Map generation device

Abstract

The present invention provides a map generation apparatus (50) comprising: a detection unit (1a) that detects the external conditions surrounding a vehicle (101); a map generation unit (17) that generates a first map of the lane (LN1) in which the vehicle (101) is traveling based on the detected external conditions; and an information acquisition unit (142) that acquires map information of the opposing lane (LN2) generated by other vehicles (102) traveling in the opposing lane (LN2) opposite to the lane (LN1). The map generation unit (17) further generates a second map of the lane (LN1) corresponding to the location where the opposing lane map was acquired by flipping the opposing lane map acquired by the information acquisition unit (142).

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 on 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 are extracted from the captured image, and white lines are identified based on these edge points.

[0003] However, as described in Patent Document 1, if only the camera images of the vehicle are used to identify the white line, a map including the location information of the white line cannot be effectively generated.

[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] A map generation apparatus according to one embodiment of the present invention includes: a detection unit that detects the external conditions surrounding a vehicle; a map generation unit that generates a first map about the lane in which the vehicle is traveling based on the external conditions detected by the detection unit; and an information acquisition unit that acquires map information about the opposite lane generated by other vehicles traveling in the opposite lane. The map generation unit further generates a second map about the lane corresponding to the location where the opposite lane map was acquired by flipping the opposite lane map 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 3 This is a block diagram illustrating the main structural components of a map generation apparatus according to an embodiment of the present invention.

[0012] Figure 4 It is shown by Figure 3 A flowchart of an example of the processing performed by the controller. Detailed Implementation

[0013] The following is for reference Figures 1-4 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 referred to as "this vehicle" to distinguish it from other vehicles. 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 where driver operation is required.

[0014] First, a general description of the vehicle's structure related 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.

[0015] External sensor group 1 is a collective term for multiple sensors (external sensors) that detect information about the vehicle's surroundings, i.e., external conditions. For example, external sensor group 1 includes: a lidar that measures the distance from the vehicle to surrounding obstacles by measuring the scattered light relative to the omnidirectional illumination light; a radar that detects other vehicles or obstacles around the vehicle by irradiating electromagnetic waves and detecting the reflected waves; and a camera mounted on the vehicle and equipped with imaging elements such as CCD and CMOS to capture images of the vehicle's surroundings (front, rear, and sides).

[0016] Internal sensor group 2 is a collective term for multiple sensors (internal sensors) that detect the vehicle's driving status. For example, internal sensor group 2 includes: a vehicle speed sensor to detect the vehicle's speed; acceleration sensors to detect the vehicle's longitudinal and lateral acceleration (lateral acceleration); a speed sensor to detect the rotational speed of the driving engine; and a yaw rate sensor to detect the rotational angular velocity of the vehicle's center of gravity around its vertical axis. Sensors that detect driver 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.

[0017] 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.

[0018] The positioning unit (GNSS unit) 4 has a positioning sensor that receives positioning signals transmitted from positioning satellites. These 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).

[0019] Map database 5 is a device that stores general map information used in navigation device 6, and is composed of, for example, a disk or semiconductor element. The map information includes: road location information, road shape (curvature, etc.) information, and the location information of intersections and forks in the road. It should be noted that the map information stored in map database 5 is different from the high-precision map information stored in storage unit 12 of controller 10.

[0020] The navigation device 6 is a device that searches for a target path on the road leading to the destination input by the driver and guides the user along the target path. The destination is input and the user is guided along the target path via the input / output device 3. The target path is calculated based on the 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 this current position and high-precision map information stored in the storage unit 12.

[0021] Communication unit 7 communicates with various servers (not shown) via a network including wireless communication networks such as the Internet and mobile phone networks, periodically or at any time, to obtain map information, driving record information, and traffic information from the servers. In addition to obtaining driving record information, communication unit 7 can also send the vehicle's driving record 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 local area networks, Wi-Fi, and Bluetooth. The obtained map information is output to map database 5 and storage unit 12, and the map information is updated.

[0022] 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 drive motor, the actuator AC includes the drive motor. Braking actuators that operate the vehicle's braking system and steering actuators that drive the steering system are also included in the actuator AC.

[0023] The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 is configured as a computer including an arithmetic unit 11 such as a CPU (microprocessor), a storage unit 12 such as ROM (read-only memory) and RAM (random access memory), and other peripheral circuits (not shown) such as I / O interfaces. It should be noted that multiple ECUs with different functions, such as an engine control ECU, a drive motor control ECU, and a braking system ECU, can be set up separately, but for convenience, they are shown separately in the following diagram. Figure 1 The controller 10 is shown as a collection of these ECUs.

[0024] 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.) information, road slope information, location information of intersections and forks in the road, the type and location information of dividing lines such as white lines, information on the number of lanes, lane width and the location information of each lane (center position of the lane, information on lane boundary lines), location information of landmarks (traffic lights, signs, buildings, etc.) used as markers on the map, and information on road surface conditions such as unevenness. The map information stored in the storage unit 12 includes: map information obtained from outside the vehicle using the communication unit 7 (referred to as external map information), and map information created by the vehicle itself using detection values ​​from external sensor group 1 or detection values ​​from external sensor group 1 and internal sensor group 2 (referred to as internal map information).

[0025] External map information refers to maps obtained using a cloud server (referred to as cloud maps), while internal map information refers to maps (referred to as environment maps) generated by mapping point cloud data using technologies such as SLAM (Simultaneous Localization and Mapping). Unlike external map information, which is shared by this vehicle and other vehicles, internal map information is unique to this vehicle (e.g., map information owned solely by this vehicle). In areas where external map information is unavailable, such as newly constructed roads, this vehicle creates its own environment map. It should be noted that internal map information can also be provided to a server device and other vehicles via communication unit 7. Storage unit 12 also stores information about various control programs, thresholds used in the programs, and other related information.

[0026] 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.

[0027] 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. It can also identify the vehicle's position using map information stored in the storage unit 12 and surrounding information detected by the external sensor group 1, thereby enabling high-precision vehicle position identification. The vehicle's movement information (movement direction, movement distance) is calculated based on the detection values ​​from the internal sensor group 2, thereby also enabling vehicle position identification. 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.

[0028] 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, billboards, pedestrians, bicycles, etc. 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), the speed and direction of pedestrians and bicycles, etc. A portion of stationary objects among other objects constitutes a landmark that marks a location on a map; the external identification unit 14 also identifies the location and category of these landmarks.

[0029] The action plan generation unit 15 generates a driving trajectory (target trajectory) of the vehicle from the current point in time up to a predetermined time, based on, for example, the target path calculated by the navigation device 6, map information stored in the storage unit 12, the vehicle position identified by the vehicle position recognition unit 13, and the external conditions identified by the external environment recognition unit 14. When multiple candidate trajectories exist on the target path, the action plan generation unit 15 selects the best trajectory that complies with the law and meets the criteria of efficient and safe driving, and sets 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 without deviating from the lane, deceleration, or 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.

[0030] 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. Then, feedback control is performed on the actuator AC to make the actual acceleration detected by, for example, the internal sensor group 2 become 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 the driving commands (steering operations, etc.) obtained from the driver by the internal sensor group 2.

[0031] While driving in manual driving mode, the map generation unit 17 generates an environmental map composed of three-dimensional point cloud data using detection values ​​detected by the external sensor group 1. Specifically, it extracts the edges that show the contours of objects from camera images acquired by the camera, based on the brightness and color information of each pixel, and extracts feature points 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, it can use data acquired by radar or lidar to extract feature points of objects around the vehicle and generate an environmental map.

[0032] 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 position changes of feature points over time. The map generation process and position estimation process are performed simultaneously using signals from, for example, cameras and LiDAR, according to a 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.

[0033] The structure of the map generation apparatus of this embodiment will be described. Figure 2 This diagram illustrates an example of a driving scenario using the map generation device of this embodiment, showing the vehicle 101 generating an environmental map while in manual driving mode. Figure 1 The scenario of driving on the side. More specifically, the scenario of driving in the lane (lane 1 LN1) defined by the left and right dividing lines L1 and L2 is shown. Figure 2 The image also shows other vehicles 102 traveling in the opposite lane that extends parallel to and is opposite to this lane, namely the opposite lane (lane 2 LN2) defined by the left and right dividing lines L2 and L3.

[0034] like Figure 2 As shown, 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 the camera's inherent 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 (e.g., white lines) L1, L2. It should be noted that the detectable range AR1 may sometimes differ from the illustration if a portion of the camera 1a's field of view is obstructed due to the presence of parts disposed around the camera 1a.

[0035] The same camera 102a as that in vehicle 101 is also mounted on the front of other vehicles 102. The detectable range AR2 of camera 102a is the same as, for example, the detectable range AR1, which is the inner side of a sector with radius r and central angle θ centered on camera 102a. It should be noted that the detectable range AR2 is determined by the performance of the camera itself and the installation position of camera 102a, and sometimes the detectable range AR2 and the detectable range AR1 are different.

[0036] Figure 2 The boundary line L0 between lane 1 (LN1) and lane 2 (LN2) is shown in the image. It should be noted that... Figure 2In the diagram, boundary line L0 and dividing line L2 are identical, but in reality, boundary line L0 and dividing line L2 may not be identical. Boundary line L0 is located in the center between the first center line LN1a, which passes through the center of the first lane LN1 in the vehicle width direction and extends along the first lane LN1, and the second center line LN2a, which passes through the center of the second lane LN2 in the vehicle width direction and extends along the second lane LN2. Therefore, on roads with a central divider, for example, there is a boundary line L0 between the dividing line on the inner side of the first lane LN1 in the vehicle width direction (the side with the central divider) and the dividing line on the inner side of the second lane LN2 in the vehicle width direction (the side with the central divider), and dividing line L2 is different from boundary line L0.

[0037] In such a driving scenario, the vehicle 101 can extract edge points from acquired camera images while driving in its lane, thereby generating a map of the lane (lane 1 LN1) contained within the detectable range AR1. Furthermore, if map information of the locations where the vehicle 101 will travel in the future can be obtained in advance, the vehicle 101 can use this map information to efficiently generate a map. For example, if map information relative to... Figure 2 If the current location P0 is located at a location P1 ahead in the direction of travel, map generation can be performed efficiently. With this in mind, the map generation apparatus is configured as follows in this embodiment.

[0038] 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 includes a controller 10, a camera 1a, and a sensor 2a.

[0039] 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 on 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 objects (camera images). Objects include road markings (e.g., lane lines). Figure 2 (The dividing lines L1 and L2). It should be noted that a lidar or similar device can also replace camera 1a, or detect objects together with camera 1a.

[0040] 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 estimates the position of the vehicle 101 using a range estimation method. For example, when driving in manual driving mode, the vehicle position is estimated using a range estimation method when creating an environmental map. It should be noted that the configuration of sensor 2a is not limited to this, and information from other sensors can also be used to estimate its own position.

[0041] Figure 3 In addition to the action plan generation unit 15 and the map generation unit 17, the controller 10 also has a vehicle recognition unit 141 and an information acquisition unit 142, which serve as the computing unit 11. Figure 1 The functional structure it undertakes. The vehicle identification unit 141 and the information acquisition unit 142 are used to identify the external environment, and these constitute... Figure 1 It is part of the external identification unit 14. It should be noted that the vehicle identification unit 141 and the information acquisition unit 142 also have map generation functions and can be included in the map generation unit 17.

[0042] The vehicle identification unit 141 identifies other vehicles 102 traveling in the opposite lane (lane 2 LN2) based on camera images acquired by camera 1a. When identifying other vehicles 102, the opposite lane can be identified, for example, by identifying the boundary line between lane 1 LN1 and lane 2 LN2. Alternatively, instead of identifying the boundary line, the opposite lane can be identified by identifying poles, walls (such as median strips) located at the boundary between lane 1 LN1 and lane 2 LN2. Other vehicles 102 traveling in the opposite lane can also be identified by identifying their orientation or through communication with other vehicles. The vehicle identification unit 141 also identifies other vehicles 102 that are traveling in the opposite lane from the location P1 where the vehicle 101 is predicted to travel in the future. The vehicle identification unit 141 can also identify other vehicles 102 by obtaining their location information via communication unit 7. It can also identify other vehicles 102 that are predicted to intersect with the vehicle 101 in the future.

[0043] The other vehicles 102 identified by the vehicle identification unit 141 are those with map generation capabilities. That is, for example... Figure 2 The configuration shown is such that other vehicles 102 extract feature points of objects (buildings, dividing lines L2, L3, etc.) around other vehicles 102 within the detectable range AR2 of camera 102a based on camera images obtained by camera 102a, thereby generating an environmental map of the second lane LN2 (called the opposite lane map).

[0044] The information acquisition unit 142 acquires map information from other vehicles 102 identified by the vehicle identification unit 141. Specifically, it acquires map information of the opposing lane map generated by other vehicles 102 by communicating with them via the communication unit 7 (vehicle-to-vehicle communication). Map information is continuously acquired until the vehicle 101 encounters another vehicle 102 or until the distance between the vehicle 101 and other vehicles 102 falls below a predetermined value (e.g., the maximum detection distance r of camera 1a). The acquired map information is stored in the storage unit 12.

[0045] The map generation unit 171 has a current map generation unit 171 that generates a map of the current location P0 where the cost vehicle 101 is currently traveling (called the current map) and a future map generation unit 172 that generates a map of the location P1 where the cost vehicle 101 is planned to travel in the future (called the future map).

[0046] When the vehicle 101 is driving in manual driving mode in lane 1 (LN1), the current map generation unit 171 extracts feature points of objects (buildings, dividing lines L1, L2, etc.) 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 (current map) of the area surrounding the current position of the vehicle 101. The generated environmental map includes internal map information of the position information of dividing lines L1 and L2 within the detection range AR1 of camera 1a, and the map information including this position information is stored in the storage unit 12.

[0047] When the vehicle recognition unit 141 identifies another vehicle 102 traveling in lane 2 LN2, the future map generation unit 172 generates an environmental map (future map) of lane 1N1, where the vehicle 101 plans to travel, based on map information of the opposing lane map obtained by the information acquisition unit 142. More specifically, firstly, a boundary line L0 between lane 1N1 and lane 2 LN2 is set based on camera images. Next, the opposing lane map is symmetrically moved about the boundary line L0 as an axis of symmetry. That is, assuming that the current lane and the opposing lane have the same structure, the opposing lane map is symmetrically flipped left and right by mirror transformation.

[0048] In other words, the prediction assumes that the current lane and the oncoming lane include the same or corresponding map information in terms of lane width, intersection location, etc. Therefore, by symmetrically shifting the oncoming lane map relative to the boundary line L0, a good environmental map of the current lane is obtained. That is, as... Figure 2As shown by the dashed line, a future map is obtained in range AR3 by symmetrically shifting the detectable range AR2. Range AR3 includes the dividing lines L1 and L2 of lane 1 LN1. The future map thus obtained is a simplified map obtained by mirror transformation before the vehicle 101 travels to location P1, equivalent to a temporary map. The information of this temporary map is stored in storage unit 12.

[0049] When the current map generation unit 171 travels to location P1 on the future map after the future map has been generated by the future map generation unit 172, it updates the map information of the future map based on camera images acquired by camera 1a. Specifically, it generates a future map whose range AR3 overlaps with at least a portion of the detectable range AR1 of camera 1a through mirror transformation. Therefore, the current map generation unit 171 combines or matches the map data from the temporary map with the map data from the camera images, thereby updating the map information. The updated map information is stored in the storage unit 12.

[0050] The updated map is a complete environmental map of location P1 in this lane (lane 1, LN1). However, when the vehicle 101 is traveling at location P1, since a temporary map has been generated in advance, the current map generation unit 171 does not need to generate an environmental map of location P1 from scratch. Therefore, the environmental map can be generated efficiently, reducing the processing load on the controller 10. When the vehicle 101 is traveling in lane 1, LN1, it can also travel in automatic driving mode using a temporary map obtained in advance through mirror transformation. In this case, the following configuration is possible: the action plan generation unit 15 sets the target path for the vehicle 101 based on the temporary map, and the driving control unit 16 controls the actuator AC to make the vehicle 101 travel automatically along the target path.

[0051] Figure 4 It shows that according to a predetermined procedure, by Figure 3 The flowchart illustrates an example of the processing performed by controller 10. The processing shown in the flowchart begins when driving in manual driving mode in lane 1 (LN1) and repeats at predetermined intervals.

[0052] like Figure 4 As shown, firstly, in step S1 (S: processing step), signals from camera 1a and sensor 2a are read in. Next, in step S2, an environmental map, i.e., a current map, is generated based on the read signals (camera images, etc.) at the current location P0 of the current lane (lane 1 LN1). Next, in step S3, based on the camera images read in step S1, it is determined whether other vehicles 102 traveling in the opposite lane (lane 2 LN2) have been identified. If S3 is affirmative (S3: yes), the process proceeds to step S4; if it is negative (S3: no), the processing ends.

[0053] In step S4, map information about the oncoming lane is obtained from other vehicles 102 via communication unit 7. That is, an environmental map (oncoming lane map) generated by other vehicles 102 is obtained. Next, in step S5, an environmental map (future map) of the future location P1 of this vehicle 101 is generated by flipping the obtained oncoming lane map. Next, in step S6, the map information of the current map generated in step S2 and the future map generated in step S5 is stored in storage unit 12, and the process ends.

[0054] It should be noted that when the controller 10 creates the current map in S2, it determines whether the map of that location is pre-stored in the storage unit 12 (illustration omitted). In other words, it determines whether the vehicle 101 is currently traveling at location P1 where the future map has been stored through the previous processing in S6. Then, if traveling at location P1 where the future map is stored, when creating the current map, the map information of the pre-stored future map (temporary map) is updated, thereby generating the current map.

[0055] When multiple other vehicles 102 are identified in S3, the controller 10 obtains map information about the oncoming lanes from each of the other vehicles 102 in S4, and performs a mirror transformation on these oncoming lane maps in S5. By repeating this process, multiple future maps can be generated for the same location (e.g., location P1). When the vehicle 101 is traveling at location P1 where multiple future maps have been generated, the controller 10 synthesizes the multiple future maps and updates the map information.

[0056] The operation of the map generation apparatus 50 in this embodiment is summarized below. For example... Figure 2 As shown, when the vehicle 101 is driving in the lane (lane 1 LN1) in manual driving mode, an environmental map within the detectable range AR1 of the camera 1a, including the position information of dividing lines L1 and L2, is generated based on camera images (S2). At this time, when another vehicle 102 traveling in the opposite lane (lane 2 LN2) to the side of location P1 is identified based on the camera image of the vehicle 101 traveling at location P0, map information about the opposite lane generated by the other vehicle 102 is obtained, and this map information is flipped to convert it into map information about the current lane (S4, S5).

[0057] This allows for the generation of an environmental map of the location P1 where the vehicle 101 will travel in the future. Therefore, the vehicle 101 does not need to generate an environmental map of location P1 from scratch; it can easily generate an environmental map of location P1 using map information about the oncoming lanes. Furthermore, the target trajectory of the vehicle 101 can be generated using the environmental map obtained through mirror transformation, enabling the vehicle 101 to drive autonomously.

[0058] The following effects can be achieved by adopting this implementation method.

[0059] (1) The map generation device 50 includes: a camera 1a that detects the external conditions around the vehicle 101; a map generation unit 17 (current map generation unit 171) that generates a current map of the lane (first lane LN1) in which the vehicle 101 is traveling based on the external conditions detected by the camera 1a; and an information acquisition unit 142 that acquires map information about the opposite lane generated by other vehicles 102 traveling in the opposite lane (second lane LN2). Figure 3 The map generation unit 17 also has a future map generation unit 172 that generates a future map of the current lane corresponding to the location P1 where the opposite lane map was obtained by flipping the opposite lane map obtained by the information acquisition unit 142. Figure 3 Therefore, it is possible to obtain map information of the location P1 where the vehicle 101 is traveling in advance, and to generate maps efficiently.

[0060] (2) The current map is the map of the current location P0 in this lane, and the future map is the map of the location P1 that this vehicle 101 has traveled relative to the current location P0. Figure 2 Therefore, it is possible to obtain map information of the future location P1 where the vehicle 101 will travel in advance. Thus, when the vehicle 101 actually passes through location P1, it is possible to use the map information of the future map to generate a map efficiently.

[0061] (3) The map generation device 50 also has a vehicle recognition unit 141 that can identify other vehicles 102 traveling in the opposite lane. Figure 3 When the vehicle identification unit 141 identifies another vehicle 102, the information acquisition unit 142 acquires map information of the oncoming lane map. Figure 4 Therefore, it is possible to obtain the map information needed to generate future maps at the right time.

[0062] (4) After generating a future map by flipping the opposing lane map, the map generation unit 17 updates the future map based on the external conditions detected by the camera 1a when the vehicle 101 is driving in the lane. Therefore, by using map information obtained during actual driving at the location P1 where the future map was generated, the future map generated in advance through mirror transformation is updated, thus improving the accuracy of the environment map generation. In this case, instead of generating a new environment map, the environment map is generated using information from the future map generated through mirror transformation, thus reducing the processing load on the controller 10.

[0063] (5) The map generation device 50 also includes a path setting unit (action plan generation unit 15) that sets the target path of the vehicle 101 when it is driving in the oncoming lane based on the future map generated by the map generation unit 17. Thus, driving in automatic driving mode can be performed even before driving in manual driving mode for generating environment maps.

[0064] 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 on-board detector such as camera 1a, i.e., external sensor group 1. However, on-board detectors other than camera 1a, such as lidar, or detection units other than on-board detectors, can also be used for detection. In the above-described embodiments, the case where other vehicles 102 generate an environmental map as an oncoming lane map in the same way as the vehicle 101 is described. However, the oncoming lane map generated by other vehicles 102 may not be an environmental map.

[0065] In the above embodiments, the information acquisition unit 142 uses the communication unit 7 to communicate with other vehicles 102 via vehicle-to-vehicle communication and obtains map information of the oncoming lane from other vehicles 102. However, it can also obtain this map information using a server device. 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 it can be used by other vehicles 102. 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 141 identifies other vehicles 102 traveling in the oncoming 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 communication unit installed on the road and the vehicle 101 (road-to-road communication) or vehicle-to-vehicle communication. Therefore, the configuration of the vehicle identification unit is not limited to those described above.

[0066] In the above embodiment, the map generation unit 17 generates a current map (first map) of the current location P0 (first location) based on the camera image acquired by the camera 1a, and generates a future map (second map) of the future location P1 (second location) by flipping the oncoming lane map acquired by the information acquisition unit 142. However, as long as the first map is generated and a second map is generated for the lane corresponding to the location where the oncoming lane map is acquired, the configuration of the map generation unit can be any form. In the above embodiment, the map generation unit 17 generates a future map of the future location P1 of the vehicle 101 as the second map, but it can also acquire a map of the location P0 where the vehicle 101 is currently traveling as the second map, and it can also acquire maps of locations that have been previously traveled as the second map. Therefore, the relationship between the first location and the second location is not limited to what has been described above.

[0067] In the above embodiment, the map generation unit 17 symmetrically moves the opposing lane map about the boundary line L0 as the axis of symmetry to generate a future map. However, the method of flipping the opposing lane map is not limited to linear symmetry about the boundary line as the axis of symmetry. In the above embodiment, the action plan generation unit 15, which is the path setting unit, uses the future map (temporary map) generated by mirror transformation to set the target path for autonomous driving. However, the target path for autonomous driving can also be set without using the temporary map, and instead using a complete map (e.g., an updated map).

[0068] In the above embodiments, an example of applying the map generation device to an autonomous vehicle was described. That is, an example of generating an environmental map by an autonomous vehicle was illustrated, but the present invention can also be applied to situations where an environmental map is generated by a manually driven vehicle with or without driver assistance functions.

[0069] The present invention can also be used as a map generation method, including: a step of generating a first map about the lane LN1 in which the vehicle 101 is traveling, based on the external conditions around the vehicle 101 detected by a detection unit such as a camera 1a; and a step of obtaining map information about the opposing lane map of the opposing lane LN2 generated by other vehicles 102 traveling in the opposing lane LN2 opposite to the lane LN1, the generation step further including generating a second map about the lane LN1 corresponding to the location where the opposing lane map was obtained by flipping the obtained opposing lane map.

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

[0071] Using this invention, map creation can be carried out efficiently.

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

Claims

1. A map generation device, characterized in that, have: A detection unit (1a) detects the external conditions surrounding the vehicle (101); a map generation unit (17) generates a first map of the lane (LN1) in which the vehicle (101) is traveling, based on the external conditions detected by the detection unit (1a); and The information acquisition unit (142) acquires map information about the opposite lane (LN2) generated by other vehicles (102) traveling in the opposite lane (LN2) of the same lane (LN1) through vehicle-to-vehicle communication. The map generation unit (17) also generates a second map of the lane (LN1) corresponding to the location where the opposite lane map was obtained by flipping the opposite lane map obtained by the information acquisition unit (142) with the boundary line (L0) between the lane (LN1) and the opposite lane (LN2) as the axis of symmetry.

2. The map generation apparatus according to claim 1, characterized in that, The first map is a map of the first location (P0) of the lane (LN1), and the second map is a map of the second location (P1) of the vehicle (101) relative to the first location (P0).

3. The map generation apparatus according to claim 1 or 2, characterized in that, It also includes a vehicle identification unit (141) that identifies other vehicles (102) traveling in the opposite lane (LN2). When the vehicle identification unit (141) identifies another vehicle (102), the information acquisition unit (142) acquires the map information of the opposing lane map.

4. The map generation apparatus according to claim 1 or 2, characterized in that, After generating the second map by flipping the opposing lane map, the map generation unit (17) updates the second map based on the external conditions detected by the detection unit (1a) when the vehicle (101) is driving in the lane (LN1).

5. The map generation apparatus according to claim 1 or 2, characterized in that, It also includes a path setting unit (15), which sets the target path for the vehicle (101) when it travels in the opposite lane (LN2) based on the second map generated by the map generation unit (17).

6. The map generation apparatus according to claim 5, characterized in that, The vehicle (101) is an autonomous vehicle with autonomous driving capabilities. The path setting unit (15) sets the target path for the vehicle (101) when it drives in the opposite lane (LN2) by automatic driving.

7. A map generation method, characterized in that, include: The step of generating a first map of the lane (LN1) in which the vehicle (101) is traveling, based on the external conditions around the vehicle (101) detected by the detection unit (1a); and The step of obtaining map information about the opposite lane (LN2) generated by other vehicles (102) traveling in the opposite lane (LN2) of the same lane (LN1) through vehicle-to-vehicle communication is as follows: The generation step further includes generating a second map of the lane (LN1) corresponding to the location where the opposite lane map was obtained by flipping the opposite lane map with the boundary line (L0) between the lane (LN1) and the opposite lane (LN2) as the axis of symmetry.

Images