Map update section decision device, map update section decision method, and map update section decision computer program

Abstract

The present disclosure relates to a map update interval decision device, a map update interval decision method, and a map update interval decision computer program. The map update interval decision device has: a selection section (41) that selects, for each combination of two places selected from among a plurality of places that can enter and exit a predetermined area, a series of road sections connecting the two places from among a plurality of road sections as a route between the two places; an evaluation value calculation section (42) that calculates, for each combination of two places, an evaluation value indicating a degree of improvement in convenience for a driver obtained by generating or updating map information using a candidate section in each road section included in the route between the two places, which is a section in which map information cannot be used; and a determination section (43) that determines, among the combinations of two places, each candidate section included in the route of a predetermined number of combinations in order from high to low in the evaluation value as a road section that becomes an object of generation or update of map information.

Description

Technical Field

[0001] This invention relates to a map update interval determination device, a map update interval determination method, and a computer program for determining road intervals that are the objects of map information generation or updating. Background Technology

[0002] For autonomous driving systems to control vehicles, high-precision maps are required to accurately represent information about features (elements) located on or around roads that are related to vehicle movement. Therefore, a technique has been proposed to determine whether map information needs to be updated based on information from vehicles actually traveling on roads (see Japanese Patent Application Publication No. 2019-40176).

[0003] The information processing apparatus disclosed in Japanese Patent Application Publication No. 2019-40176 determines whether a map for a given area needs to be updated based on at least one of the amount of change in the road shape represented by the map from the current road shape to the current road shape, and the number of times a vehicle traveling in that area has a predetermined action. Summary of the Invention

[0004] To generate or update map information for a certain area, a vehicle actually drives in that area, generating data containing information about landmarks within that area, and then sends this data via communication lines to a device that generates or updates the map information. Therefore, the collection of data containing landmark information and the generation or updating of map information based on that data incur various costs, including communication costs. On the other hand, the available time or budget for generating or updating map information is limited. Therefore, it is desirable to determine which road sections are the targets for map information generation or updating, i.e., which are the targets for collecting data containing landmark information, so that the vehicle driver can maximize the benefits (advantages) of autonomous driving control within a limited time or budget.

[0005] Therefore, the object of the present invention is to provide a map update interval determination device that determines the road intervals in each road interval that are the objects of map information generation or updating so that the driver can easily obtain the benefits of autonomous driving control.

[0006] According to one embodiment, a map update interval determination apparatus is provided. This apparatus includes: a storage unit that stores map markers indicating whether map information for a vehicle to drive autonomously in a road section among a plurality of road sections included in a predetermined area is available; a selection unit that selects a series of road sections connecting two locations from the plurality of road sections as a route between the two locations for each combination of two locations selected from a plurality of locations that can access the predetermined area; an evaluation value calculation unit that, for each combination of two locations, refers to the map markers and determines road sections among the road sections included in the route between the two locations where map information is unavailable as candidate intervals, and calculates an evaluation value indicating the degree of improvement in driver convenience obtained by generating or updating map information based on the determined candidate intervals; and a determination unit that, in the combination of two locations, determines each candidate interval included in the route of each combination of two locations as the road interval to be used for generating or updating map information in descending order of the degree of improvement in driver convenience indicated by the evaluation value.

[0007] In this map update interval determination device, preferably, the storage unit also stores, for each of the multiple road intervals, the traffic volume of that road interval, the autonomous driving cost representing the driver's workload when the vehicle is driving autonomously in that road interval using map information, the manual driving cost representing the driver's workload when the vehicle is driving manually in that road interval, and the map preparation (preparation and maintenance) cost required to generate or update map information for that road interval. Furthermore, preferably, the evaluation value calculation unit calculates, for each combination of two locations, the sum of values ​​obtained by weighting the difference between the manual driving cost and the autonomous driving cost using the ratio of traffic volume to map preparation cost for each candidate interval included in that combination, as the evaluation value.

[0008] Alternatively, in this map update interval determination device, preferably, the storage unit also stores, for each of the multiple road intervals, the traffic volume of that road interval, the autonomous driving cost representing the driver's load when the vehicle drives autonomously in that road interval using map information, and the manual driving cost representing the driver's load when the vehicle drives manually in that road interval. Furthermore, preferably, the evaluation value calculation unit calculates, for each combination of two locations, the sum of values ​​obtained by weighting the difference between the manual driving cost and the autonomous driving cost based on traffic volume for each candidate interval included in the route of that combination, as the evaluation value.

[0009] Alternatively, in this map update interval determination device, it is preferable that the storage unit also stores, for each of the multiple road intervals, the traffic volume of that road interval, the manual driving cost representing the driver's load when the vehicle travels in that road interval by manual driving, and the map preparation cost required to generate or update map information for that road interval. Furthermore, it is preferable that the evaluation value calculation unit calculates, for each combination of two locations, the sum of values ​​obtained by weighting the manual driving cost by the ratio of traffic volume to map preparation cost for each candidate interval included in the route of that combination, as the evaluation value.

[0010] Furthermore, in this map update interval determination device, it is preferable that the storage unit also stores the map preparation cost required to generate or update map information for each of the multiple road intervals. Moreover, it is preferable that the determination unit, in combinations of two locations, determines each candidate interval included in the route of each combination as the road interval to be used for generating or updating map information, in descending order of the degree of improvement in driver convenience indicated by evaluation values, until the total map preparation cost of the road intervals determined as the road intervals to be used for generating or updating map information reaches the target preparation cost.

[0011] According to another approach, a method for determining map update intervals is provided. This method includes: for each combination of two locations selected from a plurality of locations capable of accessing a predetermined area, selecting a series of road intervals connecting the two locations from a plurality of road intervals included in the predetermined area as a route between the two locations; for each combination of two locations, for each road interval included in the route of that combination, referring to a map marker indicating whether map information for a vehicle to drive autonomously in that road interval is usable, determining road intervals in the road intervals included in the route between the two locations that are not usable by the map information as candidate intervals; for each combination of two locations, calculating an evaluation value representing the degree of improvement in driver convenience obtained by generating or updating map information based on the determined candidate intervals; and in each combination of two locations, determining each candidate interval included in the route of each combination as the road interval to be the object of map information generation or updating in descending order of the degree of improvement in driver convenience represented by the evaluation value.

[0012] According to another approach, a computer program for determining map update intervals is provided. This computer program for determining map update intervals includes commands for causing a computer to perform the following processes: for each combination of two locations selected from a plurality of locations capable of accessing a predetermined area, selecting a series of road intervals connecting the two locations from a plurality of road intervals contained within the predetermined area as a route between the two locations; for each combination of two locations, for each road interval contained in the route of that combination, referring to map markers indicating whether map information for a vehicle to drive autonomously in that road interval is usable, determining road intervals in the road intervals contained in the route between the two locations that are not usable by map information as candidate intervals; for each combination of two locations, calculating an evaluation value representing the degree of improvement in driver convenience obtained by generating or updating map information based on the determined candidate intervals; and in the combination of two locations, determining each candidate interval contained in the route of each combination of the two locations as road intervals to be the object of map information generation or updating in descending order of the degree of improvement in driver convenience represented by the evaluation value.

[0013] The map update interval determination device disclosed herein has the following effect: it can determine the road intervals in each road interval that become the objects of map information generation or updating, so that the driver can easily obtain the benefits of autonomous driving control. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of a map update system equipped with a map update interval determination device.

[0015] Figure 2 It is a rough composition diagram of the vehicles included in the map update system.

[0016] Figure 3 This is a hardware configuration diagram of the data acquisition device mounted on the vehicle.

[0017] Figure 4 This is a hardware configuration diagram of a server, which serves as an example of a map update interval determination device.

[0018] Figure 5 It is a function block diagram of the processor of the server associated with map update processing, including map update interval determination processing.

[0019] Figure 6 This is a diagram illustrating the general principles of the evaluation value calculation.

[0020] Figure 7 This is a flowchart of the actions involved in determining the map update interval. Detailed Implementation

[0021] Hereinafter, with reference to the accompanying drawings, the map update interval determination device, the map update interval determination method executed in the map update interval determination device, and the computer program for map update interval determination will be described. This map update interval determination device determines the road intervals that will be the objects of map information generation or updating from among multiple road intervals included in an area that is the object of map information generation or updating used in autonomous driving control, so that many drivers can enjoy the benefits of autonomous driving control. Furthermore, the map information used in autonomous driving control includes information about features associated with vehicle travel (e.g., lane markings and other road signs, directional signs and other road markings, road curbs). The map update interval determination device selects various combinations of two locations from multiple locations that can access the area that is the object of map information generation or updating. Furthermore, for each selected combination of two locations, the map update interval determination device selects a series of road intervals connecting the two locations from among the multiple road intervals included in the area as the route between the two locations. Furthermore, for each combination of two locations, the map update interval determination device determines the road intervals whose map information is unavailable from among the various road intervals included in the route between the two locations. Hereinafter, road sections where map information is unavailable are sometimes referred to as unmaintained sections. The map update section determination device calculates an evaluation value for each route, based on the determined unmaintained sections, representing the degree of improvement in driver convenience resulting from the generation or updating of map information. Furthermore, the map update section determination device identifies a predetermined number of routes combining two locations, ordered from highest to lowest evaluation value, containing unmaintained sections as road sections for map information generation or updating. Moreover, the map update section determination device notifies the vehicle capable of generating the feature data of a collection instruction to collect data representing features associated with vehicle travel (hereinafter referred to as feature data) for the determined road sections.

[0022] Figure 1 This is a schematic diagram of a map update system equipped with a map update interval determination device. In this embodiment, the map update system 1 includes at least one vehicle 2 and a server 3, which is an example of a map update interval determination device. The vehicle 2 connects to the server 3, for example, by accessing a wireless base station 5 connected to a communication network 4 via a gateway (not shown) and thus via the wireless base station 5 and the communication network 4. Furthermore, although in Figure 1 The image shows only one vehicle 2, but the map update system 1 can also have multiple vehicles 2. Similarly, multiple wireless base stations 5 can be connected to the communication network 4. In addition, the server 3 can also be communicatively connected to a traffic information server (not shown) that manages traffic information via the communication network 4.

[0023] Figure 2 This is a schematic diagram of vehicle 2. Vehicle 2 has a camera 11, a GPS receiver 12, a wireless communication terminal 13, and a data acquisition device 14. The camera 11, GPS receiver 12, wireless communication terminal 13, and data acquisition device 14 are communicatively connected via an in-vehicle network conforming to standards such as a controller area network.

[0024] The camera 11 is an example of a camera unit used to capture images of the area around the vehicle 2. It has a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as CCD (charge-coupled device) or C-MOS (complementary metal-oxide-semiconductor), and an imaging optical system that images the area to be captured on the two-dimensional detector. The camera 11 is mounted, for example, in the interior of the vehicle 2, facing forward of the vehicle 2. The camera 11 captures images of the area in front of the vehicle 2 at predetermined shooting intervals (e.g., 1 / 30 to 1 / 10 of a second), generating an image reflecting that area. The image obtained by the camera 11 can be a color image or a grayscale image. Furthermore, the vehicle 2 may also be equipped with multiple cameras 11 with different shooting directions or focal distances.

[0025] Whenever an image is generated, the camera 11 outputs the generated image to the data acquisition device 14 via the in-vehicle network.

[0026] GPS receiver 12 receives GPS signals from GPS satellites at predetermined intervals and measures the vehicle 2's own position (location) based on the received GPS signals. Furthermore, GPS receiver 12 outputs location information, representing the vehicle 2's own position based on the GPS signals, to data acquisition device 14 via the in-vehicle network at predetermined intervals. Alternatively, vehicle 2 may have a receiver other than GPS receiver 12 that follows a satellite positioning system. In this case, the receiver can simply measure the vehicle 2's own position.

[0027] The wireless communication terminal 13 is a device that performs wireless communication processing in accordance with a predetermined wireless communication standard. For example, it connects to the server 3 via the wireless base station 5 and the communication network 4. Furthermore, the wireless communication terminal 13 receives downlink wireless signals from the wireless base station 5 and transmits the collection instructions for ground feature data from the server 3 contained in those wireless signals to the data acquisition device 14. Additionally, the wireless communication terminal 13 generates uplink wireless signals containing the ground feature data collected from the data acquisition device 14. The wireless communication terminal 13 then transmits the ground feature data to the server 3 by sending these uplink wireless signals to the wireless base station 5.

[0028] Figure 3This is a hardware configuration diagram of the data acquisition device. The data acquisition device 14 performs processing related to the generation of ground feature data based on images generated by the camera 11. For this purpose, the data acquisition device 14 includes a communication interface (I / F) 21, a memory 22, and a processor 23.

[0029] The communication interface 21 has an interface circuit for connecting the data acquisition device 14 to the in-vehicle network. Specifically, the communication interface 21 is connected to the camera 11, the GPS receiver 12, and the wireless communication terminal 13 via the in-vehicle network. Furthermore, whenever the communication interface 21 receives an image from the camera 11, it passes the received image to the processor 23. Additionally, whenever the communication interface 21 receives location information from the GPS receiver 12, it passes the received location information to the processor 23. Moreover, the communication interface 21 outputs the terrain data collected from the processor 23 to the wireless communication terminal 13 via the in-vehicle network. Furthermore, the communication interface 21 passes the collection instructions for terrain data received from the server 3 via the wireless communication terminal 13 to the processor 23.

[0030] The memory 22 may include, for example, volatile semiconductor memory and non-volatile semiconductor memory. The memory 22 may also include other storage devices such as hard disk drives. Furthermore, the memory 22 stores various data used in the processing associated with the generation of ground feature data executed by the processor 23 of the data acquisition device 14. Such data includes, for example, road maps, vehicle 2 identification information, camera 11 parameters such as installation height, shooting direction, and viewing angle, and parameter sets used to determine the identifier for detecting ground features from images. In addition, the road map may be configured as a map used for route searching in a navigation device, containing information such as the location, length, and connection relationships of each road section within the area represented by the road map, and the road sections at each intersection. Additionally, the memory 22 may store images received from the camera 11 and positioning information received from the GPS receiver 12 for a certain period. Furthermore, the memory 22 stores information indicating the road sections (hereinafter sometimes referred to as collection target sections) designated in the ground feature data collection instructions as the objects of ground feature data generation and collection. Furthermore, memory 22 can also store computer programs and the like used to implement various processes executed by processor 23.

[0031] Processor 23 has one or more CPUs (Central Processing Units) and their peripheral circuitry. Processor 23 may also have other arithmetic circuits such as logic units, numerical processing units, or graphics processing units. Furthermore, processor 23 stores images received from camera 11 and positioning information received from GPS receiver 12 in memory 22. Moreover, while vehicle 2 is in motion, processor 23 performs processing related to the generation of ground feature data at predetermined intervals (e.g., 0.1 seconds to 10 seconds).

[0032] As part of the processing associated with the generation of ground feature data, the processor 23 determines, for example, whether the vehicle 2's own location, as indicated by the positioning information received from the GPS receiver 12, is included within the target collection area. Furthermore, if the vehicle's own location is included within the target collection area, the processor 23 generates ground feature data based on images received from the camera 11.

[0033] For example, the processor 23 may use the image itself (hereinafter, sometimes referred to as the overall image) received from the camera 11 as ground feature data. Alternatively, the processor 23 may crop (cut out) a partial image (sub-image) containing the area representing the road surface from the overall image received from the camera 11, and use this cropped partial image as ground feature data. Furthermore, information indicating the area presumed to represent the road surface in the overall image may be pre-stored in the memory 22. Moreover, the processor 23 may determine the area cropped from the overall image by referring to this information representing the area.

[0034] Alternatively, processor 23 can detect features shown in the input overall image or partial image (hereinafter, sometimes simply referred to as the input image) by inputting the overall image or partial image into a pre-learned recognizer designed to detect features that are the objects to be detected. Furthermore, processor 23 can generate information representing the types of detected features as feature data. For example, processor 23 can use a so-called deep neural network (DNN) pre-learned to detect features shown in the input image. Such a DNN could be, for example, a DNN with a convolutional neural network (CNN) architecture, such as SSD (SingleShot MultiBox Detector) or Faster R-CNN. In this case, the recognizer calculates a confidence level indicating the presence of a feature in various regions of the input image, based on the type of feature being detected (e.g., lane markings, pedestrian crossings, temporary stop lines, etc.). The recognizer determines that a feature of that type is present in regions where the confidence level for that type of feature reaches a predetermined detection threshold. Furthermore, the recognizer outputs information representing the region on the input image that contains the ground features that are to be detected (e.g., the bounding rectangle of the ground features that are to be detected, hereinafter referred to as the object region), and information representing the types of ground features shown within the object region. Thus, the processor 23 can generate ground feature data in a manner that includes information representing the types of ground features shown within the detected object region.

[0035] Furthermore, the processor 23 determines the location or position of the feature represented in the feature data within the actual space and incorporates the information representing that location into the feature data. For example, the processor 23 uses the position of the vehicle 2 itself when the image used to generate the feature data is generated as the location represented in the feature data. In this case, the processor 23 can use the position represented by the positioning information received from the GPS receiver 12 at the timing closest to the generation of the image used to generate the feature data as the position of the vehicle 2 itself. Alternatively, if the electronic control unit (ECU, not shown) of the vehicle 2 estimates the position of the vehicle 2 itself, the processor 23 can also obtain information representing the estimated position of the vehicle 2 itself from the ECU via the communication interface 21. Furthermore, the processor 23 can obtain information representing the direction of travel of the vehicle 2 from the ECU. In addition, the position of each pixel on the image corresponds one-to-one with the orientation of the object represented by that pixel from the camera 11. Therefore, when the ground feature data is a whole image or a partial image, the processor 23 can also estimate the actual spatial location corresponding to the center of the whole image or partial image as the location represented in the ground feature data. In this case, the processor 23 estimates the location corresponding to the center of the whole image or partial image based on parameters such as the orientation of the camera 11, the position of the vehicle 2, the direction of travel of the vehicle 2, and the shooting direction, viewing angle, and setting height of the camera 11. Alternatively, if the ground feature data contains information indicating the types of ground features detected from the image, the processor 23 estimates the location of the ground features shown within the object area based on the orientation of the camera 11, the position of the vehicle 2, the direction of travel, and the parameters of the camera 11 corresponding to the center of gravity of the object area. Alternatively, the processor 23 can also estimate the location of the ground features represented in the ground feature data using a so-called Structure from Motion (SfM). In this case, the processor 23 uses optical flow to correlate object areas showing the same ground features between two images acquired at different times. Furthermore, the processor 23 can estimate the location of ground features by triangulation based on the position and direction of travel of the vehicle 2 when the two images are obtained, the parameters of the camera 11, and the position of the object region in each image.

[0036] Processor 23 includes the longitude and latitude of the location or feature shown in the feature data as information representing the location or feature shown in the feature data. Furthermore, processor 23 refers to a road map to determine a link that includes the location or feature shown in the feature data, or is the road section closest to that location. Moreover, processor 23 can include the identification number of the determined link in the feature data. Furthermore, when the feature data is a global image or a partial image, the position and direction of travel of vehicle 2 when these images were generated, as well as the parameters of camera 11, can also be included in the feature data, so that server 3 can estimate the location of the feature shown in the global image or partial image.

[0037] Whenever processor 23 generates feature data, it outputs the generated feature data to wireless communication terminal 13 via communication interface 21. Thus, the feature data is sent to server 3.

[0038] Next, server 3, which serves as an example of a map update interval determination device, will be described.

[0039] Figure 4 This is a hardware configuration diagram of server 3, which serves as an example of a map update interval determination device. Server 3 has a communication interface (I / F) 31, a storage device 32, a memory 33, and a processor 34. The communication interface 31, storage device 32, and memory 33 are connected to the processor 34 via signal lines. Server 3 may also have input devices such as a keyboard and mouse, and a display device such as an LCD screen.

[0040] Communication interface 31 is an example of a communication unit, and it has an interface circuit for connecting server 3 to communication network 4. Furthermore, communication interface 31 is configured to communicate with vehicle 2 via communication network 4 and wireless base station 5. That is, communication interface 31 transmits collection instructions received from processor 34 to vehicle 2 via communication network 4 and wireless base station 5. Additionally, communication interface 31 delivers ground feature data received from vehicle 2 via wireless base station 5 and communication network 4 to processor 34.

[0041] Storage device 32 is an example of a storage unit, such as having a hard disk device or an optical recording medium and its access device. Furthermore, storage device 32 stores various data and information used in the map update interval determination process. For example, storage device 32 stores information indicating areas that are the objects of map information generation or updating, road maps, and information for identifying individual road intervals and indicating the connection relationships between individual road intervals. Furthermore, as mentioned above, the road map is a map used for path searching in the navigation device. Moreover, storage device 32 stores map markers, autonomous driving costs, manual driving costs, traffic volume, and map preparation costs for each road interval. Furthermore, storage device 32 stores a target value (hereinafter referred to as the target preparation cost) of the total map preparation cost that can be used for map information generation or updating. Furthermore, storage device 32 stores a table showing the relationship between traffic volume and the weighting coefficients corresponding to traffic volume used in calculating evaluation values. The weighting coefficients will be explained later. Furthermore, storage device 32 stores feature data received from vehicle 2. Furthermore, storage device 32 may also store a computer program executed on processor 34 for performing map update interval determination processing.

[0042] Each road section can be defined as a link or node shown on a road map. That is, a road section is defined as the distance from a point where multiple roads intersect, branch, or merge (hereinafter referred to as a merging or intersection point) to an adjacent merging or intersection point. Furthermore, if such a road section is longer than a predetermined distance, it can be divided into multiple road sections. Moreover, merging or intersection points are also defined as road sections.

[0043] Map markers indicate whether map information can be used for a vehicle to drive autonomously within the road section corresponding to that marker. Specifically, when a map marker has a value indicating that map information can be used (e.g., 1), it means that the map information contains information about terrain features related to the road section corresponding to that marker, to a degree sufficient for the vehicle to drive autonomously. Conversely, when a map marker has a value indicating that map information cannot be used (e.g., 0), it means that the map information does not contain information about terrain features necessary for the vehicle to drive autonomously within the road section corresponding to that marker.

[0044] The costs of autonomous driving and manual driving are set for each road segment, with the value increasing as the driver's workload increases. The autonomous driving cost represents the driver's workload when the vehicle autonomously drives within a corresponding road segment using map information; for example, it is set as the cost per unit time of autonomous driving multiplied by the average time required to traverse the corresponding road segment. Furthermore, since the driver's workload during autonomous driving is relatively low, the autonomous driving cost can also be 0. The manual driving cost represents the driver's workload when the vehicle travels within a corresponding road segment manually; for example, it is set as the cost per unit time of manual driving multiplied by the average time required to traverse the corresponding road segment. Generally, the workload for manual driving is greater than that for autonomous driving, therefore, the manual driving cost is greater than the autonomous driving cost for the same road segment. For road segments including merging and crossing points, map markers, autonomous driving costs, and manual driving costs are set for each combination of roads accessible to vehicles connected to that road segment. For example, for a road section including intersections, map markers, autonomous driving costs, and manual driving costs are set for each road connected to the intersection, for each of the directions of going straight, turning right, and turning left from that road. However, if entry into any of the directions of going straight, turning right, and turning left is prohibited for any road connected to the intersection, map markers, autonomous driving costs, and manual driving costs may not be set for that prohibited direction.

[0045] Furthermore, map preparation cost represents the cost required to generate or update map information for a corresponding road section. For road sections excluding merging / crossing points, the longer the road section or the more lanes it contains, the higher the map preparation cost is set to. Conversely, for road sections including merging / crossing points, the map preparation cost is set to a value proportional to the number of lanes in each combination of roads connecting at the merging / crossing point and from which vehicles can pass.

[0046] Furthermore, the traffic volume of each road section is obtained from the traffic information server, for example, via communication network 4.

[0047] Memory 33 is another example of a storage unit, such as having non-volatile semiconductor memory and volatile semiconductor memory. Furthermore, memory 33 temporarily stores various data generated during the execution of map update interval determination processing.

[0048] Processor 34 is an example of a control unit, having one or more CPUs (Central Processing Units) and their peripheral circuitry. Processor 34 may also have other arithmetic circuitry, such as logic units or numerical processing units. Furthermore, processor 34 performs map update processing, including map update interval determination processing.

[0049] Figure 5 This is a function block diagram of the processor 34 associated with the map update process, which includes map update interval determination processing. The processor 34 includes a selection unit 41, an evaluation value calculation unit 42, a determination unit 43, a collection instruction unit 44, and a map update unit 45. These units of the processor 34 are, for example, functional modules implemented by a computer program operating on the processor 34. Alternatively, these units of the processor 34 may also be dedicated arithmetic circuits provided on the processor 34. Furthermore, the selection unit 41, evaluation value calculation unit 42, and determination unit 43 of the processor 34 perform processing associated with the map update interval determination process.

[0050] The selection unit 41 selects multiple combinations of two locations from multiple locations within an area that can be accessed and used to generate or update map information. Furthermore, for each selected combination of two locations, the selection unit 41 selects a series of road sections connecting the two locations from multiple road sections within the area as a route connecting the two locations.

[0051] By referring to a road map, the selection unit 41 can determine multiple locations that can access the area from which map information is generated or updated. Furthermore, the selection unit 41 arbitrarily selects multiple combinations of two locations from these multiple locations. At this time, the selection unit 41 can select all possible combinations, or it can select all possible combinations of two locations from the multiple locations that can access the area and meet predetermined conditions. The predetermined conditions can be, for example, that locations can be accessed via roads that meet predetermined road standards. Alternatively, the predetermined conditions can also be that locations can be accessed via roads with traffic volume exceeding a predetermined baseline.

[0052] For each combination of two selected locations, the selection unit 41 searches for a route connecting the two locations using a predetermined path search method such as Dijkstra's algorithm, referring to a road map. Thus, for each combination of two selected locations, the shortest route connecting the two locations, or a route designed to allow travel between the two locations in the shortest possible time, is selected. Furthermore, for each combination of two selected locations, the selection unit 41 selects a series of road sections located on the route connecting the two locations.

[0053] For each combination of two selected locations, the selection unit 41 notifies the evaluation value calculation unit 42 and the determination unit 43 of information representing a series of road sections located on the route connecting the two locations.

[0054] The evaluation value calculation unit 42 calculates an evaluation value for each combination of two locations notified from the selection unit 41, representing the degree of improvement in driver convenience brought about by the route preparation map information connecting the two locations. The evaluation value calculation unit 42 performs the same processing for each combination of two locations; therefore, the evaluation value calculation processing for a single combination will be described below.

[0055] The evaluation value calculation unit 42, referring to map markers, determines the unrepaired sections among the various road sections included in the route between two locations as the road sections referenced when calculating the evaluation value. Furthermore, road sections that are currently unrepaired but have already been selected by the determination unit 43 as objects for generating or updating map information are not referenced in the evaluation value calculation. Hereinafter, the road sections referenced when calculating the evaluation value, i.e., the candidate road sections that become objects for generating or updating map information, are sometimes simply referred to as candidate sections.

[0056] The evaluation value calculation unit 42 calculates the sum of values ​​for each determined candidate interval, weighted by the difference between the manual driving cost and the autonomous driving cost, calculated as the ratio of traffic volume to map preparation cost. That is, the evaluation value is calculated as the sum of the individual interval evaluation values ​​Ei for each candidate interval located on the route, expressed by the following formula.

[0057] Ei=(Mc-Ac)*Tv / Sc

[0058] Here, parameter Ac represents the autonomous driving cost for the candidate interval of interest. Additionally, parameter Mc represents the manual driving cost for the candidate interval of interest. Furthermore, parameter Tv represents a weighting coefficient corresponding to the traffic volume of the candidate interval of interest. For example, the higher the traffic volume of the candidate interval of interest, the larger the value of parameter Tv. Moreover, parameter Sc represents the map preparation cost for the candidate interval of interest. Furthermore, as shown in the above formula, when the autonomous driving cost is set to 0, the individual interval evaluation value Ei is calculated as a weighted average of the manual driving cost based on the ratio of traffic volume to map preparation cost.

[0059] The greater the difference between the cost of manual driving and the cost of autonomous driving, or the higher the traffic volume, the higher the evaluation value Ei for an individual section. In other words, the greater the reduction in driver burden brought about by autonomous driving through the generation or updating of map information, or the greater the number of vehicles enjoying the benefits of autonomous driving on a road section, the higher the evaluation value Ei for that individual section. Furthermore, the lower the map preparation cost for a road section, the higher the evaluation value Ei for that individual section. Therefore, routes with higher evaluation values ​​represent a greater improvement in driver convenience resulting from generating or updating map information with lower map preparation costs, and also demonstrate higher preparation efficiency.

[0060] The evaluation value calculation unit 42 notifies the determination unit 43 of the calculated evaluation value for each combination of the two locations.

[0061] The determination unit 43 determines the unmaintained sections located on the following routes as the road sections to be used for generating or updating map information: the routes of the combinations of two locations notified by the selection unit 41, in descending order of evaluation value, and in a predetermined number of combinations.

[0062] To this end, the determination unit 43 determines the combination that corresponds to the maximum value among the evaluation values ​​of each combination of the two locations, as notified by the evaluation value calculation unit 42; that is, the combination that provides the highest improvement in driver convenience. Furthermore, the determination unit 43 identifies the unmaintained sections located on the route with respect to the determined combination as road sections that will be the object of map information generation or updating.

[0063] The determination unit 43 calculates the sum of map preparation costs for each road section determined as the object of map information generation or updating, as the cumulative preparation cost value. Furthermore, the determination unit 43 determines whether the cumulative preparation cost value is less than the target preparation cost. If the cumulative preparation cost value reaches the target preparation cost, the determination unit 43 terminates the determination of the road sections that are the object of map information generation or updating. On the other hand, if the cumulative preparation cost value is less than the target preparation cost, the determination unit 43 notifies the evaluation value calculation unit 42 of the determined road sections. Moreover, after excluding the determined road sections and the combination of the two locations with the highest evaluation values ​​from the evaluation value calculation objects, the determination unit 43 causes the evaluation value calculation unit 42 to recalculate the evaluation value for each combination of the two locations.

[0064] The determination unit 43 performs the above-described process again based on the evaluation value recalculated for each combination of the two locations, thereby determining the road sections that will be the objects of map information generation or updating. Furthermore, the determination unit 43 adds the sum of the map maintenance costs for each determined road section to the accumulated maintenance cost value. The determination unit 43 repeats the above-described process until the accumulated maintenance cost value reaches the target maintenance cost. Finally, the determination unit 43 terminates the determination of the road sections that will be the objects of map information generation or updating at the point when the accumulated maintenance cost value reaches or exceeds the target maintenance cost.

[0065] Figure 6 This is an explanatory diagram summarizing the selection of road sections that become the objects of map information generation or updating. Figure 6 In the example shown, for area 600, which is the object of map information generation or updating, there are six locations a to f that can be accessed or exited. Therefore, the selection unit 41 selects a route connecting two locations from each combination of two locations selected from these six locations a to f. Then, the evaluation value calculation unit 42 calculates an evaluation value for each combination of two locations for the route connecting the two locations. In this example, it is assumed that the evaluation value of route 601 connecting location a and location d is the highest. Therefore, the determination unit 43 selects each road section 611, 612, and 613 located on route 601 as the road sections that are the objects of map information generation or updating. In this example, it is assumed that the cumulative value of the total map preparation cost of road sections 611 to 613 does not reach the target preparation cost. Therefore, route 601 and each road section on route 601 are excluded from the evaluation value calculation objects, and the evaluation value is recalculated for each combination of the remaining two locations. Assume that route 602, which connects location a and location f, has the highest evaluation value among the remaining two location combinations. In this case, road sections 614 to 616, out of the road sections 611, 612, 614, 615, and 616 located on route 602, are newly added as road sections to be generated or updated for map information. Furthermore, when the cumulative value of the total map preparation cost of road sections 611 to 616 reaches the target preparation cost, the determination unit 43 terminates the selection of road sections to be generated or updated for map information.

[0066] The determination unit 43 notifies the collection instruction unit 44 of the information of the road sections identified as objects of map information generation or updating.

[0067] The collection instruction unit 44 generates a collection instruction for collecting feature data for road sections that are the objects of map information generation or updating, as notified by the determination unit 43. That is, the collection instruction unit 44 generates the collection instruction in a manner that includes information identifying the road sections that are the objects of map information generation or updating. Furthermore, the collection instruction unit 44 sends the generated collection instruction to the vehicle 2 via the communication interface 31.

[0068] The map updating unit 45 generates or updates the map information by adding information related to land features from the collected land feature data for each road section that is the object of map information generation or updating to the map information read from the storage device 32. For example, when the land feature data is a whole image or a partial image, the map updating unit 45 performs the same processing as the data acquisition device 14 mounted on the vehicle 2, detecting land features and their types from the whole image or the partial image, and estimating the location of the detected land features. Furthermore, for land features of the same type located within a predetermined range, the map updating unit 45 determines the location of the land feature as the average of the location of the land feature contained in the collected land feature data or the location of the land feature estimated as described above. Moreover, for each land feature whose location has been determined, the map updating unit 45 updates the map information by including information indicating the type of the land feature and the determined location in the map information.

[0069] Figure 7 This is the flowchart for the map update interval determination process in server 3. The processor 34 of server 3 executes the map update interval determination process according to the flowchart shown below.

[0070] The selection unit 41 of the processor 34 selects multiple combinations of two locations from multiple locations in the area that can be entered or exited as objects of map information generation or updating (step S101). Furthermore, for each selected combination of two locations, the selection unit 41 searches for a route connecting the two locations and selects a series of road sections located on the searched route (step S102).

[0071] The evaluation value calculation unit 42 of the processor 34 calculates an evaluation value for each combination of two locations, representing the degree of improvement in driver convenience obtained by generating or updating map information for the route connecting the two locations (step S103).

[0072] The determination unit 43 of the processor 34 selects the unmaintained sections of each road section on the route with the maximum value among the calculated evaluation values ​​as the road sections to be generated or updated with map information (step S104). Furthermore, the determination unit 43 determines whether the cumulative maintenance cost of the road sections to be generated or updated with map information determined up to this point is less than the target maintenance cost (step S105). If the cumulative maintenance cost is less than the target maintenance cost (step S105: Yes), the processor 34 removes the road sections to be generated or updated with map information determined up to this point, as well as the combination of the two locations, and repeats the processing after step S103.

[0073] On the other hand, if the accumulated maintenance cost reaches the target maintenance cost (step S105: No), the processor 34 ends the map update interval determination process. After the map update interval determination process is completed, the collection instruction unit 44 of the processor 34 generates a collection instruction for collecting feature data for road intervals that are the objects of map information generation or updating, and sends the generated collection instruction to the vehicle 2 via the communication interface 31. In addition, when a predetermined amount or more of feature data for road intervals that are the objects of map information generation or updating is collected, the map updating unit 45 of the processor 34 adds the feature-related information represented in the feature data collected for each road interval that are the objects of map information generation or updating to the map information.

[0074] As described above, the map update interval determination device selects a series of road intervals connecting two locations as routes connecting those two locations for each combination of two locations that can access an area where map information is generated or updated. Furthermore, for each combination of two locations, the device calculates an evaluation value representing the degree of improvement in driver convenience resulting from generating or updating map information via the route connecting those two locations. Moreover, the device determines each unmaintained section on the route between the two locations as a road interval for generating or updating map information, in descending order of the calculated evaluation values, until the cumulative map maintenance cost reaches a target maintenance cost. Therefore, the map update interval determination device can determine the road intervals that are the objects of map information generation or updating to facilitate driver access to the benefits of autonomous driving control. Additionally, since the device can determine the road intervals that are the objects of map information generation or updating even without calculating evaluation values ​​for all combinations of road intervals, it can reduce the hardware resources required to determine the road intervals.

[0075] According to a variation, the evaluation value calculation unit 42 may also calculate the evaluation value without considering the map preparation cost. For example, the evaluation value calculation unit 42 may also calculate the evaluation value as the sum of the individual interval evaluation values ​​Ei of each candidate interval located on the route, expressed by the following formula.

[0076] Ei=(Mc-Ac)*Tv

[0077] In this variation, the map update interval determination device can also achieve the same effect as the implementation described above.

[0078] According to another variation, the evaluation value calculation unit 42 can also calculate the individual interval evaluation value Ei for each candidate interval located on the route according to the following formula.

[0079] Ei=(Ac-Mc)*Tv / Sc

[0080] In this case, since the (Ac-Mc) term is negative, the lower the evaluation value, the greater the improvement in driver convenience obtained by generating or updating map information. Therefore, the combination corresponding to the minimum evaluation value among the various combinations of the two locations selected by the selection unit 41 becomes the combination with the highest improvement in driver convenience. Thus, in this modified example, the determination unit 43 only needs to sequentially determine the route containing the road sections that are the objects of map information generation or updating, starting from the route with the combination that has the minimum evaluation value, until the cumulative maintenance cost reaches the target maintenance cost.

[0081] The computer program described above, which enables a computer to perform the processing of the various parts executed by the processor 34 of the server 3, may also be recorded in a semiconductor memory device, a magnetic recording medium, or an optical recording medium and distributed.

[0082] As described above, those skilled in the art can make various modifications within the scope of this invention and according to the implemented manner.

Claims

1. A map update interval determination device, comprising: The storage unit stores map markers indicating whether map information can be used for vehicles to drive autonomously in each of the multiple road sections included in the predetermined area. The selection unit selects a series of road sections connecting two locations from a plurality of road sections as the route between the two locations for each combination of two locations selected from a plurality of locations that can access the predetermined area. The evaluation value calculation unit, for each combination of the two locations, refers to the map markers, determines the road sections in the various road sections contained in the route between the two locations that the map information cannot use as candidate sections, and calculates an evaluation value representing the degree of improvement in driver convenience obtained by generating or updating map information based on the candidate sections. as well as The determining unit, in the combination of the two locations, identifies a predetermined number of candidate intervals contained in each of the routes of each combination as road intervals to be used for generating or updating the map information, in descending order of the degree of improvement in driver convenience represented by the evaluation value. The storage unit also stores, for each of the plurality of road sections, the map preparation cost required to generate or update the map information for that road section. The determining unit, in the combination of the two locations, determines each of the candidate intervals contained in the respective routes of the combination as road intervals to be used for generating or updating the map information, in descending order of the degree of improvement in driver convenience represented by the evaluation value, until the total map preparation cost of the road intervals determined as road intervals to be used for generating or updating the map information reaches the target preparation cost.

2. The map update interval determination device according to claim 1, For each of the plurality of road sections, the storage unit also stores the traffic volume of that road section, the autonomous driving cost representing the driver's workload when the vehicle uses the map information to drive autonomously in that road section, and the manual driving cost representing the driver's workload when the vehicle drives manually in that road section. The evaluation value calculation unit calculates the sum of the values ​​obtained by weighting the difference between the manual driving cost and the autonomous driving cost by the ratio of the traffic volume to the map preparation cost for each of the candidate intervals included in the route for the two locations, and uses this sum as the evaluation value.

3. The map update interval determination device according to claim 1, For each of the plurality of road sections, the storage unit also stores the traffic volume of that road section, the autonomous driving cost representing the driver's workload when the vehicle uses the map information to drive autonomously in that road section, and the manual driving cost representing the driver's workload when the vehicle drives manually in that road section. The evaluation value calculation unit calculates the sum of the values ​​obtained by weighting the difference between the manual driving cost and the autonomous driving cost with the traffic volume for each of the candidate intervals included in the route for each of the two locations, and uses this sum as the evaluation value.

4. The map update interval determination device according to claim 1, For each of the plurality of road sections, the storage unit also stores the traffic volume of that road section and the manual driving cost, which represents the driver's workload when the vehicle is driven manually in that road section. The evaluation value calculation unit calculates, for each combination of the two locations, the sum of the values ​​obtained by weighting the manual driving cost by the ratio of traffic volume to map preparation cost for each of the candidate intervals included in the route for that combination, as the evaluation value.

5. A method for determining map update intervals, comprising: For each combination of two locations selected from a plurality of locations that can access the predetermined area, a series of road sections connecting the two locations are selected from a plurality of road sections contained in the predetermined area as the route between the two locations; For each combination of the two locations, for each road section included in the route for that combination, referring to a map marker indicating whether map information for a vehicle to drive in that road section by autonomous driving is available, the road section in which the map information is unavailable is identified as a candidate section. For each combination of the two locations, calculate an evaluation value representing the degree of improvement in driver convenience obtained by generating or updating map information based on the candidate intervals; For each of the multiple road intervals, store the map preparation cost required to generate or update the map information for that road interval; In the combination of the two locations, a predetermined number of candidate sections contained in each of the routes of the combination are determined as road sections to be the objects of the generation or updating of the map information, in descending order of the degree of improvement in driver convenience represented by the evaluation value, until the total map preparation cost of the road sections determined as the objects of the generation or updating of the map information reaches the target preparation cost.

6. A computer program product comprising a computer program for determining map update intervals, used to cause a computer to perform: For each combination of two locations selected from a plurality of locations that can access the predetermined area, a series of road sections connecting the two locations are selected from a plurality of road sections contained in the predetermined area as the route between the two locations; For each combination of the two locations, for each road section included in the route for that combination, referring to a map marker indicating whether map information for a vehicle to drive in that road section by autonomous driving is available, the road section in which the map information is unavailable is identified as a candidate section. For each combination of the two locations, calculate an evaluation value representing the degree of improvement in driver convenience obtained by generating or updating map information based on the candidate intervals; For each of the multiple road intervals, store the map preparation cost required to generate or update the map information for that road interval; In the combination of the two locations, a predetermined number of candidate sections contained in each of the routes of the combination are determined as road sections to be the objects of the generation or updating of the map information, in descending order of the degree of improvement in driver convenience represented by the evaluation value, until the total map preparation cost of the road sections determined as the objects of the generation or updating of the map information reaches the target preparation cost.

Images