Vehicle position recognition device

Abstract

The present invention provides a vehicle location recognition device (50), comprising: a storage unit (12) storing information of a first map of a first region and information of a second map of a second region adjacent to the first region via an overlapping region; a vehicle location recognition unit (13) that identifies a first position of a vehicle (101) in the overlapping region based on the information of the first map and identifies a second position of the vehicle (101) in the overlapping region based on the information of the second map; a driving trajectory generation unit (51) that generates a first driving trajectory of the vehicle (101) in the overlapping region based on the change of the first position over time and generates a second driving trajectory of the vehicle (101) in the overlapping region based on the change of the second position over time; and a map information updating unit (52) that updates the information of the first map based on the first driving trajectory and the second driving trajectory so that the first driving trajectory and the second driving trajectory overlap.

Description

Technical Field

[0001] This invention relates to a vehicle location identification device for identifying the location of a vehicle. Background Technology

[0002] As such a device, there are known devices for implementing driving control of autonomous vehicles (see, for example, Patent Document 1). In the device described in Patent Document 1, the vehicle's own position is estimated by identifying the external environment around the vehicle, and high-precision road map information is extracted sequentially from a road map information database based on the own position, and the extracted map information is used to implement driving control of the vehicle.

[0003] However, sometimes a vehicle travels in the boundary areas of multiple adjacent maps. However, there are sometimes inherent errors in the map information of adjacent maps. Therefore, if the vehicle's position is estimated as described in Patent Document 1 above, the estimated position will be biased. When controlling driving actions based on map information, it may be difficult to perform smooth driving control when traveling in the boundary areas of multiple maps.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent Document 1: Japanese Patent Application Publication No. 2019-64562 (JP2019-064562A). Summary of the Invention

[0007] A vehicle location recognition device according to one embodiment of the present invention comprises: a storage unit storing information of a first map of a first region and information of a second map of a second region adjacent to the first region via an overlapping region; a location recognition unit that recognizes a first location of a vehicle in the overlapping region based on the information of the first map stored in the storage unit, and recognizes a second location of a vehicle in the overlapping region based on the information of the second map; a driving trajectory generation unit that generates a first driving trajectory of the vehicle in the overlapping region based on the change of the first location recognized by the location recognition unit over time, and generates a second driving trajectory of the vehicle in the overlapping region based on the change of the second location recognized by the location recognition unit over time; and a map information updating unit that updates the information of the first map based on the first and second driving trajectories generated by the driving trajectory generation unit, so that the first and second driving trajectories overlap. Attached Figure Description

[0008] The objectives, features, and advantages of the present invention are further illustrated by the following description of embodiments in conjunction with the accompanying drawings.

[0009] Figure 1This is a diagram illustrating an example of a driving scenario of an autonomous vehicle using a vehicle location recognition device according to an embodiment of the present invention.

[0010] Figure 2 This is a block diagram that schematically illustrates the overall structure of the vehicle control system of an autonomous vehicle using a vehicle location recognition device according to an embodiment of the present invention.

[0011] Figure 3 This is a diagram illustrating an example of a driving scenario for an autonomous vehicle as envisioned by the vehicle location recognition device according to an embodiment of the present invention.

[0012] Figure 4 This is a block diagram illustrating the main structural components of a vehicle location identification device according to an embodiment of the present invention.

[0013] Figure 5A It is shown by Figure 4 The image shows an example of a driving trajectory generated by the driving trajectory generation unit based on internal map information.

[0014] Figure 5B It is shown by Figure 4 The image shows an example of a driving trajectory generated by the driving trajectory generation unit based on external map information.

[0015] Figure 6 It is used to explain by Figure 4 The map information update department updates the internal map information.

[0016] Figure 7 It is shown by Figure 4 A flowchart of an example of the processing performed by the controller. Detailed Implementation

[0017] The following is for reference Figures 1 to 7 The embodiments of the present invention are described below. The vehicle location recognition device of the embodiments of the present invention can be applied to vehicles with autonomous driving functions (autonomous driving vehicles). Autonomous driving vehicles include not only vehicles that operate only in an autonomous driving mode without driver operation, but also vehicles that operate in both autonomous driving mode and manual driving mode based on driver operation.

[0018] Figure 1 This is a diagram illustrating an example of a driving scenario for an autonomous vehicle (hereinafter referred to as vehicle) 101. Figure 1The diagram illustrates an example of vehicle 101 maintaining its lane without deviating from the lane LN defined by dividing line 102 (lane-keeping driving). It should be noted that vehicle 101 can be any of the following: an engine vehicle with an internal combustion engine as its driving source, an electric vehicle with a drive motor as its driving source, or a hybrid vehicle with both an engine and a drive motor as driving sources.

[0019] Figure 2 This is a block diagram that schematically illustrates the overall structure of the vehicle control system 100 of the vehicle 101 to which the vehicle location identification device of this embodiment is applied. Figure 2 As shown, the vehicle control system 100 mainly includes a controller 10 and external sensor group 1, internal sensor group 2, input / output device 3, positioning unit 4, map database 5, navigation device 6, communication unit 7, and driving actuator AC, which are electrically connected to the controller 10.

[0020] External sensor group 1 is used to detect vehicle 101 ( Figure 1 The term "external sensor" refers to a collection of multiple sensors that provide information about the surrounding environment, i.e., the external conditions. For example, external sensor group 1 includes: a lidar that measures the distance from vehicle 101 to surrounding obstacles by measuring the scattered light relative to the omnidirectional illumination light of vehicle 101; a radar that detects other vehicles or obstacles around vehicle 101 by illuminating electromagnetic waves and detecting the reflected waves; and a camera mounted on vehicle 101 and equipped with imaging elements such as CCD and CMOS to capture images of the vehicle 101's surroundings (front, rear, and sides).

[0021] Internal sensor group 2 is a collective term for multiple sensors (internal sensors) that detect the driving status of vehicle 101. For example, internal sensor group 2 includes: a vehicle speed sensor to detect the speed of vehicle 101; an acceleration sensor to detect the longitudinal and lateral acceleration (lateral acceleration) of vehicle 101; a speed sensor to detect the rotational speed of the driving source; and a yaw rate sensor to detect the rotational angular velocity of the vehicle 101's center of gravity around its vertical axis. Sensors that detect driver operations in manual driving mode, such as operations on the accelerator pedal, brake pedal, and steering wheel, are also included in internal sensor group 2.

[0022] Input / output device 3 is a general term for devices that input commands to the driver and output information to the driver. For example, input / output device 3 includes: various switches for the driver to input various commands by operating the control components, a microphone for the driver to input commands by voice, a display that provides information to the driver by displaying images, and 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 uses the positioning information received by the positioning sensor to determine the current position (latitude, longitude, and altitude) of the vehicle 101.

[0024] Map database 5 is a device that stores general map information used in navigation device 6, and is composed of, for example, a hard disk and semiconductor components. The map information includes: road location information, road shape (curvature, etc.) information, and the location information of intersections and forks in the road. It should be noted that the map information stored in map database 5 is different from the high-precision map information stored in storage unit 12 of 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 user along the target path. The destination is input and the user is guided along the target path via the input / output device 3. The target path is calculated based on the current position of the vehicle 101 determined by the positioning unit 4 and map information stored in the map database 5. Alternatively, the current position of the vehicle 101 can be determined using the detection values ​​of the external sensor group 1, and the target path can be calculated based on this current position and high-precision map information stored in the storage unit 12.

[0026] Communication unit 7 communicates with various servers (not shown) via a network including wireless communication networks such as the Internet and mobile phone networks, periodically or at any time, to obtain map information, driving record information, and traffic information from the servers. It can also not only obtain driving record information but also send the driving record information of vehicle 101 to the server via communication unit 7. The network includes not only public wireless communication networks but also closed communication networks set up for each designated management area, such as wireless local area networks, Wi-Fi, and Bluetooth. The obtained map information is output to map database 5 and storage unit 12, and the map information is updated.

[0027] The actuator AC is a driving actuator used to control the movement of the vehicle 101. When the driving source is an engine, the actuator AC includes a throttle actuator for adjusting the opening of the engine's throttle valve and an injector actuator for adjusting the opening timing and duration of the injectors. When the driving source is a travel motor, the actuator AC includes the travel motor. A braking actuator that operates the vehicle 101's braking system and a steering actuator that drives the steering system are also included in the actuator AC.

[0028] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 is configured as a computer including an arithmetic unit 11 such as a CPU (microprocessor), a storage unit 12 such as ROM (read-only memory) and RAM (random access memory), and other peripheral circuits (not shown) such as I / O (input / output) interfaces. It should be noted that multiple ECUs with different functions, such as an engine control ECU, a drive motor control ECU, and a braking system ECU, can be set up separately, but for convenience, they are shown separately in the following diagram. Figure 2 The controller 10 is shown as a collection of these ECUs.

[0029] The storage unit 12 stores high-precision, detailed road map information for autonomous driving. The road map information includes: road location information, road shape (curvature, etc.) information, road slope information, location information of intersections and forks, type and location information of dividing lines such as white lines, information on the number of lanes, lane width and location information of each lane (center position of the lane, information on the boundary lines of the lane), location information of landmarks (traffic lights, signs, buildings, etc.) that serve as markers on the map, and information on road surface conditions such as unevenness.

[0030] The 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 created 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 includes, for example, general-purpose maps (called cloud maps) generated from data collected by dedicated survey vehicles and general autonomous vehicles driving on roads and distributed to general autonomous vehicles via cloud servers. External maps are generated in areas with high traffic volume, such as highways or towns, but not in areas with low traffic volume, such as residential areas or suburbs.

[0032] On the other hand, internal map information is a map (called an environment map) composed of point cloud data generated by mapping based on data collected by each autonomous vehicle driving on the road using technologies such as SLAM (Simultaneous Localization and Mapping). External map information is shared by vehicle 101 and other autonomous vehicles; in contrast, internal map information is dedicated map information generated solely by vehicle 101 and used for its autonomous driving (e.g., map information unique to vehicle 101). In areas where external map information does not exist, such as newly constructed roads, vehicle 101 creates its own environment map. Additionally, internal map information can be provided to the server device and other autonomous vehicles via communication unit 7.

[0033] The storage unit 12 also stores various control programs, thresholds used in the programs, and other information.

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

[0035] The vehicle position recognition unit 13 accurately identifies the position of the vehicle 101 on the map (vehicle position) based on the high-precision detailed road map information (external map information and internal 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 vehicle position can be determined using external sensors installed on or beside the road, the vehicle position can also be identified by communicating with these sensors via the communication unit 7. The vehicle position can also be identified using the position information of the vehicle 101 obtained by the positioning unit 4. Furthermore, the vehicle's movement information (movement direction and movement distance) can be calculated based on the detection values ​​of the internal sensor group 2, thereby identifying the vehicle position.

[0036] The external environment identification unit 14 identifies the external conditions around the vehicle 101 based on signals from the external sensor group 1, such as lidar, radar, and cameras. For example, it identifies the position, speed, and acceleration of surrounding vehicles (vehicles in front and behind) traveling around the vehicle 101, the position of surrounding vehicles parked or stationary around the vehicle 101, and the position and state of other objects. Other objects include signs, traffic lights, road markings (white lines, etc.), stop lines, buildings, guardrails, utility poles, signs, pedestrians, bicycles, etc. The state of other objects includes the color of traffic lights (red, green, yellow), the speed and direction of pedestrians or bicycles, etc. Some stationary objects among these other objects constitute landmarks that serve as indicators of location on a map; the external environment identification unit 14 also identifies the location and category of these landmarks.

[0037] The action plan generation unit 15 generates, for example, a driving trajectory (target trajectory) of vehicle 101 from the current time to a predetermined time, based on the target path calculated by the navigation device 6, 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 environment recognition unit 14. More specifically, it generates the target trajectory of vehicle 101 on the external map or the internal map based on the external map information or internal map information stored in the storage unit 12. When multiple candidate trajectories exist on the target path, the action plan generation unit 15 selects the best trajectory that complies with laws and regulations and meets the criteria of efficient and safe driving, and designates 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 in units of time (e.g., 0.1 seconds) for the period from the current time point up to a specified time (e.g., 5 seconds). That is, a driving plan set in a correspondence with each unit of time. The driving plan includes information on the vehicle's position and vehicle status per unit of time. The vehicle's position information includes, for example, two-dimensional coordinates on the road, and the vehicle status information includes vehicle speed information and direction information indicating the vehicle's orientation. Therefore, if the vehicle accelerates to a target speed within the specified time, the target speed information is included in the action plan. The vehicle status can be calculated based on the change in the vehicle's position per unit of time. The driving plan is updated every unit of time.

[0039] Figure 1 An example of an action plan generated by the action plan generation unit 15 is shown, namely, a driving plan for a scenario in which vehicle 101 maintains its lane without deviating from lane LN. Figure 1Each point P corresponds to the vehicle's position in each unit of time up to a specified time from the current point in time. By connecting these points P in chronological order, the target trajectory 110 is obtained. The target trajectory 110 is generated along the center line 103 of a pair of dividing lines 102 of the specified lane LN. The target trajectory 110 can also be generated along past driving tracks (driving trajectories) contained in the map information. It should be noted that in the action plan generation unit 15, in addition to lane-keeping driving, various action plans corresponding to overtaking driving (changing lanes to pass the vehicle in front), lane-changing driving (changing lanes), deceleration driving, or acceleration driving are also generated. 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. It will be taken into consideration when the action plan generation unit 15 generates an action plan for the next driving.

[0040] In autonomous driving mode, the driving control unit 16 controls each actuator AC to make the vehicle 101 travel along the target trajectory 110 generated by the action plan generation unit 15. More specifically, the driving control unit 16 considers the driving resistance determined by road gradient and other factors in autonomous driving mode, and calculates the required driving force to obtain the target acceleration per unit time calculated by the action plan generation unit 15. Furthermore, feedback control is performed on the actuator ACs to make the actual acceleration detected by, for example, the internal sensor group 2, the target acceleration. That is, the actuator ACs are controlled to make the vehicle 101 travel at the target speed and target acceleration. It should be noted that in manual driving mode, the driving control unit 16 controls each actuator AC according to driving commands (steering operations, etc.) obtained from the driver by the internal sensor group 2.

[0041] While driving in manual driving mode, the map generation unit 17 uses detection values ​​from the external sensor group 1 and the current position (absolute longitude and latitude) of the vehicle 101 determined by the positioning unit 4 to generate an environmental map composed of three-dimensional point cloud data in an absolute longitude and latitude coordinate system. Specifically, from camera images acquired by the camera, edges representing object contours are extracted based on the brightness and color information of each pixel, and feature points are extracted using this edge information. Feature points are, for example, the intersection of edges, corresponding to the corners of buildings, road signs, etc. The map generation unit 17 calculates the distance to the extracted feature points and sequentially plots the feature points on the environmental map, thereby generating an environmental map of the area surrounding the road through which the vehicle has traveled. Alternatively, instead of a camera, data acquired by radar or lidar can be used to extract feature points of objects around the vehicle and generate an environmental map.

[0042] The vehicle position recognition unit 13 and the map generation unit 17 perform vehicle position estimation processing in parallel. That is, the vehicle's position is estimated based on the changes in the positions of feature points over time. For example, map creation processing and position estimation processing are performed simultaneously according to the SLAM algorithm. The map generation unit 17 can generate environment maps not only when driving in manual driving mode but also when driving in automatic driving mode. If an environment map has already been generated and stored in the storage unit 12, the map generation unit 17 can also update the environment map based on newly obtained feature points.

[0043] The structure of the vehicle location identification device according to this embodiment will be described. Figure 3 This diagram illustrates an example of a driving scenario of vehicle 101 as envisioned by the vehicle location recognition device of this embodiment. Figure 1 Similarly, the scenario shown illustrates a vehicle 101 maintaining its lane without deviating from lane LN. It should be noted that, hereinafter, the area in storage unit 12 containing internal maps such as environmental maps will be referred to as the internal map area ARa, and the area in storage unit 12 containing external maps such as cloud maps will be referred to as the external map area ARb.

[0044] Each map information contains inherent errors, such as those arising from the measurement errors of absolute latitude and longitude when the map was generated. Therefore, such as... Figure 3 As shown, sometimes the vehicle position Pa identified by the vehicle position recognition unit 13 based on internal map information and the vehicle position Pb identified based on external map information are inconsistent. In this case, the recognition results of vehicle positions Pa and Pb deviate due to the timing of switching the map information used by the vehicle position recognition unit 13 to identify the vehicle position.

[0045] Thus, when driving in autonomous driving mode in the boundary area between the internal map region ARa and the external map region ARb with a deviation in the vehicle's position recognition result, smooth driving control of vehicle 101 may be difficult. For example, if the deviation in the vehicle's position recognition result occurs in the direction of travel of vehicle 101, and the vehicle's position switches from point Pa behind the direction of travel to point Pb in front of the direction of travel during map information switching, it may be incorrectly identified as vehicle 101 overtraveling relative to the driving plan. In this case, vehicle 101 will suddenly decelerate or brake, which may cause discomfort to the occupants of vehicle 101 and surrounding vehicles.

[0046] Similarly, when the deviation in the vehicle's position recognition result occurs in the opposite direction to the vehicle 101's travel direction, it will be incorrectly identified as a delay in the vehicle 101 relative to the travel plan, and the vehicle 101 may accelerate suddenly. In addition, when the deviation in the vehicle's position recognition result occurs in the vehicle 101's width direction, it will be incorrectly identified as the vehicle 101 deviating from the target trajectory 110, and the vehicle 101 may make an emergency turn.

[0047] Therefore, in this embodiment, the inherent errors of multiple maps are understood as the relative positional relationships between the maps, and the multiple maps are correctly combined to ensure that the vehicle's position recognition result is not biased. That is, the vehicle position recognition device is configured as follows so that by correctly combining multiple maps in advance, the bias in the vehicle position recognition result can be eliminated, and smooth driving control can be performed when driving in the boundary area of ​​multiple maps.

[0048] Figure 4 This is a block diagram illustrating the main structural components of a vehicle location identification device 50 according to an embodiment of the present invention. The vehicle location identification device 50 comprises... Figure 2 It is part of the vehicle control system 100. For example... Figure 4 As shown, the vehicle location identification device 50 has a controller 10 and an external sensor group 1. Figure 4 In addition to the vehicle position recognition unit 13, the controller 10 also has a driving trajectory generation unit 51 and a map information update unit 52, which serve as the computing unit 11. Figure 2 The functional structure undertaken by the controller 10 includes its CPU (microprocessor) and other computing units 11, which, in addition to the vehicle position recognition unit 13, also function as the driving trajectory generation unit 51 and the map information updating unit 52. Figure 4 The storage unit 12 pre-stores the internal map information of the internal map area ARa and the external map information of the external map area ARb.

[0049] The trajectory generation unit 51 generates a trajectory in the overlapping area ARc between the internal map region ARa and the external map region ARb. Figure 3 Based on the vehicle positions Pa and Pb identified by the vehicle position recognition unit 13, the actual driving trajectories La and Lb of the vehicle 101 are generated. More specifically, the vehicle positions Pa(t1, ..., t2) and Pb(t1, ..., t2) during the period t1 to t2 when the vehicle positions Pa and Pb are identified are connected in chronological order, thereby generating the driving trajectories La(t1 to t2) and Lb(t1 to t2) of the overlapping region ARc.

[0050] The map information updating unit 52 updates the internal map information based on the driving trajectories La and Lb of the overlapping area ARc generated by the driving trajectory generation unit 51, so that the driving trajectories La and Lb overlap.

[0051] Figure 5A and Figure 5B This is a diagram showing an example of driving trajectories La and Lb generated by the driving trajectory generation unit 51. Figure 5A The driving trajectory La, generated based on internal map information, is shown. Figure 5B The driving trajectory Lb, generated based on external map information, is shown. Also, Figure 6 This is a diagram used to illustrate how the map information update unit 52 updates the internal map information.

[0052] Sometimes, the absolute latitude and longitude values ​​added to feature points in the internal map information and those added to feature points in the external map information are inconsistent due to measurement errors in the absolute latitude and longitude values ​​during map generation. In this case, the vehicle position Pa(t1, ..., t2) identified by comparing the surrounding information of vehicle 101 detected by external sensor group 1 with the internal map information is inconsistent with the vehicle position Pb(t1, ..., t2) identified by comparing with the external map information. Therefore, the driving trajectories La and Lb generated based on the changes in vehicle positions Pa and Pb over time are inconsistent, such as... Figure 5A , Figure 5B As exaggeratedly shown, different positional information (coordinate values) are added to the same absolute longitude and latitude coordinate system (XY coordinate system) on the driving trajectories La and Lb.

[0053] In the overlapping region ARC( Figure 3 When a map includes characteristic road shapes such as curves and multiple forks, it's possible to overlap the feature points of the map information, thus combining the maps. However, when the overlapping area (ARc) contains only straight roads or a checkerboard pattern of recurring intersections of the same shape, it's difficult to overlap the feature points and combine the maps. Furthermore, when combining maps generated before and after changes to road markings, landmark positions, and road surface conditions due to road construction, it's also difficult to ensure that the feature points of the map information overlap and combine the maps.

[0054] On the other hand, the driving trajectories La and Lb obtained from the actual driving records in manual driving mode will have characteristic shapes even on a simple straight road due to the swaying of the driver's steering operation. Furthermore, the driving trajectories La(t1~t2) and Lb(t1~t2) generated by the vehicle position recognition unit 13 through a single algorithm within the same period t1~t2 have the same shape.

[0055] like Figure 6 As shown, the map information update unit 52 updates the internal map information by correcting the absolute latitude and longitude of at least one of the map information, such as the internal map information, in such a way that the driving trajectories La and Lb overlap. More specifically, it corrects the internal map information stored in the storage unit 12 by determining the translational movement (ΔX, ΔY) of the internal map in the absolute latitude and longitude coordinate system (XY coordinate system) and the rotational movement θ centered on the reference point Oa of the internal map, thereby updating the internal map information. For example, the translational movement (ΔX, ΔY) and rotational movement θ of the internal map are determined by the least squares method to minimize the difference (e.g., the difference in the Y-axis direction) between the driving trajectory La and the driving trajectory Lb.

[0056] In this way, the absolute latitude and longitude of the map information are corrected so that the actual driving trajectories La and Lb obtained in the overlapping area ARc coincide with each other. This allows multiple maps to be correctly combined without considering the inherent errors contained in each map. As a result, multiple maps used for driving control in autonomous driving mode are correctly combined in advance, and the deviation of the vehicle position Pa and Pb recognition results generated when the map information is switched is eliminated. Therefore, smooth driving control can be performed when driving in the boundary area of ​​multiple maps.

[0057] The updated internal map information stored in storage unit 12 can also be sent to other autonomous vehicles via vehicle-to-vehicle communication, or to a map information management server located outside vehicle 101. In this case, by pre-correcting the internal map information based on universal map information, i.e., external map information, which cannot be modified on the vehicle 101 side, the internal map information generated on the vehicle 101 side can be shared in an effective manner.

[0058] Figure 7 It is shown by Figure 4The flowchart illustrates an example of the processing performed by the controller 10. The processing shown in the flowchart begins, for example, after the vehicle 101 has been driven in manual driving mode. First, in S1 (S: processing step), the identification results of the vehicle's positions Pa and Pb, which are part of the driving record in manual driving mode, are read in. Next, in S2, based on the driving record read in S1, it is determined whether the vehicle 101 has driven in the overlapping area ARc, i.e., whether there exists a period t1 to t2 during which the vehicle's positions Pa and Pb are identified. If S2 is affirmative (S2: Yes), the process proceeds to S3; if it is negative (S2: No), the process ends.

[0059] In S3, based on the identification results of the vehicle's positions Pa(t1, ..., t2) and Pb(t1, ..., t2) in the overlapping region ARc, the driving trajectories La(t1~t2) and Lb(t1~t2) in the overlapping region ARc are generated. Next, in S4, the translational movement (ΔX, ΔY) and rotational movement θ of the internal map are determined by ensuring that the driving trajectories La(t1~t2) and Lb(t1~t2) coincide. Next, in S5, the absolute latitude and longitude of the internal map are corrected based on the coincidence results in S4, the internal map information stored in the storage unit 12 is updated, and the processing ends.

[0060] In this way, the internal map information is pre-corrected based on the vehicle's position recognition results when driving in the overlapping area ARC in manual driving mode. This enables smooth driving control when driving in the boundary area between the internal map area ARa and the external map area ARb in autonomous driving mode. That is, multiple maps used for driving control in autonomous driving mode are correctly combined in advance, thereby eliminating the deviation of the vehicle's position Pa and Pb recognition results caused when switching map information, and enabling smooth driving control when driving in the boundary area of ​​multiple maps.

[0061] The following effects can be achieved by adopting this implementation method.

[0062] (1) The vehicle position recognition device 50 includes: a storage unit 12 that stores internal map information of an internal map region ARa and external map information of an external map region ARb adjacent to the internal map region ARa via an overlapping region ARc; a vehicle position recognition unit 13 that identifies the vehicle position Pa of the vehicle 101 in the overlapping region ARc based on the internal map information stored in the storage unit 12, and identifies the vehicle position Pb of the vehicle 101 in the overlapping region ARc based on the external map information; a driving trajectory generation unit 51 that generates a driving trajectory La of the vehicle 101 in the overlapping region ARc based on the change of the vehicle position Pa identified by the vehicle position recognition unit 13 over time, and generates a driving trajectory Lb of the vehicle 101 in the overlapping region ARc based on the change of the vehicle position Pb identified by the vehicle position recognition unit 13 over time; and a map information updating unit 52 that updates the internal map information based on the driving trajectories La and Lb generated by the driving trajectory generation unit 51, so that the driving trajectories La and Lb coincide. Figure 4 ).

[0063] That is, the absolute latitude and longitude of the internal map information are corrected and updated so that the driving trajectories La and Lb of the overlapping area ARc coincide with each other. This allows multiple maps to be correctly combined without considering the inherent errors contained in each map. As a result, the deviation in vehicle position recognition caused by map information switching can be eliminated, and smooth driving control can be performed when driving in the boundary areas of multiple maps.

[0064] (2) The driving trajectory generation unit 51 generates driving trajectories La(t1~t2) and Lb(t1~t2) for the period t1~t2 during which the vehicle positions Pa and Pb are identified by the vehicle position recognition unit 13. That is, by making the driving trajectories La(t1~t2) and Lb(t1~t2) identified in the same period coincide with each other, multiple maps can be correctly combined.

[0065] (3) The internal map, external map, and driving trajectory La and Lb are defined in a single absolute longitude and latitude coordinate system (XY coordinate system). Figures 5A-6 The map information updating unit 52 updates the internal map information by determining the translational movement (ΔX, ΔY) and rotational movement θ of the internal map in the XY coordinate system. Figure 6 In this case, the translational movement (ΔX, ΔY) and rotational movement θ can be determined by means of least squares, for example, in a manner that minimizes the difference between the travel trajectories La and Lb in the Y-axis direction of the XY coordinate system.

[0066] (4) The vehicle location recognition device 50 further includes: an external sensor group 1 mounted on the vehicle 101 to detect the external conditions around the vehicle 101; and a map generation unit 17 that generates a map of the area around the vehicle 101, i.e., an internal map, based on the external conditions detected by the external sensor group 1. Figure 2 , Figure 4 The map information update unit 52 updates the information of the internal map generated by the map generation unit 17. That is, based on the external map information that is used by multiple autonomous vehicles, including vehicle 101, and cannot be rewritten on the side of each vehicle 101, the location information of the dedicated map information, i.e., the internal map information, of each vehicle 101 is corrected and updated.

[0067] The above-described embodiments can be modified in various ways. Several modifications are described below. In the above embodiments, an example of combining an internal map such as an environmental map and an external map such as a cloud map was described, but the first map and the second map are not limited to this. For example, an internal map can also be combined with an external map obtained from other autonomous vehicles via vehicle-to-vehicle communication. Multiple external maps can also be combined, as can multiple internal maps generated by segmentation. In this case, multiple internal maps are generated by segmentation in a way that produces sufficient overlapping areas, thereby enabling proper overlap of driving trajectories and correct combination of multiple maps.

[0068] In the above embodiment, an example was described where the vehicle location recognition device 50 is part of the vehicle control system 100, but the vehicle location recognition device is not limited to this. For example, it could also be a device that forms part of a map information management server or the like located outside the vehicle 101. In this case, for example, the vehicle's location recognition result (driving record information) is obtained from each vehicle, and multiple maps are combined on the server side.

[0069] In the above embodiments, Figure 3 , Figures 5A-6 The example illustrates how the deviations of multiple maps occur in the XY plane, but the same method can be used to combine multiple maps when the deviations occur in the Z-axis direction.

[0070] It is possible to combine one or more of the above-described embodiments and variations, and to combine the variations with each other.

[0071] By employing this invention, multiple maps can be correctly combined, thereby eliminating deviations in vehicle position identification and enabling smooth driving control when driving in the boundary areas of multiple maps.

[0072] The present invention has been described above in conjunction with preferred embodiments, but those skilled in the art should understand that various modifications and alterations can be made without departing from the scope of the claims described below.

Claims

1. A vehicle location identification device (50), characterized in that, have: Storage unit (12) stores information of the internal map of the internal map area and information of the external map of the external map area adjacent to the internal map area via the overlapping area of ​​the internal map area; The determination unit obtains the driving record of the vehicle (101) and determines whether the vehicle (101) has driven through the overlapping area based on the driving record; The location recognition unit (13) determines that the vehicle (101) has passed through the overlapping area. Based on the information of the internal map stored in the storage unit (12), it identifies the position of the vehicle (101) in the driving record that is driving in the overlapping area on the internal map, i.e., the first position. Based on the information of the external map, it identifies the position of the vehicle (101) in the driving record that is driving in the overlapping area on the external map, i.e., the second position. The driving trajectory generation unit (51) generates a first driving trajectory on the internal map based on the change of the first position identified by the position recognition unit (13) over time, and generates a second driving trajectory on the external map based on the change of the second position identified by the position recognition unit (13) over time, which is determined to be driving in the overlapping area. as well as The map information update unit (52) updates the information of the internal map based on the first driving trajectory and the second driving trajectory generated by the driving trajectory generation unit (51) so that the first driving trajectory and the second driving trajectory overlap.

2. The vehicle location identification device (50) according to claim 1, characterized in that, The driving trajectory generation unit (51) generates the first driving trajectory and the second driving trajectory during the period when the first position and the second position are identified by the position recognition unit (13).

3. The vehicle location identification device (50) according to claim 1, characterized in that, The internal map, the external map, the first driving trajectory, and the second driving trajectory are defined in a single coordinate system. The map information update unit (52) updates the information of the internal map by determining the amount of translation and rotation of the internal map in the coordinate system.

4. The vehicle location identification device (50) according to any one of claims 1 to 3, characterized in that, The vehicle location identification device (50) is mounted on the vehicle (101).

Images