Navigation system, navigation method, and program product

Abstract

The invention relates to a navigation system, a navigation method, and a program product. The navigation system generates navigation information on the basis of the current position of the vehicle, map information, and destination information indicating the destination of the vehicle, generates delivery information, which is information to be delivered to the driver via the user interface, on the basis of the navigation information, and transmits the information to the driver on the basis of the response of the driver to the delivery information delivered from the user interface to the driver. When it is determined that any one of the cognition, determination, and manipulation of the driver with respect to the transmission information has been disordered, the information transmission device determines whether or not the driver has been disordered on the basis of the transmission information transmitted to the driver via the user interface and the reaction of the driver with respect to the transmission information, and determines whether or not the driver has been disordered on the basis of the transmission information transmitted to the driver via the user interface and the reaction of the driver with respect to the transmission information. The transmission information is generated or the navigation information is generated so as to suppress a disorder in any one of cognition, determination, and manipulation by a driver.

Description

Technical Field

[0001] This disclosure relates to navigation systems, navigation methods, and program products. Background Technology

[0002] Patent document 1 (Japanese Patent Application Publication No. 2024-20616) describes the following main idea: adjusting the parameters of navigation commands related to manipulation considering the difficulty of manipulation; generating a measure of the difficulty of manipulation of a set of data using a machine learning model; and applying query data to a machine learning model to generate a measure of the difficulty of manipulation.

[0003] Furthermore, while Patent Document 1 describes the main causes of confusion, it does not describe any technology for suppressing driver confusion. Therefore, the technology described in Patent Document 1 (the technology for generating a measure of difficulty) cannot suppress the possibility of driver confusion when navigating a vehicle. Summary of the Invention

[0004] In view of the above problems, the purpose of this disclosure is to provide a navigation system, navigation method, and program product that can suppress the possibility of driver confusion when navigating a vehicle.

[0005] (1) One aspect of this disclosure is a navigation system having a processor that performs the following actions: generating navigation information for navigating the driver of the vehicle based on the vehicle's current location, map information, and destination information representing the vehicle's destination; generating transmission information as information to be transmitted to the driver via a user interface based on the navigation information; determining whether there is confusion in the driver's cognition, judgment, or operation of the transmission information based on the driver's reaction to the transmission information transmitted from the user interface; and when it is determined that there is confusion in the driver's cognition, judgment, or operation of the transmission information, generating the transmission information or generating the navigation information based on the transmission information transmitted to the driver via the user interface and the driver's reaction to the transmission information, so as to suppress any confusion in the driver's cognition, judgment, or operation.

[0006] (2) In the navigation system of scheme (1), the navigation system may include a first machine learning model stored in the storage device of the vehicle and a second machine learning model stored in the storage device of the server. The second machine learning model generates a prior instruction to the first machine learning model based on the destination information. The first machine learning model generates the transmission information in real time based on the prior instruction generated by the second machine learning model and the navigation information.

[0007] (3) In the navigation system of scheme (1) or (2), the processor may generate the transmission information or the navigation information based on personal information related to any of the driver’s cognition, judgment and operation, the transmission information and the driver’s reaction to the transmission information, so as to suppress confusion in any of the driver’s cognition, judgment and operation.

[0008] (4) The navigation system of any of the schemes (1) to (3) may also have a simulator configured on the server, the simulator simulates the action of generating the navigation information, and the second machine learning model cooperates with the simulator to repeatedly predict the driver's behavior and optimize the transmitted information.

[0009] (5) In any of the navigation systems in schemes (1) to (4), the information may be transmitted from the user interface to the driver as voice guidance output from a speaker or image guidance displayed on a screen.

[0010] (6) In any of the navigation systems in schemes (1) to (5), the determination of whether there is confusion in the driver's cognition, judgment and operation of the transmitted information is performed by a recognizer, wherein the recognizer detects the information of the dividing lines contained in the image captured by the front camera mounted on the vehicle.

[0011] (7) In any of the navigation systems in schemes (1) to (6), the determination of whether there is confusion in the driver's cognition, judgment and operation of the transmitted information is performed by the processor, wherein the processor controls the brake actuator or steering actuator based on the driver's operation.

[0012] (8) In any of the navigation systems in schemes (1) to (7), the determination of whether there is confusion in the driver's cognition, judgment and operation of the transmitted information is carried out by a driver monitoring system, wherein the driver monitoring system identifies the driver's reaction to the transmitted information based on the image of the driver captured by the driver monitoring camera or the voice of the driver collected by the microphone.

[0013] (9) In any of the navigation systems in schemes (1) to (8), the transmission information generated by the processor may include any one of the following: timing, sequence, granularity and specificity of guidance, additional information given during guidance, type of voice, tone, volume and speaking style, display content of image guidance, display position, display size, color and font.

[0014] (10) In any of the navigation systems in schemes (1) to (9), the processor may also perform the addition or update of the transmission information based on the driver’s response to the transmission information passed from the user interface to the driver.

[0015] (11) One aspect of this disclosure is a navigation method comprising: generating navigation information for navigating a driver of the vehicle based on the vehicle’s current location, map information, and destination information representing the vehicle’s destination; generating transmission information as information to be transmitted to the driver via a user interface based on the navigation information; and determining whether there is confusion in the driver’s cognition, judgment, or operation of the transmission information based on the driver’s reaction to the transmission information transmitted to the driver from the user interface, and when it is determined that there is confusion in the driver’s cognition, judgment, or operation of the transmission information, generating the transmission information or generating the navigation information based on the transmission information transmitted to the driver via the user interface and the driver’s reaction to the transmission information, so as to suppress confusion in the driver’s cognition, judgment, or operation.

[0016] (12) One aspect of this disclosure is a program product including a computer program that causes a processor of a computer mounted in a vehicle to perform the following actions: generating navigation information for navigating the driver of the vehicle based on the vehicle's current location, map information, and destination information representing the vehicle's destination; generating transmission information as information to be transmitted to the driver via a user interface based on the navigation information; and determining whether there is confusion in the driver's cognition, judgment, or operation of the transmission information based on the driver's reaction to the transmission information transmitted from the user interface, wherein, when it is determined that there is confusion in the driver's cognition, judgment, or operation of the transmission information, the transmission information or the navigation information is generated based on the transmission information transmitted to the driver via the user interface and the driver's reaction to the transmission information to suppress any confusion in the driver's cognition, judgment, or operation.

[0017] According to this disclosure, it is possible to suppress the possibility of driver confusion when navigating a vehicle. Attached Figure Description

[0018] Figure 1 This is a diagram illustrating an example of the navigation system SY according to the first embodiment.

[0019] Figure 2 It means that it has been applied. Figure 1 The diagram shows an example of a navigation system SY, including its vehicle VH, server SV, etc.

[0020] Figure 3 It means Figure 2 The diagram shows an example of the configuration of a vehicle's VH.

[0021] Figure 4 It means Figure 2 The diagram shows an example of the structure of a server SV.

[0022] Figure 5 This is a diagram used to illustrate the first example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1.

[0023] Figure 6 This is a diagram used to illustrate a second example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1.

[0024] Figure 7 This is a diagram used to illustrate the third example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1.

[0025] Figure 8 This is a diagram used to explain the fourth example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1.

[0026] Figure 9 This is a diagram used to explain the fifth example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1.

[0027] Figure 10 This is a flowchart illustrating an example of processing performed by the processor VH73 of the computer VH7 of the vehicle VH equipped with the navigation system SY of the second embodiment. Detailed Implementation

[0028] Hereinafter, with reference to the accompanying drawings, embodiments of the navigation system, navigation method, and program product of this disclosure will be described.

[0029] <First Implementation>

[0030] Figure 1 This is a diagram illustrating an example of the navigation system SY according to the first embodiment. Figure 2 It means that it has been applied. Figure 1 The diagram shows an example of a navigation system SY, including its vehicle VH, server SV, etc. Figure 3 It means Figure 2 The diagram shows an example of the configuration of a vehicle's VH. Figure 4 It means Figure 2 The diagram shows an example of the structure of a server SV.

[0031] exist Figures 1-4 In the example shown, the navigation system SY consists of a computer VH7 mounted on the vehicle VH, which has a communication interface VH71, a storage device VH72, and a processor VH73, and a computer server SV, which has a communication interface SV1, a storage device SV2, and a processor SV3. The navigation system SY includes a navigation information generation unit SY1, a machine learning model unit SY2, a decision-making unit SY3, and a simulator SY4.

[0032] The processor VH73 of the computer VH7 of the vehicle VH functions as a navigation information generation unit SY1. The navigation information generation unit SY1 generates navigation information for the driver of the vehicle VH based on the current location of the vehicle VH, map information, and destination information indicating the destination of the vehicle VH. The current location of the vehicle VH is calculated, for example, by the navigation information generation unit SY1 based on GPS signals received by a GPS (Global Positioning System) receiver functioning as a sensor VH6. Map information is stored, for example, in the storage device VH72 of the computer VH7.

[0033] In another example, map information can also be obtained from outside the vehicle VH via the communication interface VH71 of the computer VH7.

[0034] exist Figures 1-4 In the example shown, the destination information representing the destination of vehicle VH is input by the driver of vehicle VH via the user interface (UI) VH1 of vehicle VH.

[0035] Figure 5 This is a diagram used to illustrate the first example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1. Figure 6 This is a diagram used to illustrate a second example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1. Figure 7This is a diagram used to illustrate the third example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1. Figure 8 This is a diagram used to explain the fourth example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1. Figure 9 This is a diagram used to explain the fifth example of navigation information (driving route plan of vehicle VH) generated by the navigation information generation unit SY1.

[0036] exist Figure 5 In the example shown, the navigation information generation unit SY1 generates... Figure 5 The route plan for vehicle VH, indicated by the middle arrow, serves as the navigation information for vehicle VH from its current location to its destination. To travel from its current location to its destination, vehicle VH must not turn left onto road RD1 at the fork with road RD2, but instead continue straight on road RD1 at the fork with road RD2. Immediately following this, at the fork with road RD3, it must turn left onto road RD1.

[0037] If the assumption is based on Figure 5 The driving route plan (navigation information) of vehicle VH, indicated by the middle arrow, generates the message "Please turn left 400m ahead" as the information to be conveyed to the driver of vehicle VH. However, depending on the shape of roads RD1, RD2, and RD3, the driver's cognitive ability, and the driver's tension, the driver of vehicle VH may not be able to accurately grasp "400m ahead". Vehicle VH may not be able to properly turn left on road RD1 at the fork with road RD3 (for example, vehicle VH turns left on road RD1 at the fork with road RD2, or vehicle VH goes straight on road RD1 at the fork with road RD3, etc.).

[0038] Furthermore, if the assumption is based on Figure 5 The driving route plan (navigation information) of vehicle VH, indicated by the middle arrow, generates the message "Please turn left at the second fork" as the information to be conveyed to the driver of vehicle VH. However, depending on the shape of roads RD1, RD2, and RD3, the driver of vehicle VH's cognitive ability, the driver's tension, and the driver's spatial recognition ability, the driver of vehicle VH may not be able to accurately identify the "second fork". Vehicle VH may not be able to properly turn left on road RD1 at the fork with road RD3 (for example, vehicle VH turns left on road RD1 at the fork with road RD2, or vehicle VH goes straight on road RD1 at the fork with road RD3, etc.).

[0039] Therefore, in the navigation system SY of the first embodiment, the processing described later is performed in the machine learning model unit SY2, etc., in a manner that the vehicle VH can appropriately turn left on road RD1 at the fork with road RD3 regardless of the shape of roads RD1, RD2, RD3, the cognitive ability of the driver of vehicle VH, the tension of the driver of vehicle VH, etc.

[0040] exist Figure 6 In the example shown, the navigation information generation unit SY1 generates... Figure 6 The route plan for vehicle VH, indicated by the middle arrow, serves as the navigation information for vehicle VH from its current location to its destination. To travel from its current location to its destination, vehicle VH needs to make a left turn on road RD4 at the fork with road RD5, and then a right turn on road RD5 at the subsequent fork with road RD6.

[0041] If the assumption is based on Figure 6 The route plan (navigation information) of vehicle VH, indicated by the middle arrow, generates the message "Please turn left 300m ahead" to be transmitted to the driver of vehicle VH. It also generates the message "Please turn right 50m ahead" to be transmitted immediately after vehicle VH turns left onto road RD4 at the fork with road RD5. This requires the driver of vehicle VH to make continuous cognitive judgments, which may confuse the driver and lead to incorrect decisions (e.g., vehicle VH going straight on road RD5 instead of turning right at the fork with road RD6). Alternatively, due to processing delays, communication delays, etc., the presentation of the "Please turn right 50m ahead" message to the driver of vehicle VH may be delayed, and vehicle VH may be unable to turn right onto road RD5 at the fork with road RD6.

[0042] Furthermore, if the assumption is based on Figure 6 The driving route plan (navigation information) of vehicle VH, indicated by the middle arrow, generates the message "Please turn left 300m ahead. Then please turn right 70m ahead." This message is intended to be transmitted to the driver of vehicle VH. Therefore, this requires the driver of vehicle VH to continuously perform cognitive judgment operations. This could potentially burden the driver of vehicle VH's cognitive judgment when turning left onto road RD4 at the fork with road RD5, as the driver of vehicle VH might forget that vehicle VH needs to turn right onto road RD5 at the fork with road RD6.

[0043] Therefore, in the navigation system SY of the first embodiment, the processing described later is performed in the machine learning model unit SY2, etc., in a manner that the vehicle VH can appropriately turn left on road RD4 at the fork with road RD5 and appropriately turn right on road RD5 at the fork with road RD6, regardless of the shape of roads RD4, RD5, RD6, the cognitive ability of the driver of vehicle VH, or the tension of the driver of vehicle VH.

[0044] exist Figure 7 In the example shown, the navigation information generation unit SY1 generates... Figure 7 The route plan for vehicle VH, indicated by the middle arrow, serves as the route plan (navigation information) for vehicle VH from its current location to its destination. To travel from its current location to its destination, vehicle VH needs to proceed straight on road RD7 at the fork with the major road RD8 (following immediately after passing through intersection IS), and then turn left onto road RD7 at the fork with the minor road RD9.

[0045] If inappropriate information is generated as the information to be delivered to the driver of vehicle VH, and the driver of vehicle VH does not have sufficient time to observe the image guidance displayed on the monitor, the driver of vehicle VH may make incorrect judgments (e.g., vehicle VH turns left onto road RD7 at the fork with road RD8).

[0046] Therefore, in the navigation system SY of the first embodiment, the processing described later is performed in the machine learning model unit SY2, etc., in a manner that the vehicle VH can appropriately travel straight on road RD7 at the fork with road RD8 and appropriately turn left on road RD7 at the fork with road RD9, regardless of the shape of roads RD7, RD8, RD9, the cognitive ability of the driver of vehicle VH, or the tension of the driver of vehicle VH.

[0047] exist Figure 8 In the example shown, the navigation information generation unit SY1 generates... Figure 8 The route plan for vehicle VH, indicated by the middle arrow, serves as the navigation information for vehicle VH from its current location to its destination. To travel from its current location to its destination, vehicle VH must continue on the general road RDA, without entering the highway RDB from the general road RDA.

[0048] Generally speaking, when a vehicle enters a highway from a regular road, it usually travels in the right lane of the left or right lane of the regular road before entering the highway.

[0049] The general road RDA and the highway RDB are formed by a vehicle (VH) traveling in the left lane (LN1) of the general road RDA and the right lane (LN2) of the highway RDA. Figure 8 In the example shown, if vehicle VH is traveling in the left lane LN1 of a regular road RDA, the driver of vehicle VH might mistakenly believe that vehicle VH can continue to travel on the regular road RDA, and vehicle VH might mistakenly enter the highway RDB.

[0050] Therefore, in the navigation system SY of the first embodiment, the processing described later is performed in the machine learning model unit SY2, etc., in a manner that allows the vehicle VH to continue driving on the general road RDA regardless of the shape of the left lane LN1 and right lane LN2 of the general road RDA, the shape of the highway RDB, the cognitive ability of the driver of the vehicle VH, the tension of the driver of the vehicle VH, etc.

[0051] exist Figure 9 In the example shown, the navigation information generation unit SY1 generates... Figure 9 The route plan for vehicle VH, indicated by the middle arrow, serves as the navigation information for vehicle VH from its current location to its destination. To travel from its current location to its destination, vehicle VH needs to transition from general road RDA to highway RDB.

[0052] As mentioned above, generally speaking, when a vehicle enters a highway from a regular road, it usually travels in the right lane of the left or right lane of the regular road before entering the highway.

[0053] The general road RDA and the highway RDB are formed by a vehicle (VH) traveling in the left lane (LN1) of the general road RDA and the right lane (LN2) of the highway RDA. Figure 9 In the example shown, if we assume based on Figure 9 The driving route plan (navigation information) of vehicle VH, indicated by the middle arrow, generates the message "Enter the highway 60m ahead." This message is intended to be transmitted to the driver of vehicle VH. However, the driver of vehicle VH may mistakenly believe that in order for vehicle VH to enter the highway RDB from the regular road RDA, it needs to travel in the right lane LN2 of the regular road RDA. As a result, vehicle VH may incorrectly continue traveling in the regular road RDA (vehicle VH cannot enter the highway RDB).

[0054] Therefore, in the navigation system SY of the first embodiment, the processing described later is performed in the machine learning model unit SY2, etc., in a way that the vehicle VH can enter the highway RDB from the general road RDA regardless of the shape of the left lane LN1 and right lane LN2 of the general road RDA, the shape of the highway RDB, the cognitive ability of the driver of the vehicle VH, the tension of the driver of the vehicle VH, etc.

[0055] exist Figures 1-4 In the example shown, the navigation information generation unit SY1 stores the generated navigation information as a log of instructions issued from the navigation system SY to the driver of vehicle VH in the storage device VH72. Furthermore, the navigation information generation unit SY1 sends the generated navigation information as a driving route plan for vehicle VH to the server SV via the communication interface VH71 of the computer VH7. Moreover, the navigation information generation unit SY1 sends the generated navigation information to the machine learning model unit SY2.

[0056] The machine learning model unit SY2 generates transmission information based on the navigation information generated by the navigation information generation unit SY1, which is to be transmitted to the driver via the user interface VH1 to the vehicle VH.

[0057] exist Figures 1-4 In the example shown, the machine learning model unit SY2 includes a first machine learning model SY21 (refer to) stored in the storage device VH72 of the computer VH7 in the vehicle VH. Figure 2 The second machine learning model SY22 (refer to) and the storage device SV2 stored on server SV. Figure 2 The second machine learning model, SY22, possesses a large-scale language model (LLM) similar to SY22A (see reference). Figure 2 The first machine learning model, SY21, is lighter than the large-scale language model SY22A. (Refer to SY21A) Figure 2 It should be noted that the lightweight large-scale language model SY21A is lighter than the large-scale language model SY22A, and can also be considered a so-called small-scale language model.

[0058] The second machine learning model SY22, for example, is based on destination information input by the driver of vehicle VH via the user interface VH1 of vehicle VH and personal information of the driver of vehicle VH pre-entered by the driver of vehicle VH via the smartphone SP used by the driver of vehicle VH (characteristics of the driver of vehicle VH) (in Figure 2In the example shown, the driver's personal information for vehicle VH is stored on server SV, generating a prior instruction for the first machine learning model SY21. Specifically, the second machine learning model SY22 generates a prior instruction for the first machine learning model SY21 when the driver of vehicle VH inputs destination information (that is, before navigating the driver of a moving vehicle VH). Furthermore, the second machine learning model SY22 sends the generated prior instruction to the first machine learning model SY21.

[0059] In another example, the driver's personal information for vehicle VH can also be pre-entered via user interface VH1.

[0060] exist Figures 1-4 In the example shown, the first machine learning model SY21 generates, in real time (i.e., while the vehicle VH is in motion), delivery information to be transmitted to the driver of the vehicle VH, based on prior instructions generated by the second machine learning model SY22 and navigation information generated by the navigation information generation unit SY1. That is, the delivery information to be transmitted to the driver of the vehicle VH is not generated by the second machine learning model SY22 of the server SV, but by the first machine learning model SY21 of the vehicle VH. Therefore, delivery information can be generated in real time without the impact of communication delay between the vehicle VH and the server SV. The first machine learning model SY21 sends the generated delivery information to the user interface VH1 as voice guidance output from a speaker (part of the user interface VH1) or image guidance displayed on a monitor (another part of the user interface VH1).

[0061] The user interface VH1 presents the information (voice guidance, image guidance) generated by the first machine learning model SY21 to the driver of the vehicle VH. That is, the information generated by the machine learning model SY2 is transmitted from the user interface VH1 to the driver of the vehicle VH as voice guidance or image guidance.

[0062] The information generated by the machine learning model SY2 includes any one of the following: timing, sequence, granularity and specificity of the guidance, additional information assigned during guidance, type of speech, tone, volume and manner of speaking, content of image guidance, display position, display size, color and font.

[0063] exist Figures 1-4In the example shown, the driver of vehicle VH responds to the information transmitted from the user interface VH1 to the driver of vehicle VH, regardless of factors such as the shape of the road through which the driver of vehicle VH can drive, the driver's cognitive ability, or the driver's tension.

[0064] Specifically, in Figures 1-4 In the example shown, the processor VH73 of the computer VH7 of vehicle VH functions as a decision unit SY3. The decision unit SY3 determines whether there is any confusion in the driver's cognition, judgment, or operation of the transmitted information from the user interface VH1 to the driver of vehicle VH based on the driver's reaction to the transmitted information.

[0065] When the determination unit SY3 determines that the driver of vehicle VH is confused in any of the aspects of cognition, judgment, or operation of the transmitted information, the machine learning model unit SY2 generates transmission information based on the transmission information transmitted to the driver of vehicle VH via user interface VH1 and the driver's reaction to the transmission information, so as to suppress any confusion in the driver's cognition, judgment, or operation.

[0066] In detail, the machine learning model unit SY2 generates transmission information based on any personal information related to the driver's cognition, judgment, and operation in the vehicle VH, the transmission information generated by the machine learning model unit SY2, and the driver's reaction to the transmission information in the vehicle VH, in order to suppress any confusion in the driver's cognition, judgment, and operation in the vehicle VH.

[0067] exist Figure 2 In the example shown, personal information related to any of the driver's cognition, judgment, or operation of vehicle VH is input into the smartphone SP used by the driver of vehicle VH. The smartphone SP sends this personal information to the server SV, and this personal information is used in the second machine learning model SY22 of the machine learning model unit SY2.

[0068] In another example, personal information related to the driver's cognition, judgment, and operation of the vehicle VH can be entered into a device other than a smartphone SP, such as the user interface VH1, and sent from that device to the server SV.

[0069] exist Figures 1-4In the example shown, the actuator control unit SY31, which controls the actuators VH5 (e.g., brake actuators, steering actuators, hazard lights, etc.) based on the driver's operation of the vehicle VH, is included in the determination unit SY3.

[0070] Specifically, if the brake pedal is unnecessarily pressed (that is, the brake actuator is controlled) when the driver of vehicle VH needs to perform an operation to turn vehicle VH right or left, the determination unit SY3 (actuator control unit SY31) determines that the driver of vehicle VH is confused in any of the following aspects: perception, judgment, or operation of the transmitted information.

[0071] Furthermore, if the steering wheel is wobbled to the left or right when the driver of vehicle VH needs to perform an operation to turn vehicle VH to the right or left (that is, unnecessary control of the steering actuator is performed), the determination unit SY3 (actuator control unit SY31) determines that the driver of vehicle VH is confused in any of the following aspects: cognition of the transmitted information, judgment, or operation.

[0072] Furthermore, if the driver of vehicle VH illuminates a hazard light that is not necessary for the right or left turn when the driver of vehicle VH needs to perform the operation of turning vehicle VH to the right or left, the determination unit SY3 (actuator control unit SY31) determines that there is confusion in any of the driver's cognition, judgment, or operation of the transmitted information.

[0073] The actuator control unit SY31 sends a log of the driver's actions in vehicle VH (vehicle VH) to the second machine learning model SY22 on the server SV when the driver is deemed confused in any aspect of their perception, judgment, or operation of the transmitted information. When the actuator control unit SY31 determines that the driver of vehicle VH is confused in any aspect of their perception, judgment, or operation of the transmitted information, a log of the instructions issued from the navigation system SY to the driver of vehicle VH (navigation information generated by the navigation information generation unit SY1) is also sent to the second machine learning model SY22 on the server SV.

[0074] When the actuator control unit SY31 determines that the driver of vehicle VH is confused in any of the perception, judgment, or operation of the transmitted information, the machine learning model unit SY2 generates transmission information based on the transmission information transmitted to the driver of vehicle VH via the user interface VH1 and the driver's reaction to the transmission information (the driver's operation of vehicle VH) in order to suppress any confusion in the driver's perception, judgment, or operation of vehicle VH.

[0075] In addition, Figures 1-4In the example shown, the recognition unit SY32 includes a determination unit SY3 that detects information such as dividing lines contained in images captured by a front camera VH2 mounted on the vehicle VH. Dividing lines refer to displays placed on the road when it is necessary to properly guide traffic flow, such as traffic dividers (zebra crossings).

[0076] Specifically, when the driver of vehicle VH needs to perform an operation to make vehicle VH turn right or left, and the recognition unit SY32 detects that vehicle VH unnecessarily enters the zebra crossing, the determination unit SY3 determines that the driver of vehicle VH is confused in any of the following aspects: cognition of the transmitted information, judgment, or operation.

[0077] Furthermore, if the driver of vehicle VH needs to perform an operation to make vehicle VH turn right or left, and the recognition unit SY32 detects that vehicle VH unnecessarily enters the shoulder, the determination unit SY3 determines that the driver of vehicle VH is confused in any of the following aspects: cognition of the transmitted information, judgment, or operation.

[0078] Furthermore, when the driver of vehicle VH needs to perform an operation to make vehicle VH turn right or left, if the recognition unit SY32 detects that vehicle VH unnecessarily crosses the dividing line, the determination unit SY3 determines that the driver of vehicle VH is confused in any of the following aspects: cognition of the transmitted information, judgment, or operation.

[0079] Furthermore, if the driver of vehicle VH is required to make vehicle VH turn right or left, and the recognition unit SY32 detects that vehicle VH has violated regulations (e.g., driving against traffic), the determination unit SY3 determines that the driver of vehicle VH is confused in any of the following aspects: understanding of the transmitted information, judgment, or operation.

[0080] The identifier SY32 sends a log of the driver's actions in vehicle VH (Vehicle VH) when the driver's perception, judgment, or operation of the transmitted information is deemed confused to the server SV's second machine learning model SY22. When the identifier SY32 determines that the driver of vehicle VH is confused in any of these areas, the log of instructions issued from the navigation system SY to the driver of vehicle VH (navigation information generated by the navigation information generation unit SY1) is also sent to the server SV's second machine learning model SY22.

[0081] When the recognizer SY32 determines that the driver of vehicle VH is confused in any of the cognition, judgment, or operation of the transmitted information, the machine learning model unit SY2 generates the transmitted information based on the transmitted information transmitted to the driver of vehicle VH via the user interface VH1 and the driver's reaction to the transmitted information (the driver's operation of vehicle VH) to suppress any confusion in the driver's cognition, judgment, or operation.

[0082] Moreover, in Figures 1-4 In the example shown, the driver monitoring system SY33, which identifies the driver's response to the information transmitted by the machine learning model unit SY2, is included in the determination unit SY3.

[0083] The driver monitoring system SY33 is based on images of the driver of vehicle VH captured by the driver monitoring camera VH3 mounted on vehicle VH. It identifies the driver's response to the information transmitted by the machine learning model unit SY2 (that is, it determines whether there is any confusion in the driver's cognition, judgment, or operation of the transmitted information).

[0084] In addition, the driver monitoring system SY33, based on the voice of the driver of vehicle VH collected by the microphone VH4 mounted on vehicle VH, distinguishes the driver's response to the information transmitted by the machine learning model unit SY2 (that is, it determines whether there is any confusion in the driver's cognition, judgment and operation of the transmitted information).

[0085] The driver monitoring system SY33 sends a log of the driver's actions in vehicle VH (vehicle VH) when the driver's perception, judgment, or operation of the transmitted information is deemed confused to the second machine learning model SY22 on server SV. When the driver monitoring system SY33 determines that the driver of vehicle VH is confused in any of these areas, the log of instructions issued from navigation system SY to the driver of vehicle VH (navigation information generated by navigation information generation unit SY1) is also sent to the second machine learning model SY22 on server SV.

[0086] When the driver monitoring system SY33 determines that the driver of vehicle VH is confused in any of the aspects of cognition, judgment, or operation of the transmitted information, the machine learning model unit SY2 generates transmission information based on the transmission information transmitted to the driver of vehicle VH via the user interface VH1 and the driver's reaction to the transmission information, in order to suppress any confusion in the driver's cognition, judgment, or operation.

[0087] exist Figure 2 In the example shown, when the driver of vehicle VH is deemed confused (confused) in any aspect of the driver's perception, judgment, or operation of the transmitted information, the log of the driver's actions (the log of erroneous actions) is maintained in both vehicle VH and server SV.

[0088] For example, in the case where vehicle VH is traveling on a route different from the route indicated by navigation system SY, the log of the driver's actions corresponds to the log of erroneous actions.

[0089] For example, the log of a driver's operation in which the driver of vehicle VH unnecessarily presses the brake pedal when the driver needs to perform an operation to make vehicle VH turn right or left corresponds to the log of an incorrect operation.

[0090] For example, if the driver of vehicle VH is performing an operation that requires turning vehicle VH right or left, and the steering wheel is wobbled to the left or right (causing operational confusion), the log of the driver's operation corresponds to the log of the incorrect operation.

[0091] For example, the log of a driver's operation that causes vehicle VH to unnecessarily cross the dividing line when the driver of vehicle VH needs to perform an operation to make vehicle VH turn right or left corresponds to the log of an incorrect operation.

[0092] For example, the log of a driver's operation that unnecessarily causes vehicle VH to enter a crosswalk, shoulder, etc., when the driver needs to perform an operation to make vehicle VH turn right or left corresponds to the log of the incorrect operation.

[0093] For example, when a driver of vehicle VH needs to perform an operation that requires vehicle VH to turn right or left, the log of the driver's operation that causes the hazard lights of vehicle VH to be illuminated unnecessarily during the right or left turn corresponds to the log of the incorrect operation.

[0094] For example, the log of a driver's operation that causes vehicle VH to drive in violation of regulations (e.g., driving against traffic) when the driver of vehicle VH needs to perform an operation to make vehicle VH turn right or left corresponds to the log of the wrong operation.

[0095] exist Figures 1-4 In the example shown, simulator SY4 is configured on server SV. Specifically, the processor SV3 of the computer constituting server SV functions as simulator SY4. Simulator SY4 simulates the actions of navigation information generation unit SY1. A second machine learning model SY22 collaborates with simulator SY4 to repeatedly predict the driver's behavior in vehicle VH and optimize the transmission information generated by machine learning model unit SY2.

[0096] The machine learning model SY2 performs additions or updates to the transmitted information based on the driver's response to the information transmitted from the user interface VH1 to the driver of the vehicle VH (driver feedback such as voice, facial expressions, and gestures).

[0097] As described above, in the navigation system SY of the first embodiment, the lightweight large-scale language model SY21A and the large-scale language model SY22A are effectively utilized to optimize navigation based on the driver's communication ability, personality, preconceived notions, and experience in the vehicle (VH). Therefore, even under complex routes, road shapes, or poor communication conditions between the vehicle (VH) and the server (SV), appropriate navigation can be provided to the driver in the vehicle (VH).

[0098] In one example of the navigation system SY in the first embodiment, when the driver of vehicle VH enters the destination during the current trip, the large-scale language model SY22A of server SV uses the personal information of the driver of vehicle VH (the characteristics of the driver of vehicle VH), logs of past erroneous judgments, and the instructions of the navigation system SY at that time to predict in advance the scenarios in which the driver of vehicle VH is likely to make erroneous operations or the communication to prevent the driver of vehicle VH from making erroneous operations (the content output as voice guidance from user interface VH1, timing, tone of voice, type of voice, and content displayed on the screen), and provides advance instructions to the lightweight large-scale language model SY21A installed in vehicle VH. The lightweight large-scale language model SY21A receives real-time navigation information output from navigation information generation unit SY1, and based on the advance instructions from the large-scale language model SY22A of server SV, issues instructions to the driver of vehicle VH using the communication method most suitable for the driver of vehicle VH (voice guidance from user interface VH1, image guidance). The results of this journey are saved in a log, which helps to further improve navigation in future journeys.

[0099] If we assume that all processing is to be done using a large-scale language model integrated into the vehicle's (VH) system, the processing performance of the computer (VH7) integrated into the vehicle's VH (such as the onboard ECU (Electronic Control Unit)) becomes a bottleneck, resulting in delays and preventing navigation from occurring at the appropriate timing. If we assume that all processing is to be done using the large-scale language model SY22A on the server (SV), navigation will also fail to occur at the appropriate timing due to communication delays between the server (SV) and the vehicle's (VH) system.

[0100] Therefore, in the navigation system SY of the first embodiment, the real-time LLM processing is performed by the lightweight large-scale language model SY21A mounted on the vehicle VH, while the real-time LLM processing is performed by the large-scale language model SY22A mounted on the server SV.

[0101] In another example of the navigation system SY in the first embodiment, the navigation information generation unit SY1 may be located not only in the vehicle VH, but also in the server SV, and the simulator SY4 may perform the simulation of the navigation information generation unit SY1 in the server SV.

[0102] In this example, the large-scale language model SY22A, mounted on server SV, collaborates with simulator SY4 of navigation information generation unit SY1 within server SV to simulate the journey and navigation instructions during the process, based on pre-entered information such as the destination input by the driver of vehicle VH. It simulates how the driver of vehicle VH would react to the navigation instructions and creates pre-defined instructions based on the results. This process can also be achieved through iterative simulations and improvements.

[0103] The navigation system is very useful when the driver of a vehicle (VH) is driving toward an unfamiliar destination or when the route to the destination is complex.

[0104] For example, in existing navigation systems like the one described in Patent Document 1, in situations with complex road shapes, the instructions issued by the navigation system may not be properly conveyed to the driver, causing the driver to drive on the wrong route, or the navigation system may confuse and mislead the driver. Furthermore, in existing navigation systems, due to the processing load of the navigation system's CPU (Central Processing Unit), and the communication latency of GPS and networks, voice guidance from the navigation system to the driver may be delayed, causing driver confusion.

[0105] As described above, the navigation system SY according to the first embodiment can solve the problems of existing navigation systems.

[0106] In the navigation system SY of the first embodiment, warnings are not only issued in scenarios that specifically match the scenario in which the driver of vehicle VH makes a judgment error, but also in cases where there are previously unmanifested potential risks and unpleasant feelings, that is, cases where the driver of vehicle VH accumulates cognitive burden and stress due to confusion, etc. (log of the driver's operation in vehicle VH). The machine learning model unit SY2 (LLM) performs processing to prevent the driver of vehicle VH from making erroneous operations before they occur based on the characteristics of the driver of vehicle VH.

[0107] [First Embodiment]

[0108] If the driver of vehicle VH lacks driving experience and the ability to handle multiple instructions simultaneously from the navigation system SY, the driver of vehicle VH may sometimes panic or forget the existence of different operations when performing a certain operation.

[0109] In the first case, when the navigation system SY issued the instruction "Turn left 50m ahead. Turn right 30m later," the driver of vehicle VH panicked and turned right instead of left.

[0110] In the second case, when the navigation system SY issued the instruction "Turn left 50m ahead. Turn right 30m later," the driver of vehicle VH, after making the left turn, did not know which way to go and temporarily stopped at the zebra crossing.

[0111] In the first embodiment, the logs of the first and second examples are stored in a log database. Furthermore, the large-scale language model SY22A of server SV determines that the driver of vehicle VH is panicked by complex instructions and multiple instructions issued simultaneously. Moreover, server SV's large-scale language model SY22A considers this determination and, for example, issues a prior instruction to vehicle VH's lightweight large-scale language model SY21A in a manner that sequentially processes instructions as described below.

[0112] The lightweight large-scale language model SY21A of vehicle VH, based on prior instructions from the large-scale language model SY22A of server SV, issues the instruction "Please enter the left lane", followed by the instruction "Please reduce to ●● km / h (a speed that the driver of vehicle VH can react in time even if a right turn instruction is issued after a left turn)", followed by the instruction "Please maintain speed and turn left 50m ahead", and then the instruction "Please turn right 30m ahead".

[0113] As described above, in one example of the navigation system SY in the first embodiment, when the determination unit SY3 determines that the driver of vehicle VH is confused in any of the cognition, judgment, or operation of the transmission information which is to be transmitted to the driver of vehicle VH via user interface VH1, the machine learning model unit SY2 generates transmission information based on the transmission information transmitted to the driver of vehicle VH via user interface VH1 and the vehicle VH's response to the transmission information, so as to suppress any confusion in the driver of vehicle VH's cognition, judgment, or operation.

[0114] In a variation of the first embodiment of the navigation system SY in the first implementation, when the determination unit SY3 determines that the driver of vehicle VH is confused in any of the perception, judgment, or operation of the transmitted information, the machine learning model unit SY2 causes the navigation information generation unit SY1 to generate navigation information based on the transmitted information transmitted to the driver of vehicle VH via the user interface VH1 and the driver's response to the transmitted information, so as to suppress any confusion in the driver's perception, judgment, or operation.

[0115] In detail, in a variation of the first embodiment of the navigation system SY of the first implementation, the machine learning model unit SY2 generates navigation information based on personal information, transmitted information and the driver's reaction to the transmitted information related to any of the driver's cognition, judgment and operation of the vehicle VH, so as to suppress confusion in any of the driver's cognition, judgment and operation of the vehicle VH.

[0116] That is, in a variation of the first embodiment of the navigation system SY in the first implementation, the machine learning model unit SY2 causes the navigation information generation unit SY1 to generate navigation information, so that the navigation system SY provides route guidance that will not confuse the driver of vehicle VH.

[0117] [Second Embodiment]

[0118] For example, when driving on a long highway, the driver of vehicle VH is easily distracted and may miss the information that is to be transmitted to the driver of vehicle VH via user interface VH1.

[0119] Therefore, in the second embodiment of the navigation system SY of the first embodiment, when the driver of a vehicle VH traveling on a long-distance highway is distracted (for example, when more than 10 minutes have passed since the last navigation), the tone, volume, and intonation of the voice guidance are changed to give instructions to the driver of the vehicle VH.

[0120] [Third Embodiment]

[0121] The degree to which the driver of vehicle VH pays attention to the information transmitted to the driver of vehicle VH via user interface VH1 varies depending on whether the voice guidance from user interface VH1 to the driver of vehicle VH is in a mechanical tone, a casual tone of the opposite sex, or a casual tone of the same sex.

[0122] Therefore, in the third embodiment of the navigation system SY of the first implementation, the tone of voice guidance given to the driver of vehicle VH with a high degree of attention is analyzed, and the tone of voice guidance given to the driver of vehicle VH from user interface VH1 is optimized based on the analysis results (that is, the degree of attention of the driver of vehicle VH is increased).

[0123] [Fourth Embodiment]

[0124] If the driver of a vehicle with a VH (vehicle speed control) lacks a sense of distance, for example, when given a voice prompt like "50m ahead," the driver of a VH vehicle may not be able to accurately identify the vehicle's position after it has traveled 50m.

[0125] Therefore, in the fourth embodiment of the navigation system SY in the first implementation, when the driver of vehicle VH lacks a sense of distance as personal information of the driver of vehicle VH or the log of the driver's operation of vehicle VH, voice guidance such as "I think there is a shop on the right, please turn on the left turn signal after passing through there for 3 seconds and turn left at the first intersection" is issued instead of voice guidance such as "50m ahead".

[0126] [Fifth Embodiment]

[0127] In the fifth embodiment of the navigation system SY in the first implementation, if the driver of vehicle VH reacts to the information (guidance) generated by the machine learning model unit SY2 and transmitted to the driver of vehicle VH via the user interface VH1 with a voice like "Eh, wait a minute. I don't understand at all!", the driver's voice is collected by the microphone VH4. The driver monitoring system SY33 determines that the driver of vehicle VH is confused about the information generated by the machine learning model unit SY2, records the driver's reaction in a log, and feeds the log back to the server SV. The server SV's second machine learning model SY22 (large-scale language model SY22A) updates the information generated by the machine learning model unit SY2 so that the driver of vehicle VH no longer exhibits such a reaction.

[0128] Furthermore, in the fifth embodiment of the navigation system SY in the first implementation, if the driver of vehicle VH reacts to the information generated by the machine learning model unit SY2 and transmitted to the driver of vehicle VH via the user interface VH1 with a voice such as "Can I turn left here? Or go straight? I don't know.", the driver's voice is collected by the microphone VH4. The driver monitoring system SY33 determines that the driver of vehicle VH is confused about the information generated by the machine learning model unit SY2, records the driver's reaction in a log, and feeds the log back to the server SV. The second machine learning model SY22 of the server SV updates the information generated by the machine learning model unit SY2 so that the driver of vehicle VH no longer exhibits such a reaction.

[0129] Furthermore, in the fifth embodiment of the navigation system SY in the first implementation, if the driver of vehicle VH exhibits wide-eyed expressions and impatient gestures, etc., in response to the information (guidance) generated by the machine learning model unit SY2 and transmitted to the driver of vehicle VH via the user interface VH1, these reactions of the driver of vehicle VH are captured by the driver monitoring camera VH3. The driver monitoring system SY33 determines that the driver of vehicle VH is confused about the information generated by the machine learning model unit SY2, records the driver's reaction in a log, and feeds the log back to the server SV. The second machine learning model SY22 of the server SV updates the information generated by the machine learning model unit SY2 so that the driver of vehicle VH no longer exhibits such reactions.

[0130] [Sixth Embodiment]

[0131] In the fifth embodiment of the navigation system SY in the first implementation, if the driver of vehicle VH reacts to the information (instructions) generated by the machine learning model unit SY2 and transmitted to the driver of vehicle VH via the user interface VH1 with voices such as "Eh, wait a minute. I have no idea!" or "Can I just turn left here? Or go straight? I don't know.", the driver monitoring system SY33 determines that the driver of vehicle VH is confused about the information (instructions) generated by the machine learning model unit SY2, and the first machine learning model SY21 (lightweight large-scale language model SY21A) mounted on vehicle VH immediately issues additional instructions or generates and outputs instructions that are more specific than the information (instructions) transmitted to the driver of vehicle VH.

[0132] As described above, the navigation system SY according to the first embodiment can suppress confusion in the driver's cognition, judgment, and operation during vehicle VH as much as possible.

[0133] <Second Implementation>

[0134] Apart from the aspects described later, the navigation system SY of the second embodiment is configured in the same way as the navigation system SY of the first embodiment described above.

[0135] As described above, in an example of the navigation system SY in the first embodiment ( Figures 1-4 In the example shown, the navigation system SY consists of a computer VH7 mounted on the vehicle VH and a computer on the server SV.

[0136] On the other hand, the navigation system SY in the second embodiment is composed of a computer VH7 mounted on a vehicle VH. Specifically, in one example of the navigation system SY in the second embodiment, the processor VH73 of the computer VH7 mounted on the vehicle VH functions as a simulator SY4. Furthermore, in one example of the navigation system SY in the second embodiment, the second machine learning model SY22 (see reference...) Figure 2 The machine learning model is stored in the storage device VH72 of the computer VH7 in the vehicle VH. The second machine learning model SY22, equivalent to the navigation system SY in the second embodiment (see reference...), is... Figure 2 The machine learning model has capabilities equivalent to the large-scale language model SY22A (refer to...). Figure 2 Large-scale language models.

[0137] Figure 10 This is a flowchart illustrating an example of processing performed by the processor VH73 of the computer VH7 of the vehicle VH equipped with the navigation system SY of the second embodiment.

[0138] exist Figure 10 In the example shown, in step S10, the navigation information generation unit SY1 generates navigation information based on the current location of vehicle VH, map information, and destination information representing the destination of vehicle VH.

[0139] In step S11, the machine learning model unit SY2 generates transmission information based on the navigation information generated in step S10, which is the information to be transmitted to the driver via the user interface VH1 to the vehicle VH.

[0140] In step S12, the determination unit SY3 determines whether there is any confusion in the driver's perception, judgment, or operation of the transmitted information from the user interface VH1 to the driver of vehicle VH based on the driver's reaction to the transmitted information. If "yes", proceed to step S13; if "no", proceed to step S14.

[0141] In step S13, the machine learning model unit SY2 generates transmission information based on the transmission information transmitted to the driver of vehicle VH via user interface VH1 when it is determined in step S12 that the driver of vehicle VH is confused in any of the perception, judgment, or operation of the transmitted information, in order to suppress any confusion in the driver of vehicle VH's perception, judgment, or operation.

[0142] In step S14, for example, the determination unit SY3 determines whether navigation should end. If "yes", the navigation ends. Figure 10 The process shown returns to step S10 if "No" is selected.

[0143] <Third Implementation Method>

[0144] Apart from the aspects described later, the navigation system SY of the third embodiment is configured in the same way as the navigation system SY of the first embodiment described above.

[0145] As described above, in an example of the navigation system SY in the first embodiment ( Figures 1-4 In the example shown, the second machine learning model SY22 of the server SV generates a prior instruction to the first machine learning model SY21 based on destination information and the personal information of the driver of vehicle VH. The first machine learning model SY21 of vehicle VH generates, in real time, transmission information as information to be transmitted to the driver of vehicle VH based on the prior instruction generated by the second machine learning model SY22 and the navigation information generated by the navigation information generation unit SY1. That is to say, in the navigation system SY of the first embodiment, the communication delay between the server SV and vehicle VH is taken into account.

[0146] On the other hand, due to advancements in communication technology, a reduction in communication time between the server SV and the vehicle VH can be expected. Therefore, in one example of the navigation system SY in the third embodiment, the machine learning model unit SY2 consists only of the second machine learning model SY22 of the server SV. Specifically, in one example of the navigation system SY in the third embodiment, the second machine learning model SY22 of the server SV generates, in real time, transmission information as information to be transmitted to the driver of the vehicle VH based on the navigation information generated by the navigation information generation unit SY1.

[0147] As described above, embodiments of the navigation system, navigation method, and program product of this disclosure have been described with reference to the accompanying drawings. However, the navigation system, navigation method, and program product of this disclosure are not limited to the above embodiments, and appropriate modifications can be made without departing from the spirit of this disclosure. The configurations of the various examples of the above embodiments can also be appropriately combined. In the examples of the above embodiments, the processing performed in the navigation system SY has been described as software processing performed by executing a program, but the processing performed in the navigation system SY can also be hardware processing. Alternatively, the processing performed in the navigation system SY can be a combination of software and hardware processing. Furthermore, the program stored in the storage device VH72 of the computer VH7 of the vehicle VH of the navigation system SY (the program that implements the functions of the processor VH73 of the computer VH7 of the vehicle VH of the navigation system SY) can be recorded, for example, in a computer-readable storage medium (program product) such as a semiconductor memory, magnetic recording medium, or optical recording medium and provided, circulated, etc.

Claims

1. A navigation system having a processor, wherein, The processor performs the following actions: Navigation information for navigating the driver of the vehicle is generated based on the vehicle's current location, map information, and destination information indicating the vehicle's destination. Based on the navigation information, a transmission message is generated as the information to be passed to the driver via the user interface; Based on the driver's reaction to the information transmitted from the user interface, it is determined whether there is any confusion in the driver's cognition, judgment, or operation of the transmitted information; as well as If it is determined that the driver is confused in any of the ways of cognition, judgment, or operation of the transmitted information, the transmitted information or the navigation information is generated based on the transmitted information transmitted to the driver via the user interface and the driver's reaction to the transmitted information, so as to suppress any confusion in the driver's cognition, judgment, or operation.

2. The navigation system according to claim 1, wherein, The navigation system includes a first machine learning model stored in the vehicle's storage device and a second machine learning model stored in the server's storage device. The second machine learning model generates prior instructions for the first machine learning model based on the destination information. The first machine learning model generates the transmission information in real time based on the prior instructions and the navigation information generated by the second machine learning model.

3. The navigation system according to claim 1, wherein, The processor generates the transmission information or the navigation information based on personal information related to any of the driver's cognition, judgment, and operation, the transmission information, and the driver's reaction to the transmission information, in order to suppress confusion in any of the driver's cognition, judgment, and operation.

4. The navigation system according to claim 2, wherein, The navigation system includes a simulator configured on the server. The simulator simulates the action of generating the navigation information. The second machine learning model collaborates with the simulator to repeatedly predict the driver's behavior and optimize the transmitted information.

5. The navigation system according to claim 1, wherein, The information is transmitted to the driver from the user interface as voice guidance output from a speaker or image guidance displayed on a monitor.

6. The navigation system according to claim 1, wherein, The determination of whether the driver's cognition, judgment, and operation of the transmitted information are confused is performed by a recognition device, wherein the recognition device detects the information of dividing lines contained in the image captured by the front camera mounted on the vehicle.

7. The navigation system according to claim 1, wherein, The processor determines whether the driver's perception, judgment, and operation of the transmitted information are confused. The processor controls the brake actuator or steering actuator based on the driver's operation.

8. The navigation system according to claim 1, wherein, The driver's perception, judgment, and operation of the transmitted information are determined by a driver monitoring system. The driver monitoring system identifies the driver's response to the transmitted information based on images of the driver captured by a driver monitoring camera or voice collected by a microphone.

9. The navigation system according to claim 5, wherein, The transmission information generated by the processor includes any one of the following: timing, sequence, granularity and specificity of the guidance, additional information assigned during guidance, type of speech, tone, volume and speaking style, display content of the image guidance, display position, display size, color and font.

10. The navigation system according to claim 1, wherein, The processor performs additions or updates to the transmitted information based on the driver's response to the transmitted information passed from the user interface.

11. A navigation method, comprising: Navigation information for navigating the driver of the vehicle is generated based on the vehicle's current location, map information, and destination information indicating the vehicle's destination. Based on the navigation information, a transmission message is generated as the information to be passed to the driver via the user interface; as well as Based on the driver's response to the information transmitted from the user interface, an assessment is made as to whether there is any confusion in the driver's perception, judgment, or operation of the transmitted information. If it is determined that the driver is confused in any of the ways of cognition, judgment, or operation of the transmitted information, the transmitted information or the navigation information is generated based on the transmitted information transmitted to the driver via the user interface and the driver's reaction to the transmitted information, so as to suppress any confusion in the driver's cognition, judgment, or operation.

12. A program product comprising a computer program, said computer program being configured to cause a processor of a computer mounted in a vehicle to perform the following actions: Navigation information for navigating the driver of the vehicle is generated based on the vehicle's current location, map information, and destination information indicating the vehicle's destination. Based on the navigation information, a transmission message is generated as the information to be passed to the driver via the user interface; as well as Based on the driver's reaction to the information transmitted from the user interface, a determination is made as to whether there is any confusion in the driver's perception, judgment, or operation of the transmitted information. If it is determined that the driver is confused in any of the ways of cognition, judgment, or operation of the transmitted information, the transmitted information or the navigation information is generated based on the transmitted information transmitted to the driver via the user interface and the driver's reaction to the transmitted information, so as to suppress any confusion in the driver's cognition, judgment, or operation.

Images