Map information generation method and map information generation device

Abstract

To identify a region in which an own vehicle is to travel in order to generate map information indicating a travel path for each lane when generating map information on the basis of information which is collected by traveling the own vehicle on which a sensor is loaded.SOLUTION: A map information generation method includes: detecting an own position of an own vehicle and a peripheral environment of the own vehicle by a sensor which is loaded on the own vehicle (S1 and S2); storing information of the detected own position and information of the detected peripheral environment and generating map information (S4) indicating a travel path for each lane on a road; detecting a travel track the own vehicle travels based on the information of the own position (S3); detecting a road end based on the information of the peripheral environment (S10); evaluating sufficiency which is an index of whether or not travel tracks and road ends are detected sufficiently for the map information, for each section of a predetermined distance in an extension direction of the road (S11); and identifying a travel region in which the own vehicle is to travel based on an evaluation result of the sufficiency (S12).SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to a map information generating method and a map information generating device. [Background technology]

[0002] Patent Document 1 describes a technology for generating a high-precision map based on information collected by driving a vehicle equipped with sensors. This technology compares the learning progress for each section included in the route where driving assistance is provided, and presents the user with a recommended route that will quickly increase the learning progress. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-189871 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 determines the learning progress according to the number of times a road has been driven, so it cannot determine which lanes have not yet been driven on a road with multiple lanes. As a result, when generating map information showing the route for each lane, it is not possible to identify which areas on the road the vehicle should travel in to collect information. The present invention aims to identify the area in which a vehicle should travel in order to generate map information showing the route for each lane when generating map information based on information collected while the vehicle is traveling and equipped with a sensor. [Means for solving the problem]

[0005] In one aspect of the map information generation method of the present invention, a sensor mounted on the vehicle detects the vehicle's own position and the vehicle's surrounding environment, accumulates information on the detected vehicle's own position and information on the surrounding environment, generates map information showing the route for each lane on the road, detects the driving trajectory traveled by the vehicle based on the information on the vehicle's own position, detects road edges based on information on the surrounding environment, evaluates sufficiency, which is an indicator of whether sufficient driving trajectory and road edges have been detected for map information, for each section of a specified distance in the extension direction of the road, and identifies the driving area in which the vehicle should drive based on the sufficiency evaluation result. [Effects of the Invention]

[0006] According to the present invention, when generating map information based on information collected while driving a vehicle equipped with a sensor, the area in which the vehicle should travel can be identified in order to generate map information showing the route for each lane. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a schematic configuration diagram of an example of a map information generating device according to an embodiment; [Figure 2] FIG. 2 is a block diagram illustrating an example of a functional configuration of a controller. [Figure 3] FIG. 2 is a schematic diagram of an example of map information. [Figure 4] FIG. 2 is a schematic diagram of an example of learning map information. [Figure 5] FIG. 10 is a schematic diagram illustrating an example of road edge determination. [Figure 6] FIG. 10 is a schematic diagram illustrating another example of road edge determination. [Figure 7] FIG. 10 is a schematic diagram illustrating an example of evaluation of sufficiency. [Figure 8] FIG. 10 is a schematic diagram of an example of a recommended area presented to an occupant. [Figure 9] 1 is an overall flowchart of an example of a map information generating method according to an embodiment. [Figure 10] 10 is a flowchart illustrating an example of a recommended region presentation process. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that the drawings are schematic and may differ from the actual product. Furthermore, the embodiments of the present invention shown below are examples of devices and methods for embodying the technical concept of the present invention, and the technical concept of the present invention does not limit the structure, arrangement, etc. of component parts to those described below. The technical concept of the present invention can be modified in various ways within the technical scope defined by the claims.

[0009] (composition) 1 is a schematic configuration diagram of an example of a map information generating device according to an embodiment. A vehicle 1 includes a map information generating device 10 that generates map information based on information collected by a sensor mounted on the vehicle 1. The map information generating device 10 includes an object sensor 11, a positioning device 12, a human machine interface (HMI) 13, and a controller 14.

[0010] The object sensor 11 is a sensor that detects objects around the host vehicle 1. The object sensor 11 detects the surrounding environment of the host vehicle 1, such as the relative position of the host vehicle 1 and an object present around the host vehicle 1, the distance between the host vehicle 1 and the object, and the direction in which the object is present. The object sensor 11 may include, for example, a camera that captures the surrounding environment of the host vehicle 1. Furthermore, for example, the host vehicle 1 may include a distance measuring device such as a laser range finder (LRF), radar, or LiDAR (Light Detection and Ranging) laser radar, or a sonar sensor that detects obstacles around the host vehicle 1. The host vehicle 1 outputs surrounding environment information, which is information on the detected surrounding environment of the host vehicle 1, to the controller 14.

[0011] The positioning device 12 includes a Global Navigation System (GNSS) receiver and receives radio waves from multiple navigation satellites to measure the current position of the vehicle 1. The GNSS receiver may be, for example, a Global Positioning System (GPS) receiver. The positioning device 12 may be, for example, an inertial navigation system. The positioning device 12 outputs information about the measured current position of the vehicle 1 (current position information) to the controller 14. The object sensor 11 and the positioning device 12 are an example of the "sensor mounted on the vehicle" described in the claims.

[0012] The HMI 13 is an interface device that exchanges information between the map information generating device 10 and the occupant of the vehicle 1. The HMI 13 includes a display device (for example, a display screen of a navigation system) that can be seen by the occupant of the vehicle 1, a speaker or buzzer for outputting warning sounds, notification sounds, and audio information, and a haptic device that presents haptic signals to the occupant. The controller 14 is an electronic control unit (ECU) that generates map information based on information collected by the object sensor 11 and the positioning device 12.

[0013] The map information generated by the controller 14 may be, for example, high-precision map data suitable as a map for autonomous driving. High-precision map data is map data with higher precision than map data for navigation, and includes lane-by-lane information that is more detailed than road-by-road information. The controller 14 includes a processor 15 and peripheral components such as a storage device 16. The processor 15 may be, for example, a CPU (Central Processing Unit) or an MPU (Micro-Processing Unit).

[0014] The storage device 16 may include a semiconductor storage device, a magnetic storage device, an optical storage device, etc. The storage device 16 may include memories such as a ROM (Read Only Memory) and RAM used as main storage devices, as well as registers and cache memories. The functions of the controller 14 described below are realized by, for example, the processor 15 executing a computer program stored in the storage device 16.

[0015] The controller 14 may be formed by dedicated hardware for executing each of the information processes described below. For example, the controller 14 may include a functional logic circuit configured in a general-purpose semiconductor integrated circuit, such as a programmable logic device (PLD) such as a field-programmable gate array (FPGA).

[0016] 2 is a block diagram of an example of the functional configuration of the controller 14. The controller 14 includes map information 20, a position acquisition unit 21, a road determination unit 22, a lane boundary detection unit 23, a travel trajectory generation unit 24, learned map information 25, a sufficiency determination unit 26, and a recommended area presentation unit 27. The map information 20 and the learned map information 25 may be stored in, for example, the storage device 16, or may be stored in an external information processing device (for example, a server device) accessible to the vehicle 1. The controller 14 may access the map information 20 and the learned map information 25 stored in the external information processing device via a communication device (not shown) to receive or update this information.

[0017] 3 is a schematic diagram of an example of map information 20. For example, the map information 20 may be map data for navigation that includes information on a road-by-road basis. For example, the map information 20 is expressed as a collection of unit sections W1 to W14, ... that make up a road. In the following description, the unit sections W1 to W14, ... may be collectively referred to as "unit section W." For example, a unit section W is defined as a line segment of a road connecting intersections. Each unit section W has a connection relationship with other unit sections W, thereby expressing the topology of the road.

[0018] The unit interval W is made up of a sequence of multiple node points (node ​​points N1 to N5 in the example of unit interval W1). In the following description, the node points N1 to N5 may be collectively referred to as "node point N." Each node point N has coordinate information (x, y) that indicates the position of the node point N in a coordinate system (hereinafter referred to as the "map coordinate system") that uses a fixed point as the reference point, and information on the road traffic direction θ at the position of the node point N, thereby expressing the approximate shape of the road. In Fig. 3, the arrows added to the node points N1 to N5 indicate the road traffic direction θ. The map coordinate system may be, for example, a global coordinate system.

[0019] For example, the node points N may be set so that the distance between adjacent node points N is equal to or less than the length of one period of a broken line of a road marking (e.g., a lane boundary line) provided on a road as a broken line (i.e., the sum of the length of one line segment and the length of one interval). For example, if the length of the line segment of the broken line of the road marking is 5 m and the length of the interval between the line segments is 5 m, the node points N may be placed at intervals of approximately 10 m.

[0020] 2, the position acquisition unit 21 acquires the own position of the vehicle 1 on the map coordinate system based on the current position information from the positioning device 12. The road determination unit 22 identifies the unit section W on which the vehicle 1 is currently traveling, based on the vehicle's own position acquired by the position acquisition unit 21. The lane boundary detection unit 23 detects lane boundaries existing around the vehicle 1 based on the surrounding environment information from the object sensor 11. For example, the lane boundary detection unit 23 may detect road markings formed by solid or broken lines (e.g., outer road lines and lane boundary lines) or three-dimensional objects extending along the road (e.g., curbs, guardrails, plants, walls, etc.) as lane boundaries.

[0021] For example, the lane boundary detection unit 23 may input an image captured by the camera of the object sensor 11 to a classifier and detect road markings formed by solid or broken lines, curbs, guardrails, plants, walls, etc. Furthermore, for example, the lane boundary detection unit 23 may detect road markings such as arrows indicating the direction of travel, speed limits, and letters. As such a classifier, a DNN (Deep Neural Network) having a CNN (Convolutional Neural Network) structure that realizes semantic segmentation can be used. Note that the classifier may be a neural network for object detection, or may be a classifier based on a machine learning model other than a neural network.

[0022] The travel locus generating unit 24 generates a travel locus of the vehicle 1 in the unit section W identified by the travel road determining unit 22 based on the history of the vehicle's own position acquired by the position acquiring unit 21. The travel trajectory generating unit 24 saves (stores) in learned map information 25 information on the generated travel trajectory and information on the lane boundaries detected by the lane boundary detecting unit 23 . Fig. 4 is a schematic diagram of an example of the learning map information 25. The learning map information 25 shown in Fig. 4 records four driving trajectories T1 to T4 generated by the driving trajectory generating unit 24 and lane boundaries B1 to B11 detected by the lane boundary detecting unit 23. In the following description, the driving trajectories T1 to T4 may be collectively referred to as "driving trajectory T," and the lane boundaries B1 to B11 may be referred to as "lane boundaries B."

[0023] 4 indicates the unit section in which the driving trajectory T and lane boundary B are recorded, solid lines ER1 and ER2 indicate the right and left road edges in the unit section W, and dashed lines LM1 to LM3 indicate the lane markings in the unit section W. Also, the circular plots in FIG. 4 indicate the node points N that form the unit section W. The portion of road edge ER1 surrounded by dashed lines B1 and B2 indicates the portion where the solid road markings forming road edge ER1 were detected, and the portion of road edge ER2 surrounded by dashed lines B3 to B6 indicates the portion where the curbs forming road edge ER2 were detected.

[0024] Furthermore, the portions of the lane markings LM1 to LM3 surrounded by dashed lines B7 to B11 indicate the portions where dashed road markings forming the lane markings have been detected. The driving trajectories T1 to T4 are composed of position and attitude data representing the position (x, y) of the vehicle 1 sampled at predetermined time intervals or predetermined distance intervals and the orientation θ of the vehicle 1 (for example, the forward direction or traveling direction of the vehicle body of the vehicle 1).

[0025] The driving trajectory generation unit 24 accumulates information on the driving trajectory T generated by the driving trajectory generation unit 24 when the vehicle 1 drives the unit section W multiple times and information on the lane boundary B detected by the lane boundary detection unit 23 as learning map information 25. By accumulating (learning) information on the travel locus T and information on the lane boundaries B in the unit section W in this way, learned map information 25 can be generated as map information indicating the routes for each lane on the unit section W.

[0026] Referring to Fig. 2, the sufficiency determination unit 26 evaluates sufficiency, which is an index of whether sufficient information on the travel path T and lane boundaries B has been accumulated for the learned map information 25. In other words, sufficiency is an index of whether learning of the learned map information 25 has been sufficiently completed. See Fig. 4. The sufficiency determination unit 26 divides the unit interval W, which is the subject of the sufficiency evaluation, into intervals aligned along the extension direction of the unit interval W (for example, the extension direction of the links L1 to L4 connecting the node points N1 to N5 in Fig. 3), thereby dividing the unit interval W into a plurality of divided intervals S1 to S8. In the following description, the divided intervals S1 to S8 may be collectively referred to as "divided interval S."

[0027] For example, the length of each divided section S may be set based on the interval between node points N. For example, the length of the divided section S may be set to be equal to the interval between node points N. In other words, the length of the divided section S may be set to be equal to or less than the length of one period of a broken line of a road marking (e.g., a lane boundary line) provided on the road as a broken line. For example, if the length of the line segment of the broken line of the road marking is 5 m and the length of the interval between the line segment segments is 5 m, the length of the divided section S may be approximately 10 m.

[0028] Next, the sufficiency determination unit 26 determines the left and right road edges of the road in each divided section S. For example, the sufficiency determination unit 26 may detect the boundary between the roadway and the area outside it as the road edge. For example, the sufficiency determination unit 26 may detect the position of a three-dimensional object extending along the road, such as a curb or a guardrail, as the road edge. Furthermore, for example, the sufficiency determination unit 26 may detect a center left turn line (center yellow lane) as the road edge. A center left turn line is a lane located in the center of two-way roads in the United States, and can be used by vehicles in both directions to turn left.

[0029] Furthermore, for example, the sufficiency determining unit 26 may detect road markings consisting of solid lines (for example, outer lines of a roadway or lane boundaries) as road edges. See Fig. 5. For example, the sufficiency determination unit 26 may detect the first road marking RM as a road edge if no second road marking made of a solid line is detected outside the first road marking RM made of a solid line and over a range R1 from the first road marking RM that is equal to or greater than the width of one lane WL in the road width direction D.

[0030] In addition, the sufficiency determination unit 26 may determine the range on the opposite side of the first road marking RM from the driving trajectory T as the range outside the first road marking RM, and may determine the range closer to the driving trajectory T than the first road marking RM as the range inside the first road marking RM. See Fig. 6. For example, when a three-dimensional object is detected outside a road marking RM consisting of a solid line and within a range R2 equivalent to one lane width WL in the road width direction from this road marking RM, the sufficiency determination unit 26 may detect this road marking RM as a road edge.

[0031] In addition to detecting the boundary between the roadway and the area outside it as the road edge, the sufficiency determination unit 26 may also detect the boundary between the lane in the direction of travel of the vehicle 1 and the oncoming lane as the road edge. For example, the sufficiency determination unit 26 may detect a road marking RM consisting of a solid line as the edge of the road when an oncoming vehicle is located outside the road marking RM and within a range R2 equivalent to one lane width WL in the road width direction from the road marking RM.

[0032] Furthermore, for example, the sufficiency determination unit 26 may detect a road marking RM consisting of a solid line as the edge of the road when a road marking oriented in the opposite direction to the traveling direction of the vehicle 1 is detected outside the road marking RM and within a range R2 equivalent to one lane width WL in the road width direction from the road marking RM. Here, road markings oriented in the opposite direction to the direction of travel of the vehicle 1 refer to road markings including arrows indicating the direction of travel, speed limits, letters, etc., and are used by road users traveling in the opposite direction to the direction of travel of the vehicle 1 (for example, road markings installed in the oncoming lane).

[0033] The sufficiency determination unit 26 determines whether or not both the right and left road edges have been determined for each divided section S. If both the right and left road edges have been determined, the sufficiency determination unit 26 calculates the distance between the right and left road edges as the road width for that divided section S. If at least one of the right and left road edges has not been determined, the sufficiency determination unit 26 determines that the road width for that divided section S is undetermined.

[0034] In addition, if the distance between adjacent driving trajectories T in the road width direction is greater than or equal to the width of one lane WL plus a margin α (WL+α), the sufficiency determination unit 26 detects the area between the adjacent driving trajectories T as an untraveled area in which the vehicle 1 has not yet traveled. For example, the width of one lane WL may be 3 m, the margin α may be 0.5 m, and the width (WL+α) may be 4.5 m. In the example of FIG. 4, the distance in the road width direction between the adjacent travel trajectories T3 and T4 in the divided sections S5 to S8 is equal to or greater than the width (WL+α), and the sufficiency determination unit 26 detects the region Rn between the travel trajectory T3 and the travel trajectory T4 as an untraveled region.

[0035] Next, the sufficiency determination unit 26 evaluates sufficiency, which is an index of whether sufficient information about the travel path T and road edges has been detected for the learned map information 25. For example, the sufficiency determining unit 26 may determine that sufficient road edge information for the learning map information 25 has been detected when the road width has been determined.

[0036] Furthermore, for example, the sufficiency determining unit 26 may determine whether or not sufficient information about the travel locus T for the learning map information 25 has been detected for an area where the road width has been determined. For example, the sufficiency determination unit 26 may determine that the detected driving trajectory T is sufficient for generating the learning map information 25 when, in a divided section S where the road width is determined (i.e., a divided section S where the road edges on both the left and right sides are detected), the detected driving trajectory T is distributed at intervals equivalent to or less than one lane width WL throughout the entire range between the left and right road edges.

[0037] See Fig. 7. For example, if the distance G1 between the detected travel trajectories T1 to T3 in the road width direction is less than the width (WL+α), the distance G2 between the leftmost travel trajectory T1 and the left-side road edge ER1 is less than the width of one lane WL, and the distance G3 between the rightmost travel trajectory T3 and the right-side road edge ER2 is less than the width of one lane WL, it may be determined that the travel trajectories T1 to T3 in this divided section S are sufficient for generating the learned map information 25.

[0038] 2, the recommended area presentation unit 27 presents to the occupant a divided section S where road edges on both the left and right sides have not been detected and / or an untraveled area Rn as a recommended area in which to recommend traveling of the host vehicle 1. For example, the recommended area presentation unit 27 may present to the occupant an area where the travel trajectory T or road edge information has not been evaluated by the sufficiency determination unit 26 as being sufficiently detected due to the learned map information 25. For example, the recommended area presentation unit 27 may display the recommended area on the display device of the HMI 13.

[0039] 8 is a schematic diagram of an example of a recommended area presented to a driver. Each square in FIG. 8 represents a lane area in each divided section S. Reference numeral 30 indicates the current position of the vehicle 1 in the display of the recommended area. Untraveled areas are displayed in white (without hatching) as in the area indicated by reference numeral 31, and areas where the travel trajectory T has been detected are displayed in oblique hatching as in the area indicated by reference numeral 32.

[0040] The thick lines 33 indicate the locations where road edges have been detected. Areas where the road width has been determined (i.e., areas where road edges on both the left and right sides have been detected) are displayed with sandy hatching, as in the area indicated by reference numeral 34, unless an untraveled area exists within the area. The area 34 displayed with sand hatching is an area where the information on the travel path T or road edge is sufficient for generating the learning map information 25, and the other areas 31 and 32 are presented to the occupant as recommended areas. The recommended area presentation unit 27 may not only display the untraveled area 31 but also output a display from the HMI 13 to encourage the driver to change lanes so as to prioritize travel through the untraveled area 31 .

[0041] (operation) FIG. 9 is an overall flowchart of an example of a map information generating method according to the embodiment. In step S1, the positioning device 12 and the position acquisition unit 21 acquire the self-position of the host vehicle 1. In step S2, the object sensor 11 detects the surrounding environment of the host vehicle 1. The lane boundary detection unit 23 detects lane boundaries existing around the host vehicle 1 based on the surrounding environment information from the object sensor 11.

[0042] In step S3, the travel locus generating unit 24 detects the travel locus of the vehicle 1 based on the history of the vehicle's own position acquired by the position acquiring unit 21. In step S4, the travel trajectory generating unit 24 accumulates information about the generated travel trajectory and information about the lane boundaries detected by the lane boundary detecting unit 23 in the learning map information 25, thereby generating the learning map information 25. Then, the process ends.

[0043] In step S5, the sufficiency determination unit 26 and the recommended region presentation unit 27 execute a recommended region presentation process. Fig. 10 is a flowchart showing an example of the recommended region presentation process. In step S10, the sufficiency determination unit 26 detects the left and right road edges of the road. In step S11, the sufficiency determination unit 26 evaluates sufficiency, which is an index of whether sufficient information about the travel path T and road edges has been accumulated for the learned map information 25. In step S12, the recommended area presentation unit 27 presents to the occupant, as a recommended area, an area in which the travel path or road edge information is not evaluated as having been sufficiently detected for the learned map information 25. The recommended area presentation process then ends.

[0044] (Effects of the embodiment) (1) In the map information generation method, a sensor mounted on the vehicle detects the vehicle's own position and the surrounding environment of the vehicle, the detected information on the vehicle's own position and the surrounding environment is accumulated, map information showing the route for each lane on the road is generated, the driving trajectory of the vehicle is detected based on the information on the vehicle's own position, the road edges are detected based on the information on the surrounding environment, and for each section of a specified distance in the extension direction of the road, sufficiency is evaluated, which is an indicator of whether sufficient driving trajectory and road edges have been detected for the map information, and the driving area in which the vehicle should travel is identified based on the sufficiency evaluation result.

[0045] This allows the system to determine whether the collected driving locus information is sufficient based on the presence of road edges, making it possible to identify which areas of the road for which map information is to be generated are not covered by the collected driving locus information, thereby making it possible to identify the area in which the vehicle should travel in order to generate map information showing the route for each lane.

[0046] (2) The predetermined distance may be set based on the sum of the length of one line segment and the length of one gap of a dashed lane boundary line. This prevents the processing area from being set between dashed lines where dashed road markings are not painted, and allows lane boundary lines to be detected in any area. (3) The road edge may be a three-dimensional object extending along the road. The three-dimensional object indicates that a vehicle cannot travel beyond the road edge, and therefore, by using the three-dimensional object as the road edge, the road width can be accurately estimated.

[0047] (4) The road edge may be the boundary line of the center left turn line. This allows accurate estimation of the road width even on a two-way road separated by a center left turn line. (5) Road edges may be road markings consisting of solid lines, which allows for more accurate estimation of road width than when curbs or other structures are used as road edges. (6) If no other road markings consisting of solid lines are detected outside the solid line and within a range equivalent to one lane width or more in the road width direction from the solid line, or if a three-dimensional object is detected outside the solid line and within a range equivalent to one lane width from the solid line in the road width direction, the solid line may be detected as the road edge. By doing so, a solid line with no other solid lines outside it can be determined as the road edge, making it possible to accurately estimate the road width even in sections where lanes are separated by solid lines, such as before an intersection.

[0048] (7) When an oncoming vehicle is located outside a solid line and within a range equivalent to one lane width from the solid line in the road width direction, the solid line may be detected as the road edge. By detecting the solid line in front of the oncoming vehicle as the road edge, it is possible to prevent the oncoming lane from being mistakenly determined as the lane in the vehicle's traveling direction, and to accurately estimate the road width. (8) If a road marking facing the opposite direction to the vehicle's traveling direction is detected outside the solid line and within a range equivalent to one lane width from the solid line in the road width direction, the solid line may be determined to be the road edge. By capturing the characteristics of the oncoming lane, where the road markings face the opposite direction, and determining the solid line as the road edge, it is possible to prevent the oncoming lane from being mistakenly determined to be the lane in the vehicle's traveling direction, and to accurately estimate the road width.

[0049] (9) In a section where road edges on both sides are detected, if the detected driving loci are distributed at intervals equivalent to one lane width or less across the entire range between the left and right road edges, it may be determined that sufficient driving loci have been detected for map information. This makes it possible to accurately determine the sufficiency of the collected driving locus information through simple processing, since it is determined that sufficient driving locus information has been collected when the driving loci are distributed in the road width direction with intervals equal to or less than the width of one lane in a section where road edges on both sides are detected.

[0050] (10) When adjacent detected travel trajectories are spaced apart by a distance equivalent to the width of one lane or more, the area between the adjacent travel trajectories may be identified as an untraveled area in which the host vehicle has not yet traveled. This allows the untraveled area to be detected when the distance between the travel trajectories in the road width direction is greater than the width of one lane, making it possible to identify the untraveled area on a lane-by-lane basis. (11) Sections where road edges on both sides have not been detected and / or untraveled areas may be presented to the occupant as recommended areas for the vehicle to travel in. By presenting untraveled areas as recommended areas, trajectory data can be collected efficiently. [Explanation of symbols]

[0051] 1...Own vehicle, 10...Map information generation device, 11...Object sensor, 12...Positioning device, 13...Human-machine interface, 14...Controller, 15...Processor, 16...Storage device, 20...Map information, 21...Position acquisition unit, 22...Travel road determination unit, 23...Lane boundary detection unit, 24...Travel trajectory generation unit, 25...Learning map information, 26...Sufficiency determination unit, 27...Recommended area presentation unit

Claims

1. Detecting a position of the vehicle and a surrounding environment of the vehicle using a sensor mounted on the vehicle; accumulating the detected information on the vehicle's own position and the information on the surrounding environment to generate map information showing the route of each lane on the road; Detecting a travel path of the vehicle based on the information on the vehicle's own position; Detecting a road edge based on the information on the surrounding environment; Evaluating sufficiency, which is an index of whether or not the travel path and the road edge are detected sufficiently for the map information, for each section of a predetermined distance in the extension direction of the road; identifying a driving area in which the host vehicle should travel based on the sufficiency evaluation result; A map information generating method comprising:

2. 2. The map information generating method according to claim 1, wherein the predetermined distance is set based on the sum of the length of one line segment and the length of one gap of a dashed lane boundary line.

3. 2. The map information generating method according to claim 1, wherein the road edge is a three-dimensional object extending along the road.

4. 2. The map information generating method according to claim 1, wherein the road edge is a boundary line of a center left turn line.

5. 2. The map information generating method according to claim 1, wherein the road edges are road markings consisting of solid lines.

6. The map information generating method according to claim 5, characterized in that if no other road marking consisting of a solid line is detected outside the solid line and within a range equivalent to one lane width or more from the solid line in the road width direction, or if a three-dimensional object is detected outside the solid line and within a range equivalent to one lane width from the solid line in the road width direction, the solid line is detected as the road edge.

7. The map information generating method according to claim 5, characterized in that when an oncoming vehicle is located outside the solid line and within a range equivalent to one lane width in the road width direction from the solid line, the solid line is detected as the road edge.

8. 6. The map information generating method according to claim 5, wherein when a road marking oriented in the opposite direction to the traveling direction of the vehicle is detected outside the solid line and within a range equivalent to one lane width in the road width direction from the solid line, the solid line is detected as the road edge.

9. The map information generating method according to claim 1, characterized in that, in a section where the road edges on both the left and right sides are detected, if the detected driving locus is distributed at intervals equivalent to one lane width or less over the entire range between the left and right road edges, it is determined that the driving locus has been sufficiently detected for the map information.

10. The map information generating method according to claim 1, characterized in that, when adjacent ones of the detected driving trajectories are spaced apart by a distance equivalent to or greater than the width of one lane, the area between the adjacent driving trajectories is identified as an untraveled area in which the vehicle has not yet traveled.

11. The map information generating method according to claim 10, characterized in that sections on both the left and right sides where the road edges have not been detected and / or untraveled areas are presented to the occupant as recommended areas in which the vehicle is recommended to travel.

12. a sensor mounted on the host vehicle to detect the host vehicle's own position and the surrounding environment of the host vehicle; a controller that executes the following processes: accumulating information on the vehicle's own position and information on the surrounding environment detected by the sensor, and generating map information that indicates the path of each lane on a road; detecting a travel path of the vehicle based on the information on the own position; detecting road edges based on the information on the surrounding environment; evaluating sufficiency, which is an index of whether the travel path and the road edges have been detected sufficiently for the map information, for each section of a predetermined distance in the extension direction of the road; and specifying a travel area in which the vehicle should travel based on the evaluation result of the sufficiency; A map information generating device comprising:

Images