Driving assistance system

Abstract

To provide appropriate assistance while reducing the burden on vehicle occupants.SOLUTION: A driving assistance system 1 is provided, comprising a driving context estimation unit 212 for estimating driving context associated with situations inside and outside a vehicle V on the basis of acquired information, and an assistance content determination unit 213 for determining assistance content on the basis of the driving context.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a driving support system.

Background Art

[0002] Patent Document 1 discloses a technique for presenting information that a user may be interested in through the user's speech and subsequent conversations.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the diversification of in-vehicle devices in recent years, the opportunities for passengers to operate in-vehicle devices have increased. When the opportunities to operate in-vehicle devices increase, the operation of in-vehicle devices may be troublesome for passengers. In the case of Patent Document 1, a request by the user's speech is required as a prerequisite for information presentation. Considering future automated driving and the like, it is preferable that the opportunities for passengers to directly participate in the operation of in-vehicle devices are as few as possible. Therefore, there is a need for a driving support system that can provide appropriate support while reducing the burden on passengers.

Means for Solving the Problems

[0005] The present invention provides a driving context estimation unit that estimates a driving context related to the situation inside and outside the vehicle based on the acquired information, and a support content determination unit that determines the content of support based on the driving context, and is configured as a driving support system.

Effects of the Invention

[0006] According to the present invention, it is possible to provide a driving support system that can perform appropriate support while reducing the load on the occupant.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0008] Hereinafter, the driving support system 1 according to the embodiment of the present invention will be described. FIG. 1 is a diagram for explaining the schematic configuration of the driving support system 1 according to the embodiment. The driving support system 1 includes a processing device 2 mounted on a vehicle V, a communication unit 3, an input / output device 4, various sensors 5, various in-vehicle devices 6, and a support server SV1 to which the processing device 2 is connected via a network NT. Here, examples of the vehicle V include an engine vehicle that runs on the driving force of an engine, an electric vehicle that runs on the driving force of a motor, and a hybrid vehicle that is driven by the driving forces of an engine and a motor.

[0009] The processing device 2 has a processing unit 21, a storage unit 22, and an input / output port (I / O) 23. The processing unit 21, the storage unit 22, and the input / output port 23 are connected to each other via a bus 20. Connected to the input / output port 23 are the communication unit 3, the input / output device 4, a plurality of sensors 5, a plurality of in-vehicle devices 6, etc. via a vehicle network.

[0010] The communication unit 3 has a function of connecting to the network NT via wireless, wired, and mobile phone communication networks, etc. The processing device 2 is connected to the network NT via the communication unit 3. Then, various information can be acquired from the support server SV1 and a plurality of information providing servers SVn connected to the network NT. Here, the information providing server is a server that can provide weather forecasts, traffic information, map information, tourist destination information, tourist facility information, restaurant information, fueling / charging facility information, etc. It can be either a public or private server.

[0011] The support server SV1 is a server that stores a table (desire trend correlation table 106) in which a search code to be described later is associated with facility information (facility ID), a correlation table that stores the correlation between support content and support conditions, a presentation information database 105 that stores information on facilities (POIs) presented as information along with the desire trends of drivers and passengers, and map data, etc. The support server SV1 has at least the following functions: (a) a function of registering new information obtained from an external information providing server SVn in a database by associating it with a search code described later; and (b) a function of transmitting information registered in a table or database to the processing device 2 according to a request from the processing device 2.

[0012] The input / output device 4 is an interface used for inputting instructions from a user (driver or passenger) and transmitting information to the user. The input / output device 4 includes a microphone, a speaker, a camera, a plurality of monitors available for presenting and inputting information, and various switches.

[0013] FIG. 2 is a diagram schematically showing a view of the front side of the vehicle V as seen from the interior of the vehicle V. As shown in FIG. 2, in the instrument panel P of the vehicle V, a steering wheel SW is located in front of the driver's seat. A first monitor M1 for displaying vehicle speed and the like is installed behind the steering wheel SW. A second monitor M2 for displaying information for the passenger is installed in front of the passenger seat. A third monitor M3 for displaying a map image and an agent icon described later is installed between the driver's seat and the passenger seat.

[0014] Below the third monitor M3, a switch unit SU integrating the functions of various switches is installed. As an example, the switch unit SU is a touch panel on which switch icons and option icons are displayed. When operating the in-vehicle device 6, the displayed icons, options, etc. are appropriately changed. Note that the switch unit SU may be a console on which operation buttons and operation knobs are operably installed.

[0015] At the lower part of the windshield glass W, a strip-shaped reflection part WR is provided at the boundary with the instrument panel P. The reflection part WR is provided with a length in the vehicle width direction. Information displayed on a monitor (not shown) in the instrument panel P is projected onto the reflection part WR. The passengers of the vehicle V can visually recognize the information projected onto the reflection part WR. Here, the reflection part WR only needs to be provided in a manner capable of projecting information. As an example, a reflector that reflects the information displayed on a monitor or a reflection area formed by applying a black ceramic paint to the inner surface of the windshield glass W is adopted as the reflection part WR.

[0016] FIG. 3 is a diagram schematically showing the periphery of the slit SL provided in the instrument panel P and is a diagram for explaining the arrangement of the infrared camera C1 within the slit SL. As shown in FIG. 2, in the instrument panel P, a strip-shaped slit SL is provided below the second monitor M2 described above. The slit SL is an air outlet of the air conditioner mounted on the vehicle V. The conditioned air whose temperature and humidity are adjusted by the air conditioner blows out from the slit SL into the vehicle interior. Note that a similar slit SL is also provided on the driver's seat side, and the opening of this slit SL faces the face of the driver in the driver's seat. In the present embodiment, the infrared camera C1 is installed facing the driver side within the slit SL in order to measure (detect) at least the expression and drowsiness of the driver.

[0017] Here, the infrared camera C1 employs an infrared light irradiation unit (infrared light irradiation means) capable of irradiating high-intensity light as a light source and has a large amount of self-heat generation. Therefore, it is preferable to arrange the infrared camera C1, at least the infrared light irradiation unit, in the slit SL which is a part of the air conditioner louver. With such a configuration, the infrared camera C1 (infrared light irradiation unit) can be made less conspicuous compared to the case where the infrared camera C1 (infrared light irradiation unit) is provided outside the slit SL. Furthermore, since the infrared camera C1 (infrared light irradiation unit) can be cooled by the conditioned air passing through the slit SL, the temperature rise due to self-heat can be suppressed.

[0018] Although not shown in the figure, around the driver's seat, there are also installed other cameras for imaging the driver and other passengers, a temperature sensor for measuring the temperature inside the vehicle, a microphone for collecting the voices of the driver and other passengers, and the like.

[0019] Returning to the description of FIG. 1, the sensor 5 is a sensor capable of acquiring information inside and outside the vehicle V, and the following are exemplified. Camera, object sensor, raindrop sensor, illuminance sensor, vehicle speed sensor, inertial measurement unit, temperature Sensor, occupant detection sensor.

[0020] The camera is a conventionally known camera that images the surroundings and the interior of the vehicle and outputs image data. The camera preferably includes at least one infrared camera capable of imaging the surroundings and the interior of the vehicle regardless of day or night. In the vehicle V, the camera is installed at at least one location, preferably at a plurality of locations, so as to be able to image the surroundings and the interior of the vehicle.

[0021] The object sensor is various sensors such as an ultrasonic sensor for detecting a person or an object existing near the vehicle, a millimeter-wave radar for detecting a person or an object existing around the vehicle, and a LiDAR using laser light. These object sensors are installed facing the surroundings of the vehicle in order to detect a person or an object existing around the vehicle. Further, among the object sensors, the sensor for detecting an occupant existing in the vehicle is installed facing the seating position in the vehicle.

[0022] The in-vehicle device 6 is a device mounted on the vehicle V, and the following are exemplified. Air conditioner, audio system, wiper control device, seat adjustment device, lighting device for illuminating the interior of the vehicle, navigation system, driving operation devices such as a steering wheel and pedals, driving support systems such as AD (automatic driving) and ADAS (advanced driving assistance system).

[0023] The processing unit 21 is an arithmetic processing device such as an MPU (Main Processing Unit). The storage unit 22 is an information recording medium such as an SSD (Solid State Drive), an HDD (Hard Disk Drive), and a memory. The memory unit 22 stores map data, a table (desire tendency correlation table 221) that stores information presented during assistance, and the like. Note that the contents of the map data and the desire tendency correlation table 221 are supplied from the assistance server SV1 side and updated as appropriate. The memory unit 22 stores programs for each process executed by the processing unit 21 and data generated during the process by the programs.

[0024] The processing device 2 acquires various types of information related to the situations inside and outside the vehicle V via the sensor 5, in-vehicle devices 6, and a network NT connected via the communication unit 3. As an example, the processing device 2 has a function of determining the content of assistance mainly for the passengers of the vehicle V based on the acquired information, and a function of operating the in-vehicle devices 6 based on the determined content of assistance.

[0025] The processing unit 21 has, as functional blocks, an information acquisition unit 211, a driving context estimation unit 212, an assistance content determination unit 213, a dialogue unit 214, a presented information determination unit 215, and an assistance execution unit 216.

[0026] The information acquisition unit 211 acquires information related to the situations inside and outside the vehicle V via various sensors 5 and in-vehicle devices 6. Furthermore, the information acquisition unit 211 connects to the network NT via the communication unit 3, and from the assistance server SV1 and information providing servers SVn connected to the network NT, obtains information related to the external environment of the vehicle V such as weather forecasts and traffic jam information, and information related to facilities provided during assistance such as information on sightseeing facilities and restaurants.

[0027] The information related to the external situation of the vehicle V acquired by the information acquisition unit 211 includes, as an example, the following information: (a) information capable of specifying the presence or absence of moving objects such as people, other vehicles, and animals around the vehicle V; (b) information capable of specifying the presence or absence of fixed objects such as obstacles and walls around the vehicle V; (c) information capable of specifying the environment around the vehicle V. In case of (a), the information that can identify: (a1) the moving direction and speed of the moving object, and the distance to the moving object; (a2) in case the moving object is a person, the information that can identify the person's facial expression and gestures; (a3) in case the moving object is another vehicle, the information that can identify the moving direction and speed of the other vehicle, the distance to the other vehicle, the facial expression of the driver of the other vehicle, the driver's gestures, etc. is included. In case of (b), the information that can identify: (b1) the distance to the object; (b2) the size of the object, such as its height and width, is included. In case of (c), the information that can identify: (c1) the information of time zones (early morning, morning, noon, evening, night, etc.); (c2) future information including traffic jam prediction and weather forecast; (c3) various information in the vicinity of the current location and the destination (facilities, weather conditions such as typhoon, heavy snow, storm, earthquake, disasters such as landslide, flood, traffic jam, traffic control, etc.) is included.

[0028] As an example, the information about the internal situation of the vehicle V acquired by the information acquisition unit 211 includes the following information. (d) The information that can identify the state of the passengers. (e) The information that can identify the state of the vehicle and in-vehicle devices. In case of (d), the information that can estimate: (d1) the driver's facial expression, gestures, emotional state, physical condition, sleepiness, and posture; (d2) the facial expression, gestures, emotional state, physical condition, sleepiness, posture, and the distinction between adults and children of the passengers; (d3) the information that can identify the position of the passengers in the vehicle cabin is included. In case of (e), the information about: (e1) the environment in the vehicle cabin (temperature, humidity, etc.); (e2) the driving mode of the vehicle (automatic driving mode, semi-automatic driving mode, manual driving mode); (e3) the operation mode of the in-vehicle lighting and the illuminance of the lighting; (e4) the operation mode of the air conditioner (heating, cooling, air blowing, dehumidifying, etc.) and the operation intensity (strong, medium, weak); (e5) the position of the electric seat and the tilt angle of the backrest; (e6) the operation status (on, off) of the steering heater and seat heater and the operation intensity (strong, medium, weak) is included.

[0029] Based on the information acquired by the driving context estimation unit 212, the driving context related to the internal and external situations (internal and external situations) of the vehicle is estimated. Here, the driving context means a set (information group) of information such as the situation where the vehicle is placed, the situation where the passengers are placed, the situation where other vehicles are placed, the situation of the driver, the situation of the passengers, the situation of pedestrians, the intention of the driver of the oncoming vehicle, and the intention of pedestrians, which can be estimated.

[0030] Based on the estimated driving context, the support content determination unit 213 determines the support content. Here, the support content means an influence on the driver and other passengers of the vehicle and the surroundings of the vehicle. Here, it is preferable that the support content is an influence that is assumed to be beneficial to the driver and other passengers of the vehicle and the surroundings.

[0031] The following can be exemplified as the support content. (a) When the forward visibility is poor, present an image to supplement the forward visibility. (b) When there is no rest place over a long distance ahead, recommend taking a rest at the current time. (c) When there is a person waiting to cross the road at a crosswalk in front of the vehicle, recommend to the waiting person to cross the crosswalk. (d) When the temperature inside the vehicle is high and the temperature of the passengers' faces is high, operate the air conditioner to lower the temperature inside the vehicle.

[0032] As an example, in this embodiment, correlation data that defines the correlation between the information items of each information acquired by the information acquisition unit 211 and the support content is prepared. For example, the support content of "when the forward visibility is poor, present an image to supplement the forward visibility" is selected when predetermined conditions such as "rainfall" being "heavy", "fog" being "dense", and "visible distance ahead" being "short" are satisfied. In this way, the degree (heavy, dense, short) of each information item (rainfall, fog, visible distance ahead) is associated with the support content.

[0033] Figure 4 is a diagram showing an example of the correlation data used for determining the support content for explanatory purposes. As shown in Fig. 4(a), as an example, in the correlation data, for each "support content", a plurality of information item names used for the judgment of the support decision and the degree of each information item are scored and registered. In the case of Fig. 4, for the judgment of whether to perform the support content of "vision assistance", information items such as "rainfall state", "wiper operation", and "front vision" are used, and the score value used for the judgment of whether to select "vision assistance" as the support content is shown below the information item. For example, the score value of the "rainfall state" is defined such that as the rainfall amount increases, the score value increases, such as "0" for no rainfall and "1" for light rainfall (see Fig. 4(b)). Although the illustration is omitted, the score value of the "wiper operation speed" is "0" in the stopped state, and the score value increases as the operation speed increases. For "front vision", it is "5" when there is no poor vision, and the score value decreases as the visible distance shortens. For "vehicle interior temperature", the score value increases as the difference from the recommended temperature or set temperature increases, and the direction of the temperature deviation is indicated by +-(plus or minus). "+2" means that the temperature is higher than the recommended temperature.

[0034] Therefore, when the score value of each information item specified from the information acquired by the information acquisition unit 211 satisfies the conditions of the score value of the information item assigned to the support content of "vision assistance", the support content that satisfies the conditions is determined as the support content.

[0035] As another example, the support content determination unit 213 generates feature data (vector data in an n-dimensional space when the number of information items is n) that summarizes the feature amounts of the information items of each information acquired by the information acquisition unit 211. Then, by comparing with the feature data that identifies the support content prepared for each support content, the support content having the feature data closest to the generated feature data may be determined as the support content to be executed.

[0036] When the support content is determined, if there is information to be presented during the support (support information), the presentation information determination unit 215 determines the support information. Here, depending on the support content, it may be necessary to obtain the desire tendencies of the driver and passengers in order to determine the information to be presented. Here, the desire tendency means tendencies such as (a) the current desires of the driver and passengers, (b) potentially held desires, and (c) hopes in a certain situation.

[0037] As an example, in the case of (a), examples include (a1) appetite and (a2) sleepiness. In the case of (b), examples include (b1) liking a leisurely place, (b2) wanting to avoid crowds, and (b3) liking crowds. In the case of (c), for example, when traveling, examples include (c1) being interested in history, (c2) being interested in food and drink, and (c3) being interested in scenery and landscapes.

[0038] Therefore, when it is necessary to identify the desire tendencies of the driver and passengers, the dialogue unit 214 presents a question for identifying the desire tendencies of the driver and passengers and a plurality of options with different score values (weight values) prior to the determination of the information to be presented by the presentation information determination unit 215.

[0039] The content of the question is stored in advance in the memory unit 22 together with the content of the options prepared as answers to the question. For example, when the question is "Are you hungry?" which is related to appetite, the options prepared as answers are "No", "A little", "Yes", and "Very". In this embodiment, each option is weighted, and it is set such that the higher the desire tendency for the question, the larger the score value (weight value). As an example, the score values for each option are as follows.

[0040]

Table 1

[0041] Note that, prior to determining the support information, when it is not necessary to identify the desire trends of the driver or passengers and simply an answer regarding the necessity of support is sought, the content of the question for which an answer is sought and the options of "Yes" and "No" may be presented (see Table 2 below).

[0042]

Table 2

[0043] And when the dialogue unit 214 presents a multiple-choice question, it generates a search code (score group A) consisting of a plurality of questions and the answer score values for each question. For example, if there are the first question, the second question, and the third question, and the score values of the selected options are 4, 2, and 3 respectively, "423" is generated as the search code. The generated search code is output from the dialogue unit 214 to the presentation information determination unit 215.

[0044] The support content determined by the support content determination unit 213 includes (a) support content for which it is not necessary to confirm the desire trends of the driver or passengers or the necessity of support, and (b) support content for which confirmation is required. And in (b), there are (b1) cases where information to be uniformly presented according to the support content has been determined, and (b2) cases where there is no information to be presented. In the case of (b1), the presentation information determination unit 215 determines, as the information to be presented when executing the support, the information determined in advance according to the support content. On the other hand, in the case of (a), based on the dialogue result input from the dialogue unit 214, the content of the "information to be presented" is determined. As described above, in this embodiment, the processing device 2 actively makes an inquiry (question) to the driver or passengers, and based on the answer to the question, the presentation information determination unit 215 determines the information to be presented during the support.

[0045] As described above, a search code is input from the dialogue unit 214 to the presentation information determination unit 215. The presentation information determination unit 215 determines a facility (POI: point of interest, a tourist facility in the case of tourism) that is assumed to be highly adaptable to the input search code (score group A) as the information to be presented. Then, the determined information is read from the storage unit 22 (desire trend correlation table 221) and presented on the monitor M3. In the desire trend correlation table 221, facilities that are assumed to be highly adaptable to the search code are registered. By referring to the desire trend correlation table 221 based on the search code, information on facilities that are assumed to be highly adaptable can be obtained.

[0046] When the presentation information determination unit 215 obtains information on a facility that is assumed to be highly adaptable, for presentation to the driver and passengers, an audio message such as "The recommendations are the following n locations (n is an arbitrary integer). Please specify the information of interest as the destination" is output from the speaker. In addition, an agent icon may be displayed on the third monitor to create a sense of presence as if talking to the displayed agent.

[0047] In addition, when a plurality of facilities are presented as POIs that are assumed to be highly adaptable to the search code (score group A), when any one of the presented facilities is selected, the presentation information determination unit 215 determines the selected facility as the facility to be presented for assistance.

[0048] The support execution unit 216 executes the support determined by the presentation information determination unit 215 in the manner determined by the presentation information determination unit 215. For example, when any one of the presented facilities is determined as the facility to be presented for assistance, as an example, the support execution unit 216 displays a navigation screen showing the moving route to the determined facility on the third monitor M3.

[0049] The support server SV1 includes an information acquisition unit 101, an information registration unit 102, a presentation information database 105 (presentation information DB), and a desire trend correlation table 106.

[0050] The information acquisition unit 101 periodically connects to the information providing server SVn via the network NT to acquire information on facilities (POIs) that can be used as presentation information. At this time, information related to the evaluation items of the facilities is also collected.

[0051] The information registration unit 102 calculates the evaluation items of the facility based on the collected facility information. If the facility for which the evaluation items have been calculated is already a registered facility, the evaluation items of the facility are updated. If the facility is not registered, the facility name and the evaluation items of the facility are associated with the identifier assigned to the facility name and registered in the presentation information database 105.

[0052] The presentation information database 105 is a database that registers by associating information on facilities that can be used as presentation information with the evaluation items of the facilities.

[0053] FIG. 5 is a diagram for explaining an example of the presentation information database 105. FIG. 6 is a diagram for explaining an example of the demand trend correlation table 106. As shown in FIG. 5, the presentation information database 105 includes, as evaluation items, the amount of food, the staying time, the congestion level, traditional elements, cost, and fatigue recovery elements, and each evaluation item is scored. In the presentation information database 105, the facility name and the evaluation values of the evaluation items are registered in association with the identifier (facility ID) of the facility. For example, for facility A with facility ID "001", since the score value of the amount of food is "0", it can be seen that the facility has nothing to do with food. Since the staying time is "0.5h", it can be seen that a relatively short stay is sufficient. Since the score value of the traditional elements is "5", it can be seen that the facility is a historical facility.

[0054] The information registration unit 102 extracts information on facilities (POIs) that are assumed to have a high degree of applicability to the above-described search code (score group A) from the presentation information database 105, associates the extracted information with the search code, and registers it in the demand trend correlation table 106. The demand trend correlation table 106 is a table that associates a search code (score group A) with information on facilities (POIs) that are assumed to have a high degree of applicability to the search code (score group A). As shown in FIG. 6, in the demand trend correlation table 106, a search code consisting of score values (1 to 4) for each answer from question 1 to question 4 is associated with the facility ID of the recommended facility and registered. In the demand trend correlation table 106, the facility ID of the recommended facility is associated with all possible combinations of score values for each question.

[0055] In the demand trend correlation table 106, for each search code (score group A), facilities (facility IDs) that are assumed to have a high degree of applicability to the search code (score group A) are extracted from the presentation information database 105 and associated. The extraction of facilities (POIs) that are assumed to have a high degree of applicability to the search code (score group A) is executed based on learning data (algorithm: engine). The learning data is an engine (algorithm) generated by associating a search code with a predetermined number of facility information (score group B) determined to be correlated with the search code for a predetermined number (1000 or more) of basic data. By using this engine, the degree of correlation (high or low) between a search code and a plurality of search codes can be specified from the distribution of evaluation values of evaluation items of facilities. The information registration unit 102 extracts a predetermined number, for example, three facilities with a high degree of correlation for each search code, associates the information of the extracted facilities with the search code, and registers it in the demand trend correlation table 106.

[0056] Accordingly, by referring to the desire trend correlation table 106 based on the search code obtained through the dialogue with the driver and passengers, it becomes possible to extract and present information on facilities that conform to the desire trends of the driver and passengers.

[0057] The memory unit 22 of the vehicle V also includes a desire trend correlation table 106. In the desire trend correlation table 106 on the vehicle V side, it is preferable to store a part of the desire trend correlation table 106 provided by the support server SV1, preferably, information on POIs within a predetermined range based on the current position of the vehicle V.

[0058] In the present embodiment, on the support server SV1 side, a presentation information database DB and a desire trend correlation table 106 are generated. In the desire trend correlation table 221 of the memory unit 22, a part of the information of the desire trend correlation table 106 held by the support server SV1 is stored. The functions of the information acquisition unit 101 and the information registration unit 102 may be provided on the vehicle V side, but by providing them on the support server SV1 side, the processing load on the vehicle V side (processing device 2 side) can be reduced. If the load on the processing device 2 side becomes large, there is a possibility of a delay in the determination of the information to be presented and the start of support. By providing the functions of the information acquisition unit 101 and the information registration unit 102 on the support server SV1 side, such a situation is prevented from occurring.

[0059] In the present embodiment, the memory unit 22 of the processing device 2 has only information on facilities (POIs) within a predetermined range based on the current position of the vehicle. Therefore, when the vehicle goes outside the predetermined range from which the presentation information was obtained, information on facilities in the new range of the destination is acquired from the support server - SV1 and stored in the memory unit 22.

[0060] Hereinafter, the basic processing in the processing unit 21 will be described. FIG. 7 is a flowchart for explaining the basic processing implemented in the processing unit 21. While power for driving is being supplied from a power supply source (not shown) to the processing device 2, the processing unit 21 repeatedly executes a process of checking the necessity of assistance (assistance necessity check process: see FIG. 7). The information acquisition unit 211 of the processing unit 21 is constantly input with information acquired by various sensors 5 and information indicating the operation status of the in-vehicle device 6, and information acquired by the communication unit 3 from external servers (assistance server SV1, information providing server SVn, etc.) is input as necessary.

[0061] In the assistance necessity check process, the driving context estimation unit 212 estimates the driving context based on the various input information (step S101). For example, when it is specified from the output signal of the vehicle speed sensor that the vehicle is in a driving state and from the output signal of the raindrop sensor that the vehicle is in a rainfall state (state: rainfall, degree: heavy) that causes poor visibility, a driving context is estimated that the vehicle is driving in heavy rain with poor visibility.

[0062] The assistance content determination unit 213 determines the necessity of assistance based on the content of the estimated driving context (step S102). If it is determined that assistance is not required (step S102, No), the process returns to the process of step S101. If it is determined that assistance is required (step S102, Yes), the assistance content determination unit 213 determines the content of assistance (step S103). Thereby, the assistance execution unit executes the determined assistance (step S104).

[0063] In steps S103 and S104, different processes are executed according to the content of the determined assistance. In the present embodiment, a plurality of types of assistance to be determined are prepared. In the present embodiment, representative examples of the content of assistance are given, and the processes of steps S103 and S104 will be described below.

[0064] (Scene 1) In the case of poor visibility FIG. 8 is a schematic diagram for explaining a situation in the case of poor visibility. In the driving context estimated by the driving context estimation unit 212, when in the context of (a) a heavy rainfall state, a situation where the vehicle is traveling is recognized, the assistance content determination unit 213 determines vision assistance as the assistance content to secure the vision on the front side of the vehicle. This is because when the vehicle is traveling in a heavy rainfall state, the raindrops hit the windshield glass W, and it may not be possible to secure the vision on the front side of the vehicle only by wiping with the wiper.

[0065] Here, the heavy rainfall state is specified from the output of the raindrop sensor and the captured image of the camera that captures the surroundings of the vehicle. When vision assistance is determined as the assistance content, the assistance execution unit 216 will implement the determined assistance content. For example, in the input image from the camera that captures the front side of the vehicle V, a process of removing raindrops is executed to generate a front vehicle image without raindrops (processed image IM1), and the front vehicle image without raindrops (processed image IM1) is projected onto the reflection unit WR. As a result, a video of the front side of the vehicle without raindrops is displayed in real time on the reflection unit WR.

[0066] In this way, when the vision on the front side of the vehicle visible through the windshield glass W is poor, an image excluding the cause of the poor visibility is automatically displayed on the reflection unit WR. Therefore, the driver can grasp the state of the front side of the vehicle that has become difficult to see by checking the image displayed on the reflection unit WR.

[0067] Here, when presenting the front vehicle image on the reflection unit WR, the display range may be set so that it is at least displayed up to the position where the vehicle is assumed to reach after a predetermined time (for example, 2 seconds). Here, "2 seconds" is an example, and it is desirable to set it so that at least the time range that is necessary to ensure safety in terms of the reaction speed of humans is displayed.

[0068] In this case, the assistance execution unit 216 can improve the convenience for the driver by changing the display displacement based on the traveling speed of the vehicle V at the time of display.

[0069] (Scene 2) Intent transmission to the outside of the vehicle (2-1) In the case of a pedestrian FIG. 9 is a schematic diagram for explaining a situation where a pedestrian is about to cross a crosswalk. In the driving context estimated by the driving context estimation unit 212, when (a) a pedestrian HB (a moving object) that may cross on the vehicle's path is detected in the traveling direction of the vehicle (see (a) in FIG. 9), and (b) an intention to give priority to the pedestrian HB (a hand signal in the case of (b) in FIG. 9) is recognized in the driver, the assistance content determination unit 213 determines assistance for transmitting an intention to prompt the pedestrian HB to cross the crosswalk (in the case of (c) in FIG. 9, an arrow mark MK projected on the road surface).

[0070] Here, the presence of the pedestrian HB that may cross is specified, for example, from the captured image of the camera or the output signal of the millimeter wave radar. The moving direction and moving speed of the pedestrian HB can be specified from the captured image of the camera or the change over time of the output signal of the millimeter wave radar. Similarly, the moving direction and moving speed of the vehicle V can also be specified by in-vehicle sensors (such as a vehicle speed sensor and an inertial measurement unit). Therefore, the presence or absence of a pedestrian who may cross on the vehicle's path can be estimated from the moving direction and moving speed of the pedestrian HB and the moving direction and moving speed of the vehicle.

[0071] Also, the intention of the driver DV is estimated based on the driver's expression in the captured image of the driver obtained by the camera, the presence or absence of a hand signal, and the state of driving operations such as releasing the accelerator and stepping on the brake to decelerate (see (b) in FIG. 9). Note that it can be estimated that the driver has an intention to give priority to the pedestrian on the condition that the driver's expression is not anxious or angry but "normal" or "in a good mood" and the driver gives a hand signal to yield the road.

[0072] In the driving context, these information items to be confirmed and the degree of the information items are defined, and based on each content of each information item, it is possible to determine support for conveying the intention to prompt a pedestrian to cross a crosswalk.

[0073] The support execution unit 216 executes support for conveying the intention to prompt a pedestrian to cross a crosswalk. For example, when conveying the intention to a pedestrian HB during night driving with the headlight of the in-vehicle device turned on, operations such as reducing the illuminance of the headlight and turning off the headlight are executed as support. Further, when the vehicle V is equipped with a speaker for transmitting an audio message outside the vehicle, outputting an audio message such as "Please cross" from the speaker to the outside of the vehicle is executed as support. For example, when a device for projecting an arrow outside the vehicle is installed, the projection device is driven to project and display an arrow mark MK for prompting movement on the road surface.

[0074] As a result, various in-vehicle devices are operated in accordance with the intention of the driver who is trying to let the pedestrian HB go first, so there is no need for the driver to perform actions such as reducing the illuminance of the headlight, operating for audio output, and operating the projection device. Only the driver's expression and hand signs can be used to omit subsequent device operations.

[0075] (2-2) In the case of an oncoming vehicle FIG. 10 is a schematic diagram for explaining a situation when yielding the road on a road where passing is difficult. In the driving context estimated by the driving context estimation unit 212, when (a) an oncoming vehicle OV appears while driving on a road where passing is difficult, (b) an intention to yield the road (for example, a statement to the effect of "yield the road") is recognized in the driver DV, and (c) a driving action (evacuation) of moving the vehicle towards the road shoulder is confirmed, the support content determination unit 213 determines support for conveying the intention to yield the road to the driver of the oncoming vehicle.

[0076] Here, whether passing is difficult is specified, for example, from captured images of a camera, millimeter-wave radar, map data, or the like. Also, the driver's intention is estimated based on the driver's expression in the captured image of the driver obtained by the camera and the presence or absence of a hand signal.

[0077] When it is determined to provide support for communicating the intention to give way to the driver of the oncoming vehicle OV, the support execution unit 216 executes operations of in-vehicle devices or the like for communicating the intention. For example, when communicating the intention to the driver of an oncoming vehicle during night driving with the headlights of the in-vehicle device turned on, operations such as reducing the illuminance of the headlights and turning off the headlights are executed as support. Further, when the vehicle V is equipped with a speaker for transmitting an audio message outside the vehicle, outputting an audio message such as "After you" from the speaker to the outside of the vehicle is executed as support.

[0078] As a result, various in-vehicle devices are operated in accordance with the intention of the driver who is trying to let the oncoming vehicle OV go first, so there is no need for the driver to take actions such as reducing the illuminance of the headlights and performing operations for audio output. With only a simple utterance from the driver, subsequent operations of the device can be omitted.

[0079] (Scene 3) Proposal for rest (3-1) When refueling / charging is necessary FIG. 11 is a schematic diagram for explaining a situation of a proposal for rest when refueling is necessary. In the driving context estimated by the driving context estimation unit 212, when a situation where (a) refueling / charging is necessary is recognized, the support content determination unit 213 determines a proposal for refueling / charging as the support content.

[0080] Here, the presence or absence of the need for refueling / charging is specified based on the output signals of a fuel sensor, a battery remaining amount sensor, the surroundings of the current position of the vehicle, and the presence or absence of refueling / charging facilities on the route to the destination.

[0081] When the refueling / charging proposal determination unit 213 determines a refueling / charging proposal as the support content, the presentation information determination unit causes the monitor M3 to display the agent icon IC and outputs voice messages such as "Don't you want to refuel?" and "There are few refueling facilities ahead. Don't you want to refuel?" from the speaker. Furthermore, icons for "Yes" and "No" for answering are displayed on the display face of the switch unit SU.

[0082] When "Yes" is selected in response to the refueling request, the support execution unit 216 causes the monitor M3 to display a route guidance map to the refueling facility.

[0083] This can give notice to the driver of the possibility of fuel shortage that he / she is not aware of and reduce the possibility of running out of fuel before reaching the destination.

[0084] (3-2) When proposing a rest FIG. 12 is a schematic diagram for explaining the situation of proposing a rest. When a situation where a rest is necessary is recognized in the driving context estimated by the driving context estimation unit 212, the support content determination unit 213 determines a rest proposal as the support content.

[0085] Here, examples of situations where a rest is proposed include (a) when driving continuously without rest for a predetermined time or more, (b) when there is a possibility of encountering a meteorological disaster such as heavy rain on the route to the destination in the obtained weather forecast, (c) when actions and emotional states caused by fatigue are recognized in the driver or passengers, etc.

[0086] For example, in the image of the camera that images the inside of the vehicle, when frequent posture changes of the driver or passengers are recognized, or when expressions such as "irritable" and "angry" are recognized, it is determined that actions and emotions caused by fatigue are recognized.

[0087] When the support content determination unit 213 determines to propose a rest as the support content, the presentation information determination unit 215 displays the icon IC of the dialogue agent on the monitor M3 and requests a dialogue with the occupant. An audio message such as "Don't you want to take a rest?" or "There are few facilities where you can rest ahead. Don't you want to take a rest once?" is output from the speaker. Further, icons of "Yes" and "No" for answering are displayed on the display face of the switch unit SU.

[0088] When "Yes" is selected in response to the request for rest, the dialogue unit 214 outputs a question for confirming the desire tendency of the driver or the occupant from the speaker, and displays icons of a plurality of choices for answering on the display face of the switch unit SU.

[0089] Therefore, when it is necessary to specify the desire tendency of the driver or the occupant, the dialogue unit 214 presents a question for specifying the desire tendency of the driver or the occupant and a plurality of choices with different score values (weight values) prior to the determination of the information to be presented by the presentation information determination unit 215.

[0090] The content of the question is stored in advance in the memory unit 22 together with the content of the choices prepared as answers to the question. For example, when the question is "Are you hungry?" which is related to appetite, the choices prepared as answers are "No", "A little", "Yes", and "Very". In this embodiment, each choice is weighted, and the score value (weight value) is set to increase as the desire tendency for the question is higher. Note that the score values for each choice are as shown in Table 1 above.

[0091] When an answer to the question is received from the driver or the occupant, the dialogue unit 214 generates a search code (score group A) composed of a plurality of questions and the answer score values for each question. For example, if there are the first question, the second question, and the third question, and the score values of the selected choices are 4, 2, and 3 respectively, "423" is generated as the search code.

[0092] Then, the presentation information determination unit 215 reads out a facility (POI: Point of Interest, a tourist facility in the case of tourism) that is assumed to be highly adaptable to the input search code (score group A) from the storage unit 22 (desire trend correlation table 221), and presents it on the display face of the switch unit SU. At this time, the presentation information determination unit 215 outputs an audio message such as "The following three facilities are recommended. Please specify the destination of the information you are interested in." from the speaker. In addition, an agent icon may be displayed on the third monitor M3 to create a sense of presence as if talking to the displayed agent. Information about each facility may be displayed on the second monitor M2 to assist in selecting a facility.

[0093] (Scene 4) Support for passengers (4-1) Audio When it is estimated that support for the passenger is required in the driving context estimated by the driving context estimation unit 212, support for the passenger is determined as the support target. For example, when there is an infant among the passengers and the infant is found to be bored, crying, etc., support for improving the state of the infant is determined. Here, the state of the infant being bored, crying, etc. can be identified from the captured image of the camera that captures the interior of the vehicle and the output of the microphone that picks up the interior audio.

[0094] In this embodiment, as a countermeasure in this case, the coping methods specified by the passengers and past coping examples are stored in the database in the storage unit 22. Therefore, the support execution unit 216 identifies the support method in such a case by referring to the database. For example, when calming down the infant with video or music, support such as playing a program for infants or playing music for infants will be performed.

[0095] As a result, various in-vehicle devices are operated in accordance with the intention of the passenger who wants to calm the infant, so there is no need for the driver to take actions such as playing videos or playing music by himself. Since the assistance is executed based on the state inside the vehicle imaged by the camera, the operations of the devices of the driver and the passengers can be omitted.

[0096] Similarly, in the driving context estimated by the driving context estimation unit 212, when it is estimated that the duration of the traffic jam is long, anger and irritation are shown on the face of the driver, and assistance to the driver is necessary, the assistance to the driver is determined as the assistance target.

[0097] In this case, the assistance execution unit 216 executes assistance to calm the driver. For example, the audio device is driven to play music that has a calming effect, such as classical music, and a program for infants is played on the display, etc. Such assistance will be provided. Here, the content of the assistance can be determined by taking the most frequently selected countermeasure from the countermeasure examples in the case of the same past events.

[0098] (Scene 5) Variable switch FIG. 13 is a diagram for explaining the icons to be displayed on the display of the switch unit SU. In the driving context estimated by the driving context estimation unit 212, when (a) the vehicle is traveling by automatic driving and (b) the passengers are frequently straightening their postures and are in a state of fatigue, etc., providing a relaxation environment for the passengers is determined as the assistance target. In this case, as an example, the assistance execution unit 216 makes a proposal such as "You seem to be tired. May I recline the seat?" As a result, when there is a response such as "Yes" from the passenger, such as speech or selection of the "Yes" icon on the switch unit SU, the assistance execution unit 216 drives the actuator attached to the seat to tilt the backrest of the seat on which the driver is seated, providing a more relaxing posture.

[0099] At this time, multi-stage switch icons for setting the degree of inclination of the seat may be displayed on the display of the switch unit SU and the driver may be asked to select them (see (a) of FIG. 13). In addition, the past operation history (tilt angle) may be stored in the storage unit 22 and automatically changed to the tilt accuracy that is frequently set. Also, when the driver prefers to use the icon shown in (b) of FIG. 13 rather than the icon shown in (a) of FIG. 13, based on this tendency, the icon in (a) of FIG. 13 may be changed and the icon in (b) of FIG. 13 may be displayed from the beginning.

[0100] As described above, the driving support system 1 according to the present embodiment has the following configuration. (1) The driving support system 1 includes a driving context estimation unit 212 that estimates a driving context related to the situation inside and outside the vehicle V based on the acquired information, and a support content determination unit 213 that determines the content of support based on the driving context, and is a driving support system.

[0101] With this configuration, the content of support is determined based on the driving context estimated on the driving support system 1 side. In providing support, the burden on the passenger side in operations of devices and the like can be reduced, so that a driving support system that can provide appropriate support while reducing the burden on the passenger can be provided.

[0102] (2) When the support content determination unit 213 estimates poor visibility in the driving context, it determines, as the content of support, the presentation of the processed image IM1 (see FIG. 6) obtained by removing the influence of poor visibility from the captured image by the camera (sensor 5).

[0103] With such a configuration, a processed image that compensates for the field of view is displayed on a display in front of the driver, etc. For example, when the vehicle is running under heavy rainfall conditions, when it is not possible to secure the field of view on the front side of the vehicle only by wiping with the wiper, a vehicle front image without raindrops (processed image IM1) is generated and projected onto the reflection unit WR (see Fig. 6). Also, when the vehicle V is running at night or when it is running inside a dark tunnel, an infrared image obtained by an infrared camera or a brightness-adjusted image with adjusted brightness is projected onto the reflection unit WR

[0104] As a result, when the field of view on the front side of the vehicle visible through the windshield W is poor, an image excluding the cause of the defect is automatically displayed on the reflection unit WR. Therefore, by checking the image displayed on the reflection unit WR, the driver can grasp the state of the front side of the vehicle that has become difficult to see. Thereby, a driving support system capable of providing appropriate support can be provided.

[0105] (3) The processed image IM1 is an image whose display range is the range visible to the driver on the front side of the vehicle V, and the support content determination unit 213 adjusts the display range of the processed image IM1 based on the running speed of the vehicle V.

[0106] For example, when displaying the visible range on the front side of the vehicle, it is set so that the display range becomes wider as the vehicle speed increases. Since the range to be confirmed changes according to the vehicle speed, by setting the display range to change according to the vehicle speed, a processed image IM1 of an appropriate size can be provided.

[0107] (4) When it is estimated in the driving context that the driver intends to communicate outside the vehicle, the support content determination unit 213 determines the intention communication outside the vehicle by the operation of the in-vehicle device as the support content.

[0108] For example, in the driving context estimated by the driving context estimation unit 212, when (a) a pedestrian HB (a moving object) that may cross the vehicle's path is detected in the vehicle's traveling direction (see (a) in FIG. 9), and (b) the driver is recognized to have the intention to give priority to the pedestrian HB (hand signal in the case of (b) in FIG. 9), the support content determination unit 213 determines support to convey the intention to prompt the pedestrian HB to cross the crosswalk (in the case of (c) in FIG. 9), for example, an arrow mark MK projected on the road surface. Accordingly, in providing support, the burden on the occupant side in operations of devices and the like can be reduced, so that a driving support system can be provided that can provide appropriate support while reducing the burden on the occupant.

[0109] Also, in the driving context estimated by the driving context estimation unit 212, when (a) an oncoming vehicle OV appears at night while driving on a road where passing is difficult, and (b) the driver DV is recognized to have the intention to yield, the support content determination unit 213 determines support to convey the intention to yield to the driver of the oncoming vehicle (lowering the illuminance of the headlamp). Accordingly, in providing support, the burden on the occupant side in operations of devices and the like can be reduced, so that a driving support system can be provided that can provide appropriate support while reducing the burden on the occupant.

[0110] (5) For each pattern of intention transmission to the outside of the vehicle, the device used for intention transmission and the operation mode of the device are defined. The support content determination unit 213 determines the pattern of intention transmission based on information including at least one of the movement of the driver's hand, the driver's expression, and the road conditions on which the vehicle is traveling.

[0111] With such a configuration, for example, when support is determined to convey the intention to prompt a pedestrian attempting to cross a crosswalk to cross the crosswalk, support such as projecting the arrow mark MK on the road surface is executed. Accordingly, the burden on the occupant side in device selection, device operation, and the like can be reduced, so that a driving support system can be provided that can provide appropriate support while reducing the burden on the occupant.

[0112] (6) When the necessity of situation change is estimated in the driving context, the support content determination unit 213 determines, as the support content, the presentation of information related to the situation change, the operation of the in-vehicle device 6, etc.

[0113] For example, when driving continuously without taking a break or when it is estimated that refueling is necessary, a break or refueling is proposed. In the case of refueling, it can give a notice of the possibility of fuel shortage that the driver has not noticed, and reduce the possibility of running out of fuel before arriving at the destination. In the case of rest, it can give a notice of the accumulation of fatigue that the driver has not noticed, and reduce the possibility of driving mistakes caused by fatigue before arriving at the destination. Examples of the operation of the in-vehicle device include driving the actuator of the seat on which the driver or passenger is seated to tilt the backrest, and changing the operation mode of the multi-functional variable switch for specifying the temperature of the air conditioner.

[0114] (7) A dialogue unit 214 that presents questions for specifying the desire tendency of the passengers and obtains answers to the questions, A presentation information determination unit 215 that determines the information to be presented from the information registered in the desire tendency correlation table 221 based on the answers to the questions.

[0115] With this configuration, after estimating the desire tendency of the driver or passengers from the answers to the questions, information along the desire tendency can be presented. Thereby, compared with the case of presenting information without estimating the desire tendency of the driver or passengers, information meeting the needs of the driver or passengers can be provided.

[0116] (8) The answer to the question is one option selected from a plurality of options with different score values (weightings). The presentation information determination unit 215 determines the information to be presented from the information registered in the desire tendency correlation table 221 based on the score value of the selected option.

[0117] With this configuration, information along the desire tendency of the driver or passengers can be presented.

[0118] It has desire tendency correlation tables 106 and 221 for storing information to be presented, A plurality of questions are prepared, In the desire tendency correlation tables 106 and 221, the score values of the options for each of the plurality of questions are registered in association with a plurality of pieces of information along the desire tendency as search codes indicating the desire tendency of the occupant. The presented information determination unit 215 determines, as the information to be presented, at least one piece of information whose combination of the score values of the answers to the plurality of questions matches, by extracting it from the desire tendency correlation table 221.

[0119] With this configuration, information along the desire tendency of the driver or the occupant can be presented.

[0120] (a) The dialogue unit 214 uses the agent icon displayed on the display to execute the presentation of questions and the acquisition of answers to the questions in a pseudo-dialogue format.

[0121] Instead of operating the device, the desire tendency of the driver or the occupant can be estimated through conversation with the agent, so that the content of the support along the desire tendency of the driver can be determined.

[0122] (10) When the necessity of support for the occupant of the vehicle V in the driving context is estimated, the support content determination unit 213 determines the operation of the in-vehicle device determined according to the necessary support as the content of the support.

[0123] For example, in the driving context estimated by the driving context estimation unit 212, when the duration of the traffic jam is long and the child who is a passenger is making noise or crying, the support for the passenger is determined as the support target.

[0124] In this case, the support execution unit 216 executes support to calm down the child who is a passenger. For example, the audio device will be driven to play music that has a soothing effect such as classical music, and programs for infants will be played on the display, etc., and such support will be provided. Here, the content of the support can be determined by, for example, taking the most frequently selected countermeasure from the countermeasure examples in the case of the same type of past event.

[0125] (11) As information used for estimating the driving context, the expression and drowsiness of the driver detected by the infrared camera C1 are included. The infrared light irradiation means used for the infrared camera C1 is installed in the slit SL of the air duct of the air conditioner mounted on the vehicle V.

[0126] For example, if the infrared camera C1 is adopted as the light source, this infrared camera C1 employs an infrared light irradiation unit that can irradiate high-intensity light and has a large amount of self-heat generation. Therefore, by arranging the infrared camera at the slit SL which is a part of the air conditioner louver, the infrared camera can be made inconspicuous. Furthermore, since the unit of the infrared camera can be cooled by the air conditioner air passing through the slit SL, the temperature rise due to the self-heat generation of the unit can be suppressed.

[0127] (12) The information used for estimating the driving context includes the past operation history of in-vehicle devices. When the in-vehicle device has a plurality of operation modes with different degrees of operation, the support content determination unit 213 determines the operation mode based on the past operation history of the in-vehicle device.

[0128] With such a configuration, each time the driver or passenger operates the in-vehicle device, the frequency of changing and adjusting the operation mode of the in-vehicle device can be suppressed. As a result, the burden on the driver and passenger side in operating the device can be reduced, and a driving support system that can provide appropriate support while reducing the load on the passenger can be provided.

[0129] (13) The information used for estimating the driving context includes the vehicle's external environment (night, day), the vehicle's state (driving, stopped), and the current state of the occupant (status: driving, resting). When the support target is the in-vehicle lighting device and the driving context is estimated to be in a drowsy state at night, the support content determination unit 213 adjusts the illuminance of the lighting device in the vehicle interior.

[0130] This makes it possible to automatically reduce the illuminance of the lighting device when the driver falls asleep during a break, etc. This enables appropriate support for the driver.

[0131] (I) The information used for estimating the driving context includes at least the driver's physical state, the physical states of other occupants, in-vehicle information, out-of-vehicle information, communication information, Web information, cloud information, dialogue information, and information on the preferences of the occupants.

[0132] With this configuration, it is possible to obtain information that conforms to the vehicle's demand trends, so that appropriate information for support can be obtained while preventing the occupants from being bothered.

[0133] (II) The support content determination unit 213 determines the content of support necessary to improve the safety, convenience, and comfort of the driver and occupants based on the driving context.

[0134] With this configuration, it is possible to implement actions that are assumed to be beneficial for the vehicle's driver, other occupants, and the surroundings of the vehicle while preventing the occupants from being bothered.

[0135] (III) The support server SV1 has an information acquisition unit 101 that acquires the information to be provided for support via the network NT, and The information obtained is registered in the presentation information database 105 in association with the score value of the evaluation item of the information, and the information obtained by the information acquisition unit 101 is registered in the desire tendency correlation table 106 in association with the search code determined from the questions asked in the dialogue format and the answers to the questions. It has an information registration unit 102. The information obtained by the information acquisition unit 101 is information on facilities obtained from sensors or external clouds, and includes information on the evaluation items of the facilities. Based on the driving context generated from the information obtained by the information acquisition unit 211, the support content determination unit 213 determines the information to be presented from the desire tendency correlation table 106 so as to improve safety, convenience, and comfort.

[0136] With such a configuration, it is possible to implement the prompting that is assumed to be beneficial to the driver, other passengers, and the surroundings of the vehicle, while preventing the annoyance of the passengers.

Explanation of Signs

[0137] 1: Driving support system 2: Processing device 3: Communication unit 4: Input / output device 5: Sensor 6: In-vehicle equipment 21: Processing unit 211: Information acquisition unit 212: Driving context estimation unit 213: Support content determination unit 213: Support content determination unit 214: Dialogue unit 215: Presentation information determination unit 216: Support execution unit 22: Memory unit 221: Desire tendency correlation table 23: Input / output port SV1: Support server 101: Information acquisition unit 102: Information registration unit 105: Presentation information database 106: Desired Tendency Correlation Table P: Instrument Panel SL: Slit SU: Switch Unit SVn: Information Providing Server V: Vehicle

Claims

1. A driving support system comprising: a driving context estimation unit that estimates a driving context related to the situation inside and outside a vehicle based on acquired information; and a support content determination unit that determines the content of support based on the driving context.

2. In Claim 1, when the support content determination unit estimates poor visibility in the driving context, the driving support system determines, as the content of the support, the presentation of a processed image obtained by removing the influence of the poor visibility from a captured image captured by a camera.

3. In Claim 2, the processed image is an image having a display range within a range visible to the driver, and the support content determination unit adjusts the display range of the processed image based on the traveling speed of the vehicle.

4. In Claim 1, when the support content determination unit estimates that the driver intends to communicate outside the vehicle in the driving context, the driving support system determines, as the content of the support, the communication of the intention outside the vehicle by the operation of in-vehicle equipment.

5. In Claim 4, for each pattern of the communication of the intention outside the vehicle, the device used for the communication of the intention and the operation mode of the device are defined, and the support content determination unit determines the pattern of the communication of the intention based on information including at least one of the movement of the driver's hand, the driver's expression, and the road conditions on which the vehicle is traveling.

6. In Claim 1, when the support content determination unit estimates the necessity of changing the situation in the driving context, the driving support system determines, as the content of the support, the presentation of information related to the change of the situation.

7. In Claim 6, a dialogue unit that presents a question for specifying the desire tendency of the passenger and acquires an answer to the question; and a presentation information determination unit that determines the information to be presented based on the answer to the question.

8. In Claim 7, the answer to the question is one option selected from a plurality of options having different score values, and the presentation information determination unit determines the information to be presented based on the score of the selected option.

9. In Claim 8, it has a desire tendency correlation table that stores the information to be presented, and a plurality of the questions are prepared. In the demand tendency correlation table, the score values of the options for each of the plurality of questions are registered in association with a plurality of pieces of information conforming to the demand tendency as search codes indicating the demand tendency of the occupant. The driving support system, wherein the presentation information determination unit determines at least one piece of information that matches the combination of the score values of the answers to the plurality of questions as the information to be presented.

10. In Claim 1, when the necessity of support for the occupant of the vehicle in the driving context is estimated by the support content determination unit, the driving support system determines an operation of an in-vehicle device determined according to the necessary support as the content of the support.

11. In Claim 10, the information used for estimating the driving context includes the expression and drowsiness of the driver detected by an infrared camera, the driving support system, wherein the infrared light irradiation means used for the infrared camera is installed in a blower duct of an air conditioner mounted on the vehicle.

12. In Claim 10, the information used for estimating the driving context includes the past operation history of the in-vehicle device, when the in-vehicle device has a plurality of operation modes with different degrees of operation, the driving support system determines the operation mode based on the past operation history of the in-vehicle device by the support content determination unit.

13. In Claim 12, the information used for estimating the driving context includes the external environment of the vehicle, the state of the vehicle, and the current state of the occupant, when the support target is an in-vehicle lighting device and it is estimated that the vehicle is in a drowsy state at night in the driving context, the driving support system adjusts the illuminance by the lighting device in the vehicle interior.

Images