Map generation device

Abstract

The present invention provides a map generating device (50), comprising: a map generating unit (17) that generates a map based on a vehicle's driving record; a storage unit (12) that stores first map information including position information of a point cloud identified based on distance information to an object obtained by a first vehicle and second map information including position information of a dividing line identified based on image information obtained by a second vehicle; and a map information updating unit (17b) that updates at least one of the first map information and the second map information so that the first map and the second map are combined. The map generating unit (17) has a dividing line identifying unit (17a) that identifies the position of a dividing line based on the first map information. The map information updating unit (17b) updates at least one of the first map information and the second map information based on the position information of the dividing line identified by the dividing line identifying unit (17a) and the position information of the dividing line included in the second map information so that the first map and the second map are combined.

Description

Technical Field

[0001] The present invention relates to a map generation device for generating a high-precision map used in automatic driving of a vehicle. Background Art

[0002] In the past, there is a known device for implementing driving control of an autonomous vehicle (see, for example, Patent Document 1). In the device described in Patent Document 1, the vehicle's own position is estimated by recognizing the external environment around the vehicle, and high-precision road map information is sequentially extracted from a road map information database based on the own position, and the vehicle's driving control is implemented using the extracted map information.

[0003] However, a vehicle sometimes travels in a boundary area between multiple maps that are adjacent to each other. However, sometimes the map information of the adjacent map includes inherent errors, so if the vehicle's own position is estimated as in the device described in Patent Document 1, a deviation will occur in the estimated result of the vehicle's own position. When the vehicle is controlled based on the map information, it may be difficult to perform smooth driving control when traveling in a boundary area between multiple maps.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent document 1: Japanese Patent Application Publication No. 2019-64562 (JP 2019-064562A). Summary of the invention

[0007] A map generating device according to a technical solution of the present invention comprises: a map generating unit generating a map based on a first driving record of a first vehicle in a first area and a second driving record of a second vehicle in a second area adjacent to the first area; a storage unit storing information of a first map generated based on the first driving record and information of a second map generated based on the second driving record; and a map information updating unit updating information of at least one of the first map and the second map stored in the storage unit so as to combine the first map with the second map. The information of the first map includes position information of a point cloud recognized based on distance information to an object obtained by the first vehicle. The information of the second map includes position information of a dividing line recognized based on image information obtained by the second vehicle. The map generating unit has a dividing line recognition unit that recognizes the position of the dividing line based on the information of the first map stored in the storage unit. The map information updating unit updates information of at least one of the first map and the second map stored in the storage unit based on the position information of the dividing line recognized by the dividing line recognition unit and the position information of the dividing line included in the information of the second map so as to combine the first map with the second map. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] 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.

[0009] Figure 1 This is a diagram showing an example of a driving scenario of an autonomous driving vehicle to which the map generating device according to the embodiment of the present invention is applied.

[0010] Figure 2 This is a block diagram schematically showing the overall configuration of a vehicle control system of an autonomous driving vehicle to which a map generating device according to an embodiment of the present invention is applied.

[0011] Figure 3 Is used to illustrate the Figure 2 A map generating unit generates a map of point cloud map information and stores it in a storage unit.

[0012] Figure 4 Is used to illustrate the Figure 2 A map of road map information generated by a map generating unit and stored in a storage unit.

[0013] Figure 5 1 is a diagram showing an example of a driving scenario of an autonomous driving vehicle assumed by the map generating device according to the embodiment of the present invention.

[0014] Figure 6 This is a block diagram showing a main part configuration of a map generating device according to an embodiment of the present invention.

[0015] Figure 7 Is used to illustrate the Figure 6 FIG. 1 is a diagram showing update of map information performed by a map information updating unit.

[0016] Figure 8 It is shown by Figure 6 A flowchart of an example of a process performed by a controller. DETAILED DESCRIPTION

[0017] The following reference Figures 1 to 8 The embodiment of the present invention is described. The map generation device of the embodiment of the present invention can be applied to a vehicle with an automatic driving function (automatic driving vehicle). The automatic driving vehicle includes not only a vehicle that drives only in an automatic driving mode that does not require a driver to perform a driving operation, but also a vehicle that drives in an automatic driving mode and in a manual driving mode in which a driver performs a driving operation.

[0018] Figure 1 1 is a diagram showing an example of a driving scene of an autonomous driving vehicle (hereinafter referred to as a vehicle) 101. Figure 11 shows an example in which the vehicle 101 travels in a lane (lane keeping travel) without deviating from the lane LN defined by the dividing line 102. It should be noted that the vehicle 101 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.

[0019] Figure 2 1 is a block diagram schematically showing the overall structure of a vehicle control system 100 of a vehicle 101 to which the map generating device of the present embodiment is applied. 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 electrically connected to the controller 10 respectively.

[0020] The external sensor group 1 is used to detect the vehicle 101 ( Figure 1 ) is a general term for multiple sensors (external sensors) that collect information about the surroundings of the vehicle 101, that is, the external conditions. For example, the external sensor group 1 includes: a laser radar that measures the distance to surrounding vehicles, obstacles, and other objects based on the time it takes to irradiate laser light around the vehicle 101 and receive reflected light; a radar that measures the distance to an object based on the time it takes to irradiate electromagnetic waves and detect reflected waves; and a camera that has an imaging element such as a CCD or CMOS and captures images of the surroundings of the vehicle 101.

[0021] The internal sensor group 2 is a general term for a plurality of sensors (internal sensors) that detect the driving state of the vehicle 101. For example, the internal sensor group 2 includes: a vehicle speed sensor that detects the vehicle speed of the vehicle 101, an acceleration sensor that detects the acceleration in the front-rear direction and the acceleration in the left-right direction (lateral acceleration) of the vehicle 101, a rotation speed sensor that detects the rotation speed of the driving source, and a yaw rate sensor that detects the rotational angular velocity of the center of gravity of the vehicle 101 rotating around the vertical axis. 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, and the operation of the steering wheel, are also included in the internal sensor group 2.

[0022] 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 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 voice, etc.

[0023] The positioning unit (GNSS unit) 4 has a positioning sensor that receives positioning signals transmitted from positioning satellites. Positioning satellites are artificial satellites such as GPS satellites and quasi-zenith satellites. The positioning unit 4 measures the current position (latitude, longitude, altitude) of the vehicle 101 using the positioning information received by the positioning sensor.

[0024] 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 element. The map information includes: road location information, road shape (curvature, etc.) information, and location information of intersections and forks. It should be noted that the map information stored in the map database 5 is different from the high-precision map information stored in the storage unit 12 of the controller 10.

[0025] 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 101 measured by the positioning unit 4 and the map information stored in the map database 5. The current position of the vehicle 101 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 high-precision map information stored in the storage unit 12.

[0026] The communication unit 7 communicates with various servers not shown in the figure by using a network including a wireless communication network represented by the Internet, a mobile phone network, etc., and obtains map information, driving record information, traffic information, etc. from the server regularly or at any time. Not only the driving record information can be obtained, but also the driving record information of the vehicle 101 can be sent to the server via the communication unit 7. The network includes not only a public wireless communication network, but also a closed communication network set up for each specified management area, such as a wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), etc. The obtained map information is output to the map database 5 and the storage unit 12, and the map information is updated.

[0027] The actuator AC is a driving actuator for controlling the driving of the vehicle 101. 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 and an injector actuator for adjusting the opening period and opening time of the injector. When the driving source is a driving motor, the actuator AC includes the driving motor. The brake actuator for operating the brake device of the vehicle 101 and the steering actuator for driving the steering device are also included in the actuator AC.

[0028] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having a computing unit 11 such as a CPU (microprocessor), a storage unit 12 such as a ROM (read-only memory) and a RAM (random access memory), and other peripheral circuits not shown in the figure, such as an I / O (input / output) interface. It should be noted that multiple ECUs with different functions, such as an engine control ECU, a travel motor control ECU, and a brake device ECU, can be separately set up, but for convenience, Figure 2 The controller 10 is shown in FIG. 1 as a collection of these ECUs.

[0029] High-precision and detailed map information for automatic driving is stored in the storage unit 12. The high-precision map information includes: point cloud map information including position information of point clouds identified based on the distance to the object measured by the laser radar and road map information including position information of the dividing line 102 identified based on the image information captured by the camera. The point cloud map information also includes information on the road surface profile such as the unevenness of the road surface identified based on the position information of the point cloud. The road map information includes: road position information, road shape (curvature, etc.) information, road slope information, intersection and fork position information, white line and other dividing line 102 category information, lane number information, lane width and each lane position information (the center position of the lane, lane position boundary line information), landmarks (signals, signs, buildings, etc.) as marks on the map, etc.

[0030] The high-precision map information stored in the storage unit 12 includes: map information obtained from the outside of the vehicle 101 via the communication unit 7 (referred to as external map information) and map information produced by the vehicle 101 itself using the detection values ​​of the external sensor group 1 or the detection values ​​of the external sensor group 1 and the internal sensor group 2 (referred to as internal map information).

[0031] External map information is generated based on driving record information collected by dedicated measurement vehicles and general autonomous vehicles while driving on the road, and distributed to general autonomous vehicles via cloud servers, and map information obtained from other autonomous vehicles through inter-vehicle communication. Map information from cloud servers is generated in areas with high traffic volume such as highways and cities, but not in areas with low traffic volume such as residential areas and suburbs.

[0032] On the other hand, internal map information is map information generated based on driving record information collected while each autonomous driving vehicle (vehicle 101) is driving on the road, and is map information used for autonomous driving of the vehicle 101 (e.g., map information owned solely by the vehicle 101). In areas where map information from the cloud server does not exist, such as newly established roads, the vehicle 101 itself creates an internal map. The internal map information of each autonomous driving vehicle can also be provided to other autonomous driving vehicles as external map information through vehicle-to-vehicle communication.

[0033] The storage unit 12 also stores various control programs, information such as threshold values ​​used in the programs, and the like.

[0034] The computing unit 11 has a vehicle position recognition unit 13, an outside recognition unit 14, an action plan generation unit 15, a travel control unit 16, and a map generation unit 17 as a functional structure. That is, the computing unit 11 such as a CPU (microprocessor) of the controller 10 functions as the vehicle position recognition unit 13, the outside recognition unit 14, the action plan generation unit 15, the travel control unit 16, and the map generation unit 17.

[0035] The vehicle position recognition unit 13 recognizes the position of the vehicle 101 on the map (the vehicle position) with high precision based on the high-precision map information (point cloud map information, road map information) stored in the storage unit 12 and the surrounding information of the vehicle 101 detected by the external sensor group 1. It should be noted that when the position of the vehicle can be measured by external sensors installed on or beside the road, it is also possible to communicate with the sensor through the communication unit 7 to identify the position of the vehicle. The position of the vehicle can also be identified using the position information of the vehicle 101 obtained by the positioning unit 4. The movement information (moving direction, moving distance) of the vehicle can also be calculated based on the detection value of the internal sensor group 2 to identify the position of the vehicle.

[0036] The external recognition unit 14 recognizes the external conditions around the vehicle 101 based on the signals from the external sensor group 1 such as laser radar, radar, camera, etc. For example, the position, speed, acceleration of surrounding vehicles (front vehicles, rear vehicles) traveling around the vehicle 101, the position of surrounding vehicles parked or parked around the vehicle 101, and the position and status of other objects. Other objects include: signs, traffic lights, road dividing lines 102 (white lines, etc.) or stop lines, buildings, guardrails, telephone poles, billboards, pedestrians, bicycles, etc. The status of other objects includes: the color of the traffic light (red, green, yellow), the moving speed and direction of pedestrians and bicycles, etc. Part of the stationary objects among other objects constitutes a landmark that marks the location on the map, and the external recognition unit 14 also recognizes the location and category of the landmark. The external recognition unit 14 recognizes the surface of the road surface, roadside objects, etc. as a point cloud based on the distance to the object measured by the laser radar as the external sensor group 1, and recognizes the contours of the dividing line 102, roadside objects, etc. based on the image information captured by the camera as the external sensor group 1.

[0037] The action plan generation unit 15 generates a driving trajectory (target trajectory) of the vehicle 101 from the current time point to a specified time based on, for example, the target path calculated by the navigation device 6, the high-precision 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. More specifically, based on the point cloud map information or road map information stored in the storage unit 12, a target trajectory of the vehicle 101 is generated on the point cloud map or the road map. 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 from them that complies with the law and meets the criteria of 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.

[0038] The action plan includes a driving plan set per unit time (e.g., 0.1 seconds) during the period from the current time point to a specified time (e.g., 5 seconds), that is, a driving plan set in association with the time per unit time. The driving plan includes information on the vehicle position of the vehicle 101 per unit time and information on the vehicle state. The information on the vehicle position is, for example, two-dimensional coordinate position information on the road, and the information on the vehicle state is speed information indicating the vehicle speed and direction information indicating the orientation of the vehicle 101. Therefore, in the case of accelerating to the target speed within the specified time, the target speed information is included in the action plan. The state of the vehicle can be obtained based on the change in the position of the vehicle per unit time. The driving plan is updated per unit time.

[0039] Figure 12 shows an example of an action plan generated by the action plan generating unit 15 , that is, a travel plan for a scenario in which the vehicle 101 performs lane keeping travel without deviating from the lane LN. Figure 1 Each point P corresponds to the position of the vehicle per unit time from the current time point to the specified time, and these points P are connected in time order, thereby obtaining the target trajectory 110. The target trajectory 110 is generated, for example, along the center line 103 of a pair of dividing lines 102 used to define the lane LN. The target trajectory 110 can also be generated along the past driving track (driving trajectory) contained in the map information. It should be noted that in addition to lane keeping driving, the action plan generation unit 15 also generates various action plans corresponding to overtaking driving in which the vehicle 101 changes lanes and overtakes the vehicle in front, lane change driving in which the lane is changed, deceleration driving or acceleration driving. When generating the target trajectory 110, the action plan generation unit 15 first determines the driving mode and generates the target trajectory 110 based on the driving mode. The information of the target trajectory 110 generated by the action plan generation unit 15 is attached to the map information and stored in the storage unit 12, and is used as a reference when the action plan generation unit 15 generates an action plan during the next driving.

[0040] In the automatic driving mode, the driving control unit 56 controls each actuator AC so that the vehicle 101 travels along the target trajectory 110 generated by the action plan generation unit 15. More specifically, the driving control unit 16 calculates the required driving force for obtaining the target acceleration per unit time calculated by the action plan generation unit 15, taking into account the driving resistance determined by the road slope, etc. in the automatic driving mode. And, 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 101 travels at the target vehicle speed and target acceleration. In addition, in the manual driving mode, the driving control unit 56 controls each actuator AC according to the driving instructions (steering operation, etc.) from the driver obtained by the internal sensor group 2.

[0041] The map generation unit 17 uses the detection values ​​detected by the external sensor group 1 and the current position (absolute latitude and longitude) of the vehicle 101 measured by the positioning unit 4 to generate three-dimensional high-precision map information (internal map information) in the absolute latitude and longitude coordinate system. When a laser radar is used as the external sensor group 1, the surface of the road surface, roadside objects, etc. as the object is identified as a point cloud based on the irradiation direction of the laser and the time until the reflected light is received, and point cloud map information including the position information of the point cloud in the absolute latitude and longitude coordinate system is generated. The point cloud map information also includes information on the reflection intensity of each point cloud detected based on the irradiation intensity and the light intensity of the laser. The map generation unit 17 draws the position information of the point cloud on the point cloud map in sequence, thereby generating point cloud map information around the road where the vehicle 101 has traveled. It should be noted that radar can also be used instead of laser radar to generate point cloud map information.

[0042] On the other hand, when a camera is used as the external sensor group 1, the contours of the dividing line 102, roadside objects, etc. are extracted based on the brightness and color information of each pixel contained in the image information from the camera, and road map information including the position information of the dividing line 102 in the absolute latitude and longitude coordinate system is generated. The map generation unit 17 plots the position information of the dividing line 102 on the road map in sequence, thereby generating road map information around the road traveled by the vehicle 101. The map generation unit 17 can also update the high-precision map information stored in the storage unit 12 based on the newly recognized contours or point clouds of the dividing line 102, roadside objects, etc.

[0043] Figure 3 and Figure 4 is a diagram for explaining high-precision map information generated by the map generation unit 17. Figure 3 shows point cloud map information generated using a laser radar as an external sensor group 1, Figure 4 FIG. 4 shows road map information generated using a camera as the external sensor group 1. Figure 3 As shown in FIG. 1 , the point cloud map information is constituted as the position information of the point cloud corresponding to the surface of the road surface 104, roadside objects, etc. in the absolute latitude and longitude coordinate system (XY coordinate system). Each dividing line 102 in the point cloud map information is recorded as a point cloud corresponding to each dividing line 102, rather than a single object. Figure 4 As shown, the road map information is constituted as position information of the outlines of objects such as dividing lines 102 and roadside objects in an absolute latitude and longitude coordinate system (XY coordinate system), and each dividing line 102 in the road map information is recorded as a single object.

[0044] The vehicle position recognition unit 13 performs the vehicle position estimation process in parallel with the map generation process of the map generation unit 17. That is, the external recognition unit 14 compares the point cloud recognized by the laser radar as the external sensor group 1 with the point cloud contained in the point cloud map information (high-precision map information), and estimates the vehicle position based on the comparison result. Alternatively, the outline of the dividing line 102, roadside objects and other objects recognized by the camera as the external sensor group 1 and the outline of the dividing line 102, roadside objects and other objects contained in the road map information (high-precision map information) are compared, and the vehicle position is estimated based on the comparison result. The map making process and the position estimation process are performed simultaneously according to an algorithm such as SLAM.

[0045] The configuration of the map generating device according to this embodiment will be described. Figure 5 is a diagram showing an example of a travel scene of the vehicle 101 assumed by the map generating device of this embodiment, and Figure 1 Similarly, a scene is shown in which the vehicle 101 does not deviate from the lane LN and performs lane keeping driving. It should be noted that the area in which the point cloud map information is stored in the storage unit 12 is referred to as the point cloud map area ARa, and the area in which the road map information is stored in the storage unit 12 is referred to as the road map area ARb. For example, it is assumed that the point cloud map information generated on the vehicle 101 side is stored in the storage unit 12 as internal map information, and the road map information obtained from other autonomous driving vehicles through inter-vehicle communication is stored in the storage unit 12 as external map information.

[0046] Each map information contains inherent errors due to errors in the measurement of absolute latitude and longitude when the map was generated. Figure 5 As shown, sometimes the vehicle position Pa identified by the vehicle position recognition unit 13 based on the point cloud map information and the vehicle position Pb identified based on the road map information are inconsistent. In this case, when the map information used by the vehicle position recognition unit 13 to recognize the vehicle position is switched, the recognition results of the vehicle positions Pa and Pb deviate.

[0047] In this way, when the recognition result of the vehicle position is deviated, it may be difficult to smoothly control the vehicle 101 when driving in the boundary area between the point cloud map area ARa and the road map area ARb in the automatic driving mode. For example, the deviation of the recognition result of the vehicle position occurs in the direction of travel of the vehicle 101. When the position of the vehicle switches from point Pa behind the direction of travel to point Pb in front of the direction of travel when the map information is switched, it is mistakenly believed that the vehicle 101 is overtraveled relative to the driving plan. In this case, the vehicle 101 may decelerate or brake suddenly, causing a sense of discomfort to the occupants of the vehicle 101 and surrounding vehicles.

[0048] Similarly, when the deviation of the recognition result of the own vehicle position occurs in the opposite direction of the traveling direction of the vehicle 101, it is mistakenly considered that the vehicle 101 is delayed relative to the driving plan, and the vehicle 101 may accelerate suddenly. In addition, when the deviation of the recognition result of the own vehicle position occurs in the vehicle width direction of the vehicle 101, it is mistakenly considered that the vehicle 101 deviates from the target track 110, and the vehicle 101 may turn sharply.

[0049] Therefore, in this embodiment, the inherent errors of the plurality of maps are grasped as the relative positional relationship between the maps, and the plurality of maps are correctly combined so that the recognition result of the vehicle position does not have deviation. That is, the map generation device is configured as follows so that the deviation of the recognition result of the vehicle position can be eliminated by correctly combining the plurality of maps in advance, and smooth driving control can be performed when driving in the boundary area of ​​the plurality of maps.

[0050] Figure 6 This is a block diagram showing the main structure of the map generating device 50 according to the embodiment of the present invention. Figure 2 As part of the vehicle control system 100. Figure 6 As shown, the map generating device 50 includes a controller 10 , an external sensor group 1 , and a positioning unit 4 . Figure 6 The controller 10 includes a dividing line recognition unit 17a and a map information updating unit 17b, and a map generation unit 17 ( Figure 2 ) is a functional structure undertaken by the controller 10. That is, the CPU (microprocessor) and other computing unit 11 of the controller 10 functions as the dividing line recognition unit 17a and the map information update unit 17b. Figure 6 The storage unit 12 stores in advance the point cloud map information of the point cloud map area ARa and the road map information of the road map area ARb.

[0051] The dividing line recognition unit 17a is based on the point cloud map information ( Figure 3 ) identifies the position of the dividing line 102. More specifically, first, based on the position information of the point cloud contained in the point cloud map information, the point cloud corresponding to the road surface 104 on the XY plane is extracted. Next, based on the information of the reflection intensity of the point cloud contained in the point cloud map information, the point cloud corresponding to the road surface 104 extracted and having a reflection intensity greater than a specified intensity is identified as the dividing line 102. The reflection intensity of the point cloud corresponding to the dividing line 102 such as the white line is higher than the reflection intensity of the point cloud corresponding to the road surface 104 other than the dividing line 102, so by presetting a threshold value of the appropriate reflection intensity for identifying them, the point cloud corresponding to the dividing line 102 can be extracted.

[0052] Figure 7 17b is a diagram for explaining the updating of map information by the map information updating unit 17b. Figure 7 As shown, the map information updating unit 17b uses the contour line surrounding the point cloud corresponding to the dividing line 102 extracted by the dividing line recognition unit 17a as the dividing line object 102a corresponding to the contour of the dividing line 102, and adds the position information to the point cloud map information. That is, the dividing line object 102a surrounding the point cloud corresponding to the dividing line 102 is overlapped with the point cloud map, and the point cloud map information stored in the storage unit 12 is updated.

[0053] In addition, the map information updating unit 17b updates at least one of the point cloud map information and the road map information stored in the storage unit 12 based on the point cloud map information and the road map information stored in the storage unit 12 so as to combine the point cloud map with the road map. More specifically, as needed, the absolute latitude and longitude of any map information is corrected, and the map information is updated so that the dividing line object 102a on the point cloud map and the dividing line 102 on the road map are smoothly connected. For example, the map information is corrected by determining the translation movement amount of the map in one of the absolute latitude and longitude coordinate systems and the rotation movement amount centered on the reference point of the map.

[0054] In this way, by correcting the map information so that the dividing line object 102a on the point cloud map and the dividing line 102 on the road map are smoothly connected, the point cloud map and the road map can be correctly combined regardless of the inherent errors contained in each map. In this way, multiple maps used for driving control in the automatic driving mode can be correctly combined in advance, and the deviation of the recognition results of the vehicle positions Pa and Pb generated at the time of map information switching can be eliminated ( Figure 5 ), for smooth driving control when driving in the boundary areas of multiple maps.

[0055] In addition, the updated map information stored in the storage unit 12 can also be sent to other autonomous driving vehicles through inter-vehicle communication, and can also be sent to a map information management server or the like provided outside the vehicle 101. In this case, the internal map information generated on the vehicle 101 side can be shared in an efficient manner.

[0056] Figure 8 It is shown by Figure 6 The flowchart is a flowchart of an example of a process performed by the controller 10 of the vehicle 101. The process shown in the flowchart starts, for example, when new internal map information is generated on the vehicle 101 side or new external map information is obtained from the outside of the vehicle 101, and new high-precision map information is stored in the storage unit 12. First, in S1 (S: processing step), the high-precision map information stored in the storage unit 12 is read to determine whether there are point cloud map information and road map information of the point cloud map area ARa and road map area ARb that are adjacent to each other. When S1 is affirmative (S1: Yes), enter S2, and when it is negative (S1: No), end the process.

[0057] In S2, based on the point cloud map information stored in the storage unit 12, the point cloud corresponding to the road surface 104 is extracted from the point cloud of the point cloud map area ARa. Next, in S3, the point cloud corresponding to the dividing line 102 is extracted from the point cloud corresponding to the road surface 104 extracted in S2. Next, in S4, a dividing line object 102a is generated to surround the point cloud corresponding to the dividing line 102 extracted in S3. Next, in S5, the dividing line object 102a is overlapped with the point cloud map, and the point cloud map information stored in the storage unit 12 is updated. Next, in S6, the point cloud map and the road map are combined so that the dividing line object 102a on the point cloud map and the dividing line 10 on the road map are smoothly connected, and the map information stored in the storage unit 12 is updated to end the processing.

[0058] In this way, the map information is corrected and updated as needed so that the dividing line object 102a on the point cloud map and the dividing line 102 on the road map are smoothly connected, thereby correctly combining the point cloud map and the road map. In addition, by correctly combining the point cloud map and the road map in advance, smooth driving control can be performed when driving in the boundary area between the point cloud map area ARa and the road map area ARb in the automatic driving mode. That is, by correctly combining multiple maps used for driving control in the automatic driving mode in advance, the deviation of the recognition results of the vehicle positions Pa and Pb generated at the time of switching map information can be eliminated, and smooth driving control can be performed when driving in the boundary area of ​​multiple maps.

[0059] The present embodiment can achieve the following effects.

[0060] (1) The map generation device 50 includes: a map generation unit 17, which generates high-precision map information based on the driving record information of the vehicle 101 in the point cloud map area ARa and the driving record information of other autonomous driving vehicles in the road map area ARb adjacent to the point cloud map area ARa; a storage unit 12, which stores internal map information (point cloud map information) generated based on the driving record information of the vehicle 101 and external map information (road map information) generated based on the driving record information of other autonomous driving vehicles; and a map information updating unit 17b, which updates at least one of the point cloud map information and the road map information stored in the storage unit 12 so that the point cloud map and the road map are combined ( Figure 6 ).

[0061] The point cloud map information includes the position information of the point cloud recognized based on the distance information to the object obtained by the vehicle 101. The road map information includes the position information of the dividing line 102 recognized based on the image information obtained by other autonomous driving vehicles. The map generation unit 17 includes a dividing line recognition unit 17a ( Figure 6 The map information updating unit 17b updates at least one of the point cloud map information and the road map information stored in the storage unit 12 based on the position information of the dividing line 102 identified by the dividing line identifying unit 17a and the position information of the dividing line 102 included in the road map information, so as to combine the point cloud map and the road map.

[0062] That is, any map information is corrected as needed so that the dividing line object 102a corresponding to the dividing line 102 identified on the point cloud map and the dividing line 102 on the road map are smoothly connected, thereby correctly combining the point cloud map and the road map. In this way, by correctly combining multiple maps for autonomous driving in advance, it is possible to eliminate the deviation of the recognition result of the vehicle position generated at the time of switching map information, and to perform smooth driving control when driving in the boundary area of ​​multiple maps in the autonomous driving mode.

[0063] (2) The point cloud map information also includes information on the reflection intensity of the point cloud. The dividing line recognition unit 17a extracts the point cloud corresponding to the road surface 104 based on the position information of the point cloud included in the point cloud map information, and recognizes the point cloud with a reflection intensity of a predetermined intensity or more in the extracted point cloud as the dividing line 102 based on the information on the reflection intensity of the point cloud included in the point cloud map information. By using the position information and the information on the reflection intensity, the dividing line 102 can be recognized as an object based on the point cloud map information generated using the laser radar.

[0064] (3) The map information updating unit 17b further adds the position information of the dividing line object 102a corresponding to the dividing line 102 identified by the dividing line identifying unit 17a to the point cloud map information, and updates the point cloud map information. That is, the dividing line object 102a is overlapped with the point cloud map, and the point cloud map information stored in the storage unit 12 is updated. By adding the position information of the dividing line object 102a to the point cloud map information itself, for example, a road map generated and obtained later can be combined with the point cloud map.

[0065] The above-mentioned embodiment can be transformed into various ways. Several modified examples are described below. In the above-mentioned embodiment, an example of combining a point cloud map as an internal map generated on the vehicle 101 side and a road map as an external map obtained from the outside of the vehicle 101 is described, but the first map and the second map are not limited to these. For example, a road map as an internal map generated on the vehicle 101 side and a point cloud map as an external map obtained from the outside of the vehicle 101 can also be combined. It is also possible to combine a point cloud map and a road map as multiple internal maps generated by splitting on the vehicle 101 side. It is also possible to combine a point cloud map and a road map as multiple external maps obtained from the outside of the vehicle 101. In addition, an example of combining an internal map generated on the vehicle 101 side and an external map obtained from other autonomous driving vehicles through vehicle-to-vehicle communication is described, but it can also be combined with an external map distributed by a cloud server.

[0066] In the above embodiment, an example is described in which the map generation device 50 constitutes a part of the vehicle control system 100, but the map generation device is not limited to this. For example, it can also constitute a part of a map information management server or the like installed outside the vehicle 101. In this case, for example, the point cloud map and the road map obtained from each vehicle are combined on the server side.

[0067] In the above embodiment, Figure 5 In the examples described above, the deviation between the point cloud map and the road map occurs on a plane, but the same method can also be applied when the deviation between the point cloud map and the road map occurs in the height direction.

[0068] One or more of the above-described embodiments and modifications may be arbitrarily combined, and modifications may be combined with each other.

[0069] According to the present invention, a plurality of maps can be correctly combined, so that deviations in the recognition results of the vehicle position can be eliminated, and smooth driving control can be performed when driving in the boundary area of ​​a plurality of maps.

[0070] The present invention has been described above in conjunction with preferred embodiments. 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 disclosure of the claims set forth below.

Claims

1. A map generating device (50), characterized in that: have: A map generating unit (17) for generating a map based on a first driving record of a first vehicle in a first area and a second driving record of a second vehicle in a second area adjacent to the first area; A storage unit (12) storing information of a first map generated based on the first driving record and information of a second map generated based on the second driving record; as well as a map information updating unit (17b) for updating information of at least one of the first map and the second map stored in the storage unit (12) so as to combine the first map with the second map; The information of the first map includes position information of a point cloud recognized based on distance information to an object obtained by the first vehicle, The information of the second map includes position information of a dividing line recognized based on image information obtained by the second vehicle, The map generating unit (17) includes a dividing line identifying unit (17a) for identifying the position of the dividing line based on the information of the first map stored in the storage unit (12). The map information updating unit (17b) updates information of at least one of the first map and the second map stored in the storage unit (12) based on the position information of the dividing line identified by the dividing line identification unit (17a) and the position information of the dividing line contained in the information of the second map, so as to combine the first map and the second map.

2. The map generating device (50) according to claim 1, characterized in that: The information of the first map also includes information of the reflection intensity of the point cloud. The dividing line recognition unit (17a) extracts a point cloud corresponding to a road surface based on the position information of the point cloud contained in the information of the first map, and recognizes a point cloud in the extracted point cloud whose reflection intensity is greater than a specified intensity as the dividing line based on the information of the reflection intensity of the point cloud contained in the information of the first map.

3. The map generating device (50) according to claim 1 or 2, characterized in that: The map information updating unit (17b) further adds the position information of the dividing line identified by the dividing line identifying unit (17a) to the information of the first map, thereby updating the information of the first map.

4. The map generating device (50) according to claim 2, characterized in that: The map information updating unit (17b) generates a contour line surrounding the point cloud identified as the dividing line by the dividing line identification unit (17a) as a dividing line object corresponding to the contour of the dividing line, makes the generated dividing line object overlap with the first map, and updates the information of the first map stored in the storage unit (12).

5. The map generating device (50) according to claim 4, characterized in that: The map information updating unit (17b) updates the information of at least one of the first map and the second map stored in the storage unit (12) by determining the translation movement amount and rotation movement amount of at least one of the first map and the second map in the absolute latitude and longitude coordinate system so that the dividing line object generated by the map information updating unit (17b) and the dividing line included in the information of the second map are smoothly connected.

Images