Map generation device

Abstract

The present invention provides a map generation apparatus (50) comprising: a vehicle identification unit (173) for identifying other vehicles traveling in an opposite lane to the lane in which the vehicle is traveling; an information acquisition unit (175) for acquiring, when other vehicles are identified, information about the external conditions around other vehicles in a path-consistent interval where the vehicle's path is consistent with the path of other vehicles in the opposite lane, including the driving paths of the vehicle in the lane and the opposite lane; and a map generation unit (17) for generating a map related to the opposite lane in the path-consistent interval.

Description

Technical Field

[0001] This invention relates to a map generation device for generating a map of the area surrounding a vehicle. Background Technology

[0002] Previously known devices utilize images captured by a camera mounted on a vehicle to identify white lines in the vehicle's driving lane and white lines around parking spaces, and use the identification results for vehicle driving control and parking assistance. Such a device is described, for example, in Patent Document 1. In the device described in Patent Document 1, edge points whose brightness changes above a threshold in the captured image are extracted, and white lines are identified based on these edge points.

[0003] In the device described in Patent Document 1, white lines are identified in the lanes in which the vehicle actually travels. Therefore, in order to generate a map that includes the position information of the white lines, the vehicle needs to actually travel in each lane, making map generation difficult to perform effectively.

[0004] Existing technical documents

[0005] Patent documents

[0006] Patent document 1: Japanese Patent Application Publication No. 2014-104853 (JP2014-104853A). Summary of the Invention

[0007] As one aspect of the present invention, a map generation apparatus includes: a vehicle identification unit that identifies other vehicles traveling in an opposite lane to the lane in which the current vehicle is traveling; an information acquisition unit that, when the vehicle identification unit identifies other vehicles, acquires information about the external conditions around other vehicles in a path-consistent interval where the current vehicle's path and the opposite lane's path are consistent, obtained from the other vehicles traveling in the opposite lane; and a map generation unit that generates a map about the opposite lane in the path-consistent interval based on the information acquired by the information acquisition unit. 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 1 This is a block diagram that schematically illustrates the overall structure of a vehicle control system having a map generation apparatus according to an embodiment of the present invention.

[0010] Figure 2 This is a diagram illustrating an example of a driving scenario using a map generation device according to an embodiment of the present invention.

[0011] Figure 3This is a block diagram illustrating the main structural components of a map generation apparatus according to an embodiment of the present invention.

[0012] Figure 4A This refers to the driving scene of the map generation device according to the embodiments of the present invention. Figure 2 Diagrams showing different examples.

[0013] Figure 4B This is another example of a driving scenario illustrating an embodiment of the map generation apparatus of the present invention.

[0014] Figure 5 It is shown by Figure 3 A flowchart of an example of the processing performed by the controller. Detailed Implementation

[0015] The following is for reference Figures 1 to 5 Embodiments of the present invention will be described. The map generation apparatus of the present invention is mounted on, for example, a vehicle with autonomous driving capabilities, i.e., an autonomous vehicle. It should be noted that sometimes the vehicle equipped with the map generation apparatus of this embodiment is distinguished from other vehicles and referred to as "this vehicle". This vehicle can be any of the following: an engine vehicle with an internal combustion engine as the driving source, an electric vehicle with a drive motor as the driving source, or a hybrid vehicle with both an engine and a drive motor as driving sources. This vehicle can operate not only in an autonomous driving mode that does not require driver operation, but also in a manual driving mode based on driver operation.

[0016] First, a general description of the vehicle's structure in relation to autonomous driving will be given. Figure 1 This is a block diagram schematically illustrating the overall structure of the vehicle control system 100 of the vehicle having the map generation apparatus according to an embodiment of the present invention. Figure 1 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 communicatively connected to the controller 10.

[0017] External sensor group 1 is a collective term for multiple sensors (external sensors) that detect external conditions as information about the vehicle's surroundings. For example, external sensor group 1 includes lidar, radar, and cameras. The lidar measures the scattered light from the omnidirectional illumination of the vehicle to determine the distance from the vehicle to surrounding obstacles; the radar illuminates electromagnetic waves and detects reflected waves to detect other vehicles and obstacles around the vehicle; the cameras are mounted on the vehicle and have imaging elements such as CCD (charge-coupled device) and CMOS (complementary metal-oxide-semiconductor) to capture images of the vehicle's surroundings (front, rear, and sides).

[0018] Internal sensor group 2 is a collective term for multiple sensors (internal sensors) that detect the driving status of the vehicle. For example, internal sensor group 2 includes a vehicle speed sensor, an acceleration sensor, a speed sensor, and a yaw rate sensor. The vehicle speed sensor detects the vehicle's speed; the acceleration sensor detects the vehicle's acceleration in the longitudinal and lateral directions (lateral acceleration); the speed sensor detects the rotational speed of the drive unit; and the yaw rate sensor detects the angular velocity of the vehicle's center of gravity about its vertical axis. Sensors that detect the driver's actions in manual driving mode, such as operation of the accelerator pedal, brake pedal, and steering wheel, are also included in internal sensor group 2.

[0019] 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.

[0020] 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 vehicle's current position (latitude, longitude, and altitude).

[0021] Map database 5 is a device that stores general map information for navigation device 6, and is composed of, for example, a hard disk or 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. Furthermore, the map information stored in map database 5 is different from the high-precision map information stored in storage unit 12 of controller 10.

[0022] 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 that path. The destination is input and the driver is guided along the target path via the input / output device 3. The target path is calculated based on the vehicle's current position determined by the positioning unit 4 and map information stored in the map database 5. Alternatively, the vehicle's current position can be determined using the detection values ​​from the external sensor group 1, and the target path can be calculated based on that current position and high-precision map information stored in the storage unit 12.

[0023] Communication unit 7 communicates with various servers (not shown) via wireless communication networks, including the Internet and mobile phone networks, to periodically or at any time obtain map information, driving history information, and traffic information from the servers. In addition to obtaining driving history information, communication unit 7 can also send the vehicle's driving history information to the servers. The network includes not only public wireless communication networks but also closed communication networks set up for each designated management area, such as wireless LAN, Wi-Fi, and Bluetooth. The obtained map information is output to map database 5 and storage unit 12 to update the map information.

[0024] An actuator (AC) is a driving actuator used to control the movement of the vehicle. When the driving source is an engine, the actuator AC includes a throttle actuator for adjusting the opening of the engine's throttle valve (throttle opening). When the driving source is a travel motor, the travel motor is included in the actuator AC. Braking actuators that operate the vehicle's braking system and steering actuators that drive the steering mechanism are also included in the actuator AC.

[0025] 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 a 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 device ECU, can be set separately; however, for convenience, only one is shown. Figure 1 The diagram shows that controller 10 is a collection of these ECUs.

[0026] The storage unit 12 stores high-precision, detailed road map information for autonomous driving. This road map information includes road location information, road shape (curvature, etc.), road slope information, location information of intersections or forks in the road, 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 lane's boundary lines), location information of landmarks (traffic lights, signs, buildings, etc.) used as markers on the map, and road surface conditions such as unevenness. The map information stored in the storage unit 12 includes map information obtained from outside the vehicle via the communication unit 7 (referred to as external map information) and map information generated by the vehicle itself using detection values ​​from the external sensor group 1 or detection values ​​from both the external and internal sensor groups 1 (referred to as internal map information).

[0027] External map information includes, for example, maps obtained via a cloud server (referred to as cloud maps), while internal map information includes, for example, maps composed of point cloud data generated through mapping using technologies such as SLAM (Simultaneous Localization and Mapping) (referred to as environmental maps). External map information is shared by this vehicle and other vehicles, while internal map information is unique to this vehicle (e.g., map information possessed solely by this vehicle). In areas where no external map information exists, such as newly constructed roads, this vehicle creates its own environmental map. It should be noted that internal map information can also be provided to the server device and other vehicles via the communication unit 7. The storage unit 12 also stores various control programs and information related to thresholds used by the programs.

[0028] The computing unit 11 has a functional structure 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.

[0029] The vehicle position recognition unit 13 identifies the vehicle's position on the map (vehicle position) based on the vehicle's position information obtained from the positioning unit 4 and the map information from the map database 5. Alternatively, it can use map information stored in the storage unit 12 and surrounding information detected by the external sensor group 1 to identify the vehicle's position, thereby enabling high-precision identification. It can also calculate the vehicle's movement information (movement direction, movement distance) based on the detection values ​​from the internal sensor group 2, thereby identifying the vehicle's position. It should be noted that when the vehicle's position can be determined using external sensors installed on or beside the road, the vehicle's position can also be identified by communicating with these sensors via the communication unit 7.

[0030] The external identification unit 14 identifies the external conditions around the vehicle 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, the position of surrounding vehicles parked or stationary around the vehicle, and the position and state of other objects. Other objects include signs, traffic lights, roads, buildings, guardrails, utility poles, signs, pedestrians, and bicycles. Road markings (white lines, etc.) and stop lines are also included among other objects (roads). The state of other objects includes the color of traffic lights (red, green, yellow), and the speed and direction of movement of pedestrians or bicycles. A portion of stationary objects among other objects constitutes a landmark that serves as an indicator of location on a map; the external identification unit 14 also identifies the location and type of the landmark.

[0031] The action plan generation unit 15 generates, for example, the vehicle's driving trajectory (target trajectory) from the current point in time up 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's position identified by the vehicle position recognition unit 13, and the external conditions identified by the external environment recognition unit 14. When multiple candidate trajectories exist on the target path, the action plan generation unit 15 selects the optimal trajectory that complies with laws and meets criteria such as efficient and safe driving, and uses the selected trajectory as the target trajectory. Then, the action plan generation unit 15 generates an action plan corresponding to the generated target trajectory. The action plan generation unit 15 generates various action plans corresponding to overtaking, lane changing, following, maintaining lane position, deceleration, and acceleration. When generating the target trajectory, the action plan generation unit 15 first determines the driving mode and generates the target trajectory based on the driving mode.

[0032] In autonomous driving mode, the driving control unit 16 controls each actuator AC to make the vehicle travel along the target trajectory 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 AC to make the actual acceleration detected by, for example, the internal sensor group 2, the target acceleration. That is, the actuator AC is controlled to make the vehicle 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.

[0033] While driving in manual driving mode, the map generation unit 17 uses detection values ​​obtained from the external sensor group 1 to generate an environmental map composed of 3D point cloud data. 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 include, for example, points on edges, intersections of edges, and correspond to road markings, building corners, and road sign corners. 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 obtained from radar or lidar can be used to extract feature points of objects around the vehicle and generate an environmental map.

[0034] 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, signals from cameras and LiDAR are used, and map creation 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 mode but also when driving in automatic 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.

[0035] The structure of the map generation apparatus of this embodiment will be explained. Figure 2 This diagram illustrates an example of a driving scenario using the map generation apparatus of this embodiment, showing the vehicle 101 traveling from location A (e.g., its own residence) to its destination location B (e.g., a shop) while generating an environment map in manual driving mode. More specifically, it shows a scenario of driving in the lane (lane 1 LN1) defined by the left and right dividing lines L1 and L2. Figure 2 The image also shows other vehicles 102 traveling in the opposite lane, namely the opposite lane defined by the left and right dividing lines L2 and L3 (lane 2 LN2).

[0036] The dividing lines L1 to L3 are, for example, solid or dashed white lines. For this vehicle 101, the first lane LN1 is the route to the destination, and the second lane LN2 is the return route from the destination. The first lane LN1 and the second lane LN2 are adjacent to each other. Figure 2 Examples are shown where the outbound route and the return route consist of a single lane LN1 and LN2, respectively, but at least one of the outbound route and the return route may sometimes consist of multiple lanes.

[0037] exist Figure 2In the diagram, vehicle 101 and other vehicles 102 at the current time T0 are represented by solid lines. Vehicle 101 and other vehicles 102 at the first time point T1 after a predetermined time elapsed from the current time point T0, and at the second time point T2 after a predetermined time elapsed from the first time point T1, are represented by dashed lines. The positions of vehicle 101 at the current time point T0, the first time point T1, and the second time point T2 are respectively referred to as the current location P0, the first location P1, and the second location P2. At the current location P0, other vehicles 102 are in front of vehicle 101. At the first location P1, vehicle 101 meets other vehicles 102. At the second location P2, other vehicles 102 are behind vehicle 101.

[0038] Lane 1 LN1 and Lane 2 LN2 extend parallel to each other and are located on the same travel path RT. In the travel path RT, the section from the current location P0 to the first location P1 is the section before vehicle 101 approaches and meets other vehicles 102 (called the pre-meeting section) ΔL1, and the section from the first location P1 to the second location P2 is the section after vehicle 101 leaves other vehicles 102 (called the post-meeting section) ΔL2.

[0039] A camera 1a is mounted at the front of the vehicle 101. The camera 1a has an inherent field of view θ and a maximum detection distance r, determined by its own performance. The area inside a sector AR1 with radius r and central angle θ centered on the camera 1a constitutes the area of ​​external space that can be detected by the camera 1a, i.e., the detectable range AR1. This detectable range AR1 includes, for example, multiple dividing lines L1 and L2. It should be noted that if a portion of the field of view of the camera 1a is obstructed due to the presence of components disposed around the camera 1a, the detectable range AR1 may differ from the range shown in the figure.

[0040] A camera 102a, identical to that of vehicle 101, is also mounted on the front of other vehicles 102. The detectable range AR2 of camera 102a is, for example, the same as the detectable range AR1, defined as the inner side of a sector with radius r and central angle θ centered on camera 102a. This detectable range AR2 includes, for example, multiple dividing lines L2 and L3. That is, in this embodiment, the detectable range AR1 of camera 1a in vehicle 101 and the detectable range AR2 of camera 102a in other vehicles 102 include the same dividing line L2 among dividing lines L1 to L3. Furthermore, the detectable ranges AR1 and AR2 are determined not only by the performance of cameras 1a and 102a, but also by the vehicle model in which cameras 1a and 102a are mounted, the mounting position of cameras 1a and 102a, etc., and sometimes the detectable ranges AR1 and AR2 are different from each other.

[0041] In this driving scenario, by extracting edge points from images taken by camera 1a while the vehicle 101 is traveling in its lane, an environmental map of the lane (lane 1, LN1) within the detectable range AR1 can be generated. That is, by the vehicle 101 actually traveling in lane 1, LN1 (the outbound route), an environmental map of the outbound route (outbound route map) can be obtained. Furthermore, by obtaining camera images of the loop while the vehicle 101 is actually traveling in lane 2, LN2 (the loop) after passing through the outbound route, an environmental map of the loop (loop map) can be generated.

[0042] However, if an environmental map of the loop cannot be obtained after traveling the route until actual travel on the loop, the time required for map generation increases, making map generation inefficient. Therefore, in order to achieve effective map generation, this embodiment constructs a map generation apparatus as follows.

[0043] Figure 3 This is a block diagram showing the main structural components of the map generation apparatus 50 according to this embodiment. The map generation apparatus 50 comprises... Figure 1 It is part of the vehicle control system 100. For example... Figure 3 As shown, the map generation device 50 has a controller 10, a camera 1a and a sensor 2a.

[0044] Camera 1a is a single-lens camera with imaging elements (image sensors) such as CCD (charge-coupled device) and CMOS (complementary metal-oxide-semiconductor), constituting... Figure 1 It is part of the external sensor group 1. Camera 1a can also be a stereo camera. Camera 1a is mounted, for example, at a predetermined position at the front of the vehicle 101. Figure 2 The camera continuously captures images of the space in front of the vehicle 101 to obtain images of the objects (camera images). Objects include buildings or signs surrounding the vehicle 101, and road markings (e.g., lane lines). Figure 2 (The dividing lines L1 and L2). It should be noted that it can also replace camera 1a or be used together with camera 1a by lidar or other sensors to detect objects.

[0045] Sensor 2a is a detector used to calculate the amount and direction of movement of the vehicle 101. Sensor 2a is part of the internal sensor group 2, which may consist of, for example, a vehicle speed sensor and a yaw rate sensor. That is, the controller 10 (e.g., Figure 1The vehicle position recognition unit 13) integrates the vehicle speed detected by the vehicle speed sensor to calculate the movement of the vehicle 101, and integrates the yaw rate detected by the yaw rate sensor to calculate the yaw angle, and uses a ranging method to estimate the position of the vehicle 101. For example, when driving in manual driving mode, the ranging method is used to estimate the vehicle's position when creating an environmental map. It should be noted that the structure of sensor 2a is not limited to this, and information from other sensors can also be used to estimate its own position.

[0046] Figure 3 The controller 10, in addition to the action plan generation unit 15 and the map generation unit 17, also has a vehicle recognition unit 173, a route determination unit 174, and an information acquisition unit 175, serving as the computing unit 11. Figure 1 The functional structure undertaken by the vehicle recognition unit 173, the route determination unit 174, and the information acquisition unit 175 has map generation functions. Therefore, they can also be included in the map generation unit 17.

[0047] The vehicle identification unit 173 identifies other vehicles 102 traveling in the opposite lane (lane 2 LN2) based on camera images acquired by camera 1a. Other vehicles 102 traveling in the opposite lane include not only vehicles ahead of the vehicle 101 that are about to pass, but also vehicles behind the vehicle 101 that are about to pass. Other vehicles 102 can also be identified using radar or lidar. The vehicle identification unit 173 can also identify other vehicles 102 by obtaining their location information via communication unit 7.

[0048] When the vehicle recognition unit 173 identifies another vehicle 102, the path determination unit 174 estimates the driving path of the other vehicle 102 based on the camera image. Then, it determines whether there exists an interval (called a path-matching interval) in the driving paths RT of the current vehicle 101 and the other vehicle 102 that is consistent with each other's driving paths. For example, in... Figure 2 In the example, the pre-meeting interval ΔL1 where vehicle 101 approaches other vehicles 102 and the post-meeting interval ΔL2 where vehicle 101 separates from other vehicles 102 are respectively called the path-consistent intervals.

[0049] Vehicle 101 moved to location P1 ( Figure 2 In the state of (), the section before the meeting of vehicles 101 ΔL1 and the section after the meeting of vehicles 102 can be regarded as the following sections. That is, the section before the meeting of vehicles 101 ΔL1 is the section where the path already traveled by this vehicle 101 is consistent with the path that other vehicles 102 plan to travel in the future, and the section after the meeting of vehicles 102 ΔL2 is the section where the path that this vehicle 101 plans to travel in the future is consistent with the path that other vehicles 102 have already traveled.

[0050] The interval with the same path does not always include the interval before the meeting ΔL1 and the interval after the meeting ΔL2. Figure 4A , Figure 4B This diagram illustrates an example of a vehicle 101 traveling in its own lane (lane 1 LN1) and another vehicle 102 traveling in the opposite lane (lane 2 LN2) meeting at an intersection. Figure 4A This illustrates an example where vehicle 101 is proceeding straight at intersection 103, while another vehicle 102 is turning left at intersection 103. In this case, the other vehicle 102 does not travel on the path already traveled by vehicle 101; the path alignment interval is only the interval ΔL2 after the vehicles meet. On the other hand, Figure 4B This illustrates an example where vehicle 101 is proceeding straight through intersection 103 while other vehicle 102 enters intersection 103 and travels in lane 2 LN2. In this case, vehicle 101 does not travel on the path already traveled by other vehicle 102; the path alignment interval is only the interval ΔL1 before the meeting point.

[0051] It should be noted that within the same path section, vehicle 101 and other vehicles 102 may not actually meet. For example, in Figure 4A When other vehicles 102 turn left at intersection 103 and this vehicle 101 passes through intersection 103, Figure 4B In the case where other vehicles 102 enter intersection 103 after vehicle 101 has passed through intersection 103, there will be no meeting between vehicle 101 and other vehicles 102. However, in this case, there are also sections where the path traveled by or passed by vehicle 101 is the same as the path traveled by or passed by other vehicles 102, and there are sections where the paths are the same.

[0052] The vehicle identification unit 173 determines whether there is a path-coherent interval for other vehicles 102 identified by the vehicle identification unit 173. Therefore, the other vehicles 102 identified by the vehicle identification unit 173 include other vehicles 102 traveling in the opposite lane (second lane LN2) at the current time T0. Figure 2 In addition to 102 other vehicles that had traveled in the opposite lane at a previous time point, this also includes 102 other vehicles. Figure 4A ) and other vehicles 102 that are planned to travel in the opposite lane at a future time. Figure 4B That is, even if other vehicles 102 are not traveling in the opposite lane at the current time T0, there may be a path matching interval with this vehicle 101. All other vehicles 102 that may have a path matching interval with this vehicle 101 are included in the other vehicles 102 identified by the vehicle identification unit 173.

[0053] When the path determination unit 174 determines that there is a path-coherent section between the vehicle 101 and other vehicles 102, the information acquisition unit 175 acquires information from the other vehicles 102 via the communication unit 7. That is, information is acquired through vehicle-to-vehicle communication. Specifically, information such as images captured by the camera 102a of the other vehicle 102 within the path-coherent section is acquired. This information includes lane markings, lane widths, road shapes, road surface conditions, construction information, accident information, etc., within the path-coherent section. Alternatively, signals from radar, lidar, or other devices mounted on the other vehicle 102 may be acquired instead of signals from the camera 102a. The other vehicle 102 may also generate an environmental map based on the images from the camera 102a, just like the vehicle 101. In this case, the information acquisition unit 175 can acquire information from the environmental map generated by the other vehicle 102.

[0054] The map generation unit 17 includes a route map generation unit 171 for generating an environmental map of the route (route map) and a loop map generation unit 172 for generating an environmental map of the loop (loop map). When driving on the route in manual driving mode, the route map generation unit 171 extracts feature points of objects around the vehicle 101 based on camera images acquired by camera 1a, and estimates the vehicle's position using sensor 2a, thereby generating an environmental map of the route. The generated route map is stored in the storage unit 12. The route map generation unit 171 identifies the dividing lines L1 and L2 within the detectable range AR1 of camera 1a. Figure 2 The location of the dividing line will be included in the map information (such as internal map information) for storage.

[0055] When driving on a route in manual driving mode, the loop map generation unit 172 generates an environment map of the loop if the loop map generation conditions are met. The loop map generation conditions are met when the path determination unit 174 determines that there is a path-consistent interval. On the other hand, when driving on a route in manual driving mode, if the loop map generation conditions are not met, no environment map of the loop is generated. In this case, when driving on a loop in manual driving mode, similar to the route map generation unit 171, the loop map generation unit 172 extracts feature points of objects around the vehicle 101 based on camera images and estimates the vehicle's position using the sensor 2a, thereby generating an environment map of the loop. The generated loop map is stored in the storage unit 12.

[0056] When the loop map generation conditions are met while the vehicle 101 is traveling on the outbound route, the loop map generation unit 172 generates an environmental map of the loop based on information obtained by the information acquisition unit 175. Specifically, it generates the loop map based on information representing the external conditions around other vehicles 102 within the same path interval, specifically based on camera images. Thus, a loop map is obtained before the vehicle 101 travels on the loop. The generated loop map is stored in the storage unit 12. The loop map generation unit 172 identifies the dividing lines L2 and L3 within the detectable range AR2 of the camera 102a. Figure 2 The location of the dividing line is included in the map information (e.g., internal map information) and stored. Additionally, when driving on a destination road in manual driving mode, the map generation unit 17 generates a destination road map from the destination road map generation unit 71 and a loop road map from the loop road map generation unit 172. That is, both the destination road map and the loop road map are generated simultaneously. Alternatively, the loop road map can be generated after the destination road map is generated.

[0057] When the vehicle 101 is traveling on a loop in automatic driving mode, the action plan generation unit 15 uses the loop map stored in the storage unit 12 to set the target path. The driving control unit 16 ( Figure 1 The control actuator AC enables the vehicle 101 to automatically travel along the target path. Thus, even when the vehicle 101 is traveling on the loop for the first time, it can use the loop environment map obtained during the outbound journey to drive in automatic driving mode.

[0058] Figure 5 It means that according to the predetermined procedure, by Figure 3 A flowchart illustrating an example of the processing performed by controller 10. The processing shown in this flowchart begins when driving in manual driving mode on lane 1 (LN1) and repeats at predetermined intervals. Additionally, see below for further details. Figure 2 illustrate Figure 5 The processing.

[0059] like Figure 5 As shown, firstly, in S1 (S: processing step), signals from camera 1a and sensor 2a are read in. Next, in S2, an environmental map of the current location P0 of the current lane (lane 1 LN1), i.e., a route map, is generated based on the read signals (camera images, etc.). Next, in S3, based on the camera images, etc., read in S1, it is determined whether other vehicles 102 traveling in the opposite lane (lane 2 LN2) are identified around the current vehicle 101. If S3 is affirmative (S3: yes), proceed to S4; if it is negative (S3: no), skip S4 to S6 and proceed to S7.

[0060] In S4, based on the camera images and other data read in S1, the driving paths of other vehicles 102 are estimated. The estimated driving paths include not only the current driving path of other vehicles 102, but also the paths they have previously traveled and the paths they plan to travel in the future. For example, when vehicle 101 is located... Figure 2 The processing of location P1 at time T1 includes the travel path from location P2 of other vehicle 102 to location P1 (past path) and the path from location P2 to location P0 (future path). Furthermore, in S4, it is determined whether there exists an interval where the presumed travel path of other vehicle 102 is consistent with the travel path of this vehicle 101, i.e., a path-consistent interval. When S4 is affirmative (S4: Yes), proceed to S5; when it is negative (S4: No), skip S5 and S6 and proceed to S7.

[0061] In step S5, information about the path-aligned section is obtained from other vehicles 102 via vehicle-to-vehicle communication through communication unit 7; specifically, information such as camera images is obtained. Next, in step S6, an environmental map related to the oncoming lane, i.e., a loop map, is generated based on the obtained information (camera images, etc.). Then, in step S7, the outbound route map generated in step S2 and the loop map generated in step S6 are stored in storage unit 12, and the processing ends.

[0062] It should be noted that S5 processing can be performed each time the flowchart is repeated. However, if other vehicles 102 have the function of storing information, S5 processing may not be performed each time the process is repeated. Instead, the stored information can be retrieved from other vehicles 102 at a predetermined time. For example, the information can also be retrieved from the local vehicle 101. Figure 2 Before reaching the first location P1 from location P0, no information is acquired even if other vehicles 102 are identified. At the time of arrival at the first location P1, information about the interval ΔL2 after the meeting point is acquired from other vehicles 102. This reduces the processing load on the controller 10.

[0063] Alternatively, information can be withheld at time points in S4 where a path-consistent interval is identified, while information can be collected at time points where the length of the path-consistent interval is greater than a specified length. Thus, when other vehicles 102 are traveling on roads intersecting this lane, or when other vehicles 102 are merely crossing the oncoming lane, information is not collected from other vehicles 102, preventing the acquisition of useless information with low value for generating loop maps.

[0064] The operation of the map generation device 50 in this embodiment is summarized as follows. Figure 2As shown, when the vehicle 101 is driving in manual driving mode in this lane (lane 1 LN1), an environmental map (S2) is generated within the detectable range AR1 of the camera 1a, including the position information of dividing lines L1 and L2, based on the camera image. At this time, when another vehicle 102 traveling in the opposite lane (lane 2 LN2) is identified through the camera image of the vehicle 101, information about the path alignment interval where the driving path of the vehicle 101 is consistent with the driving path of the other vehicle 102 is obtained from the other vehicle 102, such as information from the camera image obtained by the other vehicle 102 (S5). That is, information obtained when the other vehicle 102 travels in the interval ΔL2 after meeting other vehicles from location P2 to location P1 and information obtained when traveling in the interval ΔL1 before meeting other vehicles from location P1 to location P0 is obtained.

[0065] Therefore, even before the vehicle 101 actually drives on the loop in manual driving mode, a loop map (S6) can be generated as a map of the oncoming lane. Thus, the vehicle 101 can drive on the loop in automatic driving mode based on this loop map. When the vehicle 101 does not drive in automatic driving mode, but generates the loop environment map in manual driving mode... Figure 1 When traveling on a loop, the loop map information already stored in the storage unit 12 during the outbound journey can be used (S7). Therefore, it is not necessary to generate the loop map from scratch, which reduces the processing load of the controller 10.

[0066] According to this embodiment, the following effects can be achieved.

[0067] (1) The map generation device (50) includes: a vehicle identification unit 173, which identifies other vehicles 102 traveling in the opposite lane (second lane LN2) opposite to the lane (first lane LN1) in which the vehicle 101 is traveling; an information acquisition unit 175, which, when the vehicle identification unit 173 identifies other vehicles 102, acquires information about the external conditions around other vehicles 102 in the path matching interval (pre-meeting interval ΔL1, post-meeting interval ΔL2) in the path matching interval of the vehicle 101 in the path RT including the lane and the opposite lane, obtained by the other vehicles (102) traveling in the opposite lane; and a map generation unit 17 (loop map generation unit 172), which generates a map related to the opposite lane in the path matching interval, i.e., a loop map, based on the information acquired by the information acquisition unit 175. Therefore, even after the vehicle 101 has traveled the past road, but before traveling on the loop, the vehicle 101 itself can generate a loop map, enabling efficient map generation.

[0068] (2) The map generation device 50 also includes a path determination unit 174 for determining whether a path-consistent interval exists. Figure 3 When the path determination unit 174 determines that a path-consistent section exists, the information acquisition unit 175 acquires information about the external conditions surrounding other vehicles 102 within the path-consistent section. Figure 5 Thus, information about the external conditions around other vehicles 102 that are of high value for generating loop maps is obtained, thereby suppressing the acquisition of useless information.

[0069] (3) The route-consistent interval includes the interval where the planned route of vehicle 101 is consistent with the route already traveled by other vehicles 102, i.e., the interval ΔL2 after the meeting. Figure 2 , Figure 4A Therefore, the travel path of vehicle 101 after meeting oncoming traffic can reliably match the actual travel path of other vehicles 102, and the reliability of path consistency within the path consistency interval is high.

[0070] (4) The path-consistent section also includes the section where the path already traveled by vehicle 101 is consistent with the path planned to be traveled by other vehicles 102, i.e., the section ΔL1 before the meeting point. Figure 2 , Figure 4B Therefore, it is possible to obtain information about the travel path of the loop corresponding to the actual traveled route, and to obtain useful information for generating loop maps.

[0071] (5) The map generation device 50 also includes a camera 1a for detecting the external conditions around the vehicle 101. Figure 3 The map generation unit 17 (outbound route map generation unit 171) further generates a map related to the current lane, i.e., an outbound route map, based on the external conditions detected by the camera 1a. Figure 5 Therefore, it is possible to generate both the outbound route map and the return route map while driving on the outbound route. This enables efficient map generation.

[0072] (6) The map generation device 50 also includes a route setting unit (action plan generation unit 15), which sets the target route for the vehicle 101 when it travels in the opposite lane based on the map related to the opposite lane generated by the map generation unit 17. Figure 3 Therefore, it is possible to drive in automatic mode even before driving in manual driving mode, which is used to generate environment maps.

[0073] The above-described embodiments can be modified in various ways. Several modifications will be described below. In the above-described embodiments, the external conditions around the vehicle 101 are detected by an onboard detector such as camera 1a, i.e., external sensor group 1. However, onboard detectors other than camera 1a, such as lidar, or detection units other than onboard detectors, can also be used for detection. In the above-described embodiments, the information acquisition unit 175 communicates with other vehicles 102 via communication unit 7 through vehicle-to-vehicle communication, thereby acquiring information obtained by other vehicles 102. However, the map information can also be acquired via a server device, and the structure of the information acquisition unit is not limited to the above structure.

[0074] In the above embodiments, the map generated by the map generation unit 17 is stored in the storage unit 12. However, the map information can also be sent to the server device via the communication unit 7 so that other vehicles 102 can use the map information. Alternatively, the map information can be sent directly to other vehicles 102 via vehicle-to-vehicle communication. In the above embodiments, the vehicle identification unit 173 identifies other vehicles 102 traveling in the opposite lane based on camera images. However, it can also identify other vehicles based on information from other detection units such as lidar, or through communication between the vehicle 101 and the communication unit located on the road (road-to-road communication) or vehicle-to-vehicle communication. Therefore, the structure of the vehicle identification unit is not limited to the above structure. In the above embodiments, the existence of a path-matching interval is determined by identifying the driving path of other vehicles 102 based on images from the camera 1a. However, the existence of a path-matching interval can also be determined by identifying the driving path of other vehicles 102 based on information obtained via the communication unit 7. Therefore, the structure of the path determination unit is not limited to the above structure.

[0075] In the above embodiment, the map generation unit 17 generates an environmental map of the route to the current location P0 (current time point T0) based on camera images acquired by camera 1a, and generates a loop environmental map using information from other vehicles 102 acquired by information acquisition unit 175. However, it is also possible to generate the route map and the loop map simultaneously. If a route map has already been generated, the map generation unit 17 (loop map generation unit 172) may also generate only the loop map based on information from other vehicles 102. Therefore, the structure of the map generation unit is not limited to the above structure.

[0076] In the above embodiments, an example of applying the map generation device in an autonomous vehicle was described. That is, an example of generating an environmental map for an autonomous vehicle was described, but the present invention can also be applied to generating environmental maps for manually driven vehicles with or without driver assistance functions.

[0077] The present invention can also be used as a map generation method, comprising the following steps: identifying other vehicles 102 traveling in the opposite lane LN2 of the lane LN1 where the vehicle 101 is traveling; when other vehicles 102 are identified, obtaining information about the external conditions around other vehicles 102 in the path-consistent interval where the travel path of the vehicle 101 and the travel path of other vehicles 102 are consistent, obtained from the travel path RT of the other vehicles 102 traveling in the opposite lane LN2, including the lane LN1 and the opposite lane LN2; and generating a map related to the opposite lane LN2 in the path-consistent interval based on the obtained information.

[0078] One or more of the above embodiments and variations can be combined arbitrarily, and variations can also be combined with each other.

[0079] Using this invention, maps can be produced efficiently.

[0080] 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 map generation device, characterized by comprising: Possessing: a vehicle recognition unit (173) that recognizes another vehicle (102) traveling on an opposite lane (LN2) opposite a home lane (LN1) in which a host vehicle (101) travels; a detection unit (la) that detects an external condition around the host vehicle (101); an information acquisition unit (175) that, when another vehicle (102) is recognized by the vehicle recognition unit (173), acquires, from the other vehicle (102) via a communication unit (7) capable of communicating with the other vehicle (102), information on an external condition around the other vehicle (102) in a path-conforming section in which a travel path of the host vehicle (101) coincides with a travel path of the other vehicle (102) in a travel path (RT) including the home lane (LN1) and the opposite lane (LN2) obtained by the other vehicle (102) traveling on the opposite lane (LN2); and a map generation unit (17) that generates a map related to the home lane (LN1) based on the external condition detected by the detection unit (la), and generates a map related to the opposite lane (LN2) in the path-conforming section based on the information acquired by the information acquisition unit (175).

2. The map generation device according to claim 1, characterized by further comprising a path determination unit (174) that determines whether or not the path-conforming section exists, the information acquisition unit (175) acquires the information on the external condition around the other vehicle (102) in the path-conforming section when the path-conforming section is determined to exist by the path determination unit (174).

3. The map generation device according to claim 2, characterized in that the path-conforming section is an interval (AL2) in which a path in which the host vehicle (101) plans to travel coincides with a path in which the other vehicle (102) has traveled.

4. The map generation device according to claim 2, characterized in that the path-conforming section is an interval (AL1) in which a path in which the host vehicle (101) has traveled coincides with a path in which the other vehicle (102) plans to travel.

5. The map generation device according to any one of claims 1 to 4, characterized in that the map generation unit (17) generates the map related to the home lane (LN1) based on the external condition detected by the detection unit (la), and generates the map related to the opposite lane (LN2) based on the information acquired by the information acquisition unit (175).

6. The map generation device according to any one of claims 1 to 4, characterized in that the information acquired by the information acquisition unit (175) includes position information on a dividing line (L2, L3) that divides the opposite lane (LN2) into left and right, and the detection unit (la) detects one (L2) of the left and right dividing lines (L2, L3).

7. The map generation device according to any one of claims 1 to 4, characterized in that ​ Further provided is a path setting section (15) that sets a target path of the host vehicle (101) when the host vehicle (101) travels on the opposite lane (LN2) based on a map related to the opposite lane (LN2) generated by the map generation section (17).

8. The map generation device according to claim 7, wherein The host vehicle (101) is an automated vehicle having an automated driving function, The path setting section (15) sets a target path of the host vehicle (101) when the host vehicle (101) travels on the opposite lane (LN2) by automated driving.

9. A map generation method characterized by, comprises the steps of: identifying another vehicle (102) traveling on an opposite lane (LN2) opposite a host lane (LN1) in which the host vehicle (101) travels; detecting an external condition around the host vehicle (101); when the another vehicle (102) is identified, acquiring, from the another vehicle (102) via a communication unit (7) capable of communicating with the another vehicle (102), information on an external condition around the another vehicle (102) in a path coincidence section in which a travel path of the host vehicle (101) coincides with a travel path of the another vehicle (102) in a travel path (RT) of the another vehicle (102) traveling on the opposite lane (LN2) including the host lane (LN1) and the opposite lane (LN2); and generating a map related to the host lane (LN1) based on the detected external condition, and generating a map related to the opposite lane (LN2) in the path coincidence section based on the acquired information.

Images