JP7809247B2 - Travel information generating device, map data generating system, and travel information generating method - Google Patents

Description

This disclosure relates to a driving information generating device that generates information regarding vehicle driving, particularly information regarding lane changes.

For example, Patent Document 1 below discloses a driving assistance device that generates a risk map for each lane based on the vehicle's surrounding conditions obtained by analyzing images of the vehicle's surroundings captured by an onboard camera, and encourages the driver to drive in lanes with lower risk.

Japanese Patent Application Laid-Open No. 2021-123254

Information indicating the lane a vehicle should be traveling in, such as the risk map in Patent Document 1, is useful information for determining whether or not to change lanes and helps drivers drive smoothly. Therefore, improving the accuracy of information indicating the lane a vehicle should be traveling in is an important issue.

This disclosure has been made to solve the above problems and aims to provide technology that generates information that can contribute to improving the accuracy of information indicating the lane in which a vehicle should be traveling.

The driving information generating device according to the present disclosure includes a position information acquiring unit that acquires information about the position of the vehicle, a driving lane information acquiring unit that acquires driving lane information indicating the lane in which the vehicle is traveling, a vehicle state information acquiring unit that acquires vehicle state information that is information including at least one of the driving state of the vehicle and the state of the driver of the vehicle, a surrounding information acquiring unit that acquires surrounding information that is information about the surrounding conditions of the vehicle, an intention estimating unit that detects a lane change of the vehicle from the driving lane information and estimates whether the intention to change lanes was a smooth intention, that is, an intention to drive the vehicle smoothly, based on the vehicle state information or surrounding information before and after the lane change of the vehicle, and a lane change information generating unit that generates lane change information that includes the position of the lane change, the lanes before and after the lane change, and the estimated result of the intention to change lanes.

According to the present disclosure, lane change information is generated that includes information on past lane change intentions, which can contribute to improving the accuracy of information indicating whether or not a lane change is necessary.

The objects, features, aspects, and advantages of the present disclosure will become more apparent from the following detailed description and accompanying drawings.

1 is a diagram showing a configuration of a driving information generating device according to a first embodiment; FIG. 10 is a diagram illustrating an example of a logic for estimating an intention to change lanes. FIG. 10 is a diagram illustrating an example of a logic for estimating an intention to change lanes. FIG. 10 is a diagram illustrating an example of a logic for estimating an intention to change lanes. FIG. 10 is a diagram illustrating an example of a logic for estimating an intention to change lanes. FIG. 10 is a diagram illustrating an example of a logic for estimating an intention to change lanes. FIG. 10 is a diagram illustrating an example of lane change information. FIG. 10 is a diagram illustrating an example of lane change information. 4 is a flowchart showing the operation of the driving information generating device according to the first embodiment. 10 is a flowchart showing the operation of the traveling information generating device according to the second embodiment; FIG. 10 is a diagram showing the configuration of a driving information generating device according to a third embodiment. 10 is a flowchart showing the operation of a map data generating unit. FIG. 4 is a diagram illustrating an example of lane change assistance information included in map data stored in a map database. FIG. 2 is a diagram illustrating an example of map data stored in a map database. FIG. 10 is a diagram for explaining a modified example of the driving information generating device according to the third embodiment. FIG. 10 is a diagram for explaining a modified example of the driving information generating device according to the third embodiment. FIG. 10 is a diagram showing the configuration of a driving information generating device according to a fourth embodiment. FIG. 10 is a diagram for explaining the operation of the driving information generating device according to the fourth embodiment. FIG. 10 is a diagram for explaining the operation of the driving information generating device according to the fourth embodiment. FIG. 2 is a diagram illustrating an example of a hardware configuration of a driving information generating device. FIG. 2 is a diagram illustrating an example of a hardware configuration of a driving information generating device.

First Embodiment
FIG. 1 is a diagram showing the configuration of a driving information generating device 10 according to the first embodiment. In this embodiment, the driving information generating device 10 is mounted on a vehicle 100, and hereinafter, the vehicle 100 on which the driving information generating device 10 is mounted is referred to as the "host vehicle." However, the driving information generating device 10 does not need to be permanently installed on the host vehicle 100. In addition, the driving information generating device 10 may be implemented on a mobile terminal capable of communicating with the host vehicle 100, such as a mobile phone, a smartphone, or a PND (Portable Navigation Device).

As shown in Figure 1, the driving information generating device 10 is connected to a locator 21, a surrounding detection device 22, and an in-vehicle LAN 23 equipped in the vehicle 100, and is configured to be able to record data on a recording medium 24.

The locator 21 is equipped with high-precision map data (HD map data) containing road shape information on a lane-by-lane basis and a high-precision positioning unit, and compares the measured position of the vehicle 100 with the high-precision map data to identify the road and lane on which the vehicle 100 is traveling. The driving information generating device 10 can obtain information on the position of the vehicle 100 and the road and lane on which the vehicle is traveling from the locator 21.

The surroundings detection device 22 is composed of, for example, LiDAR (Light Detection and Ranging), an on-board camera, an image processing device, etc., and detects the surrounding conditions of the vehicle 100. The driving information generating device 10 can obtain information about the surrounding conditions of the vehicle 100 from the surroundings detection device 22, such as the position, movement direction, and movement speed of other vehicles and obstacles present around the vehicle 100.

The in-vehicle LAN 23 is a network within the vehicle 100, and the driving information generating device 10 can acquire information on the driving state of the vehicle 100 and information on the state of the driver of the vehicle 100 from the in-vehicle LAN 23. Information on the driving state of the vehicle 100 includes, for example, speed, acceleration, and direction of travel. Information on the state of the driver of the vehicle 100 may include, for example, information on driving operations such as steering angle and accelerator depression, as well as information on the driver's line of sight, facial expression, and posture acquired by a DMS (Driver Monitoring System).

The recording medium 24 may be any type of medium on which the vehicle 100 can record data.

The driving information generating device 10 includes a position information acquisition unit 11, a driving lane information acquisition unit 12, a vehicle state information acquisition unit 13, a surrounding information acquisition unit 14, an intention estimation unit 15, and a lane change information generating unit 16.

The location information acquisition unit 11 acquires information on the location of the vehicle 100 from the locator 21.

The driving lane information acquisition unit 12 acquires driving lane information indicating the lane in which the vehicle 100 is traveling from the locator 21.

The vehicle state information acquisition unit 13 acquires vehicle state information from the in-vehicle LAN 23, which includes information on at least one of the driving state of the vehicle 100 and the state of the driver of the vehicle 100.

The surrounding information acquisition unit 14 acquires surrounding information, which is information about the surrounding conditions of the vehicle 100, from the surrounding detection device 22.

The intention estimation unit 15 detects a lane change by the vehicle 100 from the driving lane information acquired by the driving lane information acquisition unit 12. The intention estimation unit 15 also estimates whether the detected lane change intention was a smooth intention, i.e., an intention to drive the vehicle 100 smoothly, based on the vehicle state information acquired by the vehicle state information acquisition unit 13 or the surrounding information acquired by the surrounding information acquisition unit 14.

The lane change information generation unit 16 generates lane change information, which is information on lane changes made by the vehicle 100. The lane change information includes the location of the lane change, the lanes before and after the lane change, and the estimation result of the intention for the lane change by the intention estimation unit 15. The location of the lane change is determined from the position of the vehicle 100 acquired by the position information acquisition unit 11 when the lane change is detected, and the lanes before and after the lane change are determined from the driving lane information acquired by the vehicle state information acquisition unit 13 before and after the lane change is detected. The lane change information generated by the lane change information generation unit 16 is recorded on the recording medium 24.

Here, we will explain the logic used by the intention estimation unit 15 to estimate the intention to change lanes. Any logic may be used to estimate the intention to change lanes, but the following estimation logic can be applied. Note that in Figures 2 to 6 shown below, the oncoming lane of the lane in which the vehicle 100 is traveling is omitted. Also, the vehicle marked with the symbol "101" is another vehicle.

For example, the intention estimation unit 15 may estimate that the intention to change lanes is a smooth intention if the traveling speed of the host vehicle 100 after the lane change is higher than the traveling speed of the host vehicle 100 before the lane change and the difference is equal to or greater than a predetermined threshold. That is, as shown in FIG. 2, the position of the host vehicle 100 at time t1 before the lane change is P(t1) and the speed is V(t1), and as shown in FIG. 3, the position of the host vehicle 100 at time t2 after the lane change is P(t2) and the speed is V(t2), and the threshold value is Vth1. If the relationship V(t2) ≧ V(t1) + Vth1 holds, the intention estimation unit 15 may estimate that the intention to change lanes is a smooth intention.

The threshold value Vth1 is, for example, 10 km/h. The speed V(t) may also be the average value over a certain period (for example, 5 seconds) or a certain distance (for example, 50 m). If the time between time t1 and time t2 is extremely short, the above formula will not hold, so it is preferable to set time t2 approximately 5 seconds after time t1.

The intention estimation unit 15 may also estimate the traveling speed of the host vehicle 100 if the vehicle were to travel without changing lanes, and if the traveling speed of the host vehicle 100 after the lane change is higher than the estimated traveling speed of the host vehicle 100 if the vehicle were to travel without changing lanes and the difference is equal to or greater than a predetermined threshold, may estimate the intention to change lanes as a smooth lane change. That is, as shown in FIG. 4, the position of the host vehicle 100 at time t2 after the lane change is P(t2), the speed is V(t2), the estimated position of the host vehicle 100 at time t2 if the vehicle were to travel without changing lanes is PE(t2), the estimated speed is VE(t2), and the threshold is Vth2. If the relationship V(t2) ≥ VE(t2) + Vth2 holds, the intention estimation unit 15 may estimate the intention to change lanes as a smooth lane change. The estimated speed VE(t2) can be estimated from the status of moving objects around the vehicle 100, such as whether there is traffic congestion or whether there are stopped vehicles, which is included in the surrounding information acquired by the surrounding information acquisition unit 14.

The threshold value Vth2 may be the same as or different from Vth1. If the lane before the lane change is congested or if there are stopped vehicles in the lane before the lane change, it is preferable to set Vth2 > Vth1. For example, the threshold value Vth2 may be set to 15 km/h.

The intention estimation unit 15 may also estimate the intention to change lanes as a smooth lane change if there is a driving obstruction ahead of the vehicle 100 in the lane before the lane change and no driving obstruction ahead of the vehicle 100 in the lane after the lane change. Driving obstructions include, for example, obstacles, stopped vehicles (such as buses with passengers boarding or disembarking), and traffic jams. Traffic jams, such as right-turn wait traffic at intersections or forks, and left-turn wait traffic near parking lot entrances, occur on a lane-by-lane basis. For example, as shown in Figure 5, if there is a driving obstruction traffic jam (left-turn wait traffic) ahead of the vehicle 100 in the lane before the lane change and no traffic jam ahead of the vehicle 100 in the lane after the lane change, as shown in Figure 6, the intention to change lanes is estimated as a smooth lane change. The presence or absence of driving obstructions on each lane can be determined from the surrounding information acquired by the surrounding information acquisition unit 14.

The intention estimation unit 15 may also calculate the level of the collision risk of the host vehicle 100 with an obstacle before and after a lane change, and if the collision risk after the lane change is lower than the collision risk before the lane change and the difference is equal to or greater than a predetermined threshold, estimate the lane change intention as a smooth intention. The collision risk of the host vehicle 100 with an obstacle in each lane can be determined from information about obstacles ahead of the host vehicle 100 contained in the surrounding information acquired by the surrounding information acquisition unit 14. Obstacles that are subject to collision risk are not limited to those located in the lane in which the host vehicle 100 is traveling, but may also include, for example, pedestrians or bicycles that may jump out from the sidewalk, other vehicles that may change lanes from an adjacent lane into the lane in which the host vehicle 100 is traveling, and other vehicles located behind the host vehicle 100 that may rear-end the host vehicle 100.

The intention estimation unit 15 may also estimate that the intention to change lanes is a smooth intention if the driver's psychological discomfort index (irritation, tension) after changing lanes is lower than the driver's psychological discomfort index before changing lanes and the difference is equal to or greater than a predetermined threshold. The driver's psychological discomfort index can be determined from information about the driver's vehicle state (e.g., the driver's line of sight, facial expression, physiological measurements, etc.) included in the vehicle state information acquired by the vehicle state information acquisition unit 13.

The intention estimation unit 15 may estimate the intention to change lanes using two or more of the five estimation logics described above, and then estimate the intention to change lanes comprehensively from the estimation results. Furthermore, when two or more estimation logics are used, the threshold value for estimating whether or not the intention is smooth (e.g., Vth1 or Vth2 described above) may be lowered compared to when only one estimation logic is used.

Next, we will explain the lane change information generated by the lane change information generation unit 16. For example, if the host vehicle 100 changes lanes at point Pn (n = 1, 2, ...) shown in Figure 7, the lane change information generation unit 16 generates lane change information as shown in Figure 8. Figure 8 is an example of lane change information data. Each piece of lane change information shown in Figure 8 includes information on the data ID, the lane change location, the date and time of the lane change, the lanes before and after the lane change, and the estimated lane change intention (whether or not there is an intention to change smoothly). Figures 7 and 8 show an example where the host vehicle 100 is traveling in one direction, but lane change information is generated regardless of the host vehicle 100's traveling direction. The lane change information generated by the lane change information generation unit 16 is recorded on the recording medium 24, for example, in SQL format.

In this way, the driving information generating device 10 according to embodiment 1 generates lane change information, which is information about lane changes that have actually been made, and can therefore contribute to improving the accuracy of information indicating the lane in which the vehicle 100 should be traveling. Information indicating the lane in which the vehicle 100 should be traveling serves as a basis for determining whether or not to change lanes, and improved accuracy leads to smoother driving of the vehicle 100.

Next, the operation of the driving information generating device 10 will be explained with reference to the flowchart in Figure 9.

When the host vehicle 100 starts traveling, the position information acquisition unit 11 acquires information on the position of the host vehicle 100 from the locator 21, and the driving lane information acquisition unit 12 acquires driving lane information of the host vehicle 100 from the locator 21 (step S101).

In addition, the vehicle state information acquisition unit 13 acquires vehicle state information from the in-vehicle LAN 23 (step S102). The surrounding area information acquisition unit 14 acquires surrounding area information of the vehicle 100 from the surrounding area detection device 22 (step S103).

The intention estimation unit 15 determines whether the vehicle 100 has changed lanes based on the driving lane information acquired by the driving lane information acquisition unit 12 (step S104).

If the vehicle 100 has changed lanes (YES in step S104), the intention estimation unit 15 estimates whether the lane change intention was a smooth lane change based on the vehicle state information acquired by the vehicle state information acquisition unit 13 or the surrounding information acquired by the surrounding information acquisition unit 14 (step S105). The lane change information generation unit 16 then generates lane change information, which is information about the lane change performed by the vehicle 100, and records it on the recording medium 24 (step S106). The lane change information includes the location of the lane change, the lanes before and after the lane change, and the estimation result of the intention estimation unit 15 regarding the lane change intention.

If the vehicle 100 is not changing lanes (NO in step S104), steps S105 and S106 are skipped.

Then, the driving information generating device 10 checks whether the driving of the vehicle 100 has ended (step S107). If the driving of the vehicle 100 is continuing (NO in step S107), the process returns to step S101. If the driving of the vehicle 100 has ended (YES in step S107), the process in FIG. 9 ends.

[Modification]
The lane change information generator 16 may include, in the lane change information, information on factors that hindered smooth driving of the vehicle 100 in the lane before the lane change, i.e., information on events that triggered the driver to make a smooth lane change. Factors that hinder smooth driving include a decrease in the speed of the vehicle 100, an encounter with a driving-hindering factor, the occurrence of a collision risk, an increase in the driver's psychological discomfort index, etc. The factors that hinder smooth driving that are included in the lane change information may be more detailed information, such as traffic congestion waiting to turn right at an intersection or fork, traffic congestion waiting to turn left, traffic congestion waiting to enter a parking lot, and lane occupancy by stopped vehicles.

In addition, the lane change information generation unit 16 may include image data, audio data, sensor output data, etc. of events that hinder smooth driving (e.g., stopped vehicles or other vehicles in a traffic jam) in the lane change information.

The driving information generating device 10 may exchange accumulated lane change information with another driving information generating device 10 installed in another vehicle via vehicle-to-vehicle communication using a communication device (not shown). For example, lane change information obtained from the driving information generating device 10 of the other vehicle may be recorded on the recording medium 24 of the vehicle 100. In this case, the driving information generating device 10 may select and record only lane change information for roads on which the vehicle 100 has traveled (i.e., roads on which the vehicle 100 has traveled in the past) on the recording medium 24. This prevents lane change information for roads on which the vehicle 100 is unlikely to travel from being recorded on the recording medium 24, thereby conserving storage capacity on the recording medium 24.

The intention estimation unit 15 may detect lane changes by other vehicles around the vehicle 100 from the surrounding information acquired by the surrounding information acquisition unit 14, and may estimate whether the other vehicle's lane change intention was a smooth lane change based on the surrounding information. If the other vehicle's lane change intention was a smooth lane change, the lane change information generation unit 16 generates lane change information corresponding to that lane change and stores it in the recording medium 24. Since not only the lane change information of the vehicle 100 but also the lane change information of other vehicles is recorded, a large amount of lane change information can be collected.

The intention estimation unit 15 may analyze the surrounding image captured by the camera of the surrounding detection device 22 when a lane change is made, learn the relationship between the analysis results of the surrounding image and the judgment results of the smooth intention using artificial intelligence (AI), and formulate a smooth intention estimation logic based on the results of that learning. The judgment logic formulated from the learning is applied to the intention estimation unit 15 and used to estimate the lane change intention.

<Second Embodiment>
The configuration of the driving information generation device 10 according to the second embodiment is the same as that of the first embodiment (FIG. 1). However, in the second embodiment, the intention estimation unit 15 estimates the intention to change lanes and calculates the driving smoothness of the vehicle 100 before and after the lane change, and the lane change information generation unit 16 includes the information on the driving smoothness in the lane change information. The operation of the other elements is the same as that of the first embodiment, and therefore a description thereof will be omitted here.

Figure 10 is a flowchart showing the operation of the driving information generating device 10 according to embodiment 2. The flowchart in Figure 10 is the same as the flowchart in Figure 9 except that step S111 is added between step S105 and step S106.

In step S111, the intention estimation unit 15 calculates the driving smoothness of the vehicle 100 before and after the lane change. In step S106, the lane change information generation unit 16 generates lane change information including information on the driving smoothness of the vehicle 100 before and after the lane change, and records it on the recording medium 24. The other steps are the same as in embodiment 1 (Figure 9).

The driving smoothness of the vehicle 100 is a numerical value that quantifies the degree of smoothness of driving of the vehicle 100. Here, the higher the driving smoothness numerical value, the smoother the driving.

The intention estimation unit 15 may use any method to calculate driving smoothness, but the following calculation method can be applied.

For example, the intention estimation unit 15 may calculate the driving smoothness based on the speed of the host vehicle 100. Specifically, the driving smoothness SDL(t) of the host vehicle 100 at time t may be calculated from the speed V(t) of the host vehicle 100 at time t and the speed limit Vlimit of the road on which the host vehicle 100 is traveling at time t, using the formula SDL(t) = V(t)/Vlimit (where the upper limit of SDL is 1).

The intention estimation unit 15 may calculate the driving smoothness based on the density of factors that impede driving of the vehicle 100 (for example, the density of vehicles in traffic jams). In this case, the lower the density of factors that impede driving, the higher the driving smoothness.

The intention estimation unit 15 may calculate the driving smoothness based on the level of collision risk of the vehicle 100. In this case, the lower the collision risk, the higher the driving smoothness.

The intention estimation unit 15 may calculate the driving smoothness using two or more of the above calculation methods and determine the driving smoothness comprehensively from the estimation results.

The lane change information generation unit 16 may include two or more driving smoothness levels calculated using different methods in the lane change information. The lane change information generation unit 16 may also include the difference in driving smoothness levels of the vehicle 100 before and after the lane change in the lane change information as the improvement in driving smoothness due to the lane change. The lane change information generation unit 16 may also record on the recording medium 24 only lane changes for which the improvement in driving smoothness level is equal to or greater than a predetermined threshold.

The driving information generating device 10 according to the second embodiment generates lane change information including the driving smoothness before and after a lane change. Therefore, it becomes possible to evaluate the degree of improvement in driving smoothness due to a lane change from the lane change information.

<Third Embodiment>
Fig. 11 is a diagram showing the configuration of a driving information generation device 10 according to embodiment 3. The configuration of the driving information generation device 10 in Fig. 11 differs from the configuration in Fig. 1 in that a map database 25 is connected to the driving information generation device 10 and a map data generation unit 17 is provided in the driving information generation device 10.

The map database 25 is a database in which map data is stored. The map data stored in the map database 25 includes lane change assistance information indicating the lanes in which a vehicle should travel for smooth driving, i.e., lanes that are advantageous for smooth driving, on a lane link or sub-link basis. This map data may also include lane change locations that specify locations in more detail than a sub-link.

The map data generation unit 17 generates map data including lane change assistance information based on the lane change information stored in the recording medium 24, and updates the map data in the map database 25 at predetermined times.

Figure 12 is a flowchart showing the operation of the map data generation unit 17.

When the vehicle 100 starts traveling, the map data generation unit 17 determines whether it is time to update the map data (step S201). The map data may be updated at any time, for example, periodically (e.g., once a month) or when a specific event occurs (e.g., when a certain number of new lane change information items (e.g., 100 items) have been accumulated in the recording medium 24).

When it is time to update the map data (YES in step S201), the map data generation unit 17 generates updated map data including lane change assistance information based on the lane change information stored in the recording medium 24 (step S202). In this embodiment, the map data generation unit 17 generates lane change assistance information by setting the driving smoothness level of the lane before a smooth lane change is made to 1 and the driving smoothness level of the lane after a smooth lane change is made to 2. In addition, if there are multiple lane change information pieces within a sublink, the driving smoothness level for each lane of the sublink is calculated using statistical processing.

Then, the map data generation unit 17 updates the map data in the map database 25 using the generated update map data (step S203).

In this embodiment, the processing in Figure 12 is executed in parallel with the lane change information generation processing (Figure 9 or Figure 10). However, the two processes do not necessarily have to be executed in parallel, and any software configuration, including a single process, is acceptable.

Examples of map data stored in the map database 25 will be described using Figures 13 and 14. Figure 13 is an example of lane change assistance information included in the map data in the map database 25. Figure 14 shows the map data corresponding to the lane change assistance information in Figure 13 as a map image, and the map in Figure 14 indicates lanes that are advantageous for smooth driving. In Figures 13 and 14, "L" represents a link representing a road, "N" represents a node representing a location, "SL" represents a sublink dividing a link, and "SN" represents a subnode representing a location between sublinks. In this example, the lane that is advantageous for smooth driving in sublink SL1-3 is lane 1, and the lane that is advantageous for smooth driving in sublinks SL1-1, SL1-2, and SL2-1 is lane 2.

[Modification]
The map data in the map database 25 may include information on factors that have hindered smooth driving, i.e., events that triggered the driver to change lanes with the intention of smooth driving. Also, the map database 25 may be provided for each factor that has hindered smooth driving.

The map data generation unit 17 may identify roads on which lane changes contrary to the lane change assistance information in the map data have occurred based on new lane change information stored in the recording medium 24, and may modify the lane change assistance information for roads on which lane changes contrary to the lane change assistance information have occurred with a certain frequency or more. For example, the map data generation unit 17 determines that a lane change contrary to the lane change assistance information has occurred when the vehicle 100 changes lanes from a lane determined to be advantageous for smooth driving to a lane determined to be disadvantageous for smooth driving.

For example, the lane change assistance information for a road where lane changes contrary to the lane change assistance information are made more frequently than necessary may be modified so as not to assign advantages or disadvantages to smooth driving. If no advantages or disadvantages are assigned, the driving smoothness of the first lane and the second lane in Figure 13 may be set to the same value. Alternatively, if driving smoothness is expressed in multiple stages, the driving smoothness of the first lane and the driving smoothness of the second lane may be made closer to each other. For example, if the number of lane changes from the first lane to the second lane is n1 and the number of lane changes from the second lane to the first lane is n2, the driving smoothness of the first lane and the second lane may be determined according to the ratio of n1, as shown in Figure 15.

The intention estimation unit 15 analyzes the surrounding image captured by the camera of the surrounding detection device 22 when a lane change is made, and uses artificial intelligence (AI) to learn the relationship between the analysis results of the surrounding image and the judgment results of smooth driving intention, and may formulate smooth driving intention estimation logic, judgment logic for the degree of driving smoothness, judgment logic for factors that hinder smooth driving, etc. based on the results of this learning.

The intention estimation unit 15 may analyze the surrounding image captured by the camera of the surrounding detection device 22 when a lane change is made, learn the relationship between the analysis results of the surrounding image and driving smoothness, and build logic to determine driving smoothness and lane change factors based on the results of this learning. In this case, the learning may be performed by increasing the weight of the surrounding image when a lane change is made that goes against the lane change assistance information.

As shown in FIG. 16, the map data generation unit 17 and the map database 25 may be constructed in a server 200 installed outside the vehicle 100. In other words, a map data generation system may be constructed that is composed of a vehicle equipped with a driving information generation device 10 and a server 200 that has the map data generation unit 17 and the map database 25. In this case, the map data generation unit 17 of the server 200 may collect lane change information as so-called probe information from the driving information generation devices 10 of multiple vehicles 100, and generate map data including lane change assistance information based on the collected lane change information.

In addition, some of the elements shown in Figure 16 within the vehicle 100 or the driving information generating device 10 may be constructed on the server 200. In particular, learning using AI is effective when performed on the server 200, which has high CPU and memory performance.

<Fourth Embodiment>
Fig. 17 is a diagram showing the configuration of a driving information generation device 10 according to embodiment 4. The configuration of the driving information generation device 10 in Fig. 17 is different from the configuration in Fig. 11 in that a notification device 26 is connected to the driving information generation device 10 and a driving assistance unit 18 is provided in the driving information generation device 10.

The notification device 26 is a means by which the driving information generating device 10 presents lane change assistance information to the driver of the vehicle 100. The notification device 26 may be any device capable of presenting information to the driver, such as an audio output device or a display device. The display device may also be a head-up display (HUD) that can display an image directly in the driver's field of view by projecting an image onto the windshield, etc., of the vehicle 100.

The driving assistance unit 18 prompts the driver of the vehicle 100 to change lanes that are advantageous for smooth driving based on the position of the vehicle 100, the lane the vehicle is traveling in, information about the surrounding area of the vehicle 100, and lane change assistance information in the map data stored in the map database 25, thereby assisting the driver in driving the vehicle 100. Specifically, if the lane the vehicle 100 is traveling in is not advantageous for smooth driving, the driving assistance unit 18 uses the notification device 26 to issue a notification prompting the driver to change lanes to a lane that is advantageous for smooth driving.

For example, as shown in FIG. 18, consider a situation in which the host vehicle 100 is traveling in a section (sub-node SL1-2) where the second lane is advantageous for smooth driving, toward a section (sub-node SL1-3) where the first lane is advantageous for smooth driving. If the host vehicle 100 is traveling in the second lane when it approaches sub-node SL1-3 (e.g., when the host vehicle 100 reaches 20 m before sub-node SL1-3, or 2 seconds before the host vehicle 100 enters sub-node SN1-3), the driving assistance unit 18 issues a notification to the driver of the host vehicle 100 urging them to change lanes to the first lane. For example, if the notification device 26 is a HUD, the driving assistance unit 18 uses the HUD to display a display object such as that shown in FIG. 19 in the driver's field of view to urge the driver to change lanes. If the driver changes lanes in response to this notification, the driver can travel in the lane (first lane) that is advantageous for smooth driving even when entering sub-node SL1-3, allowing the driver to continue driving smoothly, which in turn contributes to easing traffic congestion and safe driving.

The method of providing notifications for lane change assistance is not limited to using a HUD. For example, as shown in Figure 18, a map showing the lane in which to drive may be displayed on the screen of the notification device 26, or audio guidance may be provided to encourage the driver to change lanes.

The timing of the notification to encourage a lane change may be variable. For example, the greater the improvement in driving smoothness due to a lane change, the earlier the notification may be made.

The lane change information generation unit 16 may include information on the time taken to change lanes in the lane change information, and the map data generation unit 17 may determine the difficulty of changing lanes from the information on the time taken to change lanes included in the lane change information, and include the information on the difficulty of changing lanes in the lane change assistance information of the map data. In this case, it is preferable that the driving assistance unit 18 issue a notification urging the driver to change lanes earlier in locations where lane change difficulty is high than in locations where lane change difficulty is low.

The time it takes to change lanes is defined as the time from when the driver intends to change lanes to when the lane change actually occurs. Furthermore, the timing at which the driver intends to change lanes can be defined as, for example, when the speed of the vehicle 100 decreases due to the influence of another vehicle ahead, when the driver moves the vehicle 100 toward the lane to which the lane is to be changed, when the driver turns on the turn signal, or when the driver repeatedly looks toward the lane to which the lane is to be changed.

In addition, the driver's intention to change lanes may be treated as a "deemed lane change," and even if a lane change is not actually made, the intention estimation unit 15 may estimate the intention of a "deemed lane change," and the lane change information generation unit 16 may generate lane change information including the estimated result of the intention of a "deemed lane change."

The map data generation unit 17 may calculate the degree of improvement in driving smoothness due to a lane change from information on the driving smoothness of the vehicle 100 before and after the lane change, and include the information on the degree of improvement in driving smoothness due to a lane change in the lane change assistance information of the map data. In this case, the driving assistance unit 18 may change the method of presenting lanes advantageous for smooth driving to the driver depending on the degree of improvement in driving smoothness due to a lane change on the road on which the vehicle 100 is traveling. For example, if the degree of improvement in driving smoothness due to a lane change is small, it is preferable to strongly encourage the driver to make a lane change with a large improvement, such as by presenting only an image, and if the degree of improvement is large, by presenting using audio in addition to an image.

The method of presenting lanes advantageous for smooth driving to the driver may also be changed depending on factors that hinder smooth driving of the vehicle 100. For example, if the factor that hinders smooth driving is the risk of a collision and guidance is provided to change lanes to avoid the risk of a collision, the electric power steering (EPS) may be activated to apply a force sensation to the steering wheel, or automatic driving control may be used to assist in some or all of the driving operation of changing lanes.

The driving assistance unit 18 may have a function to analyze surrounding video captured when a lane change is made and learn the surrounding conditions of the vehicle 100 when a lane change was made in the past. If the driving assistance unit 18 determines that the lane the vehicle 100 is traveling in is not one that is advantageous for smooth driving and that the conditions around the vehicle 100 have become similar to the surrounding conditions when a lane change was made in the past, it issues a warning to encourage the vehicle to change lanes to a lane that is advantageous for smooth driving.

Lane change information may be categorized by driving conditions such as day of the week, weather, time of day, holidays, events, etc. and recorded on the recording medium 24. In this case, the driving assistance unit 18 may present the driver with a lane that is advantageous for smooth driving when the current situation of the vehicle 100 matches any of the categorized driving conditions.

In addition, some of the elements shown in Figure 17 within the vehicle 100 or the driving information generating device 10 may be constructed on a server. In particular, learning using AI is effective when performed on a server with high CPU and memory performance.

<Hardware configuration example>
20 and 21 are diagrams illustrating examples of the hardware configuration of the driving information generation device 10. The functions of the components of the driving information generation device 10 illustrated in FIG. 1 are realized, for example, by a processing circuit 50 illustrated in FIG. 20. That is, the driving information generation device 10 includes a processing circuit 50 that acquires information on the position of the host vehicle, acquires driving lane information indicating the lane in which the host vehicle is traveling, acquires vehicle state information that includes at least one of the driving state of the host vehicle and the state of the driver of the host vehicle, acquires surrounding information that is information on the surrounding conditions of the host vehicle, detects a lane change of the host vehicle from the driving lane information, estimates whether the intention to change lanes was a smooth intention to drive the host vehicle smoothly based on the vehicle state information or the surrounding information, and generates lane change information that includes the position of the lane change, the lanes before and after the lane change, and the estimated result of the lane change intention. The processing circuit 50 may be dedicated hardware, or may be configured using a processor (also called a central processing unit (CPU), processing device, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor)) that executes a program stored in memory.

When the processing circuit 50 is dedicated hardware, the processing circuit 50 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination of these. The functions of each component of the driving information generating device 10 may be realized by a separate processing circuit, or these functions may be realized together by a single processing circuit.

Figure 21 shows an example of the hardware configuration of the driving information generation device 10 when the processing circuit 50 is configured using a processor 51 that executes a program. In this case, the functions of the components of the driving information generation device 10 are realized by software, etc. (software, firmware, or a combination of software and firmware). The software, etc. is written as a program and stored in memory 52. The processor 51 realizes the functions of each part by reading and executing the program stored in memory 52. That is, the driving information generation device 10 includes a memory 52 for storing a program that, when executed by the processor 51, results in the execution of the following processes: acquiring information on the position of the vehicle, acquiring driving lane information indicating the lane in which the vehicle is traveling, acquiring vehicle state information including at least one of the driving state of the vehicle and the state of the driver of the vehicle, acquiring peripheral information which is information on the surrounding conditions of the vehicle, detecting a lane change of the vehicle from the driving lane information and estimating, based on the vehicle state information or the peripheral information, whether the intention to change lanes was a smooth intention to drive the vehicle smoothly, and generating lane change information including the position of the lane change, the lanes before and after the lane change, and the estimated result of the lane change intention. In other words, this program can be said to cause a computer to execute the procedures and methods of the operations of the components of the driving information generation device 10.

Here, memory 52 may be, for example, non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), HDD (Hard Disk Drive), magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD (Digital Versatile Disc) and its drive device, or any storage medium to be used in the future.

The above describes a configuration in which the functions of the components of the driving information generating device 10 are realized either through hardware or software, etc. However, this is not limited to this, and the configuration may also be such that some of the components of the driving information generating device 10 are realized through dedicated hardware, and other components are realized through software, etc. For example, the functions of some components may be realized by a processing circuit 50 as dedicated hardware, and the functions of other components may be realized by the processing circuit 50 as a processor 51 reading and executing a program stored in memory 52.

As described above, the driving information generating device 10 can realize each of the above-mentioned functions through hardware, software, etc., or a combination of these.

In addition, it is possible to freely combine each embodiment, and to modify or omit each embodiment as appropriate.

It is understood that the above description is illustrative in all respects and that countless variations not illustrated can be envisioned.

10 Driving information generation device, 11 Position information acquisition unit, 12 Driving lane information acquisition unit, 13 Vehicle state information acquisition unit, 14 Surrounding information acquisition unit, 15 Intention estimation unit, 16 Lane change information generation unit, 17 Map data generation unit, 18 Driving assistance unit, 21 Locator, 22 Surrounding detection device, 23 In-vehicle LAN, 24 Recording medium, 25 Map database, 26 Notification device, 50 Processing circuit, 51 Processor, 52 Memory, 100 Host vehicle, 101 Other vehicles, 200 Server.

Claims (20)

a position information acquisition unit that acquires information about the position of the vehicle;
a driving lane information acquisition unit that acquires driving lane information indicating the lane on which the host vehicle is traveling;
a vehicle state information acquisition unit that acquires vehicle state information that includes at least one of a running state of the host vehicle and a state of a driver of the host vehicle;
a surrounding information acquisition unit that acquires surrounding information, which is information about the surrounding conditions of the host vehicle;
an intention estimation unit that detects a lane change of the host vehicle from the driving lane information, and estimates whether the intention of the lane change was a smooth intention, which is an intention to drive the host vehicle smoothly, based on the vehicle state information or the surrounding information before and after the lane change of the host vehicle;
a lane change information generating unit that generates lane change information including the position of the lane change, the lanes before and after the lane change, and an estimation result of the intention of the lane change;
A driving information generating device comprising: the vehicle state information acquisition unit acquires a traveling speed of the host vehicle as the vehicle state information;
the intention estimation unit estimates the intention to change lanes to be the smooth intention when the traveling speed of the host vehicle after the lane change is higher than the traveling speed of the host vehicle before the lane change and the difference is equal to or greater than a predetermined threshold.
The driving information generating device according to claim 1 . the vehicle state information acquisition unit acquires a traveling speed of the host vehicle as the vehicle state information;
The intention estimation unit estimates a traveling speed of the host vehicle when traveling without changing lanes, and when the traveling speed of the host vehicle after changing lanes is higher than the estimated value of the traveling speed of the host vehicle when traveling without changing lanes and the difference is equal to or greater than a predetermined threshold, estimates that the intention to change lanes is the intention to smooth the lane.
The driving information generating device according to claim 1 . the surrounding information acquisition unit acquires, as the surrounding information, information on travel obstruction factors ahead of the host vehicle;
the intention estimation unit estimates the intention to change lanes to be the intention to smoothly change lanes when the driving obstruction factor is present ahead of the host vehicle in the lane before the lane change and the driving obstruction factor is not present ahead of the host vehicle in the lane after the lane change.
The driving information generating device according to claim 1 . the surrounding information acquisition unit acquires information about an obstacle ahead of the host vehicle as the surrounding information;
the intention estimation unit calculates a level of a collision risk of the host vehicle with the obstacle before and after the lane change, and, when the collision risk after the lane change is lower than the collision risk before the lane change and the difference is equal to or greater than a predetermined threshold, estimates that the intention to change lanes is the smooth intention.
The driving information generating device according to claim 1 . the vehicle state information acquisition unit acquires a psychological discomfort index of the driver as the vehicle state information,
the intention estimation unit estimates the intention to change lanes to be the intention to smooth the lane change when the psychological discomfort index after the lane change is lower than the psychological discomfort index before the lane change and the difference is equal to or greater than a predetermined threshold.
The driving information generating device according to claim 1 . the lane change information generation unit includes, in the lane change information, any one of a decrease in speed of the host vehicle, an encounter with a driving obstruction factor, and an occurrence of a collision risk as information on a factor that obstructed smooth driving in the lane before the lane change;
The driving information generating device according to claim 1 . the intention estimation unit calculates driving smoothness of the host vehicle before and after the lane change;
The lane change information generation unit includes information on the driving smoothness before and after the lane change in the lane change information.
The driving information generating device according to claim 1 . a map data generating unit configured to generate map data including lane change assistance information indicating lanes advantageous for smooth driving based on the lane change information;
The driving information generating device according to claim 1 . 10. The driving information generation device according to claim 9, wherein the map data generation unit identifies a road on which the lane change contrary to the lane change assistance information in the map data has occurred based on the new lane change information, and corrects the lane change assistance information for roads on which the lane change contrary to the lane change assistance information has occurred with a frequency equal to or greater than a certain frequency. the surrounding information acquisition unit acquires, as the surrounding information, a surrounding image that is an image captured around the host vehicle;
The intention estimation unit analyzes the surrounding image captured when the lane change is performed, learns the relationship between the analysis result of the surrounding image and the determination result of the smooth driving intention, and formulates the smooth driving intention estimation logic based on the learning result.
The driving information generating device according to claim 1 . The vehicle navigation system further includes a driving assistance unit that presents to the driver lanes that are advantageous for smooth driving based on the lane change assistance information of the map data.
The driving information generating device according to claim 9. the driving assistance unit, when the lane in which the host vehicle is traveling is not a lane advantageous for smooth driving, issues a notification to encourage the host vehicle to change to the lane advantageous for smooth driving;
the lane change information generating unit includes information about the time taken to change lanes in the lane change information,
the map data generation unit determines a degree of difficulty of the lane change from information on a time taken to change lanes, which is included in the lane change information, and includes the information on the degree of difficulty of the lane change in the lane change assistance information of the map data;
The driving assistance unit may make the timing of the notification prompting the driver to change lanes earlier in a location where the degree of difficulty in changing lanes is high than in a location where the degree of difficulty in changing lanes is low.
The driving information generating device according to claim 12. the intention estimation unit calculates driving smoothness of the host vehicle before and after the lane change,
the lane change information generation unit includes information on the driving smoothness of the host vehicle before and after the lane change in the lane change information,
the map data generation unit calculates an improvement degree of the driving smoothness due to the lane change from information on the driving smoothness of the host vehicle before and after the lane change, which is included in the lane change information, and includes the information on the improvement degree of the driving smoothness due to the lane change in the lane change assistance information of the map data;
the driving assistance unit changes a method of presenting a lane advantageous for smooth driving to the driver according to the degree of improvement in the driving smoothness due to the lane change on the road on which the host vehicle is traveling.
The driving information generating device according to claim 12. the surrounding information acquisition unit acquires, as the surrounding information, a surrounding image that is an image captured around the host vehicle;
the driving assistance unit analyzes the surrounding image captured when the lane change is performed, and learns the surrounding situation of the host vehicle when the lane change was performed in the past;
When the lane on which the host vehicle is traveling is not a lane advantageous for smooth driving and the situation around the host vehicle becomes similar to the situation around the host vehicle when the lane change was previously performed, the driving assistance unit issues a notification to encourage the host vehicle to change to a lane advantageous for smooth driving.
The driving information generating device according to claim 12. the intention estimation unit detects that the driver has an intention to change lanes based on the vehicle state information or the surrounding information;
The lane change information generating unit includes, in the lane change information, a time period from when the driver intends to change lanes until the lane change is actually performed, as information on a time period taken to change lanes.
The driving information generating device according to claim 1 . the intention estimation unit detects that the driver has an intention to change lanes based on the vehicle state information or the surrounding information, treats the driver's intention to change lanes as a deemed lane change, and estimates the driver's intention to change lanes;
the lane change information generation unit generates the lane change information including an estimation result of the assumed lane change intention.
The driving information generating device according to claim 1 . The intention estimation unit further detects a lane change of another vehicle around the host vehicle from the surrounding information, and estimates whether the lane change intention of the other vehicle was the smooth intention based on the surrounding information;
The lane change information generating unit further generates the lane change information corresponding to the smooth lane change performed by the other vehicle.
The driving information generating device according to claim 1 . A vehicle equipped with the driving information generating device according to claim 1;
a server having a map data generation unit that collects the lane change information from the driving information generation devices of the plurality of vehicles and generates map data including lane change assistance information that indicates lanes that are advantageous for smooth driving based on the collected lane change information;
A map data generation system comprising: a position information acquisition unit of the driving information generating device acquires information on the position of the vehicle;
a driving lane information acquisition unit of the driving information generation device acquires driving lane information indicating a lane in which the host vehicle is traveling;
a vehicle state information acquisition unit of the driving information generating device acquires vehicle state information that is information including at least one of a driving state of the host vehicle and a state of a driver of the host vehicle;
a surrounding information acquisition unit of the traveling information generation device acquires surrounding information that is information about a surrounding situation of the host vehicle;
an intention estimation unit of the driving information generation device detects a lane change of the host vehicle from the driving lane information, and estimates whether the intention of the lane change was a smooth intention, which is an intention to drive the host vehicle smoothly, based on the vehicle state information or the surrounding information before and after the lane change of the host vehicle;
a lane change information generating unit of the traveling information generating device generating lane change information including a position of the lane change, lanes before and after the lane change, and an estimation result of the intention of the lane change;
A method for generating driving information.