Driving assist system

Abstract

To provide a driving assist system making it possible to, even when detailed map information is unavailable, generate a proper travel trajectory by combining map information with a result of detection by a detector.SOLUTION: Road link information for route guide contained in map information is used to acquire a travel scheduled route including information which specifies a lane in which a vehicle will travel in the future. Information which segments a width direction of a road on which the vehicle travels is information that is detected based on a result of image recognition around the vehicle performed using an outside camera 19. The road link information is matched with the information which segments the width direction of the road on which the vehicle travels. Thus, an area of a lane in which the vehicle travels and which lies ahead in an advancing direction of the vehicle is identified as a travel enabled area. A travel trajectory on which the vehicle travels within the travel enabled area along the travel scheduled route is generated. Driving assist of the vehicle is carried out based on the generated travel trajectory.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to a driving assistance device that assists in driving a vehicle. [Background technology]

[0002] In recent years, in addition to manual driving, in which a vehicle is driven based on a user's driving operation, new automated driving assistance systems have been proposed that assist a user in driving a vehicle by having the vehicle perform some or all of the user's driving operations.The automated driving assistance system, for example, constantly detects the current position of the vehicle, the lane in which the vehicle is traveling, and the positions of other vehicles in the vicinity, and automatically controls the vehicle, including steering, drive sources, and braking, so that the vehicle travels along a predetermined route.

[0003] Furthermore, when driving using the above-mentioned automated driving assistance or when providing various other driving assistance services to vehicles, a recommended driving trajectory is generated in advance on the road on which the vehicle will travel based on the vehicle's planned driving route, map information, etc. Here, in order to generate a vehicle's driving trajectory that specifies the specific trajectory on which the vehicle will travel on the road, it is necessary to understand how lane markings and lanes are arranged on the road and the extent of the area in which the vehicle can travel, and detailed map information that specifies these is required. For example, Japanese Patent No. 7347522 discloses generating a static driving trajectory on which the vehicle is recommended to travel using high-precision map information including information on road shape, curvature, lane width, lane markings, etc. for each lane. It also discloses generating a dynamic driving trajectory that reflects the detection results for objects detected by cameras and sensors within their detection ranges, and correcting the static driving trajectory based on the generated dynamic driving trajectory. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7347522 (paragraphs 0030, 0053, 0055-0058) Summary of the Invention [Problem to be solved by the invention]

[0005] While Patent Document 1 discloses generating a driving trajectory based on high-precision map information including detailed information about lane markings painted on road surfaces, it has been practically difficult to accurately create a database of such detailed map information for roads across the country. Patent Document 1 also discloses generating a driving trajectory based on detection results from cameras and sensors. However, generating a driving trajectory solely from information obtained by cameras and sensors does not guarantee that the information necessary for generating a driving trajectory can be obtained. In particular, on large roads, much of the information falls outside the detection range, making it impossible to generate an appropriate driving trajectory. Patent Document 1 also discloses an example in which a static driving trajectory generated based on high-precision map information is combined with a dynamic driving trajectory generated based on information obtained by cameras and sensors. However, even in this case, the vehicle's driving trajectory is still based on the static driving trajectory, and detailed information about lane markings is still required to generate a driving trajectory.

[0006] The present invention has been made to solve the above-mentioned problems in the conventional technology, and aims to provide a driving assistance device that can generate an appropriate driving trajectory by combining map information and the detection results of a detection device, even if detailed information about the lane markings painted on the road surface is not available. [Means for solving the problem]

[0007] In order to achieve the above-mentioned object, a first driving assistance device according to the present invention has: a planned driving route acquisition means that acquires a planned driving route including information that identifies the lanes in which the vehicle will travel in the future, by using road link information for route guidance included in map information; a detection result acquisition means that acquires detection results from a detection device that detects the conditions around the vehicle; a drivable area identification means that detects information that divides the width of the road on which the vehicle will travel based on the detection results from the detection device, and identifies the area of ​​the lanes in which the vehicle will travel ahead in the direction of travel of the vehicle as a drivable area by matching the road link information with the information that divides the width of the road on which the vehicle will travel; a driving trajectory generation means that generates a driving trajectory for traveling within the drivable area along the planned driving route; and a driving assistance means that provides driving assistance for the vehicle based on the driving trajectory generated by the driving trajectory generation means.

[0008] In addition, the second driving assistance device according to the present invention has: a planned driving route acquisition means for acquiring a planned driving route including information specifying the lanes along which the vehicle will travel in the future, by using road link information for route guidance included in map information; a detection result acquisition means for acquiring detection results from a detection device that detects the conditions around the vehicle; a driving trajectory generation means for detecting information that divides the width of the road along which the vehicle will travel based on the detection results from the detection device, and matching the planned driving route with the information that divides the width of the road along which the vehicle will travel, thereby generating a driving trajectory along which the vehicle will travel within the road ahead in the direction of travel of the vehicle; and a driving assistance means for providing driving assistance to the vehicle based on the driving trajectory generated by the driving trajectory generation means. [Effects of the Invention]

[0009] The first driving assistance device according to the present invention having the above configuration detects information that divides the width direction of the road on which the vehicle is traveling based on the detection results of the detection device, and by matching road link information with these detection results, it is possible to accurately identify the drivable area ahead in the direction of travel of the vehicle without having detailed information about the lane markings. As a result, it is possible to generate an appropriate driving trajectory for the vehicle that matches the drivable area, and to provide appropriate driving assistance.

[0010] According to the second driving assistance device of the present invention having the above configuration, information that divides the width direction of the road on which the vehicle is traveling is detected based on the detection results of the detection device, and by matching the planned traveling route with these detection results, it is possible to generate an appropriate traveling trajectory even without detailed information about the lane markings. As a result, it is possible to provide appropriate driving assistance based on the traveling trajectory. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram showing a navigation device according to an embodiment of the present invention; [Figure 2] FIG. 2 is a diagram showing an imaging range of an outside-vehicle camera according to the present embodiment. [Figure 3] 4 is a flowchart of an autonomous driving assistance program according to the present embodiment. [Figure 4] FIG. 2 is a diagram showing lane flags indicating the correspondence between lanes. [Figure 5] FIG. 2 is a diagram showing an example of a planned driving route of a vehicle. [Figure 6] FIG. 6 is a diagram showing an example of a lane network constructed for the planned travel route shown in FIG. 5. [Figure 7] FIG. 2 is a diagram showing virtual lanes set along a planned travel route. [Figure 8] 10A and 10B are diagrams illustrating a detection method for detecting information that divides a road on which a vehicle is traveling in the width direction. [Figure 9]10 is a diagram showing the center position and width of a lane detected by an external camera. FIG. [Figure 10] FIG. 10 is a diagram illustrating a manner in which a virtual lane is corrected. [Figure 11] FIG. 10 is a diagram showing an example of a driving trajectory generated for a turning section. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment in which a driving assistance device according to the present invention is embodied in a navigation device 1 will be described in detail with reference to the drawings. First, a schematic configuration of the navigation device 1 according to this embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the navigation device 1 according to this embodiment.

[0013] Here, the navigation device 1 is an on-board device that is mounted on a vehicle and displays a map of the area around the vehicle's position based on map information stored in the navigation device 1 or map information acquired from an external source, allows the user to input a destination, displays the vehicle's current position on a map image, and provides travel guidance along a set guide route. In this embodiment, various types of assistance information related to autonomous driving assistance are generated, particularly when the vehicle is performing assisted driving using autonomous driving assistance. Examples of assistance information include a recommended driving trajectory for the vehicle and a speed plan that indicates the vehicle speed when driving.

[0014] As shown in FIG. 1 , the navigation device 1 according to this embodiment includes a current position detection unit 11 that detects the current position of the vehicle in which the navigation device 1 is installed, a data recording unit 12 that records various data, a navigation ECU 13 that performs various calculations based on input information, an operation unit 14 that accepts user operations, a liquid crystal display 15 that displays to the user a map of the area around the vehicle and information about the guide route (the planned route of the vehicle) set in the navigation device 1, a speaker 16 that outputs audio guidance regarding the route guide, a DVD drive 17 that reads a DVD as a storage medium, and a communication module 18 that communicates with an information center such as a probe center or a VICS (Vehicle Information and Communication System) center. The navigation device 1 is also connected to various sensors, such as an external camera 19 and an ultrasonic sensor 20, installed in the vehicle in which the navigation device 1 is installed via an in-vehicle network such as a CAN. The navigation device 1 is also connected to a vehicle control ECU 21 that performs various controls for the vehicle in which the navigation device 1 is installed, allowing bidirectional communication. Various operation buttons 22 installed in the vehicle, such as an automatic driving start button, are also connected.

[0015] Here, a vehicle equipped with the navigation device 1 is a vehicle capable of manual driving, in which the vehicle travels based on the user's driving operations, as well as assisted driving using automatic driving assistance, in which the vehicle travels automatically along a pre-set route or road without the user's driving operations.

[0016] Furthermore, autonomous driving assistance may be provided for all road sections, or may be configured to be provided only while the vehicle is traveling on a specific road section (for example, a highway with a gate (manned or unmanned, toll or free) at the boundary). In the following explanation, the autonomous driving section where autonomous driving assistance is provided includes all road sections, including general roads and highways, as well as parking lots, and the explanation will be given assuming that autonomous driving assistance is basically provided from the time the vehicle starts traveling until it ends traveling (until the vehicle is parked). However, autonomous driving assistance is not always provided when the vehicle is traveling on an autonomous driving section, but is preferably provided only when the user selects to provide autonomous driving assistance (for example, by turning on the autonomous driving start button) and it is determined that autonomous driving assistance is possible. On the other hand, the vehicle may be a vehicle that is only capable of assisted traveling with autonomous driving assistance.

[0017] In vehicle control in automated driving assistance, for example, the current position of the vehicle, the lane the vehicle is traveling on, and the positions of surrounding obstacles are detected at any time, and vehicle control of the steering, drive source, brakes, etc. is automatically performed so that the vehicle travels at a speed according to a speed plan generated along a travel trajectory generated by the navigation device 1, as will be described later. Note that in assisted driving with automated driving assistance in this embodiment, lane changes, right and left turns, and parking operations are also performed by performing vehicle control with the automated driving assistance described above, but special driving operations such as lane changes, right and left turns, and parking operations may be performed by manual driving without using automated driving assistance.

[0018] Each of the components of the navigation device 1 will be explained below in order. The current position detection unit 11 is composed of a GPS 25, a vehicle speed sensor 26, a steering sensor 27, a gyro sensor 28, etc., and is capable of detecting the current vehicle position, direction, vehicle traveling speed, current time, etc. Here, the vehicle speed sensor 26 in particular is a sensor for detecting the vehicle's travel distance and speed, and generates pulses in response to the rotation of the vehicle's drive wheels and outputs the pulse signals to the navigation ECU 13. The navigation ECU 13 then calculates the rotation speed of the drive wheels and travel distance by counting the generated pulses. Note that the navigation device 1 does not need to be equipped with all four types of sensors described above, and the navigation device 1 may be configured to be equipped with only one or more of these types of sensors.

[0019] The data recording unit 12 also includes a hard disk (not shown) as an external storage device and recording medium, and a recording head (not shown) which is a driver for reading the map information DB 31 and predetermined programs recorded on the hard disk and for writing predetermined data to the hard disk. Note that the data recording unit 12 may be configured with a memory card or an optical disk such as a CD or DVD instead of a hard disk. The map information DB 31 may also be stored in an external server and acquired by the navigation device 1 through communication.

[0020] Here, the map information DB 31 is a storage means for storing simple map information including road link information and the like used in the route search process and route guidance to the destination in the navigation device 1. This simple map information includes, for example, link data (road link information for route guidance) 33 related to roads (links), node data 34 related to node points, search data 35 used in processes related to route search and change, facility data 36 related to facilities, map display data for displaying the map, intersection data related to each intersection, search data for searching for points, and the like.

[0021] The link data 33 also includes data representing the width, gradient, cant, bank, road surface condition, merging section, road structure, presence or absence of shoulder space, number of lanes, points where the number of lanes decreases, points where the width narrows, and railroad crossings for each link constituting a road; data representing the radius of curvature, intersections, T-junctions, corner entrances and exits for corners; data representing downhill roads, uphill roads, and other road attributes for road types; and data representing toll roads such as national highways, prefectural roads, and narrow streets, as well as national expressways, urban expressways, motorways, general toll roads, and toll bridges for road types. In particular, in this embodiment, the data also includes information necessary for assisted driving using autonomous driving assistance, such as the number of lanes on a road, traffic divisions in the direction of travel for each lane, and connections between roads (specifically, for example, at points where the number of lanes increases or decreases or at intersections where lanes end, the correspondence between the lanes on the road before and the lanes on the road after passing), as well as the speed limit set for the road. However, it does not include information specifying the specific positions of lanes and lane markings (how lanes and lane markings are positioned relative to the road).Furthermore, the information only includes general road and lane widths predetermined for each road type (for example, lane widths of 3.0m to 3.5m on ordinary roads and 3.5m on expressways), but does not include information specifying the actual lane width.

[0022] The node data 34 also includes data such as the coordinates (positions) of actual road branching points (including intersections, T-junctions, etc.) and node points set at predetermined distances on each road depending on the radius of curvature, node attributes indicating whether the node corresponds to an intersection, a connecting link number list which is a list of link numbers of links connecting to the node, an adjacent node number list which is a list of node numbers of nodes adjacent to the node via links, and the height (altitude) of each node point.

[0023] Furthermore, various data used in route search processing for searching for a route from a starting point (for example, the current position of the vehicle) to a set destination are recorded as the search data 35. Specifically, cost calculation data used to calculate search costs, such as a cost that quantifies the suitability of an intersection as a route (hereinafter referred to as intersection cost) and a cost that quantifies the suitability of a link that constitutes a road as a route (hereinafter referred to as link cost), are stored.

[0024] Additionally, various data related to facilities (locations) across the country, such as the facility genre, name, and location information, is stored as facility data 36. In particular, for parking lots, data necessary for parking using automated driving assistance is stored, including, for example, information about the entrance to the parking lot, layout information for the aisles and parking spaces in the parking lot, information about the dividing lines that separate the parking spaces, and connection information indicating the connection relationship between the entrance to the parking lot and the lanes (which lanes can be used to enter the parking lot), etc.

[0025] Meanwhile, the navigation ECU (Electronic Control Unit) 13 is an electronic control unit that controls the entire navigation device 1. It includes a CPU 41, which functions as a calculation device and control device; a RAM 42, which is used as a working memory when the CPU 41 performs various calculation processes and stores route data and other information used when a route is searched; a ROM 43, which stores control programs as well as the automated driving assistance program (see FIG. 3 ), which will be described later; and a flash memory 44, which stores programs read from the ROM 43. The navigation ECU 13 also includes various processing algorithms. For example, the planned driving route acquisition means acquires a planned driving route, including information identifying the lanes the vehicle will travel in, by using road link information for route guidance included in map information. The detection result acquisition means acquires the detection results from the exterior camera 19, which detects the vehicle's surroundings. The drivable area identification means detects information that divides the width of the road on which the vehicle is traveling based on the detection results of the exterior camera 19, and identifies the area of ​​the lane on which the vehicle is traveling ahead in the direction of travel as the drivable area by matching the road link information with the information that divides the width of the road on which the vehicle is traveling. The driving trajectory generation means generates a driving trajectory for traveling within the drivable area along the planned driving route. The driving assistance means provides driving assistance for the vehicle based on the generated driving trajectory.

[0026] The operation unit 14 is operated when inputting a departure point as a starting point of a trip and a destination point as a destination of a trip, and has a plurality of operation switches (not shown) such as various keys and buttons. The navigation ECU 13 controls the execution of various corresponding operations based on switch signals output by pressing each switch. The operation unit 14 may have a touch panel provided on the front surface of the liquid crystal display 15. It may also have a microphone and a voice recognition device.

[0027] The liquid crystal display 15 also displays map images including roads, traffic information, operation guidance, operation menus, key guidance, guidance information along the guided route (planned driving route), news, weather forecasts, time, emails, television programs, etc. Note that a HUD or HMD may be used instead of the liquid crystal display 15.

[0028] Furthermore, the speaker 16 outputs audio guidance for guiding the vehicle along a guide route (planned travel route) based on instructions from the navigation ECU 13, and traffic information guidance.

[0029] The DVD drive 17 is a drive that can read data recorded on a recording medium such as a DVD or CD. Based on the read data, music and video are played, and the map information DB 31 is updated. Instead of the DVD drive 17, a card slot for reading and writing data to a memory card may be provided.

[0030] The communication module 18 is a communication device for receiving traffic information, probe information, weather information, etc. transmitted from a traffic information center, such as a VICS center or a probe center, and corresponds to, for example, a mobile phone or DCM. It also includes a vehicle-to-vehicle communication device for communicating between vehicles and a road-to-vehicle communication device for communicating with roadside devices.

[0031] The exterior camera 19 is composed of a camera using a solid-state image sensor such as a CCD, and is attached to the rear of the vehicle's rearview mirror or the front bumper, with its optical axis oriented downward at a predetermined angle from the horizontal. The exterior camera 19 captures images of the area ahead of the vehicle when the vehicle is traveling in an autonomous driving zone. The exterior camera 19 may be configured to be located behind or to the side of the vehicle, in addition to the front. However, as shown in FIG. 2, it is desirable that the imaging range (detection range) 49 of the exterior camera 19 includes at least the lane 46 in which the vehicle 45 is traveling and the lanes 47 and 48 adjacent to the lane in which the vehicle is traveling.

[0032] The navigation ECU 13 then performs image processing on the captured image to detect obstacles such as lane markings on the road on which the vehicle is traveling and other vehicles in the vicinity, and generates various types of assistance information related to autonomous driving assistance based on the detection results. As an example, the navigation ECU 13 detects information that divides the width of the road on which the vehicle is traveling (e.g., lanes, lane markings, road edges, lane width, road width, etc.), and matches the detected information with the link data 33 included in the simple map information and the planned route of travel of the vehicle to identify a drivable area in which the vehicle can travel, and further calculates the travel trajectory. The navigation ECU 13 also identifies the lane on which the vehicle is currently traveling using the image recognition results and the simple map information. Details will be described later.

[0033] The ultrasonic sensors 20 are arranged, for example, at the front, rear, and sides of the vehicle at predetermined intervals. They transmit ultrasonic waves as probe waves around the vehicle and receive reflected waves from objects around the vehicle, thereby detecting the objects that have reflected the probe waves. Specifically, they are a type of distance sensor that can detect the distance (measured distance) to the object that has reflected the probe wave by measuring the time from transmission to reception. Objects that can be detected by the ultrasonic sensors 20 include, for example, people, bicycles, other vehicles, walls, and other obstacles that the vehicle must avoid when traveling, or obstacles that form parking spaces. Note that millimeter-wave sensors or laser sensors may be used as distance sensors instead of ultrasonic sensors.

[0034] The vehicle control ECU 21 is an electronic control unit that controls the vehicle equipped with the navigation device 1. The vehicle control ECU 21 is also connected to each drive unit of the vehicle, such as the steering, brake, and accelerator, and in this embodiment, after automatic driving assistance has started in the vehicle, the vehicle control ECU 21 controls each drive unit to implement automatic driving assistance for the vehicle. If an override is performed by the user during automatic driving assistance, the ECU 21 detects that an override has been performed.

[0035] Here, the navigation ECU 13 transmits various types of assistance information related to autonomous driving assistance generated by the navigation device 1 to the vehicle control ECU 21 via the CAN when the planned driving route (guidance route) of the vehicle is determined or after the vehicle starts driving. The vehicle control ECU 21 then uses the received various types of assistance information to provide autonomous driving assistance after the vehicle starts driving. Examples of assistance information include a driving trajectory that is recommended for the vehicle, a speed plan that indicates the vehicle speed when driving, etc. Note that it is also possible to transmit information that specifies the planned driving route (guidance route) that specifies the route the vehicle will travel, without transmitting the specific driving trajectory.

[0036] Next, an automatic driving assistance program executed by the CPU 41 in the navigation device 1 according to this embodiment having the above configuration will be described with reference to Fig. 3. Fig. 3 is a flowchart of the automatic driving assistance program according to this embodiment. Here, the automatic driving assistance program is executed when the vehicle starts traveling with automatic driving assistance after the ACC power supply (accessory power supply) of the vehicle is turned on, and is a program that performs assisted traveling with automatic driving assistance in accordance with assistance information generated by the navigation device 1. The program shown in the flowchart in Fig. 3 below is stored in the RAM 42 or ROM 43 provided in the navigation device 1, and is executed by the CPU 41.

[0037] First, in step (hereinafter abbreviated as S) 1 of the autonomous driving assistance program, the CPU 41 identifies the current position of the vehicle based on the detection result of the current position detection unit 11 and map information. When identifying the current position of the vehicle, a map matching process is also performed to match the current position of the vehicle with the map information.

[0038] In addition, in S1, the CPU 41 also identifies the "host vehicle driving lane," which is the lane in which the host vehicle is currently traveling, by performing image recognition processing on the image captured by the exterior camera 19. Specifically, the host vehicle driving lane is identified by the following processing.

[0039] First, the CPU 41 recognizes (detects) features located around the vehicle by performing image processing on the image captured by the exterior camera 19. Specifically, the CPU 41 recognizes (detects) lane markings on the road surface (including the road surface of the lane in which the vehicle is traveling as well as the road surface of lanes other than the lane in which the vehicle is traveling) and road edges (specifically, the edge of the roadway, which is the boundary between the roadway and the sidewalk if a sidewalk is present). It is desirable to also detect the color and type (solid line, dashed line, etc.) of the lane markings. Regarding road edges, structures such as blocks, guardrails, and medians located at the roadside are generally detected as road edges. However, for roads without such structures at the road edge, gaps in the asphalt or the outermost lane markings (when a lane is separated from oncoming traffic by a center line, the center line also serves as the road edge) may be detected as the road edge. The CPU 41 then identifies the lane in which the vehicle is traveling by referring to map information in addition to the results of the lane marking and road edge detection. For example, as shown in Figure 2, if the road on which the host vehicle 45 is traveling has a total of three lanes (excluding the oncoming lane), and it is possible to confirm that a lane can be seen on both the left and right of the host vehicle 45, or if it is possible to detect that there is a road edge on the left side of the lane 47 to the left of the host vehicle 45, or that there is a road edge on the right side of the lane 48 to the right of the host vehicle 45, then the center lane 46 of the three lanes can be identified as the host vehicle's traveling lane. Note that the map information stored in the map information DB 31 is simple map information that does not have specific position information for lanes and dividing lines, but it is possible to identify the host vehicle's traveling lane if there is information that identifies the presence or absence of oncoming lanes for each link and the number of lanes.

[0040] However, the method for identifying the lane the vehicle is traveling in is not limited to the above method, and it is also possible to identify the lane by, for example, detecting other vehicles traveling on the same road as the vehicle (the existence of lanes can be inferred from other vehicles), or by detecting features painted on the road surface other than lane markings (for example, traffic divisions by direction of travel).

[0041] The detection of the current position of the vehicle and the lane in which the vehicle is traveling in step S1 is continued until the vehicle stops traveling.

[0042] Next, in S2, the CPU 41 searches for a route from the current position of the vehicle to the destination set by the user using the link data 33, which is road link information for route guidance stored in the map information DB 31, and specifies the searched route as the planned driving route for the vehicle. For example, the search is performed using the well-known Dijkstra algorithm. However, the planned driving route searched in S2 does not include information specifying the lanes on which the vehicle will travel, but only specifies the links (roads) on which the vehicle will travel. In other words, it is information specifying the series of links included in the route from the current position to the destination. Note that if a destination has not been set, the route along the road from the current position of the vehicle may be specified as the planned driving route.

[0043] Furthermore, the route search to the destination in S2 may be performed by an external server device rather than the navigation device 1. In this case, the CPU 41 transmits a route search request to the server device. The route search request includes a terminal ID that identifies the navigation device 1 that sent the route search request, and information that identifies the departure point (for example, the current position of the vehicle) and the destination. When re-searching, information that identifies the destination is not necessarily required. Thereafter, the CPU 41 receives the searched route information transmitted from the server device in response to the route search request.

[0044] Next, in S3, the CPU 41 acquires information specifying the number of lanes on the road, the traffic divisions in the direction of travel for each lane, and the connections between roads (specifically, for example, for a point where the number of lanes increases or decreases or an intersection where a lane ends, the correspondence between the lanes included in the road before and after passing the relevant point) for the section from the vehicle's current position to the destination using link data 33, which is road link information for route guidance stored in the map information DB 31. Note that the map information stored in the map information DB 31 is simple map information, and does not include information specifying the specific positions of lanes and dividing lines (how lanes and dividing lines are arranged relative to the road), but does include information regarding the number of lanes and the connections between lane lines between roads.

[0045] For example, regarding the connection of lanes between roads at an intersection, as shown in FIG. 4, for each road connected to the intersection, a lane flag indicating the correspondence between lanes is set and stored for each combination of a road entering the intersection and a road exiting the intersection. For example, FIG. 4 shows a lane flag for entering the intersection from the road on the right and exiting to the road above, a lane flag for entering the intersection from the road on the right and exiting to the road on the left, and a lane flag for entering the intersection from the road on the right and exiting to the road below. Furthermore, among the lanes included in the road before passing through the intersection, lanes with lane flags set to "1" correspond to lanes included in the road after passing through the intersection, lanes with lane flags set to "1" correspond, i.e., indicate that the lanes are movable before and after passing through the intersection. When constructing a lane network at S4, described below, the CPU 41 references the lane flags to form connections between lane nodes and lane links at the intersection.

[0046] Next, in S4, the CPU 41 constructs a lane network for the section from the current position of the vehicle to the destination based on the information regarding the number of lanes and the lane connections between roads acquired in S3. Here, the lane network is a network that indicates the lane movement that the vehicle can select.

[0047] Here, as an example of constructing a lane network in S4, a case where a vehicle travels along the planned travel route shown in Figure 5 will be described. The planned travel route shown in Figure 5 is a route in which the vehicle travels straight from the current position of the vehicle, turns right at the next intersection 51, then turns right at the next intersection 52, and turns left at the next intersection 53. On the planned travel route shown in Figure 5, for example, when turning right at intersection 51, it is possible to enter either the right lane or the left lane. However, since it is necessary to turn right at the next intersection 52, it is necessary to move to the rightmost lane when entering the intersection 52. Similarly, when turning right at intersection 52, it is possible to enter either the right lane or the left lane. However, since it is necessary to turn left at the next intersection 53, it is necessary to move to the leftmost lane when entering the intersection 53. A lane network constructed for a section in which such lane movement is possible is shown in Figure 6.

[0048] As shown in Fig. 6, the lane network divides the route from the current position of the vehicle to the destination into multiple sections (groups). Specifically, the division is made at the intersection entry position, intersection exit position, and positions where lanes increase or decrease, which serve as boundaries. Node points (hereinafter referred to as lane nodes) 55 are set for each lane located at the boundary of each divided section. Furthermore, links (hereinafter referred to as lane links) 56 are set to connect the lane nodes 55. Note that the lane links 56 are basically set in the center of the lane when there is no crossing of lanes.

[0049] The lane network also includes information that identifies the correspondence between lanes included in the road before the intersection and lanes included in the road after the intersection, particularly by connecting lane nodes and lane links at the intersection. That is, information that identifies the lanes that a vehicle can move between after passing the intersection and the lanes included in the road before the intersection. Specifically, the information indicates that a vehicle can move between lanes corresponding to lane nodes connected by lane links between lane nodes set on the road before the intersection and lane nodes set on the road after the intersection. The simplified map information stored in the map information DB 31 for generating such a lane network includes lane flags that indicate the correspondence between lanes for each combination of roads entering and leaving the intersection, as described above, for each road connecting to the intersection (see FIG. 4). When constructing the lane network at S4, the CPU 41 references the lane flags to form connections between lane nodes and lane links at the intersection.

[0050] 6 shows an example of a lane network constructed for roads, but if a parking lot is included in the section for generating the driving trajectory, a similar network (hereinafter referred to as a parking lot network) may be constructed for the parking lot. Also, if the distance to the destination is long, the lane network may be constructed for an area within a predetermined distance (for example, 3 km) from the current position of the vehicle.

[0051] Next, in S5, the CPU 41 sets a start lane (start node) from which the vehicle will start moving for the lane node located at the start point of the lane network constructed in S4, and sets a target lane (destination node) to which the vehicle will move for the lane node located at the end point of the lane network. If the start point of the lane network is a road with multiple lanes in each direction, the lane node corresponding to the lane in which the vehicle is currently located becomes the start lane. On the other hand, if the end point of the lane network is a road with multiple lanes in each direction, the lane node corresponding to the leftmost lane (for left-hand traffic) becomes the target lane.

[0052] Thereafter, in S6, the CPU 41 refers to the lane network constructed in S4 and derives the route with the smallest lane cost (hereinafter referred to as the recommended route) from among the routes that continuously connect the start lane to the target lane. For example, the route is searched for from the target lane side using the Dijkstra algorithm. However, search methods other than the Dijkstra algorithm may be used as long as they can search for a route that continuously connects the start lane to the target lane. The derived recommended route is a planned driving route (driving path) that includes information specifying the lane in which the vehicle will travel in the future, and also contains information specifying the recommended lane movement mode of the vehicle when moving (the lane in which it is recommended to travel and the recommended position for lane movement).

[0053] Furthermore, the lane cost used in the route search is assigned to each lane link 56. The lane cost assigned to each lane link 56 has the length of the lane link 56 or the time required for movement as a reference value. In particular, in this embodiment, the length of the lane link (in meters) is used as the reference value for the lane cost. Furthermore, for lane links involving lane changes, a lane change cost (for example, 50) is added to the reference value. Note that the value of the lane change cost may be changed depending on the number of lane changes and the location of the lane changes. For example, it is possible to increase the value of the lane change cost added when a lane change is made near an intersection or when a lane change is made across two lanes.

[0054] Next, in S7, the CPU 41 temporarily sets virtual lanes along a planned travel route ahead in the vehicle's direction of travel, using the link data 33 stored in the map information DB 31. FIG. 7 is a diagram showing an example of the virtual lanes set in S7. As shown in FIG. 7, the number of virtual lanes set is equal to the number of lanes included in the road on which the vehicle is traveling. For example, the left diagram of FIG. 7 shows a case in which the vehicle is traveling on a two-lane road with an upper and lower section, in which a virtual lane 61 corresponding to the left lane and a virtual lane 62 corresponding to the right lane are set. On the other hand, the right diagram of FIG. 7 shows a case in which the vehicle is traveling on a two-way road with one lane in each direction, in which a virtual lane 63 corresponding to the lane in the vehicle's direction of travel and a virtual lane 64 corresponding to the oncoming lane are set. The presence or absence of an oncoming lane and the number of lanes on the road can be acquired from the link data 33 stored in the map information DB 31. Furthermore, oncoming lanes may be excluded from the setting of virtual lanes.

[0055] The virtual lane is set in the lane network along the lane link 56 on which the vehicle will travel (the link included in the recommended route searched for in S6). Specifically, the virtual lane is set so that the center of the virtual lane corresponding to the lane on which the vehicle will travel (for example, the virtual lane 61 located on the left side of the two lanes in the left diagram of FIG. 7) coincides with the lane link 56. The lanes on which the vehicle will travel along the planned travel route are identified in S6. Here, the lane link 56 is constructed based on the simple map information stored in the map information DB 31, so the positions of the links and nodes may deviate from the positions of the actual lanes and intersections. However, even in such cases, the virtual lane is finally corrected to the correct position in S9, which will be described later. The virtual lane may also be set along the links included in the link data 33, rather than the lane link 56 included in the lane network.

[0056] On the other hand, the lane width of the virtual lane is set based on the link data 33. Here, the lane width in the link data 33 only contains information about general lane widths predetermined for each road type, and therefore may differ from the lane width of the road on which the vehicle actually travels. However, even in such a case, the lane width of the virtual lane is finally corrected to the correct lane width in S9, which will be described later.

[0057] The range in which the virtual lane is set in S7 is wider than the range (detection range) in which the vehicle's surrounding conditions can be detected by the exterior camera 19 or other sensors, and is, for example, a section within 300 m from the vehicle's current position.

[0058] Next, in S8, the CPU 41 detects information that divides the width of the road on which the vehicle is traveling based on the image recognition results using the exterior camera 19. Here, examples of information that divides the width of the road on which the vehicle is traveling include lanes, dividing lines, road edges, lane widths, and road widths, but in the following example, the positions of each lane included in the road (more specifically, the center positions of the lanes) and lane widths are detected.

[0059] As described above, the exterior camera 19 mounted on the vehicle 45 has an image capture range that includes at least the lane in which the vehicle is traveling and the adjacent lane adjacent to the lane in which the vehicle is traveling. Therefore, image recognition processing is performed on the captured image captured by the exterior camera 19 to detect the dividing lines that separate the traveling lane and the adjacent lane adjacent to the traveling lane. Specifically, as shown in FIG. 8, dividing lines that are "within lane width / 2 + 1 m" to the left of the center line of the vehicle 45 are detected as the left dividing line that separates the traveling lane 46 and the right dividing line that separates the adjacent lane 47 adjacent to the traveling lane on the left side. Meanwhile, dividing lines that are "within lane width / 2 + 1 m" to the right of the center line of the vehicle are detected as the right dividing line that separates the traveling lane 46 and the left dividing line that separates the adjacent lane 48 adjacent to the traveling lane on the right side. Furthermore, a marking line located to the left of the vehicle's centerline that is "more than lane width / 2 + 1 m but within lane width x 1.5 + 1 m" is detected as a left marking line that defines adjacent lane 47. On the other hand, a marking line located to the right of the vehicle's centerline that is "more than lane width / 2 + 1 m but within lane width x 1.5 + 1 m" is detected as a right marking line that defines adjacent lane 48. Note that the above numerical ranges are merely examples, and it is desirable to change the definition depending on, for example, the road type (lane width). Furthermore, if there are no adjacent lanes 47 or 48, only the marking line that defines travel lane 46 is detected. Furthermore, for roads without marking lines, such as narrow streets, road edges (e.g., gaps in the asphalt) are detected instead of marking lines, and for roads with two-way traffic, a center line is also considered to be located in the center of the left and right road edges.

[0060] In the above-mentioned lane marking detection process, brightness correction is performed based on the brightness difference between the road surface and the lane marking to detect the lane markings in the image captured by the exterior camera 19. Then, binarization processing is performed to separate the lane markings from the image, geometric processing is performed to correct distortion, and smoothing processing is performed to remove noise from the image to detect the boundary line between the road surface and the lane markings. The existence and type of lane markings are identified based on the detected boundary line. Furthermore, the color of the lane markings can also be detected by extracting the image portion of the range where the lane markings are detected and performing color recognition (RGB value detection).

[0061] The CPU 41 then detects the left and right dividing lines that separate the host vehicle's lane from the adjacent lane based on the image recognition results as described above, thereby identifying the lane center positions and lane widths for at least the host vehicle's lane and the adjacent lane among the lanes included in the road. That is, the lane center position is a position equidistant from the left and right dividing lines, and the lane width is the distance in the road width direction between the left and right dividing lines. For example, as shown in FIG. 9 , when traveling in the left lane of a two-lane road, the CPU 41 identifies the center position x and lane width a of the left lane, and the center position y and lane width b of the right lane, both of which are included in the image capture range (detection range) 49 of the exterior camera 19. Note that the lane center positions and lane widths may be similarly identified for other lanes, as long as they can be identified. Alternatively, the lane center position and lane width may be identified for only the host vehicle's lane (e.g., the left lane in FIG. 9 ), excluding the adjacent lane.

[0062] Thereafter, in S9, the CPU 41 corrects the virtual lane by matching the virtual lane temporarily set in S7 with the information detected in S8. Note that the virtual lane is information generated based on the link data (road link information) 33 stored in the map information DB 31 and the planned vehicle travel route identified in S6. Therefore, S9 also corresponds to the process of matching the link data 33 with the planned vehicle travel route with the information detected in S8. Specifically, first, the position of the virtual lane in the road width direction is corrected by aligning the center position of the virtual lane with the center position of the detected lane. Second, the width of the virtual lane is corrected by aligning the width of the virtual lane with the width of the detected lane.

[0063] The virtual lane correction process of S9 will be described in more detail below with reference to FIG. 10. First, as shown in (a), the virtual lanes 61 and 62 provisionally set in S7 are superimposed on the same coordinate system as the information on the lane center position and lane width detected in S8. The coordinate system may be absolute coordinates (latitude and longitude) or relative coordinates based on the vehicle's current position. Next, as shown in (b), only the virtual lane 61 corresponding to the lane on which the vehicle is traveling and the information detected in S8 corresponding to the lane on which the vehicle is traveling (center position x and lane width a) are extracted, and the virtual lane 62 and information corresponding to other lanes (center position y and lane width b) are deleted. Next, as shown in (c), the center position of the virtual lane 61 corresponding to the lane on which the vehicle is traveling is aligned with the center position x of the lane on which the vehicle is traveling detected in S8, thereby correcting (matching) the position of the virtual lane 61 in the road width direction to match the image recognition results. Finally, as shown in (d), the lane width of the virtual lane 61 corresponding to the lane on which the vehicle is traveling is enlarged or reduced to match the lane width a of the lane on which the vehicle is traveling detected in S8, thereby correcting (matching) the lane width of the virtual lane 61 to match the image recognition results. As a result of the above processing, the virtual lane 61 becomes information with the accurate position and lane width corresponding to the lane on which the vehicle is actually traveling.

[0064] In the virtual lane correction process, the positions and widths of virtual lanes are corrected not only within the imaging range (detection range) 49 of the exterior camera 19, but also outside the imaging range 49. That is, by extending the corrected virtual lanes within the imaging range 49 along the driving route, the virtual lanes outside the imaging range 49 are also corrected.

[0065] Then, in S10, the CPU 41 identifies, among the virtual lanes corrected in S9, the virtual lane corresponding to the lane on which the vehicle is traveling, i.e., the area of ​​the virtual lane that was not deleted in S9 but remained and whose position and lane width have been corrected, as the drivable area in which the vehicle can travel. For example, in the example shown in FIG. 10, the area of ​​virtual lane 61 is identified as the drivable area. Note that, since the center position and lane width of the lane are not directly detected outside the imaging range (detection range) 49 of the exterior camera 19, which is far from the current position of the vehicle, some error may occur in the drivable area. However, as described above, by extending the corrected virtual lane within the detection range 49 along the traveling route, it is possible to estimate and identify the drivable area outside the detection range 49 from the drivable area identified within the detection range 49 and the shape of the planned traveling route. As a result, it is possible to generate a traveling trajectory that is not limited to the detection range of the exterior camera 19 but covers a wider range.

[0066] Next, in S11, the CPU 41 generates a recommended driving trajectory for the vehicle when traveling within the drivable area identified in S10 along the planned driving route identified in S6. In particular, the CPU 41 not only identifies the lane along which the vehicle is recommended to travel, but also generates a driving trajectory that identifies the specific driving position within the lane along which the vehicle is recommended to travel.

[0067] The process of generating the travel path in step S11 will be described below with a specific example. The driving trajectory generated in S11 is basically a trajectory that travels along the center of the drivable area, i.e., the center of the lane, in straight sections. However, even in straight sections, in sections where lane changes are required, a driving trajectory that moves between lanes by combining clothoid curves is inserted. On the other hand, for the turning section, as shown in Fig. 11, a start vector 71 is set at the start point of the turning section near the center of the driveable area 70, and an end vector 72 is set at the end point of the turning section near the center of the driveable area 70, and a curve connecting the start vector 71 and the end vector 72 within the driveable area 70 is generated as a driving trajectory 73. The driving trajectory 73 is generated as a curve that is as smooth as possible, has a large turning radius, and does not exceed an upper limit on the lateral acceleration generated in the vehicle, and is made up of a combination of at least one of a straight line, a clothoid curve, and a circular arc.

[0068] The travel trajectory generated in S11 is stored in the flash memory 44 or the like as support information used for automatic driving support.

[0069] Next, in S12, the CPU 41 generates a speed plan for the vehicle when traveling along the travel path generated in S11, using the simple map information stored in the map information DB 31. For example, the CPU 41 calculates a recommended travel speed for the vehicle when traveling along the travel path, taking into consideration speed limit information and speed change points (e.g., intersections, curves, railroad crossings, crosswalks, etc.) on the planned travel route.

[0070] The speed plan generated in S12 is stored in the flash memory 44 or the like as support information to be used for autonomous driving support together with the driving trajectory generated in S11. In addition, an acceleration plan indicating the acceleration / deceleration of the vehicle required to realize the speed plan generated in S12 may also be generated as support information to be used for autonomous driving support.

[0071] Next, in S13, the CPU 41 calculates control amounts for the vehicle to travel along the travel trajectory generated in S11 at a speed in accordance with the speed plan generated in S12. Specifically, control amounts for the accelerator, brake, gear, and steering are calculated. Note that the processing of S11 and S12 may be performed not by the navigation device 1 but by the vehicle control ECU 21 that controls the vehicle.

[0072] Thereafter, in S14, the CPU 41 reflects the control amount calculated in S13. Specifically, the calculated control amount is transmitted to the vehicle control ECU 21 via the CAN. The vehicle control ECU 21 performs vehicle control of the accelerator, brake, gear, and steering based on the received control amount. As a result, driving assistance control is possible to drive the vehicle along the driving trajectory generated in S11 at a speed in accordance with the speed plan generated in S12.

[0073] Next, in S15, the CPU 41 determines whether the vehicle has traveled a certain distance since the travel trajectory was generated in S11. For example, the certain distance is set to 100 m.

[0074] If it is determined that the vehicle has traveled a certain distance since the generation of the travel trajectory in S11 (S15: YES), the process returns to S7. After that, the virtual lane is corrected and the travel trajectory is generated again based on the image recognition results of a new image captured by the exterior camera 19 (S7 to S11).

[0075] On the other hand, if it is determined that the vehicle has not traveled a certain distance since the generation of the travel trajectory in S11 (S15: NO), it is determined whether or not to end the assisted travel by autonomous driving assistance (S16). Assisted travel by autonomous driving assistance can be ended not only when the vehicle has arrived at the destination, but also when the user intentionally cancels (overrides) the assisted travel by autonomous driving assistance by operating an operation panel provided in the vehicle, or by operating the steering wheel or brakes.

[0076] If it is determined that the assisted driving by the autonomous driving assistance should be ended (S16: YES), the autonomous driving assistance program is ended. On the other hand, if it is determined that the assisted driving by the autonomous driving assistance should be continued (S16: NO), the process returns to S15.

[0077] As described above in detail, the navigation device 1 and the computer program executed by the navigation device 1 according to this embodiment use road link information for route guidance included in map information to obtain a planned driving route, including information identifying the lanes the vehicle will travel in the future (S6). At the same time, the navigation device 1 detects information defining the width of the road along which the vehicle will travel based on image recognition results from the exterior camera 19, and matches the road link information with the information defining the width of the road along which the vehicle will travel to identify the lane area ahead of the vehicle as a drivable area (S10). A driving trajectory for traveling within the drivable area along the planned driving route is generated (S11). Vehicle driving assistance is provided based on the generated driving trajectory (S14). This makes it possible to accurately identify the drivable area ahead of the vehicle, even without detailed information about lane markings. As a result, it is possible to generate an appropriate vehicle driving trajectory tailored to the drivable area, and to provide appropriate driving assistance. In addition, map information is used to provisionally set virtual lanes along the planned driving route (S7), and the virtual lanes are corrected by aligning the center position of the virtual lanes with the center position of the lanes obtained based on the image recognition results of the outside vehicle camera 19 (S9).Of the corrected virtual lanes, the area of ​​the virtual lanes that corresponds to the lane in which the vehicle is driving on the planned driving route is identified as the drivable area (S10).Therefore, by using the virtual lanes, it is possible to accurately identify the drivable area ahead in the direction of travel of the vehicle. In addition, the center position of the virtual lane is adjusted to the center position of the lane obtained from the image recognition results of the exterior camera 19, and the width of the virtual lane is adjusted to the width of the lane obtained from the image recognition results of the exterior camera 19, thereby correcting the virtual lane (S9).By correcting the virtual lane to the position and width of the actual lane, it is possible to accurately identify the drivable area ahead of the vehicle in the direction of travel. In addition, for the detection range of the exterior camera 19, the drivable area is identified based on the matching results, and for areas outside the detection range of the exterior camera 19, the drivable area is estimated and identified from the drivable area identified within the detection range and the shape of the planned route, so it is possible to generate a driving trajectory that is not limited to the detection range of the exterior camera 19 but covers a wider range.

[0078] The present invention is not limited to the above-described embodiment, and it goes without saying that various improvements and modifications are possible within the scope of the present invention. For example, in this embodiment, the drivable area is identified by setting virtual lanes, and then the driving trajectory is generated. However, it is also possible to generate the driving trajectory without setting virtual lanes or identifying the drivable area. Specifically, the CPU 41 generates, as an initial driving trajectory, a recommended route (planned driving route) that connects the lane network from the start lane searched for in S6 to the target lane. Here, since the lane network is generated based on the simplified map information stored in the map information DB 31, the generated driving trajectory may not match the actual lanes. However, accurate values ​​for the center position and lane width of the vehicle's driving lane are detected from the image recognition results in S8, and the generated driving trajectory is corrected to match the detected center position and lane width of the driving lane (S9). In other words, by matching the driving trajectory with information that divides the width direction of the road on which the vehicle is traveling, it is possible to generate a driving trajectory that matches the actual lanes. Since the lane link 56 included in the recommended route searched for in S6 is a straight line, the lane link 56 itself is not used as the driving trajectory, but the trajectory is corrected as necessary to a clothoid curve or a circular arc within intersections or sections where lane changes are required.

[0079] In this embodiment, the center position and lane width of the lane on which the vehicle is traveling are detected from the image recognition results of the exterior camera 19 (S8) as information for correcting the virtual lane, but instead of the lane center position and lane width, dividing lines may be detected. In that case, it is possible to correct the virtual lane in accordance with the detected dividing lines. Furthermore, the means for detecting the center position and lane width of the lane on which the vehicle is traveling is not limited to the image recognition results of the exterior camera 19, and other sensors may be used to detect them.

[0080] Furthermore, in this embodiment, when matching the virtual lanes with the information obtained from the image recognition results (S9), the matching is performed after leaving only the virtual lane corresponding to the lane on which the vehicle is traveling and deleting the other virtual lanes, but it is also possible to perform the matching while leaving the other virtual lanes.

[0081] In addition, in this embodiment, after generating a travel trajectory, vehicle control is performed to drive the vehicle according to the generated travel trajectory (S13, S14), but the processes related to vehicle control from S13 onwards may be omitted. For example, the navigation device 1 may be a device that guides the user along a recommended travel trajectory without controlling the vehicle based on the travel trajectory.

[0082] In addition, in this embodiment, the lane network is generated using the link data 33 stored in the map information DB 31 (S4), but each network targeting roads across the country may be stored in the DB in advance and read out from the DB as needed.

[0083] In addition, in this embodiment, the vehicle control ECU 21 has been described as controlling all of the accelerator operation, brake operation, and steering operation, which are operations related to the vehicle's behavior, as autonomous driving assistance for automatically driving the vehicle without the user's driving operation. However, the autonomous driving assistance may also be defined as the vehicle control ECU 21 controlling at least one of the accelerator operation, brake operation, and steering operation, which are operations related to the vehicle's behavior, as part of the vehicle operations. On the other hand, manual driving by the user's driving operation will be described as the user performing all of the accelerator operation, brake operation, and steering operation, which are operations related to the vehicle's behavior, as part of the vehicle operations.

[0084] Furthermore, the driving assistance of the present invention is not limited to automatic driving assistance related to automatic driving of a vehicle. For example, driving assistance can be provided by displaying the driving trajectory generated in S11 on a navigation screen and providing guidance using voice, a screen, or the like (for example, guidance on lane changes, guidance on recommended vehicle speeds, etc.). Furthermore, displaying the driving trajectory on a navigation screen may be used to assist the user's driving operation.

[0085] In addition, in this embodiment, the automatic driving assistance program (FIG. 3) is configured to be executed by the navigation device 1, but it may also be configured to be executed by an in-vehicle device other than the navigation device 1 or the vehicle control ECU 21. In that case, the in-vehicle device or the vehicle control ECU 21 is configured to acquire the current position of the vehicle, map information, etc. from the navigation device 1. Furthermore, an external server device may execute some or all of the steps of the automatic driving assistance program (FIG. 3). In that case, the server device corresponds to the driving assistance device of the present application.

[0086] Furthermore, the present invention can be applied to devices other than navigation devices, such as mobile phones, smartphones, tablet devices, and personal computers (hereinafter referred to as mobile devices, etc.). It can also be applied to a system consisting of a server and a mobile device, etc. In that case, each step of the above-described automatic driving assistance program (see FIG. 3) may be implemented by either the server or the mobile device, etc. However, when applying the present invention to a mobile device, etc., a vehicle capable of executing automatic driving assistance and the mobile device, etc., must be connected to each other so that they can communicate (whether wired or wireless). [Explanation of symbols]

[0087] 1...navigation device (driving assistance device), 13...navigation ECU, 19...exterior camera, 21...vehicle control ECU, 31...map information DB, 33...link data (road link information), 41...CPU, 55...lane node, 56...lane link, 61-64...virtual lane, 70...drivable area, 73...driving trajectory

Claims

1. a planned driving route acquisition means for acquiring a planned driving route including information specifying a lane on which the vehicle will travel in the future by using road link information for route guidance included in the map information; a detection result acquisition means for acquiring a detection result of a detection device that detects the surrounding conditions of the vehicle; a drivable area specifying means for detecting information that divides the width direction of a road on which the vehicle is traveling based on the detection result of the detection device, and for specifying the area of ​​the lane on which the vehicle is traveling ahead in the traveling direction of the vehicle as a drivable area by matching the road link information with the information that divides the width direction of the road on which the vehicle is traveling; a travel trajectory generation means for generating a travel trajectory for traveling within the travelable area along the planned travel route; and a driving assistance means for providing driving assistance for the vehicle based on the traveling trajectory generated by the traveling trajectory generating means.

2. The travelable area specifying means provisionally setting a virtual lane based on the road link information; correcting the virtual lane by aligning the center position of the virtual lane with the center position of the lane obtained from the detection result of the detection device; The driving assistance device according to claim 1 , wherein an area of ​​the revised virtual lanes that corresponds to a lane on which the vehicle is traveling along the planned travel route is identified as the drivable area.

3. The travelable area specifying means The driving assistance device according to claim 2 , wherein the virtual lane is corrected by adjusting the width of the virtual lane to the width of the lane obtained from the detection result of the detection device.

4. The travelable area specifying means The detection range of the detection device is determined based on the matching result, and the travelable area is identified.

4. The driving assistance device according to claim 1, wherein the driving area outside the detection range of the detection device is estimated and identified from the driving area identified within the detection range and the shape of the planned driving route.

5. a planned driving route acquisition means for acquiring a planned driving route including information specifying a lane on which the vehicle will travel in the future by using road link information for route guidance included in the map information; a detection result acquisition means for acquiring a detection result of a detection device that detects the surrounding conditions of the vehicle; a travel trajectory generation means for detecting information that divides the width direction of a road on which the vehicle is traveling based on the detection result of the detection device, and for generating a travel trajectory for the vehicle to travel on the road ahead in the traveling direction of the vehicle by matching the planned travel route with the information that divides the width direction of the road on which the vehicle is traveling; and a driving assistance means for providing driving assistance for the vehicle based on the traveling trajectory generated by the traveling trajectory generating means.

6. The running trajectory generating means The driving assistance device according to claim 5 , wherein the driving trajectory is generated by correcting the position of the planned driving route in accordance with the center position of the lane obtained from the detection result of the detection device.

Images