JP2017117367A - Drive support apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a drive support apparatus capable of presenting a driver with high reliable drive support information better reflecting actual situation.SOLUTION: A drive support apparatus performs: defining a vehicular state including a surrounding environment of a vehicle itself, presence of co-occupant, a degree of difference between a desired time of arrival at a destination and a current clock-time, the number of times of traveling the same road, and a positional relation between the vehicle itself and a nearby vehicle, thus learning, through a drive characteristic learning part 101, a presence of lane change of the vehicle itself for each vehicular state, as a drive characteristic; predicting, through a vehicle-itself drive behavior prediction part 103, a presence of execution of lane change of the vehicle itself in a present vehicular state, as a drive action, while referring to the learning result of the drive characteristic of the vehicle itself; obtaining, using an inter-vehicular communication system, a presence of execution of lane change predicted for the nearby vehicle, thus predicting, through a nearby vehicle drive action prediction part 105, a drive action of the nearby vehicle; and presenting, through a presentation content selection part 106, drive support information on the basis of the drive action of the vehicle itself and nearby vehicle.SELECTED DRAWING: Figure 1

Description

  The present invention predicts the presence or absence of a lane change of a plurality of vehicles including the host vehicle and surrounding vehicles, and presents to the driver of the host vehicle as driving assistance information, such as whether to decelerate or change lanes based on the prediction result. The present invention relates to a driving support device.

  Conventionally, for example, an apparatus described in Patent Document 1 is known as this type of driving support apparatus. In this device, the driver's driving skill is evaluated in a hierarchy such as “beginner level”, “intermediate level”, “advanced level”, and the lower the driver's driving skill evaluation result, the more the vehicle travels in the adjacent lane. The degree to which the rear vehicle is approaching is estimated to be high. As a result, a vehicle with a wide range of driving support information (driving support information) that strongly calls the driver's attention when the driver's driving skill falls within the “beginner level” when changing to the adjacent lane On the other hand, when the driver's driving skill falls within the "advanced level", the area where the driving support information is presented is restricted to an excessively wide area and is not alerted It has come to be. Also, with this device, when the surrounding environment of the vehicle tends to increase the driving load on the driver, such as when the surroundings of the vehicle are dark or raining, the degree to which the rear vehicle traveling in the adjacent lane approaches Is corrected to increase. As a result, the driving assistance information presentation mode is changed so that the driving area of the vehicle on which the driving assistance information is presented covers a wide range under a driving environment in which the driver is driving.

JP, 2015-103070, A

  Incidentally, whether or not the driver can accurately recognize the driving support information is influenced by various factors other than the driving skill of the driver and the surrounding environment of the vehicle. For this reason, it is not always sufficient to simply present the driving support information in consideration of the driving skill of the driver and the surrounding environment.

  The present invention has been made in view of such circumstances, and an object thereof is to provide a driving support device capable of presenting a driver with highly reliable driving support information in accordance with a more realistic situation. It is in.

  A driving support device that solves the above problem predicts whether or not to execute lane change of a vehicle based on a function of learning whether or not a lane change of the vehicle is performed as a driving characteristic based on the operation history of the vehicle and a learning result of the driving characteristic. A driving support device that presents driving support information based on a prediction result of driving behavior of the host vehicle and surrounding vehicles using a vehicle-to-vehicle communication system configured such that a plurality of vehicles having a function to perform communication with each other by wireless communication It includes the surrounding environment of the host vehicle, the presence or absence of passengers, the degree of divergence between the desired time of arrival at the destination and the current time, the number of travels on the same road, and the positional relationship between the host vehicle and the surrounding vehicle. The vehicle characteristic is defined by the driving characteristic learning unit that learns the driving characteristic based on the operation history of the vehicle based on the operation history of the vehicle, and the driving characteristic learning unit The own vehicle driving behavior prediction unit that predicts whether or not the lane change of the own vehicle is executed in the current vehicle state while referring to the learning result of the driving characteristics of the own vehicle, and the execution of the lane change predicted in the surrounding vehicles A surrounding vehicle driving behavior prediction unit that obtains the presence or absence of the vehicle by the wireless communication and predicts the driving behavior of the surrounding vehicle from the viewpoint of the own vehicle, the driving behavior of the host vehicle predicted by the own vehicle driving behavior prediction unit, and A support information presentation unit that presents driving support information to the driver of the host vehicle based on the driving behavior of the surrounding vehicle predicted by the surrounding vehicle driving behavior prediction unit.

  According to the above configuration, the surrounding environment of the own vehicle, the presence or absence of a passenger, the degree of deviation between the desired time and the current time of arrival at the destination, the number of times of traveling on the same road, the positional relationship between the own vehicle and the surrounding vehicle, etc. In addition, the presence / absence of a change in the lane of the host vehicle is learned as the driving characteristic while considering each element of the vehicle state that affects the driving characteristic of the host vehicle. Similarly, in the surrounding vehicle, the presence or absence of the lane change of the surrounding vehicle is learned as the driving characteristic while considering each element of the vehicle state that affects the driving characteristic of the surrounding vehicle. Therefore, it is possible to predict with high reliability whether or not there is a lane change between the own vehicle and the surrounding vehicle according to the individual vehicle state. And by communicating the prediction result regarding the presence or absence of such a reliable lane change between the own vehicle and the other vehicle, both the own vehicle and the other vehicle accurately predict each other's driving behavior, Based on the prediction result, it is possible to present to the driver highly reliable driving support information that is more realistic.

1 is a block diagram showing a schematic configuration of a vehicle to which an embodiment of a driving support device and a driving support device of the embodiment are applied. The figure which shows the various elements which define a vehicle state. (A) is a figure for demonstrating the lane change accompanying an overtaking action, (b) is a figure for demonstrating the lane change accompanying the transfer behavior by a back vehicle approach. The flowchart which shows the process sequence of a driving | operation characteristic learning process. The flowchart which shows the process sequence of a driving action prediction process. The flowchart which shows the process sequence of a support information proposal process.

Hereinafter, an embodiment of the driving support device will be described.
The driving support device according to the present embodiment learns the frequency of the lane change operation by the driver of each vehicle as the driving characteristics of the driver while classifying the frequency according to each vehicle state of the vehicle. And when the frequency of the lane change of the vehicle corresponding to the current vehicle state of the vehicle is high, it is predicted that the possibility that the lane change is executed in the vehicle state is high. Note that such lane change prediction is executed not only in the host vehicle but also in surrounding vehicles using an inter-vehicle communication system. When it is determined that the vehicle is likely to be hindered by the surrounding vehicle, the host vehicle presents a proposal for deceleration or lane change to the driver of the host vehicle as driving support information as necessary.

First, the configuration of the apparatus according to the present embodiment will be described with reference to the drawings.
As shown in FIG. 1, the driving support device 100 includes peripheral environment information D1, road information D2, as an example of information that is an evaluation item in learning the driving characteristics of the driver of the host vehicle C1 and the surrounding vehicle C2. Passenger information D3, surrounding vehicle information D4, and schedule information D5 are acquired. Here, the surrounding environment information D1 is information related to brightness, weather, and the like outside the vehicle, an illuminance sensor 10 that detects the illuminance of ambient light outside the vehicle, and a road traffic information center that manages road traffic information and weather information. (Registered trademark) 11. The road information D2 is information regarding the number of times the vehicle has traveled on the same road, and is acquired through the navigation system 12 having a function of recording a travel history of the vehicle as a log. The passenger information D3 is information relating to the presence or absence of a passenger, and performs image recognition processing on an image captured through the in-vehicle camera 13 or detects pressure applied to each seat of the vehicle through the seating sensor 14. It is acquired by doing. The surrounding vehicle information D4 is information on the positional relationship and distance between the host vehicle and the surrounding vehicle, and vehicles, obstacles, and the like that are in the detection range while using laser light having a wavelength of several hundred nm to several hundreds of nm. Is acquired through a laser radar 15 that detects the position and distance of the vehicle and a millimeter wave radar 16 that detects the position and distance of a vehicle or an obstacle in the detection range while using radio waves having a wavelength of 1 to 10 nm. The schedule information D5 is information regarding the degree of deviation between the desired time (schedule time) to arrive at the destination and the current time, and is acquired through the external device 17 having a schedule management function such as a portable information terminal. . And various information D1-D5 used as these evaluation items is sent to the driving characteristic learning part 101, and is used for the classification | category of the present vehicle state of the own vehicle C1.

  Here, in the example shown in FIG. 2, “bad weather”, “brightness”, “number of times of travel”, “passenger”, “distance between vehicles ahead”, “rear vehicle” The distance between the vehicle and the distance between the vehicle traveling in the adjacent lane and the deviation time are defined. In the example shown in the figure, regarding “bad weather” among these elements, if it is raining, it is determined that the weather is bad when the rainfall is 15 [mm / h] while traveling on the highway. If it is snow, it is determined that the weather is bad regardless of the amount of snowfall. The “brightness” is determined to be bright when the illuminance value detected by the illuminance sensor 10 is 1000 lux or more, for example, and dark when the illuminance value is less than 1000 lux. In addition, the “running frequency” is determined to be large when it is 5 times or more, and conversely when it is less than 5 times. For “passenger”, if there is even one passenger, it is determined that there is a passenger. Further, the “distance between the vehicle ahead”, the “distance between the vehicle behind” and the “distance between the vehicle traveling in the adjacent lane” are set to “far” when in the range of 100 to 200 m, It is determined as “medium” when it is in the range of ˜100 m, and “close” when it is in the range of 1 to 50 m. The “deviation time” is determined as “many” if the current time is 15 minutes or more later than the desired time, and conversely as “small” if the current time is not more than 15 minutes later than the desired time. . And vehicle state P1-Pn is defined individually for every combination of the determination result of each element.

  The driving characteristic learning unit 101 determines whether or not the lane change of the host vehicle C1 is executed based on various vehicle operation histories such as the vehicle speed, the accelerator opening, the brake state, the steering angle, and the direction indicator state. To do. Here, for the lane change to be judged, the overtaking action indicated by arrow A1 in FIG. 3A (lane change to the left), and the overtaking action indicated by arrow A2 in FIG. 3A (lane change to the right). ) And FIG. 3B include a transfer behavior due to the approach of the rear vehicle indicated by an arrow A3. A lane change accompanying an overtaking action is determined to be a lane change when a series of flows such as “approaching the preceding vehicle → lane change (left / right) → acceleration” is detected based on the vehicle operation history described above. The On the other hand, a lane change due to a swaying action due to approaching a rear vehicle is when a series of flows such as “the rear vehicle approaches ⇒ a lane change from an overtaking lane to a driving lane” is also detected based on the above-described vehicle operation history. It is judged that there is a lane change. When it is determined that there is a lane change, the driving characteristic learning unit 101 cumulatively adds the lane change frequency for each vehicle state of the vehicle based on the definition shown in FIG.

  The driving characteristic learning result by the driving characteristic learning unit 101 is accumulated in the memory of the driving characteristic learning unit 101 while the ignition switch of the host vehicle is turned on, and the ignition switch of the host vehicle is turned off. Is written in the driving characteristic storage unit 102 and used for the prediction of the driving behavior of the host vehicle C1 by the host vehicle driving behavior prediction unit 103.

  Specifically, the host vehicle driving behavior predicting unit 103 first determines whether the host vehicle C1 is based on various vehicle operation histories such as the vehicle speed, the accelerator opening, the brake state, the steering angle, and the direction indicator state. Identify the types of lane changes that may be made (passing behavior (left / right), transfer behavior due to approaching rear vehicle). The own vehicle driving behavior prediction unit 103 reads out the lane change frequency for the identified type of lane change from the driving characteristic storage unit 102 and the current vehicle of the own vehicle C1 with respect to the lane change frequency in all vehicle states. The ratio of the lane change frequency in the state is calculated as the frequency rate. Then, the host vehicle driving behavior prediction unit 103 predicts whether or not the target lane change is executed in the current vehicle state based on the calculated frequency rate. In addition, the host vehicle driving behavior prediction unit 103 considers the operating function state of the host vehicle C1 (for example, radar cruise control, lane keeping assist, etc.) as the vehicle operation history, and changes the lane of the host vehicle C1. Predict driving behavior including.

  Such prediction of driving behavior is performed not only in the own vehicle C1 but also in the surrounding vehicle C2 equipped with the driving support device of the present embodiment. Then, the host vehicle C1 receives the driving behavior prediction result by the surrounding vehicle C2 through the communication unit 104 and sends it to the surrounding vehicle driving behavior prediction unit 105. The surrounding vehicle driving behavior prediction unit 105 associates the prediction result of the driving behavior received from the surrounding vehicle C2 with the positional relationship and distance between the host vehicle C1 and the surrounding vehicle C2 included in the surrounding vehicle information D4. Thereby, the surrounding vehicle driving behavior prediction unit 105 predicts the driving behavior of the surrounding vehicle C2 from the viewpoint of the host vehicle C1, such as overtaking of the rear vehicle, deceleration of the preceding vehicle, interruption from the adjacent lane, and the prediction result. Is sent to the vehicle driving behavior prediction unit 103.

  The own vehicle driving behavior prediction unit 103 refers to the prediction result of the driving behavior of the surrounding vehicle C2 by the surrounding vehicle driving behavior prediction unit 105, and further combines the prediction result of the driving behavior of the own vehicle C1 by itself. The positional relationship between the host vehicle C1 and the surrounding vehicle C2 after a predetermined time has elapsed (for example, after 5 seconds) is predicted. The prediction result by the own vehicle driving behavior prediction unit 103 is sent to the presentation content selection unit 106 and is used for selection of the presentation content of the driving support information by the presentation content selection unit 106.

  Specifically, the presentation content selection unit 106 has a presentation content list 106A that shows a list of presentation content that may be proposed as driving support information to the driver of the host vehicle C1. Then, the presentation content selection unit 106 considers the possibility that the driving behavior of the surrounding vehicle C2 hinders the driving behavior of the own vehicle C1 based on the above-described prediction result of the positional relationship between the own vehicle C1 and the surrounding vehicle C2. The presentation content required for the host vehicle C1 is selected from the presentation content list 106A as necessary. The presentation content selected in this way is sent from the presentation content selection unit 106 to the HMI (Human Machine Interface) control unit 107. For example, a driver through the HMI 20 such as a warning sound through a speaker or a warning display through a vehicle-mounted display. Used to propose driving assistance information for The presentation contents registered in the presentation content list 106A include, for example, those related to “deceleration proposal” or “lane change proposal”.

  Next, a specific processing procedure of the driving characteristic learning process executed by the driving support apparatus 100 according to the above embodiment will be described. Here, the driving assistance device 100 starts the driving characteristic learning process shown in FIG. 4 on the condition that the ignition switch of the vehicle is turned on.

  As shown in FIG. 4, in this driving characteristic learning process, first, the surrounding environment information D1, which is information related to the brightness and weather outside the vehicle, is acquired through the illuminance sensor 10 and the road traffic information center 11 (step S10). Further, road information D2, which is information relating to the number of times of traveling on the same road, is acquired through the navigation system 12 (step S11). Passenger information D3, which is information relating to the presence or absence of a passenger, is acquired through the vehicle interior camera 13 and the seating sensor 14 (step S12). Moreover, the surrounding vehicle information D4 which is the information regarding the positional relationship and distance of the own vehicle C1 and the surrounding vehicle C2 is acquired through the laser radar 15 and the millimeter wave radar 16 (step S13). Further, schedule information D5, which is information relating to the degree of deviation between the desired time of arrival at the destination and the current time, is acquired through the external device 17 (step S14). In addition, the acquisition order of each information which concerns on step S10-step S14 can be changed suitably.

  Subsequently, based on the operation history of the vehicle such as the speed of the vehicle, the accelerator opening, the brake state, the steering angle, the state of the direction indicator, etc., the driving characteristic learning unit 101 determines whether or not the lane change is performed. It determines with action (step S15). The type of lane change determined in this way is associated with each vehicle state of the vehicle defined based on various information D1 to D5 acquired in the previous steps S10 to S14, and the frequency of the lane change. Are accumulated to learn the driving characteristics of the driver (step S16). The driving characteristic learning result is accumulated in a memory included in the driving characteristic learning unit 101.

  And while the ignition switch of a vehicle is ON (step S17 = NO), the process returns to step S10, and the process of step S10-step S16 is repeated with a predetermined period. On the other hand, when the ignition switch of the vehicle is turned off (step S17 = YES), it is assumed that learning of driving characteristics is once completed, and the driving characteristic learning result stored in the memory of the driving characteristic learning unit 101 at that time Is stored (written) in the driving characteristic storage unit 102, and the driving characteristic learning process shown in FIG.

  Next, a specific processing procedure of the driving action prediction process executed by the driving support apparatus 100 according to the above embodiment will be described. Here, the driving assistance device 100 executes the driving behavior prediction process shown in FIG. 5 at a predetermined cycle under the condition that the ignition switch of the vehicle is on.

  As shown in FIG. 5, in this driving behavior prediction process, first, learning results of driving characteristics stored in the driving characteristics storage unit 102 are collected through the own vehicle driving behavior prediction unit 103 (step S20). When the driving characteristic learning result is stored in the driving characteristic storage unit 102 (step S21 = YES), that is, when the driving characteristic learning process shown in FIG. 4 is executed in advance, the vehicle at that time In order to grasp the state, various types of information D1 to D5 are acquired through the same processing as Step S10 to Step S14 shown in FIG. 4 (Step S22 to Step S26).

  In addition, in order to identify the type of lane change (passing behavior (left / right), transfer behavior due to approaching the rear vehicle) that the host vehicle C1 may perform through the host vehicle driving behavior prediction unit 103, for example, the vehicle speed, accelerator Various vehicle operation histories related to driving behavior such as opening, brake state, steering angle, and direction indicator are collected (step S27). And about the kind of lane change specified in this way, the frequency of the lane change in the vehicle state defined based on the various information D1-D5 acquired in previous step S22-step S26 is read from the driving characteristic memory | storage part 102. FIG. Further, the ratio of the lane change frequency in the current vehicle state of the host vehicle C1 to the lane change frequency in all vehicle states is calculated as a frequency rate.

  Then, based on the calculated frequency rate, the vehicle driving behavior prediction unit 103 predicts whether or not the target lane change is executed in the current vehicle state (step S28). Further, the frequency rate calculated in the previous step S28 is regarded as the prediction accuracy of the driving action, and whether or not the prediction accuracy is 80% or more which is a threshold value, that is, the target lane change is performed in the current vehicle state. It is determined whether or not the vehicle state has a probability of 80% or more and the possibility is very high (step S29). When the prediction accuracy of the driving action is 80% or more (step S29 = YES), it is determined that the prediction result of the driving action in the current vehicle state is obtained (step S30), and the determination result is the own vehicle. After storing in the memory of the driving behavior prediction unit 103, the driving behavior prediction process shown in FIG.

  On the other hand, when the prediction accuracy of the driving action is less than 80% (step S29 = NO), it is determined that the prediction result of the driving action in the current vehicle state is not obtained, and the determination result is predicted to drive the own vehicle. After storing in the memory of the unit 103 (step S31), the driving behavior prediction process shown in FIG. 5 is terminated. Even when the learning result of the driving characteristic is not stored in the driving characteristic storage unit 102 in the previous step S21 (step S21 = NO), it is determined that the driving behavior in the current vehicle state cannot be predicted ( Step S31), the determination result is stored in the memory of the host vehicle driving behavior prediction unit 103, and the driving behavior prediction process shown in FIG. 5 is terminated.

  Next, a specific processing procedure of the support information proposal processing executed by the driving support device 100 according to the above embodiment will be described. Here, the driving assistance device 100 executes the assistance information suggestion process shown in FIG. 6 at a predetermined cycle under the condition that the ignition switch of the vehicle is turned on.

  As shown in FIG. 6, in this support information proposal process, first, the prediction result of the driving action of the surrounding vehicle C2 is received and collected through the communication unit 104 (step S40). Subsequently, it is determined whether or not the prediction result of the driving behavior of the surrounding vehicle is obtained, that is, whether or not it is determined that there is a prediction result in the surrounding vehicle C2 in step S30 shown in FIG. 5 (step S41). . When the prediction result of the driving action of the surrounding vehicle C2 is obtained (step S41 = YES), the driving action prediction result collected from the surrounding vehicle C2 in the previous step S40 is referred through the surrounding vehicle driving action prediction unit 105. (Step S42). Subsequently, the prediction result of the driving behavior of the host vehicle is read from the memory included in the driving behavior prediction unit 103 of the host vehicle, and the operation function state of the own vehicle C1 (for example, radar cruise control or lane keeping assist) is read out from the read prediction result. Etc.) and driving behavior including lane change of the host vehicle C1 is predicted (step S43). Then, by further combining the prediction result of the driving behavior of the host vehicle predicted in the previous step S43 with the prediction result of the driving behavior of the surrounding vehicle referred in the previous step S42, after a predetermined time has elapsed from the present time. The positional relationship between the host vehicle C1 and the surrounding vehicle C2 is predicted (for example, after 5 seconds). Further, based on the predicted positional relationship between the own vehicle C1 and the surrounding vehicle C2, whether or not the driving behavior of the surrounding vehicle C2 may interfere with the driving behavior of the own vehicle C1 is shown through the presentation content selection unit 106. Determination is made (step S44).

  When the driving behavior of the surrounding vehicle C2 may interfere with the driving behavior of the host vehicle C1, the driving support information is proposed to the driver of the host vehicle C1 (step S45 = YES), driving support information suitable for the vehicle state is selected from the presentation content list 106A through the presentation content selection unit 106 (step S46). Thereafter, the selected presentation content is output (proposed) as driving support information to the driver through the HMI 20 (step S47), and the support information proposing process shown in FIG. 6 is terminated.

  On the other hand, when there is no vehicle state in which driving support information should be proposed to the driver of the host vehicle C1 in the previous step S45 (step S45 = NO), the presentation content selection unit 106 proposes driving support information through the HMI 20. The support information proposal process shown in FIG. Further, even when the prediction result of the driving action of the surrounding vehicle C2 is not obtained in the previous step S41 (step S41 = NO), it is difficult to predict the positional relationship between the own vehicle C1 and the surrounding vehicle C2. Then, without providing the driving support information through the HMI 20 by the presentation content selection unit 106, the support information proposing process shown in FIG.

As described above, according to the present embodiment, the following effects can be obtained.
(1) The driving characteristic learning unit 101 includes the surrounding environment of the host vehicle C1, the presence / absence of a passenger, the degree of divergence between the desired time of arrival at the destination and the current time, the number of travels on the same road, and the host vehicle and the surrounding vehicles. The presence / absence of a change in the lane of the host vehicle C1 is learned as the driving characteristics while considering each element of the vehicle state that affects the driving characteristics of the host vehicle, such as the positional relationship with Similarly, in the peripheral vehicle C2, the driving characteristic learning unit 101 learns whether or not the lane change of the peripheral vehicle C2 is performed as the driving characteristic while considering each element of the vehicle state that affects the driving characteristic of the peripheral vehicle C2. To do. Therefore, the own vehicle driving behavior prediction unit 103 can predict whether or not the lane change of the own vehicle C1 and the surrounding vehicle C2 is highly reliable in accordance with each vehicle state. And by communicating the prediction result regarding the presence or absence of such a reliable lane change between the own vehicle C1 and the surrounding vehicle C2 using the inter-vehicle communication system, both the own vehicle C1 and the surrounding vehicle C2 It is possible to accurately predict each other's driving behavior and present highly reliable driving support information according to a realistic situation to the driver through the presentation content selection unit 106 based on the prediction result.

In addition, the said embodiment can also be implemented with the following forms.
In the above embodiment, as shown in step S27 of FIG. 5, prior to the prediction of the driving behavior of the host vehicle, for example, the speed of the vehicle, the accelerator opening, the brake state, the steering angle, the state of the direction indicator, etc. Based on the operation histories of various vehicles, the type of lane change (passing behavior (left / right), transfer behavior due to approaching a rear vehicle) that the vehicle C1 may perform is specified. Instead, the frequency rate of the lane change in the current vehicle state of the host vehicle C1 is obtained for all types of lane changes without specifying the type of lane change in advance, and the frequency rate is the highest. You may make it judge that the kind of lane change has the possibility of the own vehicle C1. In this case, it is not always necessary to compare the prediction accuracy (frequency rate of lane change) with a predetermined threshold value (for example, 80% or more) for the type of driving action that has the highest frequency rate.

  In the above embodiment, as shown in step S43 of FIG. 6, the lane change of the host vehicle C1 is changed in consideration of the operation function state of the host vehicle C1 (for example, radar cruise control, lane keeping assist, etc.). The driving behavior included was predicted. Instead of this, the driving behavior may be predicted only for whether or not the lane change of the host vehicle C1 is executed.

  In the above embodiment, the driving support information is presented by selecting from the presentation content list 106A. Instead of this, for example, every time it is determined that the driving behavior of the surrounding vehicle C2 may hinder the driving behavior of the own vehicle C1, based on the distance between the own vehicle C1 and the surrounding vehicle C2, etc. You may make it produce | generate the driving assistance information which should be shown.

  DESCRIPTION OF SYMBOLS 10 ... Illuminance sensor, 11 ... Road traffic information center, 12 ... Navigation system, 13 ... Vehicle camera, 14 ... Seating sensor, 15 ... Laser radar, 16 ... Millimeter wave radar, 17 ... External equipment, 20 ... HMI, 100 ... Driving support device 101 ... Driving characteristic learning unit 102 ... Driving characteristic storage unit 103 ... Own vehicle driving behavior prediction unit 104 ... Communication unit 105 ... Peripheral vehicle driving behavior prediction unit 106 ... Presentation content selection unit 106A ... Presented content list, 107: HMI control unit, C1: host vehicle, C2: surrounding vehicles.

Claims (1)

A plurality of vehicles having a function of learning whether or not a lane change of a vehicle is executed as a driving characteristic based on the operation history of the vehicle and a function of predicting whether or not a lane change of the vehicle is executed based on a learning result of the driving characteristic are wireless A driving support device that presents driving support information based on a prediction result of driving behavior of the host vehicle and surrounding vehicles using a vehicle-to-vehicle communication system configured to be able to communicate with each other by communication,
Vehicle conditions including the surrounding environment of the host vehicle, the presence or absence of passengers, the degree of divergence between the desired time of arrival at the destination and the current time, the number of trips on the same road, and the positional relationship between the host vehicle and the surrounding vehicle A driving characteristic learning unit that learns whether or not there is a lane change of the host vehicle for each defined vehicle state as a driving characteristic based on the operation history of the vehicle;
A host vehicle driving behavior prediction unit that predicts whether or not to execute a lane change of the host vehicle in the current vehicle state as a driving behavior while referring to a learning result of the driving property of the host vehicle by the driving property learning unit;
A surrounding vehicle driving behavior prediction unit that obtains the presence or absence of execution of a lane change predicted in the surrounding vehicle by the wireless communication and predicts the driving behavior of the surrounding vehicle from the viewpoint of the own vehicle;
Support for presenting driving support information to the driver of the host vehicle based on the driving behavior of the host vehicle predicted by the host vehicle driving behavior prediction unit and the driving behavior of the surrounding vehicle predicted by the surrounding vehicle driving behavior prediction unit A driving support device comprising: an information presentation unit.