit 111 using the detection value of the external sensor group 1 or the detection value 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 produced 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.

[0054] The storage unit 12 may also store information on programs of various controls, threshold values ​​used by the programs, and the like.

[0055] The map generation unit 111 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 111 extracts feature points of features recognized by, for example, the external recognition unit 14 from the camera image obtained by the camera 1a. The map generation unit 111 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.

[0056] It should be noted that, as described above, the map generation unit 111 performs the map generation process in the same manner as in the manual driving mode, not limited to when the vehicle is traveling in the manual driving mode. When the vehicle is traveling in the automatic driving mode, the map generation process is performed in the same manner as in the manual driving mode.

[0057] The reliability calculation unit 112 calculates the reliability of the environment map. For example, the location of the same feature (such as road markings) is measured multiple times, and the reliability of the environment map is calculated based on the distribution of the measured locations obtained in each measurement. The reliability calculation method is based on the central limit theorem, which states: "When the population of the extracted samples has a mean μ and a variance σ 2 In the case of , as the number of samples n increases, the distribution of sample means gradually approaches the mean μ and variance σ. 2 / n’s normal distribution N(μ,σ 2 / n)”.

[0058] Figure 3A This is a schematic diagram for explaining the distribution of estimated values ​​of the positions of features on a map. In the embodiment, the position coordinates of the same feature acquired in each frame based on the detection values ​​of n frames acquired at close times among the detection values ​​of multiple frames acquired by the camera 1a at a predetermined frame rate 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 environment map.

[0059] The reliability calculation unit 112 calculates the variance σ of the normal distribution N 2 / n, as reliability information indicating the reliability of the environment map. It can be said that the variance σ 2 The smaller / n is, the higher the reliability is. 2 The larger the / n, the lower the reliability.

[0060] The map updating unit 113 updates the existing environment map when an environment map different from the existing environment map stored in the storage unit 12 is generated. Specifically, when at least a part of the new environment map newly generated by the map generating unit 111 is included in the existing environment map stored in the storage unit 12, the map updating unit 113 updates the data of the corresponding section of the existing environment map corresponding to the generation section of the new map based on the data and reliability of the above generation section of the new environment map and the data and reliability of the above corresponding section of the existing environment map. That is, when the updated environment map is generated by fusing the existing environment map and the new environment map, the data of the environment map with high reliability (in other words, the variance of the estimated value distribution is small) is given priority.

[0061] In the embodiment, the environment map generated by the map generation unit 111, that is, the environment map before the update process by the map update unit 113 is referred to as a new map. In addition, the environment map stored in the storage unit 12 is referred to as an existing map. The update process refers to the fusion of the new map and the existing map to obtain a new environment map (referred to as an updated map). Furthermore, when the updated map is stored in the storage unit 12, the stored updated map is referred to as an existing map.

[0062] Figure 3B The figure is a schematic diagram showing the relationship between the existing map, the new map, and the updated map for the location of features on the map. The solid line curve, the thin dotted line curve, and the thick dotted line curve respectively show the distribution of the estimated values ​​of the location of features on the updated map, the existing map, and the new map. This corresponds to the average value of the position coordinates of the feature in the updated map (in other words, the estimated position of the feature). This corresponds to the average value of the position coordinates of the feature in the existing map (in other words, the estimated position of the feature). Corresponds to the average value of the position coordinates of the feature in the new map (in other words, the estimated position of the feature).

[0063] During an update, the map updating unit 113 merges the data of the existing map and the new map using the following equations (1) to (3) to obtain the data of the updated map.

[0064]

[0065] In the formula, symbol w1 represents the estimated position of the feature relative to the existing map The symbol w2 represents the estimated position of the feature relative to the new map. The weight of .

[0066]

[0067]

[0068] As shown in equation (2), the map updating unit 113 converts the inverse of the variance of the normal distribution N of the existing map n1 / σ1 2 As the weight w1 for the data of the existing map. In addition, as shown in formula (3), the inverse of the variance of the normal distribution N of the new map is n2 / σ2 2 As the weight w2 of the data relative to the new map.

[0069] It should be noted that the symbols n1 and σ1 represent the number of samples and the standard deviation of the existing map, respectively, and the symbols n2 and σ2 represent the number of samples and the standard deviation of the new map, respectively. As an example, in the embodiment, the number of samples n2 of the new map is 5. Therefore, the value of the number of samples n1 of the existing map increases by 5 each time it is updated. It should be noted that the value of the number of samples n2 is not limited to 5 and can be changed appropriately.

[0070] exist Figure 3B In the example, the waveform width of the normal distribution N of the existing map is narrower than the waveform width of the normal distribution N of the new map, so the variance σ1 of the normal distribution N of the existing map is 2 / n1 is greater than the variance σ2 of the normal distribution N of the new map 2 / n2 is small. Therefore, the weight w1 of the existing map is larger than the weight w2 of the new map, and the updated map is more affected by the existing map than the new map. Conversely, the new map has less influence on the updated map than the existing map.

[0071] It should be noted that, when any of the above-mentioned generation intervals of the new environment map newly generated by the map generation unit 111 is not included in the existing environment map stored in the storage unit 12, the map update unit 113 adds the data (sample number n2=5) and reliability of the above-mentioned generation interval of the new environment map to the existing environment map as it is, thereby updating the existing environment map. 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 interval is 5 until the data of the interval is updated next time.

[0072] Figure 4A 1 is a diagram illustrating a scene in which the host vehicle 101 is traveling on the road RD. Figure 4A In the illustrated scenario, the map generation unit 111 generates an environmental map that records the position information of the road markings L1, L2, etc. used to define the lanes through which the vehicle 101 has traveled, and the reliability calculation unit 112 calculates the reliability of the environmental map based on the position information of the road markings L1, L2, etc.

[0073] The external recognition unit 14 recognizes, for example, a curb, a wall, a ditch, a guardrail, or a road marking indicating the boundary of the road RD as a road boundary line RL, RB based on the camera image obtained by the camera 1a, and recognizes the road structure represented by the boundary line RL, RB. As described above, the road marking lines L1, L2, etc. include white lines (including lines of different colors), curb lines, road spikes, etc., and the driving lane of the road RD is defined by the markings of these road marking lines L1, L2, etc.

[0074] It should be noted that the example in which the outside world recognition unit 14 recognizes the area sandwiched by the boundary lines RL and RB as the area corresponding to the road RD has been described, but the method of recognizing the road RD is not limited to this, and other methods may be used for recognition.

[0075] Figure 4B It is a schematic diagram showing a camera image acquired by the camera 1 a on a two-dimensional map such that the road RD is viewed from above. Figure 4B The up-down direction in corresponds to the depth direction as viewed from the vehicle 101. Figure 4B The left-right direction in corresponds to the road width direction as viewed from the host vehicle 101 .

[0076] The vehicle position recognition unit 13 obtains the position information of the feature (feature point) from the environment map stored in the storage unit 12, and estimates the position of the vehicle 101 based on the moving speed and moving direction (e.g., azimuth) of the vehicle 101. The map generation unit 111 performs coordinate conversion with the position of the vehicle 101 as the center every time a camera image is obtained by the camera 1a through measurement during driving, and obtains the relative position of the feature based on the obtained camera image.

[0077] Here, the field of view angle of camera 1a is set to a blank interval in which no data is generated in the traveling direction of road RD between the camera image of the previous frame obtained by the last shooting and the camera image of the next frame obtained by the current shooting, and is set to include the features at the same position on road RD in at least a specified number of consecutive frames (for example, 5 frames corresponding to the sample number n2).

[0078] As an example, the map generation unit 111 is configured to obtain the position information of the ground feature (e.g., road markings) based on the position information commonly included in the five frames from the most recent frame F1 to the frame F5. As a result, due to the offset of the field of view angle of the camera 1a between frames caused by, for example, the shaking of the traveling vehicle 101, the road markings L1 and the road markings L2 are observed as five road markings L1 and road markings L2. The external recognition unit 14 calculates the approximate curves based on the road markings L1 and the road markings L2 observed in each frame for five frames. As a result, five (5 frames) approximate curves corresponding to the road markings L1 and the road markings L2 are obtained respectively. When paying attention and zooming in Figure 4B When the area surrounded by a circle in the road marking line L2 is as shown on the right side of the figure.

[0079] like Figure 4B As shown in FIG. 1 , by configuring the road line at the same position on the road RD to be included in common in five consecutive frames, five (sample number n=5) position coordinates are obtained for the road line at the same position on the road RD through one trip. The map generation unit 111 sets the estimated position of the road line in the new map obtained through one trip 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 obtained by adding the sample number n2 to the sample number n1 of the existing map.

[0080] exist Figure 4BIn FIG. 1 , the points P1, P2, P3, etc. indicated by white circles correspond to the reliability calculation positions performed by the reliability calculation unit 112. The points P1, P2, P3, etc. represent the average values ​​of the position coordinates corresponding to the respective calculation positions obtained in the frames from the frame F1 to the frame F5, that is, the estimated position of the road marking line L2. The points P1, P2, P3, etc. also correspond to the calculation positions of the data of the fusion of the existing map and the new map performed by the map update unit 113.

[0081] <Explanation of the flow chart>

[0082] Figure 5 It shows that according to a predetermined procedure Figure 2 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.

[0083] exist Figure 5 In step S10, the controller 10 obtains sensor information from the camera 1a, the laser radar 1b and the sensor 2a, and proceeds to step S20.

[0084] In step S20 , the controller 10 generates a new map by the map generating unit 111 and then proceeds to step S30 .

[0085] In step S30, the controller 10 calculates the reliability of the new map generated in step S20 through the reliability calculation unit 112, and proceeds to step S40. The reliability calculation unit 112 performs reliability calculation processing for each 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.

[0086] In step S40, the controller 10 determines whether the new map is included in the existing map. If at least a part of the creation section of the new map newly generated by the map generation unit 111 is included in the existing map stored in the storage unit 12, the controller 10 determines that step S40 is affirmative (S40: Yes), and proceeds to step S50. If the creation section of the new map is not included in the existing map, the controller 10 determines that step S40 is negative (S40: No), and proceeds to step S90.

[0087] In step S50, the controller 10 determines whether the new map is a lane that has been created in the existing map. If the new map is a map of a driving lane that has been created, the controller 10 determines that step S50 is positive (S50: Yes) and proceeds to step S60. If the new map is a map of an unfinished driving lane, the controller 10 determines that step S50 is negative (S50: No) and proceeds to step S90.

[0088] In step S60, the controller 10 merges the new map with the existing map through the map updating unit 113. Specifically, based on the data and reliability of the above-mentioned generation interval of the new map, and the data and reliability of the above-mentioned corresponding interval of the existing map stored in the storage unit 12, the data of the corresponding interval of the existing map corresponding to the generation interval of the new map is merged. The fusion processing is based on the above formulas (1) to (3). The map updating unit 113 performs the above-mentioned fusion processing for each position information included in the environment map.

[0089] Fig. 6A This is an example of Figure 4B Schematic diagram of the fusion processing of the interval corresponding to the enlarged image shown on the right side of the figure. Fig. 6A Points R1, R2, R3, ..., indicated by white circles in the figure correspond to the calculated positions of the reliability of the updated map by the reliability calculation unit 112. Points R1, R2, R3, ..., are the position coordinates of the road line L2 constituting the data of the updated map, and more specifically, represent the average value (X) of the position coordinates corresponding to the respective calculated positions obtained in a plurality of consecutive frames. Fig. 6A Points Q1, Q2, Q3, ..., indicated by thin dashed white circles in the figure, respectively correspond to the calculated positions of the reliability of the existing map by the reliability calculation unit 112. Points Q1, Q2, Q3, ..., respectively represent the position coordinates of the road line L2 constituting the data of the existing map, and more specifically, represent the average values ​​of the position coordinates corresponding to the respective calculated positions obtained in a plurality of consecutive frames. In addition, Fig. 6A Points P1, P2, P3, ..., indicated by thick dashed white circles in the figure, respectively correspond to the calculated positions of the reliability of the new map by the reliability calculation unit 112. Points Q1, Q2, Q3, ..., respectively are the position coordinates of the road line L2 constituting the data of the new map, and more specifically, represent the average values ​​of the position coordinates corresponding to the respective calculated positions obtained in a plurality of consecutive frames.

[0090] exist Fig. 6A In the example, update the map New Map Influenced by existing maps The impact is greater, update the map The estimated position of the road marking L2 in the new map is The estimated position of the road marking L2 in the map is closer to the existing map The estimated position of the road marking L2 in .

[0091] When the controller 10 executes the above merging process as the updating process, the process proceeds to step S70 .

[0092] In step S70, the controller 10 calculates the reliability of the updated map obtained by fusion in step S60 through the reliability calculation unit 112, and proceeds to step S80. The reliability calculation unit 112 performs reliability calculation processing for each 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.

[0093] In step S80, the controller 10 records the updated map (environmental map) and the reliability information indicating the reliability of the updated map in the storage unit 12 as environmental map information through the map updating unit 113, and ends the process. Figure 5 processing.

[0094] It should be noted that, in the case where 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 storage unit 12, and the process ends. Figure 5 processing.

[0095] In step S90 entered when the determination in step S40 or step S50 is negative, the controller 10 adds the new map to the existing map through the map updating unit 113. Specifically, the data and reliability of the generated section of the new map are added to the existing environmental map information intact. The map updating unit 113 performs the new map addition process for each location information included in the new map. When the controller 10 performs the above-mentioned addition process, it enters step S80.

[0096] When calculating the reliability in the above steps S30 and S70, the reliability calculation unit 112 can set at least one of the position coordinates of the vehicle 101 in the environmental map, the sample number n of the identification information identified by the external recognition unit 14, and the position information of the driving lane identified by the external recognition unit 14 (in other words, the road markings L1, L2, etc. that specify the driving lane) as a parameter, and calculate the estimated value distribution (normal distribution) of the position information based on the parameter.

[0097] In addition, the reliability calculation unit 112 can also calculate the estimated value distribution with different variance values ​​based on at least one of the position information of the driving lane obtained by the external recognition unit 14, the recognition result of the external recognition unit 14, the update frequency of the above-mentioned existing map, the presence or absence of past driving history records corresponding to the generation interval of the above-mentioned new map, and the driving frequency.

[0098] Figure 6Bis another schematic diagram of an exemplary fusion process. In the case where the new map is fused into the existing map in the above step S60, Figure 6B As shown in FIG. 1 , sometimes the average value of the coordinates of a plurality of predetermined positions of the road line L2 constituting the data of the new map is represented. The depth direction positions of points P1, P2, P3, ... and the average value of a plurality of predetermined position coordinates of the road line L2 representing the data constituting the existing map The positions of point Q1, point Q2, point Q3, ... in the depth direction do not necessarily correspond to each other.

[0099] In this case, the map updating unit 113 may also calculate the predetermined position information of the points R1, R2, R3, ... on the updated map based on the map shape estimated by, for example, polynomial approximation using the data of the new map and the data of the existing map. Specifically, the position information of the points R1, R2, R3, ... on the updated map estimated by the weighted least square method using the following formula (4) is calculated.

[0100]

[0101] Where S is the cost function, n is the number of data points, m is the number of polynomial approximations, and x is i ,y i is the coordinate value of each data point, w i is the weight of each data point, θ j are the coefficients of the polynomial approximation.

[0102] The above-described implementation mode has the following effects.

[0103] (1) The map generating device 50 includes: an external environment recognition unit 14 that recognizes external environment conditions around the host vehicle 101; a map generating unit 111 that generates an environment map including position information indicating the position of a predetermined feature based on the recognition information obtained by the external environment recognition unit 14; a reliability calculating unit 112 that calculates the reliability of the generated environment map for each position information; a storage unit 12 that stores the environment map and the reliability information indicating the reliability as environment map information; and a map updating unit 113 that updates the 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 part of the new map newly generated by the map generating unit 111 is included in the existing map stored in the storage unit 12 as the environment map information.

[0104] Because of this configuration, when the vehicle 101 travels on the same road RD, the existing map that has been created is updated using the newly obtained identification information each time the number of times of travel is repeated. When updating, the data of the corresponding space of the existing map corresponding to the generation interval of the new map is updated based on the data and reliability of the new map of the generation interval and the data and reliability of the existing map of the corresponding interval. Therefore, it is needless to say that the reduction in the accuracy of the map data caused by the update is suppressed. When the existing map is updated each time the existing map is traveled on the road included in the existing map (in other words, the same road as the road traveled in the past), the accuracy of the map data can be improved. This is because according to the central limit theorem, as the number of samples increases, its average value (estimated value) will be closer to the true value.

[0105] (2) In the map generating device 50 of (1) above, the reliability calculating unit 112 sets at least one of the position coordinates of the host vehicle 101 in the map information, the number of samples n of the identification information identified by the external recognition unit 14, and the position information of the driving lane identified by the external recognition unit 14 as parameters, and calculates the estimated value distribution of the position information of the feature as reliability information based on the parameters.

[0106] Due to this configuration, the overall probability distribution is estimated from the parameters based on the position information represented by the map, thereby improving the accuracy of the estimated value distribution as the reliability information.

[0107] (3) In the map generation device 50 of (2) above, the reliability calculation unit 112 calculates the estimated value distribution in the generation interval when a new map is generated, and calculates the estimated value distribution in the corresponding interval when an existing map is updated. The map updating unit 113 prioritizes the data of the map with the smaller variance among the estimated value distribution calculated in the corresponding interval of the existing map and the estimated value distribution calculated in the generation interval of the new map, and merges the existing map of the corresponding interval with the new map of the generation interval, thereby updating the location information of the existing map.

[0108] With this configuration, when updating a map, map information with high reliability can be preferentially integrated between the existing map and the new map, thereby suppressing a decrease in the accuracy of map data due to the update.

[0109] (4) In the map generating device 50 of (3) above, the reliability calculating unit 112 sets the weights of the data of the existing map and the new map based on at least one of the position information of the driving lane identified by the external recognition unit 14, the recognition result of the external recognition unit 14, the frequency of updating of the existing map, the presence or absence of past driving history records, and the driving frequency.

[0110] With this configuration, the map can be updated appropriately by setting weights for determining the priority of the existing map and the new map in fusion during map updating in consideration of the recognition information of the outside world recognition unit 14, the map update frequency, and the travel frequency.

[0111] (5) In the map generation device 50 of (3) above, when the positions in the depth direction of points P1, P2, P3, ... as the first position information of features in the generation interval of the new map do not correspond to the positions in the depth direction of points Q1, Q2, Q3, ... as the second position information of features in the corresponding interval of the existing map, the map updating unit 113 updates the position information of the existing map by fusing the existing map of the corresponding interval with the new map of the generation interval based on the map shape of the updated map estimated by polynomial approximation using data of the new map of the generation interval and data of the existing map of the corresponding interval.

[0112] With this configuration, when corresponding points to be merged between the new map and the existing map cannot be uniquely determined, the shape of the update map is estimated by polynomial approximation, thereby enabling map update with less error.

[0113] (6) In the map generation device 50 of (1) above, the external environment recognition unit 14 recognizes external conditions at a prescribed frame rate, and the reliability calculation unit 112, when calculating the reliability of a new map, calculates each position information of the same feature respectively recognized in a plurality of frames with close acquisition times; and when calculating the reliability of an existing map, calculates each position information of the same feature included in the existing map updated by the map update unit 113.

[0114] With such a configuration, the reliability calculation unit 112 can calculate the reliability of the environment map generated by the map generation unit 111 only by one travel for each piece of position information, even if the host vehicle 101 does not travel on the same road RD multiple times.

[0115] In addition, since the reliability calculation unit 112 calculates the reliability of each location information of the same feature contained in the existing map updated by the map updating unit 113, the map updating unit 113 can appropriately perform the next update based on the data and reliability of the new map of the generated interval and the data and reliability of the existing map of the corresponding interval.

[0116] The above-described embodiment can be modified in various forms. Modifications will be described below.

[0117] (Variant 1)

[0118] In the embodiment, the following example is described. When the vehicle 101 is traveling on the road RD and the map generation unit 111 generates a new map, there is a past travel history record for the generation interval. In other words, when the generation interval of the new map is included in the existing map, the existing map is always updated. Alternatively, for example, the map update unit 113 may update the existing map only when the driver intervenes in the driving operation of the vehicle 101, for example, because the vehicle 101 is driving too far toward the end of the driving lane while using the existing map information to implement automatic driving, so as to limit the update opportunity of the existing map. More specifically, after the affirmative determination in step S40 (S40: Yes), the controller 10 determines whether there is a driving operation intervention by the driver in the generation interval of the new map through the map update unit 113. When there is no driving operation intervention, the process may be terminated without entering step S50. It should be noted that the presence or absence of driving operation intervention may also be determined based on whether the operation of the steering wheel is detected based on the sensor value of the internal sensor group 2, or other methods may be used for determination.

[0119] With this configuration, it is possible to appropriately determine the timing for updating the existing map, thereby omitting the updating of the existing map that does not hinder autonomous driving and updating the existing map that is not suitable for autonomous driving.

[0120] (Variant 2)

[0121] In the embodiment, as the weight w used when fusing the data of the existing map and the new map, the variance (σ) representing the breadth of the estimated value distribution (normal distribution) of the location information of the feature is used. 2 / n) as the weight w for the estimated value distribution (the smaller the variance, the larger the weight w is, and the larger the variance, the smaller the weight w is). Alternatively, the weight w for the estimated value distribution and the weight w calculated based on the time factor can be used. T (For example, the higher the update frequency of the existing map, the larger it is, or the newer the update period of the existing map, the larger it is) T, as the weight w1 of the existing map used when fusing the data of the existing map and the new map. For example, in step S80, when the controller 10 stores the updated map and the reliability information of the updated map in the storage unit 12 through the map updating unit 113, the information showing the update time (hereinafter referred to as the update history information) is associated with the interval corresponding to the updated map (hereinafter referred to as the update interval) and is stored in the storage unit 12. When the update history information corresponding to the update interval is already stored in the storage unit 12, the update time of this time is added to the update history information. Thereafter, when the new map is merged with the existing map in step S60, the controller 10 obtains the update frequency and the latest update period of the map in the generation interval of the new map from the update history information stored in the storage unit 12, and calculates the above-mentioned weight w based on the obtained information. T .

[0122] With such a configuration, an existing map that was last updated not long ago can be less susceptible to the influence of a new map when it is updated. In other words, an old existing map that has been updated for a long time can be easily influenced by a new map when it is updated.

[0123] The above description is merely an example, and the above embodiment and modified examples do not limit the present invention unless the features of the present invention are impaired. One or more of the above embodiment and modified examples can be arbitrarily combined, and the modified examples can be combined with each other.

[0124] By adopting the present invention, the accuracy of map data can be improved with each update.

[0125] 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: An external recognition unit (14) for recognizing external conditions around the vehicle; a map generating unit (111) for generating a map including position information showing the position of a predetermined feature based on the identification information acquired by the external recognition unit (14); A calculation unit (112) for calculating the reliability of each piece of position information for the generated map; a storage unit (12) storing the map and reliability information indicating the reliability as map information; as well as An updating unit (113) updates the data of a corresponding section of the existing map corresponding to a 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 part of the new map newly generated by the map generating unit (111) is included in the existing map stored as the map information in the storage unit (12).

2. The map generating device according to claim 1, characterized in that: The calculation unit (112) sets at least one of the position coordinates of the vehicle in the map information, the number of samples of the identification information identified by the external recognition unit (14), and the position information of the driving lane identified by the external recognition unit (14) as parameters, and calculates the estimated value distribution of the position information of the feature as the reliability information based on the parameters.

3. The map generating device according to claim 2, characterized in that: The calculation unit (112) calculates the estimated value distribution in the generation interval when the new map is generated, and calculates the estimated value distribution in the corresponding interval when the existing map is updated. The updating unit (113) prioritizes the data of the map with smaller variance among the estimated value distribution calculated in the corresponding interval of the existing map and the estimated value distribution calculated in the generated interval of the new map, and fuses the data of the map with the existing map of the corresponding interval and the new map of the generated interval, thereby updating the location information of the existing map.

4. The map generating device according to claim 3, characterized in that: The calculation unit (112) sets weights for data of the existing map and the new map based on at least one of position information of a driving lane identified by the outside world identification unit (14), an identification result of the outside world identification unit (14), an update frequency of the existing map, the presence or absence of past driving history records, and a driving frequency.

5. The map generating device according to claim 3, characterized in that: When the first position information of the features in the generated interval of the new map does not correspond to the second position information of the features in the corresponding interval of the existing map, the updating unit (113) merges the existing map of the corresponding interval and the new map of the generated interval based on a map shape estimated by polynomial approximation using data of the new map of the generated interval and data of the existing map of the corresponding interval, thereby updating the position information of the existing map.

6. The map generating device according to claim 1, characterized in that: The external environment recognition unit (14) recognizes the external environment condition at a predetermined frame rate. When calculating the reliability of the new map, the calculation unit (112) calculates each position information of the same feature identified in multiple frames with similar acquisition times. When calculating the reliability of the existing map, the calculation unit (112) calculates each position information of the same feature included in the existing map after update by the update unit (113).

7. The map generating device according to claim 1, characterized in that: It also has sensors to detect whether there is any interference in driving operations. When at least a portion of the new map is included in the existing map, the updating unit (113) determines whether the driving operation is involved in the generation interval of the new map based on the detection data of the sensor, and when there is no intervention of the driving operation, the data of the corresponding interval of the existing map corresponding to the generation interval is not updated.

Images