Map data generation method

Abstract

To provide a map data generation method capable of generating map data including detailed information.SOLUTION: A histogram is created for positions of a plurality of vehicles 2 in the width direction of a road, and normal traveling zone information and transient traveling zone information are generated based on a position where the maximum value is obtained and a variance σ which is dispersion. This allows the map data to include more detailed information than lane width information indicating whether or not the vehicle can travel.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a method for generating map data.

Background Art

[0002] Conventionally, for the purpose of providing a lot of information to passengers, an information processing device has been proposed which includes a lane detection means for detecting a lane in which a vehicle is traveling and an adjacent lane, and an information presentation means capable of presenting information to a passenger of the vehicle (see, for example, Patent Document 1). In the information processing device described in Patent Document 1, by presenting information indicating the positional relationship between the traveling lane and the adjacent lane to the passenger, the passenger can know that the lane detection is appropriately performed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, simply detecting lanes as described in Patent Document 1 may be insufficient as information for implementing driving support and the like. For example, when detecting a lane and other moving objects, even if another moving object is traveling while wobbling within an adjacent lane, if it does not protrude from the lane, there is a possibility that this moving object will be judged to be normal. Also, there were problems in supporting driving in accordance with the actual road conditions with only information such as width and number of lanes.

[0005] Therefore, an example of the problem to be solved by the present invention is to provide a method for generating map data that can generate map data including detailed information.

Means for Solving the Problems

[0006] To solve the aforementioned problems and achieve the objective, the map data generation method of the present invention described in claim 1 is characterized by comprising: a calculation step of calculating the position of a mobile body in the road width direction relative to the road information by comparing surrounding information measured by a measuring unit mounted on a measuring mobile body with road information stored in advance; an information generation step of generating at least one of first information indicating a range in which the distribution density is greater than or equal to a predetermined value and second information indicating a range outside the range of the first information, based on the distribution of the positions of a plurality of mobile bodies in the road width direction relative to the road information; and a map data generation step of generating map data including at least one of the first information and the second information. [Brief explanation of the drawing]

[0007] [Figure 1] This is a schematic block diagram of the map data generation system according to the first embodiment of the present invention. [Figure 2] This is an example of a histogram generated by the aforementioned map data generation system. [Figure 3] This is a schematic diagram showing the normal driving zone information and transient driving zone information included in the map data generated by the aforementioned map data generation system. [Figure 4] This is a block diagram illustrating the evaluation system of the first embodiment described above. [Figure 5] This is a schematic block diagram of the driver assistance system of the second embodiment described above. [Modes for carrying out the invention]

[0008] Embodiments of the present invention will be described below. A map data generation method according to an embodiment of the present invention includes: a calculation step of calculating the position of a mobile body in the road width direction relative to road information by comparing surrounding information measured by a measuring unit mounted on a measuring mobile body with road information stored in advance; an information generation step of generating at least one of first information indicating a range in which the distribution density is greater than or equal to a predetermined value and second information indicating a range outside the range of the first information, based on the distribution of the positions of a plurality of mobile bodies in the road width direction relative to road information; and a map data generation step of generating map data including at least one of the first information and the second information.

[0009] Since the first and second pieces of information are generated based on the distribution of the positions of multiple moving objects in the road width direction, the road width direction positions corresponding to the first piece of information indicate a high frequency of movement by the moving objects, and the road width direction positions corresponding to the second piece of information indicate a low frequency of movement by the moving objects. In other words, the map data can include more detailed information than just lane width information that simply indicates whether or not a moving object can travel.

[0010] By including the first and second types of information in the map data, the map data can be used in several ways, as illustrated below. First, while standard width information may include sidewalks and median strips, making the actual drivable area unclear, generating the first and second types of information based on the distribution of the positions of multiple moving objects in the road width direction allows for the understanding of the actual drivable area and the guidance of moving objects to that area. This is particularly useful for guiding moving objects appropriately in autonomous driving. Furthermore, in manual driving, driving is performed according to road conditions, and the vehicle does not necessarily travel in the center of each lane in the width direction. Therefore, by using the first and second types of information based on the distribution of the positions of multiple moving objects in the road width direction for guidance, it becomes easier to achieve driving that is in line with actual road conditions even in autonomous driving. In addition, the behavior of other moving objects can be predicted based on the first and second types of information, and driving assistance can be provided based on the prediction results. Moreover, the driver's intentions and driving behavior can be analyzed based on the first and second types of information.

[0011] Furthermore, this method of generating map data may be carried out, for example, by an external server that acquires information from a mobile object. In this case, not all processes have to be carried out by the external server; some or all processes may be carried out by a control unit mounted on the mobile object. Also, if the surrounding information includes multiple mobile objects, the position in the road width direction should be calculated for each of the multiple mobile objects. In addition, multiple measuring mobile objects may be in motion and the external server may collect information from these mobile objects, or the external server may collect information from a single mobile object.

[0012] In the information generation process, it is preferable to generate a histogram for the positions of multiple moving objects in the road width direction, and to generate at least one of the first information and the second information based on the position of the maximum value and the degree of variation. This makes it possible to generate information that corresponds to the actual driving conditions at each position on the road. That is, if the variation in the driving position of the moving objects in the road width direction is small, the range corresponding to the first information becomes narrow, and if the variation is large, the range corresponding to the first information becomes wide.

[0013] An evaluation method according to an embodiment of the present invention generates map data including second information using the map data generation method described above, and evaluates the driving state of the driver of the moving object based on the behavior of the moving object at a position in the road width direction corresponding to the second information.

[0014] If a moving vehicle, at a position corresponding to the second piece of information in the road width direction, suddenly brakes or abruptly changes direction (orientation), it may have attempted a lane change but failed. If such behavior occurs frequently, it can be determined that the driver operating the vehicle has low skill. Furthermore, based on the behavior of the vehicle at a position corresponding to the second piece of information in the road width direction, aggressive driving or distracted driving can be identified, and the degree of safe driving can be evaluated. By evaluating driving skills and the degree of safe driving, this can be used as a basis for determining, for example, automobile insurance premiums.

[0015] The driving assistance method according to an embodiment of the present invention generates map data including second information using the map data generation method described above, predicts the subsequent behavior of another moving object based on the behavior of the other moving object at a road width direction position corresponding to the second information, and provides driving assistance to the moving object based on the predicted information.

[0016] Based on the behavior of another moving vehicle at a position in the road width direction corresponding to the second piece of information, it is possible to determine, for example, that the other moving vehicle is attempting to change lanes. That is, even before the other moving vehicle signals with its turn signal, it may be traveling at a position in the road width direction corresponding to the second piece of information, and based on this behavior, it is possible to determine that it intends to change lanes. If it is determined that the other moving vehicle intends to change lanes, the system may provide driving assistance by communicating this to the driver of the moving vehicle, or it may be reflected in the control of the automated driving system.

[0017] The driving assistance method according to an embodiment of the present invention generates map data including second information using the map data generation method described above, and when the collision prediction degree with another moving object exceeds a predetermined value, it guides the moving object to travel along a road width direction position corresponding to the second information.

[0018] The road width direction position corresponding to the second piece of information is a drivable position, although the frequency of travel by the moving vehicle is low. Therefore, for example, if the collision prediction rate exceeds a predetermined value due to another moving vehicle traveling in the opposite direction straying from its lane, the vehicle can be guided to travel to the road width direction position corresponding to the second piece of information, thereby avoiding a collision with the other moving vehicle. Furthermore, if the collision prediction rate exceeds a predetermined value, the driver of the vehicle may be shown the position to which it should travel to provide driving assistance, or this may be reflected in the control of the automated driving system.

[0019] The driving support method according to an embodiment of the present invention generates map data including first information and second information by the above-described map data generation method, detects a moving object located outside the range in the road width direction corresponding to the second information, and guides the moving body to travel at a road width direction position corresponding to the first information according to the detection status of the moving object.

[0020] When the pedestrian traffic volume on the sidewalk is large or the sidewalk width is narrow, pedestrians may walk out of the sidewalk. On roads where such situations frequently occur, the position in the road width direction corresponding to the first information may be biased to the side opposite to the sidewalk with respect to the center in the width direction of the lane. On the other hand, when pedestrians do not protrude from the sidewalk, drivers often drive so that the moving body travels at the center in the width direction of the lane, and in the case of automatic driving, it may also be controlled to travel at the center in the width direction. Thus, when the moving body travels at the center in the width direction of the lane and a moving object (such as a pedestrian) located outside the range in the road width direction corresponding to the second information is detected, by guiding the moving body to travel at the road width direction position corresponding to the first information, even when the moving object enters the lane, it is easy to suppress a collision.

[0021] Further, it may be a map data generation program that causes a computer to execute the above-described map data generation method. By doing so, map data including detailed information can be generated using a computer.

[0022] Further, the above-described map data generation program may be stored in a computer-readable recording medium. By doing so, in addition to incorporating the program into a device, it can be distributed alone, and version updates and the like can be easily performed.

Example

[0023] Hereinafter, embodiments of the present invention will be specifically described.

[0024] <First Embodiment> In this embodiment, map data is generated by a map data generation system 1 as shown in Figure 1, and the driver's driving condition is evaluated using the map data by an evaluation system 10 as shown in Figure 4.

[0025] [Map Data Generation System] The map data generation system 1 comprises multiple vehicles (mobile devices) 2 and an external server (information processing device) 3. The vehicles 2 may be ordinary vehicles or measurement vehicles specifically designed for generating map data.

[0026] Vehicle 2 is equipped with an information acquisition unit 20, which comprises a position measuring unit 21, a measuring unit 22, a communication unit 23, a storage unit 24, and a vehicle-side control unit 25.

[0027] The position measurement unit 21 measures the current position (absolute position) of the vehicle 2, and can be, for example, a GPS receiver that receives radio waves transmitted from multiple GPS (Global Positioning System) satellites. The position measurement unit 21 only needs to acquire latitude and longitude information as the current position of the vehicle 2.

[0028] The measurement unit 22 is capable of measuring surrounding information and can be, for example, an optical sensor (so-called LIDAR; Light Detection and Ranging or Laser Imaging Detection and Ranging) that projects light and receives reflected light from an object being illuminated. In this case, the surrounding information can be point cloud data obtained by the optical sensor. Alternatively, a video camera or the like may be used as the measurement unit 22, and the surrounding information may be measured by (VSLAM; Visual Simultaneous Localization and Mapping).

[0029] The communication unit 23 consists of circuits and antennas for communicating with networks such as the internet or public telephone lines, and communicates with the external server 3 to send and receive information. The communication unit 23 may also only transmit information to the external server 3. Alternatively, a removable storage medium may be provided instead of the communication unit 23, allowing the operator to transfer data to the external server 3 by removing this storage medium.

[0030] The memory unit 24 is composed of, for example, a hard disk or non-volatile memory, and stores information for self-position estimation. That is, when the position measurement unit 21 measures the current position, it is possible to perform map matching using the self-position estimation information.

[0031] The vehicle-side control unit 25 is composed of a CPU (Central Processing Unit) equipped with memory such as RAM (Random Access Memory) and ROM (Read Only Memory), and is responsible for the overall control of the information acquisition unit 20.

[0032] The external server 3 comprises a storage unit 31, a communication unit 32, and a server-side control unit 33. It is physically separated from the vehicle 2 and can communicate with the vehicle 2 via a network such as the Internet. It is configured to collect, process, and store information from the vehicle 2. The part of the external server 3 that stores information and the part that processes information may be physically separated.

[0033] The storage unit 31 is composed of, for example, a hard disk or non-volatile memory, and stores road information, which is read and written under control from the server-side control unit 33. The road information includes matching information corresponding to point cloud data, and road configuration information including the structure of the road in the width direction and the width information of each part.

[0034] The matching information can include, for example, information about features or white lines. That is, by comparing the point cloud data obtained by the optical sensor that corresponds to features or white lines with the matching information, it is possible to determine that the point cloud that does not overlap with the matching information and is located on the lane corresponds to another vehicle (moving object).

[0035] Table 1 shows an example of road configuration information.

[0036] [Table 1]

[0037] The road configuration information shown in Table 1 includes, for each road link ID, the start and end nodes, the lane link ID, and the lane width for each lane link. The number of lane link IDs corresponds to the number of lanes on that road.

[0038] The communication unit 32 consists of circuits, antennas, etc., for communicating with networks such as the Internet or public telephone lines, and communicates with the vehicle 2 to send and receive information.

[0039] The server-side control unit 33 is composed of a CPU (Central Processing Unit) equipped with memory such as RAM (Random Access Memory) and ROM (Read Only Memory), and is responsible for the overall control of the external server 3. As will be described later, it processes the information acquired from the vehicle 2 and stores the processed information in the storage unit main body 31.

[0040] An example of a specific method for generating map data in the map data generation system 1 described above will be explained.

[0041] First, surrounding information is obtained by performing measurements using the measurement unit 22 while vehicle 2 is in motion. The obtained surrounding information is combined with the current position information of vehicle 2 at the time of measurement and transmitted to the external server 3 via the communication unit 23. By repeating the above process, the external server 3 collects multiple pieces of surrounding information. In addition, the external server 3 collects surrounding information from multiple vehicles 2.

[0042] The server-side control unit 33 extracts point clouds corresponding to other vehicles for each of the collected surrounding information and calculates the widthwise position of the other vehicles relative to the reference position (calculation step). That is, it uses the position information corresponding to the current position information from the matching information and compares it with the surrounding information, which is point cloud data. This makes it possible to extract point clouds corresponding to other vehicles and point clouds representing the reference position from the point cloud data. The reference position can be the position of a specific white line (for example, the white line closest to the sidewalk) or a median strip. Based on the point clouds corresponding to other vehicles and the point clouds representing the reference position, the widthwise position of the other vehicles can be calculated.

[0043] The position of another vehicle in the road width direction is the range within which the other vehicle exists. For example, in a lane with a width of 3m, if the distance from the white line, which is the reference position (origin), to one end of the other vehicle in the road width direction is 0.5m and the distance to the other end in the road width direction is 2.3m (i.e., the width dimension of the other vehicle is 1.8m), then the range from 0.5 to 2.3m from the origin is the position of the other vehicle in the road width direction.

[0044] If a single set of surrounding information includes point cloud data of multiple other vehicles, the road width direction position of each of these other vehicles is calculated.

[0045] The server-side control unit 33 generates a histogram for each road link, showing the widthwise positions of other vehicles from a reference position. Based on the position of the maximum value and the degree of variation, it generates normal lane information as first information and transient lane information as second information (information generation process). The histogram, as shown in Figure 2 for example, is divided into appropriate units with the horizontal axis representing the widthwise position (m), which is the distance from the origin, and the vertical axis representing the number of distributions (items).

[0046] For example, a lane with a width of 3m is divided into 10cm sections, creating areas 1 through 30 from the origin. If the position of other vehicles in the road width direction is within the range of 0.5 to 2.3m from the origin, then the distribution count is 1 for each of areas 6 through 23.

[0047] When a histogram is generated in this way, the distribution number is maximized near the center of the lane in the width direction. Furthermore, the standard deviation σ can be calculated as the variability at the road width position. The area within ±2σ of the road width position where the distribution number is maximized is defined as the normal driving zone, and the area outside of this zone but within the lane is defined as the transient driving zone. If there are multiple lanes, information for both the normal and transient driving zones is generated for each lane. In this case, histograms may be generated independently for multiple lanes, or they may be generated together.

[0048] In the example shown in Figure 2, the area from 0.3 to 2.1 m from the origin becomes the normal driving zone, while the area from 0.3 m from the origin and the area from 2.1 to 3 m become the transient driving zones. Thus, areas with a high distribution density of other vehicles in the road width direction become the normal driving zones, and areas with a low distribution density become the transient driving zones. Alternatively, a threshold for distribution density may be set, and the area where the distribution density exceeds this threshold may be designated as the normal driving zone. In this case, the threshold for distribution density may be set according to the width, for example, and may differ from one another for each road link.

[0049] In the method described above, the range where other vehicles exist was used as the road width direction position of other vehicles when generating the histogram, but the central position of other vehicles in the road width direction may also be used. Alternatively, a histogram can be generated using the central position, the range of the central position can be calculated based on the position of the maximum and the variability, and the normal driving lane can be determined by adding an appropriate vehicle width to this range.

[0050] The server-side control unit 33 generates map data that includes normal lane information and transient lane information (map data generation process). First, by adding normal lane information and transient lane information to the road configuration information shown in Table 1, detailed road configuration information as shown in Table 2 is generated.

[0051] [Table 2]

[0052] The detailed road configuration information shown in Table 2 includes not only the lane width but also information about the location of the normal and transient driving lanes within the lane. This defines the normal and transient driving lanes as shown in Figure 3. Furthermore, as will be described later, when performing various processes using the normal and transient driving lane information, the width of the normal driving lane may be increased or decreased depending on the size (width) of the vehicle in question. That is, in the case of large vehicles, even when driving normally, they are more likely to deviate from the normal driving lane, so the normal driving lane may be widened as a correction. Also, although Table 2 above shows an example when there is one lane, if there are multiple lanes, detailed road configuration information will be generated for each lane.

[0053] The server-side control unit 33 generates map data including detailed road configuration information and stores it in the storage unit main body 31. The map data may also include information about features around the roads, in addition to detailed road configuration information.

[0054] [Evaluation System] As shown in Figure 4, the evaluation system 10 comprises an evaluation target vehicle (mobile device) 4 and an external server (information processing device) 3.

[0055] The vehicle under evaluation 4 is equipped with an information acquisition unit 40, which comprises a position measuring unit 41, a measuring unit 42, a communication unit 43, a storage unit 44, a vehicle-side control unit 45, and a behavior measuring unit 46. Each of the parts 41 to 45 of the information acquisition unit 40 has the same configuration as each of the parts 21 to 25 of the information acquisition unit 20 of vehicle 2.

[0056] The behavior measurement unit 46 is for measuring the displacement of the vehicle under evaluation 4 as part of its behavior, and consists of, for example, a vehicle speed pulse acquisition unit that acquires the vehicle speed pulse of the vehicle under evaluation 4, a gyro sensor for measuring the azimuth displacement of the vehicle under evaluation 4, and an acceleration sensor for acquiring the acceleration of the vehicle under evaluation 4. The behavior measurement unit 46 provides behavior information of the vehicle under evaluation 4.

[0057] When the vehicle under evaluation 4 is in motion, the vehicle-side control unit 45 combines surrounding information and behavioral information with the current location information of the vehicle under evaluation 4 at the time of measurement, and transmits it to the external server 3 via the communication unit 43.

[0058] In this embodiment, the external server 3 for map data generation and the external server 3 for evaluation are assumed to be the same, but different external servers may be used.

[0059] In the evaluation system 10 described above, an example of a specific method for evaluating the driving condition of the driver of the vehicle under evaluation 4 will be explained.

[0060] The server-side control unit 33 calculates the position of the vehicle under evaluation 4 in the road width direction on each road link based on the surrounding information measured by the measurement unit 42 and the matching information stored in the storage unit main body 31. Based on the position of the vehicle under evaluation 4 in the road width direction and the normal lane information and transient lane information on each road link, it is possible to determine which lane the vehicle under evaluation 4 traveled in. Whether or not the vehicle under evaluation 4 traveled in a transient lane may be determined based on whether or not at least a part of the vehicle under evaluation 4 entered the transient lane, or it may be determined based on whether or not a specific part of the vehicle under evaluation 4 (for example, the center in the width direction) entered the transient lane.

[0061] The server-side control unit 33 determines whether the behavior of the vehicle under evaluation 4 meets predetermined conditions for the road link through which the vehicle under evaluation 4 traveled in the transient zone.

[0062] For example, if the acceleration of vehicle 4 under evaluation is negative and its absolute value is greater than or equal to a predetermined value, it can be determined that vehicle 4 under evaluation is decelerating rapidly in the transient zone. Such rapid deceleration can occur when attempting to change lanes but nearly colliding with a surrounding vehicle. Therefore, if vehicle 4 under evaluation frequently decelerates rapidly in the transient zone, it can be determined that the driver has difficulty predicting the movements of surrounding vehicles and has poor driving skills.

[0063] Furthermore, if the directional displacement of vehicle 4 under evaluation exceeds a predetermined value, it can be determined that vehicle 4 changed direction by sudden steering in the transient driving zone. Such a change in direction can occur when attempting to change lanes but nearly colliding with a surrounding vehicle. Therefore, if vehicle 4 frequently changes direction in the transient driving zone, it can be determined that the driver has difficulty predicting the movements of surrounding vehicles and has poor driving skills.

[0064] Furthermore, if the frequency of vehicle 4 entering and exiting the transitional lane from the normal lane (number of entries and exits per predetermined time) exceeds a predetermined value, it can be determined that vehicle 4 is engaging in aggressive driving, or driving in a manner that is perceived as aggressive driving by those around it. In such cases, it can be determined that the driver's level of safe driving is low. Note that depending on crosswinds and road conditions, the vehicle body may shake unintentionally, causing repeated entries and exits from the normal lane to the transitional lane even without aggressive driving. Therefore, it may be possible to measure the time spent in the transitional lane and determine whether aggressive driving is occurring if the entry time exceeds a threshold.

[0065] Furthermore, if the time spent by the vehicle under evaluation (Vehicle 4) in the transient lane exceeds a predetermined value, or if the angle between the vehicle's direction of travel and the road's direction of travel in the transient lane is below a predetermined value, it can be determined that the driver's level of alertness is low. In other words, if the driver is feeling drowsy or driving inattentively, they tend to stay in the transient lane for a long time. Also, if the driver is feeling drowsy or driving inattentively, the angle between the vehicle's direction of travel and the road's direction of travel when entering the transient lane from the normal lane tends to be smaller compared to intentional entry into the transient lane, such as a lane change. In such cases, it can be determined that the driver's level of safe driving is low.

[0066] Furthermore, by collecting data on the behavior of each vehicle under evaluation (4) in the transient driving zone, it is possible to determine the driver's driving tendencies. For example, if a driver frequently enters the transient driving zone, it can be determined that the driver is prone to frustration.

[0067] As described above, the server-side control unit 33 can evaluate the driver's driving state based on the behavior of the vehicle under evaluation 4 in the transient driving zone. This information on driving state is used to evaluate the driver and can be used as a basis for determining automobile insurance premiums, etc., or, in the case of elderly drivers, as a basis for deciding whether to surrender their driver's license. In other words, the transient driving zone is normally an area where drivers perform preparatory or preliminary actions for the next action (such as changing lanes or turning left or right), and staying in such an area for a long time or performing sudden acceleration or deceleration in such an area can induce an accident. Therefore, the driver's driving state can be evaluated based on the behavior of the vehicle under evaluation 4 in the transient driving zone.

[0068] With the above configuration, by generating normal lane information and transient lane information based on the distribution of the positions of multiple vehicles 2 in the road width direction, it is possible to include more detailed information in the map data than just lane width information that simply indicates whether or not a vehicle can travel.

[0069] Furthermore, by evaluating the driver's driving condition based on the behavior of the vehicle 4 being evaluated in the transient driving zone, it is possible to assess the driver's driving skills and safe driving level, which can then be used as a basis for determining automobile insurance premiums, etc.

[0070] <Second Example> In this embodiment, map data is generated by a map data generation system 1 as shown in Figure 1, and the driver's driving state is evaluated using the map data by a driving support system 100 as shown in Figure 5.

[0071] [Driving assistance system] The driver assistance system 100 comprises a vehicle to be supported (mobile) 5, which is a manually driven vehicle, and an external server (information processing device) 3.

[0072] The vehicle 5 to be supported is equipped with a driver support unit 50, which comprises a position measuring unit 51, a measuring unit 52, a communication unit 53, a storage unit 54, a vehicle-side control unit 55, and an information output unit 56. The parts 51 to 55 of the information acquisition unit 40 have the same configuration as the parts 21 to 25 of the information acquisition unit 20 of the vehicle 2.

[0073] The information output unit 56 is composed of, for example, an audio output unit such as a speaker and a display unit such as a screen, and is configured to output information to the passenger. If the vehicle to be assisted 5 is an autonomous vehicle, a driving control unit may be provided instead of the information output unit 56.

[0074] The vehicle-side control unit 55 acquires matching information and detailed road configuration information from the external server 3 via the communication unit 53 and stores them in the storage unit 54. The vehicle-side control unit 55 compares the surrounding information, which is point cloud data measured by the measurement unit 52, with the matching information to extract point clouds of objects not included in the matching information. Among the objects not included in the matching information, those located on the roadway can be determined to be other vehicles, and those located on the sidewalk can be determined to be pedestrians, bicycles, etc.

[0075] (Driving assistance based on predicting the behavior of other vehicles) If a point cloud corresponding to another vehicle is extracted, the vehicle-side control unit 55 calculates the position of this other vehicle in the road width direction by comparing it with a reference position included in the matching information, and determines whether this other vehicle is traveling in the normal lane or the transient lane. Furthermore, the vehicle-side control unit 55 calculates the direction of travel of the other vehicle and the distance between the other vehicle and the vehicle being supported 5 in the road width direction.

[0076] The vehicle-side control unit 55 predicts the subsequent behavior of other vehicles based on their behavior in the transient lane. For example, if another vehicle enters the transient lane from the normal lane and the angle between the vehicle's direction of travel and the road's direction of travel is greater than a predetermined value, it can be determined that the other vehicle entered the transient lane intentionally. Therefore, it is predicted that the driver of the other vehicle intends to change lanes.

[0077] The vehicle-side control unit 55 outputs information to the information output unit 56 when it detects that another vehicle is intending to change lanes. At this time, it may output that there is a possibility that the other vehicle is changing lanes, or it may instruct the vehicle to accelerate or decelerate so as not to obstruct the lane change, or to instruct the vehicle to prohibit the lane change. For example, if it is determined that another vehicle traveling adjacent to the vehicle in the direction of the road width is about to change lanes, it should instruct the vehicle to decelerate, and if it is determined that a following vehicle is about to change lanes, it should instruct the vehicle to prohibit the lane change to avoid double overtaking.

[0078] Furthermore, if the vehicle being supported 5 is an autonomous vehicle, the vehicle-side control unit 55 should send commands to the driving control unit to accelerate or decelerate or prohibit overtaking, as described above.

[0079] (Driving assistance when collision with another vehicle is predicted) The vehicle-side control unit 55 calculates the likelihood of a collision with the oncoming vehicle based on the distance between the vehicle and the vehicle being supported in the road width direction. For example, if an emergency vehicle such as an ambulance crosses the center line in the oncoming lane to overtake, the distance between the emergency vehicle and the vehicle being supported 5 narrows, increasing the likelihood of a collision. In such cases, it is preferable for the vehicle being supported 5 to avoid the emergency vehicle in order to prioritize its passage.

[0080] Therefore, if the collision prediction rate with an oncoming vehicle exceeds a predetermined value, the vehicle-side control unit 55 instructs the information output unit 56 to drive in the transient lane located on the opposite side of the oncoming vehicle. If the vehicle being supported 5 is an autonomous vehicle, the vehicle-side control unit 55 only needs to send a command to the driving control unit to drive in the transient lane located on the opposite side of the oncoming vehicle.

[0081] (Driving assistance when pedestrians are present) On sidewalks with heavy pedestrian traffic or narrow sidewalks, pedestrians may sometimes extend beyond the sidewalk. On roads where this frequently occurs, the normal driving lane may be biased away from the sidewalk relative to the center of the lane in the width direction. On the other hand, when pedestrians are not extending beyond the sidewalk, drivers often drive the vehicle being supported (Vehicle 5) to stay in the center of the lane in the width direction, and the vehicle may unintentionally drive in the transitional driving lane.

[0082] If a point cloud located on the sidewalk is extracted and its density or absolute number exceeds a predetermined value, it is estimated that there are many pedestrians. In such cases, the vehicle-side control unit 55 instructs the information output unit 56 to output information to drive in the normal lane. If the vehicle being supported 5 is an autonomous vehicle, the vehicle-side control unit 55 only needs to send a command to the driving control unit to drive in the normal lane.

[0083] (Driving assistance during snowy conditions) Drivers who are familiar with the road conditions when there is no snow will drive in a way that avoids ditches and other obstacles that become invisible when there is snow. If there is a discrepancy between the normal driving lane and the center of the lane in the width direction, drivers who are not familiar with the road conditions when there is no snow may not be aware of the presence of ditches and other obstacles and may attempt to drive in the center of the combined area of ​​the lane and the ditches in the width direction. In such cases, the vehicle control unit 55 will output information to the information output unit 56 to drive in the normal driving lane.

[0084] Furthermore, if the vehicle being supported 5 is an autonomous vehicle, the vehicle-side control unit 55 only needs to send a command to the driving control unit to drive in the normal lane. In this way, the vehicle being supported 5 will be able to drive more easily on the ruts formed by the driving of a driver who is familiar with the road conditions when there is no snow.

[0085] With the above configuration, by using map data that includes normal lane information and transient lane information to assist driving, collisions with other vehicles, pedestrians, etc., can be suppressed. In addition, in autonomous driving, the vehicle can travel in a position in the road width direction similar to manual driving, reducing anxiety for passengers.

[0086] Furthermore, the present invention is not limited to the embodiments described above, and includes other configurations that can achieve the objectives of the present invention, as well as the following modifications.

[0087] For example, in the above embodiment, the calculation process for generating map data, the information generation process, and the map data generation process are all performed on the external server 3 side, but some or all of each process may be performed on the vehicle side.

[0088] Furthermore, in the above embodiment, a histogram was generated for the positions of multiple vehicles 2 in the road width direction, and the range within ±2σ from the position of the maximum value was determined to be the normal driving zone. However, the method of determination is not limited to this. For example, the range based on the position of the maximum value may be made even narrower or wider. Alternatively, an absolute value of the distribution number may be defined, and positions beyond this absolute value may be considered the normal driving zone.

[0089] Furthermore, while the best configurations and methods for carrying out the present invention are disclosed in the above description, the present invention is not limited thereto. That is, although the present invention is particularly illustrated and described with respect to specific embodiments, those skilled in the art can make various modifications to the embodiments described above in terms of shape, material, quantity, and other detailed configurations without departing from the scope of the technical idea and objectives of the present invention. Therefore, the descriptions of shapes, materials, etc. disclosed above are illustrative to facilitate understanding of the present invention and do not limit the present invention. Accordingly, descriptions of components with some or all of these limitations removed are included in the present invention. [Explanation of Symbols]

[0090] 1. Map Data Generation System 2 vehicles 3. External Servers 4. Vehicles to be evaluated 5. Vehicles eligible for support 10. Evaluation System 100 Driver Assistance Systems

Claims

1. An evaluation method performed by a server, The map data generation method, executed by the server, is characterized by comprising: a calculation step of calculating the position of a mobile body in the road width direction relative to the road information by comparing surrounding information measured by a measuring unit mounted on a measuring mobile body with pre-stored road information; an information generation step of generating at least one of first information indicating a range where the distribution density is greater than or equal to a predetermined value, and second information indicating a range outside the range of the first information, based on the distribution of the positions of a plurality of mobile bodies in the road width direction relative to the road information; and a map data generation step of generating map data that includes at least one of the first information and the second information. An evaluation method characterized by evaluating the driving state of the driver of a moving body based on the acceleration of the moving body at a position in the road width direction corresponding to the second information, or the direction of travel of the moving body.

2. The evaluation method according to claim 1, wherein in the information generation step of the map data generation method, a histogram is generated for the positions of the plurality of moving bodies in the road width direction, and at least one of the first information and the second information is generated based on the position of the maximum value and the degree of variation.

3. A driver assistance method executed by a server, The map data generation method, executed by the server, is characterized by comprising: a calculation step of calculating the position of a mobile body in the road width direction relative to the road information by comparing surrounding information measured by a measuring unit mounted on a measuring mobile body with pre-stored road information; an information generation step of generating at least one of first information indicating a range where the distribution density is greater than or equal to a predetermined value, and second information indicating a range outside the range of the first information, based on the distribution of the positions of a plurality of mobile bodies in the road width direction relative to the road information; and a map data generation step of generating map data that includes at least one of the first information and the second information. A driving assistance method characterized by predicting whether or not another moving object will change lanes based on the behavior of that other moving object at a position in the road width direction corresponding to the second piece of information, and outputting information for driving assistance to the moving object when it is predicted that the other moving object will change lanes.

4. The driving assistance method according to claim 3, wherein in the information generation step of the map data generation method, a histogram is generated for the positions of the plurality of moving bodies in the road width direction, and at least one of the first information and the second information is generated based on the position of the maximum value and the degree of variation.

5. An evaluation method performed by a server, An evaluation method characterized by evaluating the driving state of the driver of a moving object based on the acceleration of the moving object at a position in the road width direction corresponding to a predetermined range, or the direction of travel of the moving object, within a range where the distribution density based on the distribution of the positions of multiple moving objects in the road width direction is less than or equal to a predetermined value.

6. The evaluation method according to claim 5, wherein the position of the plurality of moving bodies in the road width direction is calculated by comparing surrounding information measured by a measuring unit mounted on a measuring moving body with road information stored in advance.

7. A driver assistance method executed by a server, A driving assistance method characterized by predicting whether or not another moving object will change lanes based on the behavior of another moving object at a position in the road width direction corresponding to a predetermined value, within a range where the distribution density based on the distribution of positions of multiple moving objects in the road width direction is below a predetermined value, and outputting information for driving assistance to the moving object when it is predicted that the other moving object will change lanes.

8. The driving assistance method according to claim 7, wherein the position of the plurality of moving bodies in the road width direction is calculated by comparing surrounding information measured by a measuring unit mounted on a measuring moving body with road information stored in advance.

Images