Map generation device and vehicle position recognition device
The map generation device reduces map data by generating first and second maps based on lane markings and feature points, enhancing vehicle position recognition efficiency.
Patent Information
- Application Number
- JP2021037060
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2021-03-09
- Publication Date
- 2024-11-14
- Estimated Expiration
- 2041-03-09
AI Technical Summary
As map accuracy increases and target areas expand, the amount of data in the map itself increases, making it challenging to sufficiently reduce the data using conventional methods like deleting overlapping partial maps.
A map generation device that includes an on-vehicle detector to detect the surrounding situation, recognizes lane markings, generates a first map based on these markings, extracts feature points, and deletes a second map corresponding to a predetermined distance behind the vehicle, while a vehicle position recognition device recognizes the vehicle's position on either the first or second map based on detected data.
This approach effectively reduces the amount of map data and processing load, allowing for efficient vehicle position recognition even in areas without clear lane markings.
Smart Images

Figure 0007583649000001 
Figure 0007583649000002 
Figure 0007583649000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a map generating device that generates a map, and a vehicle position recognizing device that recognizes the position of a vehicle by using a map generated by the map generating device. [Background technology]
[0002] Conventionally, as this type of device, a device that generates an overall map by arranging partial maps corresponding to multiple points on a single map coordinate system is known (see, for example, Patent Document 1). In the device described in Patent Document 1, when there are overlapping partial maps, the amount of map data is reduced by deleting relatively old partial maps from a storage unit. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2020-135579 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, as the accuracy of a map increases and the area covered by the map expands, the amount of data on the map itself increases. Therefore, simply deleting overlapping partial maps as in the device described in Patent Document 1 may not be enough to reduce the amount of map data. [Means for solving the problem]
[0005] A map generating device according to one aspect of the present invention is a map generating device that generates a map used to acquire the position of the vehicle, and includes an on-board detector that detects the surroundings of the vehicle while it is traveling, a lane line recognition unit that recognizes lane lines on the road based on detection data acquired by the on-board detector, a first map generating unit that generates a first map based on the recognized lane lines while the lane lines are recognized by the lane line recognition unit, and a second map generating unit that extracts feature points from the detection data and generates a second map using the extracted feature points. The second map generating unit deletes any second map that corresponds to a position that is a predetermined distance or more behind the vehicle from among the second maps generated while the lane lines are recognized by the lane line recognition unit.
[0006] A vehicle position recognition device according to another aspect of the present invention includes the above-described map generating device and a position recognition unit that recognizes the position of the vehicle while it is traveling. When a lane line is recognized by the lane line recognition unit 141, the position recognition unit 131 recognizes the position of the vehicle on the first map based on the detection data and the first map, and when a lane line is not recognized by the lane line recognition unit 141, the position recognition unit 131 recognizes the position of the vehicle on the second map based on the detection data and the second map. Effect of the Invention
[0007] According to the present invention, the amount of map data can be significantly reduced. [Brief description of the drawings]
[0008] [Figure 1] 1 is a block diagram showing an overall configuration of a vehicle control system according to an embodiment of the present invention; [Diagram 2] 1 is a block diagram showing a configuration of a main part of a vehicle position recognition device having a map generating device according to an embodiment of the present invention. [Figure 3A] FIG. 2 is a diagram showing a state in which a host vehicle travels along a road while generating an environmental map. [Figure 3B] 3B is a diagram showing the state in which the vehicle travels through the location in FIG. 3A in autonomous driving mode. [Figure 4] 3 is a flowchart showing an example of processing executed by a CPU of the controller of FIG. 2; [Diagram 5] FIG. 5 is a diagram showing how the host vehicle travels in autonomous driving mode based on the map generated by the processing of FIG. 4. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, an embodiment of the present invention will be described with reference to Figs. 1 to 5. A map generating device according to an embodiment of the present invention can be applied to a vehicle having an automatic driving function, that is, an automatic driving vehicle. The vehicle to which the map generating device according to the present embodiment is applied may be called the host vehicle to distinguish it from other vehicles. The host vehicle may be any of an engine vehicle having an internal combustion engine (engine) as a driving source, an electric vehicle having a driving motor as a driving source, and a hybrid vehicle having an engine and a driving motor as driving sources. The host vehicle can run not only in an automatic driving mode in which no driving operation by the driver is required, but also in a manual driving mode in which the driver operates the vehicle.
[0010] First, a schematic configuration relating to automatic driving will be described. Fig. 1 is a block diagram showing a schematic overall configuration of a vehicle control system 100 having a map generating device according to an embodiment of the present invention. As shown in Fig. 1, the vehicle control system 100 mainly includes a controller 10, an external sensor group 1 communicably connected to the controller 10, 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.
[0011] The external sensor group 1 is a collective term for a plurality of sensors (external sensors) that detect the external situation, which is information about the surroundings of the vehicle. For example, the external sensor group 1 includes a lidar that measures the distance from the vehicle to obstacles in the vicinity by measuring the scattered light in response to the omnidirectional irradiation light of the vehicle, a radar that detects other vehicles and obstacles in the vicinity of the vehicle by irradiating electromagnetic waves and detecting reflected waves, and a camera that is mounted on the vehicle and has an imaging element such as a CCD or CMOS to capture images of the surroundings (front, rear, and sides) of the vehicle.
[0012] The internal sensor group 2 is a collective term for a plurality of sensors (internal sensors) that detect the driving state of the vehicle. For example, the internal sensor group 2 includes a vehicle speed sensor that detects the vehicle speed of the vehicle, an acceleration sensor that detects the acceleration in the forward and backward directions and the acceleration in the left and right directions (lateral acceleration) of the vehicle, a rotation speed sensor that detects the rotation speed of the driving source, a yaw rate sensor that detects the rotation angular velocity around the vertical axis of the center of gravity of the vehicle, etc. The internal sensor group 2 also includes sensors that detect the driving operations of the driver in the manual driving mode, such as the operation of the accelerator pedal, the operation of the brake pedal, the operation of the steering wheel, etc.
[0013] The input / output device 3 is a general term for devices that receive commands from the driver and output information to the driver. For example, the input / output device 3 includes various switches through which the driver inputs various commands by operating operating members, a microphone through which the driver inputs commands by voice, a display that provides information to the driver through displayed images, and a speaker that provides information to the driver by voice.
[0014] The positioning unit (GNSS unit) 4 has a positioning sensor that receives positioning signals transmitted from positioning satellites. The 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 using the positioning information received by the positioning sensor.
[0015] The map database 5 is a device that stores general map information used in the navigation device 6, and is configured with, for example, a hard disk or a semiconductor element. The map information includes road position information, road shape (curvature, etc.) information, intersection and branch point position information, and speed limit information set for the road. Note that the map information stored in the map database 5 is different from the highly accurate map information stored in the storage unit 12 of the controller 10.
[0016] The navigation device 6 is a device that searches for a target route on roads to a destination input by the driver and provides guidance along the target route. The input of the destination and guidance along the target route are performed via the input / output device 3. The target route is calculated based on the current position of the vehicle measured by the positioning unit 4 and map information stored in the map database 5. The current position of the vehicle can also be measured using detection values of the external sensor group 1, and the target route may be calculated based on this current position and highly accurate map information stored in the memory unit 12.
[0017] The communication unit 7 communicates with various servers (not shown) via networks including wireless communication networks such as the Internet and mobile phone networks, and acquires map information, driving history information, traffic information, and the like from the servers periodically or at any timing. Networks include not only public wireless communication networks but also closed communication networks provided for each predetermined management area, such as wireless LAN, Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like. The acquired map information is output to the map database 5 and the storage unit 12, where the map information is updated.
[0018] The actuators AC are driving actuators for controlling the driving of the host vehicle. When the driving source for driving is an engine, the actuators AC include a throttle actuator that adjusts the opening of a throttle valve (throttle opening) of the engine. When the driving source for driving is a driving motor, the actuators AC include the driving motor. The actuators AC also include a brake actuator that operates the braking device of the host vehicle and a steering actuator that drives the steering device.
[0019] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having an arithmetic unit 11 such as a CPU (microprocessor), a storage unit 12 such as a ROM, a RAM, and other peripheral circuits (not shown) such as an I / O interface. Note that although a plurality of ECUs with different functions, such as an engine control ECU, a travel motor control ECU, and a braking device ECU, can be provided separately, the controller 10 is shown in FIG. 1 as a collection of these ECUs for the sake of convenience.
[0020] The storage unit 12 stores highly accurate and detailed map information (referred to as high-accuracy map information). The high-accuracy map information includes road position information, road shape (curvature, etc.), road gradient information, intersection and branch point position information, number of lanes, lane width and position information for each lane (information on lane center position and lane position boundary), position information of landmarks (traffic lights, signs, buildings, etc.) as markers on the map, and road surface profile information such as road surface unevenness. The high-accuracy map information stored in the storage unit 12 includes map information acquired from outside the vehicle via the communication unit 7, for example, map information acquired via a cloud server (referred to as cloud map), and map information created by the vehicle itself using detection values from the external sensor group 1, for example, map information consisting of point cloud data generated by mapping using a technology such as SLAM (Simultaneous Localization and Mapping) (referred to as environmental map). The storage unit 12 also stores information on various control programs, threshold values used in the programs, and other information.
[0021] The calculation unit 11 has, as its functional configuration, a vehicle position recognition unit 13, an external environment recognition unit 14, an action plan generation unit 15, a driving control unit 16, and a map generation unit 17.
[0022] The vehicle position recognition unit 13 recognizes the position of the vehicle on the map (the vehicle position) based on the vehicle position information obtained by the positioning unit 4 and the map information in the map database 5. The vehicle position may be recognized using the map information stored in the storage unit 12 and the surrounding information of the vehicle detected by the external sensor group 1, thereby making it possible to recognize the vehicle position with high accuracy. When the vehicle position can be measured by a sensor installed externally on or beside the road, the vehicle position can also be recognized by communicating with the sensor via the communication unit 7.
[0023] The external environment recognition unit 14 recognizes the external situation around the vehicle based on signals from the external sensor group 1, such as a lidar, radar, and camera. For example, it recognizes the positions, running speeds, and accelerations of surrounding vehicles (vehicles ahead and vehicles behind) traveling around the vehicle, the positions of surrounding vehicles stopped or parked around the vehicle, and the positions and states of other objects. The other objects include signs, traffic lights, markings (road markings) such as road division lines and stop lines, buildings, guardrails, utility poles, signs, pedestrians, bicycles, and the like. The states of the other objects include the colors of traffic lights (red, green, yellow), and the moving speeds and directions of pedestrians and bicycles. Some of the stationary objects among the other objects constitute landmarks that serve as indicators of positions on a map, and the external environment recognition unit 14 also recognizes the positions and types of the landmarks.
[0024] The action plan generating unit 15 generates a running trajectory (target trajectory) of the vehicle from the current time to a predetermined time ahead based on, for example, a target route calculated by the navigation device 6, the vehicle position recognized by the vehicle position recognition unit 13, and the external situation recognized by the external environment recognition unit 14. When there are multiple trajectories that are candidates for the target trajectory on the target route, the action plan generating unit 15 selects an optimal trajectory that satisfies criteria such as complying with laws and regulations and traveling efficiently and safely, and sets the selected trajectory as the target trajectory. Then, the action plan generating unit 15 generates an action plan according to the generated target trajectory. The action plan generating unit 15 generates various action plans corresponding to the running modes such as overtaking running to overtake a preceding vehicle, lane changing running to change the running lane, following running to follow a preceding vehicle, lane keeping running to maintain the lane so as not to deviate from the running lane, decelerating running or accelerating running. When generating the target trajectory, the action plan generating unit 15 first determines the running mode, and generates the target trajectory based on the running mode.
[0025] In the autonomous driving mode, the driving control unit 16 controls each actuator AC so that the vehicle travels along the target trajectory generated by the behavior plan generating unit 15. More specifically, the driving control unit 16 calculates a required driving force for obtaining the target acceleration per unit time calculated by the behavior plan generating unit 15, taking into consideration the driving resistance determined by the road gradient in the autonomous driving mode. Then, for example, the driving control unit 16 feedback-controls the actuators AC so that the actual acceleration detected by the internal sensor group 2 becomes the target acceleration. That is, the driving control unit 16 controls the actuators AC so that the vehicle travels at the target vehicle speed and the target acceleration. In the manual driving mode, the driving control unit 16 controls each actuator AC in response to a driving command (such as a steering operation) from the driver acquired by the internal sensor group 2.
[0026] The map generating unit 17 generates an environmental map consisting of three-dimensional point cloud data using detection values detected by the external sensor group 1 while driving in manual driving mode. Specifically, from the captured image acquired by the camera 1a, edges showing the contours of objects are extracted based on the brightness and color information of each pixel, and feature points are extracted using the edge information. The feature points are, for example, intersections of edges, and correspond to corners of buildings and corners of road signs. The map generating unit 17 sequentially plots the extracted feature points on the environmental map, thereby generating an environmental map of the area around the road on which the vehicle has traveled. Instead of the camera, data acquired by a radar or a lidar may be used to extract feature points of objects around the vehicle, and an environmental map may be generated. In addition, when generating the environmental map, the map generating unit 17 determines whether or not landmarks such as traffic lights, signs, and buildings as marks on the map are included in the captured image acquired by the camera, for example, by pattern matching processing. Then, when it is determined that a landmark is included, the position and type of the landmark on the environmental map are recognized based on the captured image. This landmark information is included in the environmental map and stored in the memory unit 12.
[0027] The vehicle position recognition unit 13 performs a position estimation process of the vehicle in parallel with the map creation process by the map generation unit 17. That is, the vehicle position is estimated and acquired based on the change in the position of the feature points over time. The vehicle position recognition unit 13 also estimates and acquires the vehicle position based on the relative positional relationship between the landmarks around the vehicle and the feature points of the objects around the vehicle. The map creation process and the position estimation process are performed simultaneously according to, for example, a SLAM algorithm. The map generation unit 17 can generate an environmental map not only when driving in a manual driving mode, but also when driving in an automatic driving mode. If an environmental map has already been generated and stored in the storage unit 12, the map generation unit 17 may update the environmental map with the newly obtained feature points.
[0028] Incidentally, an environmental map made up of point cloud data has a large amount of data, and the larger the area to be created, the larger the amount of data becomes. Therefore, if an environmental map for a wide area is to be created, there is a risk that a large amount of capacity of the storage unit 12 will be consumed. Therefore, in this embodiment, the map generating device is configured as follows so that a wide-area environmental map can be created while suppressing an increase in the amount of data.
[0029] Fig. 2 is a block diagram showing a main configuration of a vehicle position recognition device having a map generation device according to an embodiment of the present invention. This vehicle position recognition device 60 acquires the current position of the vehicle itself 101, and constitutes a part of the vehicle control system 100 of Fig. 1. As shown in Fig. 2, the vehicle position recognition device 60 has a controller 10, a camera 1a, a radar 1b, and a lidar 1c. The vehicle position recognition device 60 also has a map generation device 50 that constitutes a part of the vehicle position recognition device 60. The map generation device 50 generates maps (a lane line map and an environmental map, which will be described later) based on an image captured by the camera 1a.
[0030] The camera 1a is a monocular camera having an imaging element (image sensor) such as a CCD or a CMOS, and constitutes a part of the external sensor group 1 in FIG. 1. The camera 1a may be a stereo camera. The camera 1a captures images of the surroundings of the vehicle. The camera 1a is attached, for example, at a predetermined position in the front of the vehicle, and continuously captures images of the space in front of the vehicle to obtain image data of the object (hereinafter, referred to as captured image data or simply captured image). The camera 1a outputs the captured image to the controller 10. The radar 1b is mounted on the vehicle and detects other vehicles and obstacles around the vehicle by irradiating electromagnetic waves and detecting reflected waves. The radar 1b outputs a detection value (detection data) to the controller 10. The lidar 1c is mounted on the vehicle and measures scattered light in response to irradiated light in all directions of the vehicle to detect the distance from the vehicle to obstacles in the vicinity. The lidar 1c outputs a detection value (detection data) to the controller 10.
[0031] The controller 10 has a position recognition unit 131, a lane line recognition unit 141, a first map generation unit 171, and a second map generation unit 172 as functional components carried out by the calculation unit 11 (FIG. 1). The lane line recognition unit 141, the first map generation unit 171, and the second map generation unit 172 are included in the map generation device 50. The position recognition unit 131 is configured, for example, by the vehicle position recognition unit 13. The lane line recognition unit 141 is configured, for example, by the external environment recognition unit 14 in FIG. 1. The first map generation unit 171 and the second map generation unit 172 are configured, for example, by the map generation unit 17 in FIG. 1.
[0032] The lane line recognition unit 141 recognizes lane lines on a road based on the captured image acquired by the camera 1a. The first map generation unit 171 generates a map based on the positions of the recognized lane lines while the lane lines are being recognized by the lane line recognition unit 141. Hereinafter, the map generated by the first map generation unit 171 is referred to as the lane line map or the first map.
[0033] The second map generating unit 172 extracts feature points from the captured image acquired by the camera 1a, and generates an environmental map using the extracted feature points. Hereinafter, the environmental map generated by the second map generating unit 172 is referred to as the second map. FIG. 3A is a diagram showing how the host vehicle 101 travels on a road while generating an environmental map. In the example shown in FIG. 3A, the host vehicle 101 is traveling on a left-hand traffic road RD1 with one lane on each side toward an intersection IS. FIG. 3A shows the host vehicle 101 at time t1, time t2 after time t1, and time t3 after time t2. As shown in FIG. 3A, at time t1, the imaging range of the vehicle-mounted camera (camera 1a) of the host vehicle 101 includes a building BL1 and a road sign RS1. At time t2, it is assumed that the imaging range includes a building BL2, a telephone pole UP, and a traffic light SG2 of the oncoming lane. It is assumed that the imaging range includes a traffic light SG1 and a building BL3 of the lane on which the host vehicle is traveling at time t3. The second map generating unit 172 extracts feature points of these objects from the captured image of the camera 1a. The objects surrounded by circular frames in the figure represent objects whose feature points are extracted by the second map generating unit 172 at each of the times t1, t2, and t3. Note that the imaging range of the camera 1a includes the lane markings of the road (center line CL and outer lane line OL) at all of the times t1 to t3, and the second map generating unit 172 also extracts feature points of the lane markings of the road from the captured image of the camera 1a. In this way, the environmental map (second map) includes information (feature points) about objects around the road and the lane markings of the road, and therefore the amount of data is larger than that of a lane marking map that does not include information other than the lane markings of the road.
[0034] While the vehicle 101 is traveling in autonomous driving mode, the position recognition unit 131 recognizes the position of the vehicle based on the image captured by the camera 1a and at least one of the lane line map generated by the first map generation unit 171 and the second map generated by the second map generation unit 172.
[0035] Fig. 3B is a diagram showing how the host vehicle 101 travels in autonomous driving mode at the location in Fig. 3A. The position of the host vehicle 101 in Fig. 3B is assumed to be the same as the position of the host vehicle 101 at time t2 in Fig. 3A. Therefore, the imaging range of the vehicle-mounted camera (camera 1a) of the host vehicle 101 in Fig. 3B includes a building BL2, a utility pole UP, a traffic light SG2 in the oncoming lane, a center line CL of the road, and an outer side line OL of the road.
[0036] When the position recognition unit 131 recognizes the position of the vehicle 101 based on the lane line map, it first recognizes the lane lines (center lines CL and outer lane lines OL) included in the image captured by the camera 1a by pattern matching processing, etc. Then, the position recognition unit 131 checks the recognized lane line against the lane line map, and when a point on the lane line map that matches the recognized lane line is present, it recognizes the point as the position of the vehicle 101.
[0037] On the other hand, when recognizing the position of the vehicle 101 based on the environmental map, the position recognition unit 131 first compares the feature points of objects such as a lane marking and a building BL2 extracted from the image captured by the camera 1a with the environmental map. Then, when feature points that match the feature points of the objects are recognized on the environmental map, the position recognition unit 131 recognizes the position of the vehicle 101 on the environmental map based on the positions of the recognized feature points on the environmental map. In Fig. 3B, an object surrounded by a circular dashed frame represents an object whose feature points are extracted by the position recognition unit 131 at the time of Fig. 3B.
[0038] When there are no markings on the road on which the vehicle 101 is traveling, or when the markings on the road on which the vehicle 101 is traveling are faint, the markings are not recognized from the image captured by the camera 1a. In such a case, the position recognition unit 131 cannot recognize the position of the vehicle 101 on the marking line map. On the other hand, even if the feature points of the marking lines are not extracted from the image captured by the camera 1a, if the feature points of other objects are extracted, the position recognition unit 131 can recognize the position of the vehicle 101 on the environmental map based on those feature points.
[0039] Therefore, in sections where lane lines are not recognized by the lane line recognition unit 141, the position recognition unit 131 recognizes the position of the vehicle 101 on the environmental map based on the image captured by the camera 1a and the environmental map. On the other hand, in sections where lane lines are recognized by the lane line recognition unit 141, the position recognition unit 131 recognizes the position of the vehicle 101 on the lane line map based on the image captured by the camera 1a and the lane line map. In this way, in sections where the position of the vehicle 101 can be recognized based on either the lane line map or the environmental map, the lane line map is used preferentially. As a result, the environmental map is not necessary in sections where lane lines can be recognized, and the amount of data in the environmental map can be reduced.
[0040] Fig. 4 is a flowchart showing an example of a process (map generation process) executed by the controller 10 of Fig. 2 according to a predetermined program, in particular, an example of a process related to map generation. The process shown in the flowchart of Fig. 4 is repeated at a predetermined cycle while the vehicle is traveling in the autonomous driving mode.
[0041] First, in step S11, it is determined whether or not a lane line has been recognized from the image captured by camera 1a. If the result in step S11 is affirmative, in step S12, a lane line map is generated and stored in memory unit 12. If a lane line map has already been stored in memory unit 12, information on the lane lines recognized in step S11 is added to the lane line map stored in memory unit 12 to update the lane line map. In this way, a lane line map of the road on which vehicle 101 is traveling is formed. In step S13, an environmental map is generated based on the group of feature points extracted from the image captured by camera 1a and stored in memory unit 12. If an environmental map has already been stored in memory unit 12, the environmental map is updated with the group of extracted feature points.
[0042] The environmental map includes data of feature points (point cloud data) extracted from the captured image acquired by the camera 1a, and a pose graph. The pose graph is composed of nodes and edges. The nodes represent the position and attitude of the vehicle 101 at the time when the point cloud data was acquired, and the edges represent the relationship between the relative positions (distances) and attitudes between the nodes. If the environmental map is a three-dimensional map, the attitude is expressed by a pitch angle, a yaw angle, and a roll angle. When updating the environmental map, new point cloud data acquired at the current position of the vehicle 101 is added, and a node corresponding to the added point cloud data and an edge representing the relationship between the node and an existing node are added to the pose graph.
[0043] In step S14, it is determined whether the lane markings have been continuously recognized for a predetermined distance or more. Specifically, it is determined whether the distance from the point where the lane markings recognized in step S11 began to be recognized (hereinafter referred to as the lane marking start point) to the current position of the vehicle 101 is a predetermined distance or more. If the result in step S14 is negative, the processing is terminated. If the result in step S14 is positive, in step S14, a part of the environmental map is deleted. Specifically, the environmental map from the lane marking start point to a predetermined point a predetermined distance behind the current position of the vehicle 101 is deleted from the memory unit 12.
[0044] On the other hand, if the result in step S11 is negative, an environmental map is generated based on the group of feature points extracted from the image captured by camera 1a and stored in storage unit 12. If an environmental map has already been stored in storage unit 12, the environmental map is updated with the group of extracted feature points.
[0045] FIG. 5 is a diagram showing how the host vehicle 101 travels in an autonomous driving mode based on the map (the lane map and the environmental map) generated by the map generation process of FIG. 4. In the example shown in FIG. 5, the host vehicle 101 is traveling on a left-hand traffic road RD2 with one lane on each side. FIG. 5 shows the host vehicle 101 at time t11, time t12 after time t11, and time t13 after time t12. On the road RD2, there is a section B between section A and section B where no lane lines exist. When the host vehicle 101 travels through sections A and B, the position recognition unit 131 recognizes the position of the host vehicle 101 on the lane map based on the lane lines CL and OL recognized based on the captured image of the camera 1a and the lane map corresponding to sections A and C. On the other hand, when the vehicle 101 travels through section B, the position recognition unit 131 recognizes the position of the vehicle 101 on the environmental map based on the characteristic points of buildings BL4, BL5 and road sign RS2 extracted from the image captured by the camera 1a and the environmental map corresponding to section B. Furthermore, when starting to recognize the vehicle's position based on the environmental map at the boundary between sections A and B, the position recognition unit 131 calculates the position of the vehicle 101 on the environmental map based on the position of the vehicle 101 on the lane line map that was recognized immediately before.
[0046] Usually, when vehicle position recognition based on an environmental map is started, a search for the vehicle position (initial position) on the environmental map is performed. This search involves complex calculation processing, which increases the processing load of the calculation unit 11. However, as described above, by calculating the initial position of the vehicle 101 on the environmental map based on the position of the vehicle 101 on the lane line map that was previously recognized, it becomes unnecessary to search for the initial position, and the processing load of the calculation unit 11 can be reduced. This makes it possible to smoothly start recognition of the vehicle position based on the environmental map at the boundary between Section A and Section B.
[0047] According to the embodiment of the present invention, the following advantageous effects can be obtained. (1) The map generating device 50 is a map generating device that generates a map used to acquire the position of the vehicle. The map generating device 50 includes a camera 1a that detects the surroundings of the vehicle while it is traveling, a lane line recognition unit 141 that recognizes lane lines on the road based on detection data (captured image) acquired by the camera 1a, a first map generating unit 171 that generates a first map (lane line map) based on the recognized lane lines while the lane lines are recognized by the lane line recognition unit 141, and a second map generating unit that extracts feature points from the captured image of the camera 1a and generates a second map (environmental map) using the extracted feature points. The second map generating unit 172 deletes the second map corresponding to a position at a predetermined distance or more behind the vehicle 101 from the second map generated while the lane lines are recognized by the lane line recognition unit 141. This makes it possible to reduce the amount of map data.
[0048] (2) The vehicle position recognition device 60 includes a map generating device 50 and a position recognition unit 131 that recognizes the position of the vehicle itself while it is traveling. When the lane line recognition unit 141 recognizes a lane line, the position recognition unit 131 recognizes the position of the vehicle itself on the first map based on the image captured by the camera 1a and the first map, and when the lane line recognition unit 141 does not recognize a lane line, the position recognition unit 131 recognizes the position of the vehicle itself on the second map based on the image captured by the camera 1a and the second map. This makes it possible to recognize the vehicle's position in a section where a lane line exists if there is a lane line map, and eliminates the need to generate an environmental map for such a section. This reduces the amount of map data.
[0049] (3) When the lane marking recognition unit 141 no longer recognizes the lane markings, the position recognition unit 131 calculates an initial position of the host vehicle on the second map based on the position of the host vehicle on the first map, and starts recognizing the host vehicle's position on the second map based on the calculated initial position. This eliminates the need to search for the host vehicle's position (initial position) on the second map when the host vehicle 101 moves from a section where a lane marking exists (e.g., section A in FIG. 5) to a section where no lane marking exists (e.g., section B in FIG. 5). This makes it possible to reduce the processing load when starting recognition of the host vehicle's position based on the second map, and to smoothly start recognition of the host vehicle's position based on the second map.
[0050] The above embodiment can be modified in various ways. Some modified examples will be described below. In the above embodiment, the camera 1a detects the surroundings of the vehicle, but the on-board detector may have any configuration as long as it detects the surroundings of the vehicle. For example, the on-board detector may be a radar 1b or a lidar 1c. In the above embodiment, the process shown in FIG. 4 is executed while driving in the manual driving mode, but the process shown in FIG. 4 may be executed while driving in the automatic driving mode.
[0051] In the above embodiment, the first map is a lane line map, but the first map is not limited to the lane line map. The first map may be a map other than the lane line map as long as the map is capable of recognizing the position of the vehicle based on detection data from an on-board detector and has a smaller amount of data than the second map. In the above embodiment, the map generating device 50 is applied to an autonomous vehicle, but the map generating device 50 can be applied to vehicles other than autonomous vehicles. For example, the map generating device 50 can be applied to a manually driven vehicle equipped with an ADAS (Advanced driver-assistance systems).
[0052] The above description is merely an example, and the present invention is not limited to the above-mentioned embodiment and modifications, as long as the features of the present invention are not impaired. One or more of the above-mentioned embodiment and modifications can be arbitrarily combined, and modifications can also be combined with each other. [Explanation of symbols]
[0053] 1a camera, 1b radar, 1c lidar, 10 controller, 50 map generating device, 60 vehicle position recognition device, 141 lane marking recognition unit, 171 first map generating unit, 172 second map generating unit, 100 vehicle control system
Claims
1. A map generating device that generates a map used to acquire the position of a vehicle, An on-board detector that detects the surroundings of the vehicle while it is moving; a lane marking recognition unit that recognizes lane marks on a road based on the detection data acquired by the vehicle-mounted detector; a first map generating unit that generates a first map based on the recognized lane markings while the lane markings are being recognized by the lane marking recognition unit; a second map generating unit that extracts feature points from the detection data and generates a second map by using the extracted feature points; The map generating device is characterized in that the second map generation unit deletes the second map that corresponds to a position that is a predetermined distance or more behind the vehicle from the second map that was generated while the lane markings were being recognized by the lane marking recognition unit.
2. A map generating device according to claim 1 ; A vehicle position recognition device including a position recognition unit that recognizes a position of a vehicle while the vehicle is traveling, A vehicle position recognition device characterized in that when a lane line is recognized by the lane line recognition unit, the position recognition unit recognizes the position of the vehicle on the first map based on the detection data and the first map, and when a lane line is not recognized by the lane line recognition unit, the position recognition unit recognizes the position of the vehicle on the second map based on the detection data and the second map.
3. 3. The vehicle position recognition device according to claim 2, The vehicle position recognition device is characterized in that, when the lane marking recognition unit no longer recognizes lane marks, the position recognition unit calculates an initial position of the vehicle on the second map based on the position of the vehicle on the first map, and begins recognizing the position of the vehicle on the second map based on the calculated initial position.
Citation Information
Patent Citations
Simultaneous positioning and mapping method, system and device and storage medium
CN111737278A
Geographical map preparation device, geographical map preparation program, and geographical map preparation method
JP2014174275A
Vehicle position estimation system, device, method, and camera device
JP2015108604A
Travel controller for vehicles
JP2018173304A
Map creation device and map creation program
JP2020135579A
