Driving assistance device, driving assistance method, and program
The driver assistance device uses a voice recognition unit and LLM to generate timely and accurate voice responses to ADAS questions, addressing the need for on-the-go activation of ADAS features and providing tailored instructions, thus enhancing driver assistance.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- TOYOTA JIDOSHA KK
- Filing Date
- 2023-07-20
- Publication Date
- 2026-06-23
Smart Images
Figure 0007878199000001 
Figure 0007878199000002 
Figure 0007878199000003
Abstract
Description
Technical Field
[0001] The present disclosure relates to a driving support device, a driving support method, and a program.
Background Art
[0002] Patent Document 1 describes an agent device that receives vehicle state information from a vehicle, receives questions from a user, estimates the intention of the questions, and obtains answers to the questions based on the estimated intention of the questions. Further, Patent Document 1 describes that the questions are texturized by voice recognition. Furthermore, Patent Document 1 describes that information related to the answers to the questions is received from an agent server.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] By the way, although Patent Document 1 exemplifies questions such as how to turn off a lamp, what switch it is, and what the meter lamp (tire pressure warning lamp) is as questions from a user, it does not exemplify questions related to ADAS (Advanced Driver-Assistance Systems). ADAS functions include features such as ACC (Adaptive Cruise Control) and Lane Change Assist, which the driver cannot activate while the vehicle is stationary, but can only activate while the vehicle is in motion. Questions regarding such ADAS functions are likely to be asked by the driver while the vehicle is in motion. For example, in order to enable drivers unfamiliar with ADAS to activate such functions while the vehicle is in motion, it is necessary to quickly generate voice responses to questions regarding such ADAS functions. However, the technology described in Patent Document 1 does not take into consideration the need to quickly generate voice responses to questions. Therefore, the technology described in Patent Document 1 may not be able to appropriately generate voice responses to voice questions from the driver regarding ADAS.
[0005] In view of the above, the purpose of this disclosure is to provide a driver assistance device, a driver assistance method, and a program that can appropriately generate voice responses to voice questions from the driver regarding ADAS. [Means for solving the problem]
[0006] One aspect of this disclosure is a driver assistance device comprising: an acquisition unit that acquires voice questions about ADAS received from a driver while driving a vehicle; a voice recognition unit that recognizes the voice questions about ADAS acquired by the acquisition unit; and an answer generation unit that uses large language models (LLMs) to generate voice answers corresponding to the voice questions about ADAS recognized by the voice recognition unit. [Effects of the Invention]
[0007] According to this disclosure, it is possible to appropriately generate voice responses to voice questions from the driver regarding ADAS. [Brief explanation of the drawing]
[0008] [Figure 1] This figure shows an example of a vehicle to which the driver assistance system of the first embodiment is applied. [Figure 2] Figure 1 shows an example of a specific configuration of the driver assistance system. [Figure 3] This figure illustrates a first example of processing performed in a vehicle to which the driver assistance system of the first embodiment is applied. [Figure 4] This is a flowchart illustrating an example of a process performed by the driver assistance device of the first embodiment. [Figure 5] This figure shows an example of a vehicle to which the driver assistance system of the second embodiment is applied. [Figure 6] This figure shows an example of the flow of data, etc., in a vehicle to which the driver assistance system of the second embodiment is applied. [Modes for carrying out the invention]
[0009] The embodiments of the driver assistance device, driver assistance method, and program of this disclosure will be described below with reference to the drawings.
[0010] <First Embodiment> Figure 1 shows an example of a vehicle 1 to which the driver assistance device 10 of the first embodiment is applied. Figure 2 shows an example of a specific configuration of the driver assistance device 10 shown in Figure 1. In the example shown in Figures 1 and 2, vehicle 1 is equipped with a vehicle status sensor 2, a GPS (Global Positioning System) unit 3, a map information unit 4, a driver monitoring camera 5, an HMI (Human Machine Interface) 6, and a driver assistance device 10. The vehicle status sensor 2, GPS unit 3, map information unit 4, driver monitoring camera 5, HMI 6, and driver assistance device 10 are connected via an in-vehicle network 20. In the examples shown in Figures 1 and 2, vehicle 1 is equipped with a vehicle state sensor 2, a GPS unit 3, a map information unit 4, a driver monitor camera 5, and an HMI 6. However, in other examples, vehicle 1 may not be equipped with all of these. In yet another example, vehicle 1 may be equipped with other sensors (e.g., external sensors) in addition to all or some of these.
[0011] In the examples shown in Figures 1 and 2, the vehicle condition sensor 2 includes, for example, a vehicle speed sensor, a brake pedal sensor, an accelerator pedal sensor, a lane marking detection device, a seat belt sensor, a door sensor, and an ABS (anti-lock braking system) determination device that determines whether or not the ABS is operational. In other examples, the vehicle condition sensor 2 may not include all of the sensors mentioned above. In yet another example, the vehicle condition sensor 2 may include other sensors (e.g., external sensors) in addition to all or some of the sensors mentioned above.
[0012] In the examples shown in Figures 1 and 2, the driver assistance device 10 comprises a communication interface (I / F) 11, memory 12, processor 13, and signal lines 14. The driver assistance device 10 can be configured by a computer such as a Raspberry Pi®. The driver assistance device 10 may also be configured by a driver assistance ECU (electronic control unit). In the examples shown in Figures 1 and 2, the processor 13 has the functions of an acquisition unit 131, a speech recognition unit 132, a response generation unit 133, and an update unit 134. The acquisition unit 131 acquires voice questions regarding ADAS received by the HMI 6 from the driver while the vehicle 1 is in operation. The acquisition unit 131 also acquires signals indicating the vehicle status detected by the vehicle status sensor 2 (vehicle status signals, which are the output signals of the vehicle status sensor 2). Furthermore, the acquisition unit 131 acquires location information indicating the position of the vehicle 1, which is determined based on the GPS signal received by the GPS unit 3 and the map information stored in the map information unit 4. The acquisition unit 131 also acquires data from the user manual (instruction manual), for example in PDF format, stored in the memory 12. The speech recognition unit 132 recognizes the voice questions related to ADAS acquired by the acquisition unit 131. The speech recognition unit 132 recognizes the voice questions related to ADAS acquired by the acquisition unit 131 by using techniques similar to those described in paragraphs 0031, 0033 to 0036 of Japanese Patent No. 7062958 (the section describing Figures 2A and 3 of the corresponding U.S. Patent No. 11011167 (speech recognition device 10A, speech recognition unit 30A, and information generation unit 31A)).
[0013] The response generation unit 133 can use a large-scale language model. A large-scale language model is a language model constructed using a very large dataset and deep learning technology. Compared to conventional natural language models, large-scale language models have increased computational complexity, data volume, and number of parameters. Large-scale language models can engage in fluent conversations close to those of humans and can perform various processing using natural language with high accuracy. Representative examples of large-scale language models include "BERT," announced by Google in 2018, and "GPT-3," announced by OpenAI in 2020. One example of an application of large-scale language models is "ChatGPT," which was announced in December 2022 and is a fine-tuned version of the "GPT-3.5 series," trained in early 2022, for chat (dialogue). The response generation unit 133 can use a publicly known (e.g., open-source) large-scale language model. The response generation unit 133 generates a voice response corresponding to the voice question regarding the ADAS recognized by the voice recognition unit 132 by using the large language model installed in the driving assistance device 10. The update unit 134 updates (updates) the voice response corresponding to the voice question regarding the ADAS generated by the response generation unit 133 in response to, for example, an update (update) of the functions of the ADAS.
[0014] FIG. 3 is a diagram for explaining a first example of the process executed in the vehicle 1 to which the driving assistance device 10 of the first embodiment is applied. In the example shown in FIG. 3, the HMI 6 receives a voice question "Can ACC be activated now?" from the driver of the vehicle 1, and the acquisition unit 131 acquires the voice question. The voice recognition unit 132 recognizes the voice question acquired by the acquisition unit 131. Specifically, the voice recognition unit 132 executes text conversion of the voice question. The response generation unit 133 acquires the question text-converted by the voice recognition unit 132. When the HMI 6 receives a voice question, the vehicle speed sensor detects the vehicle speed of the vehicle 1 (55 miles per hour (about 88.5 km)), the brake pedal sensor detects the off state of the brake pedal, the accelerator pedal sensor detects the on state of the accelerator pedal, the seat belt sensor detects the wearing state of the seat belt in the driver's seat, the door sensor detects the closed state of the door of the vehicle 1, and the ABS determination device determines that the ABS is in an operable state (not in an inoperable state). The acquisition unit 131 acquires those detection results and determination results as a vehicle state signal, and the response generation unit 133 acquires the vehicle state signal. Also, when the HMI 6 receives a voice question, the GPS unit 3 and the map information unit 4 identify that the vehicle 1 is traveling on a highway provided with lane marks (lane dividing lines). The acquisition unit 131 acquires the identification result as the position information of the vehicle 1, and the response generation unit 133 acquires the position information. Furthermore, when the HMI 6 receives a voice question, the acquisition unit 131 acquires the data of the user manual stored in the memory 12. In the user manual, as conditions for operating the ACC of the vehicle 1, the vehicle speed of the vehicle 1 is 20 miles per hour (about 32.2 km) or more (not less than the threshold value), the brake pedal is in the off state, the accelerator pedal is in the on state, the seat belt of the driver's seat is worn, the door of the vehicle 1 is closed, the ABS is in an operable state, and the vehicle 1 is traveling on a highway or the like where lane marks are provided are described. The answer generation unit 133 acquires the data of the user manual. In other examples, the conditions for operating the ACC of the vehicle 1 may be different from the above-described conditions.
[0015] In the example shown in FIG. 3, the answer generation unit 133 uses a large language model to generate an audio answer corresponding to the voice question "Can the ACC be activated now?" from the driver of the vehicle 1 based on the question "Can the ACC be activated now?" from the driver of the vehicle 1, the vehicle state signal, the position information of the vehicle 1, and the user manual. Specifically, the answer generation unit 133 determines that the state of the vehicle 1 and the position of the vehicle 1 indicated by the vehicle state signal satisfy the conditions for operating the ACC of the vehicle 1 described in the user manual, and generates an audio answer indicating that the ACC can be activated. In addition, the answer generation unit 133 generates an audio answer explaining the operation of the driver of the vehicle 1 required to activate the ACC. Specifically, the answer generation unit 133 generates text information such as "Since the vehicle 1 is traveling on a highway where the vehicle speed is higher than 20 miles per hour (about 32.2 km) and lane marks (lane dividing lines) are provided, the ACC can be activated now. To activate the ACC, please click the ACC button." and generates an audio answer by performing voice conversion of the text information. The HMI 6 outputs the audio answer generated by the answer generation unit 133. In the example shown in Figure 3, the response generation unit 133 generates an audio response explaining the driver's actions required to activate ACC. However, in other examples, the response generation unit 133 does not need to generate an audio response explaining the driver's actions required to activate ACC.
[0016] As described above, in the example shown in Figure 3, the voice response to a voice question made by the driver of vehicle 1 while traveling at 55 miles per hour (approximately 88.5 km / h) is generated by the response generation unit 133 without the need to reduce the vehicle speed of vehicle 1 to zero (without reducing the vehicle speed of vehicle 1 to below a threshold). Therefore, the driver of vehicle 1 can immediately activate the ACC (Adaptive Cruise Control) according to the voice response generated by the response generation unit 133 (i.e., without the need to reduce the vehicle speed of vehicle 1 to zero and then increase it to above a threshold). In other words, in the example shown in Figure 3, it is possible to appropriately (quickly and accurately) generate voice responses to the driver's voice questions regarding ACC.
[0017] The name for ACC varies among car manufacturers. For example, Toyota calls ACC "Radar Cruise Control," while Mercedes-Benz calls it "Distronic Plus." Therefore, in the second example of processing performed in a vehicle 1 to which the driver assistance system 10 of the first embodiment is applied, measures are taken to address the fact that the name of ACC differs among automobile manufacturers. Specifically, in the second example, information indicating the name of ACC used by each automobile manufacturer is stored in memory 12 in advance, for example, when the vehicle 1 is manufactured. When HMI6 receives a voice question from the driver of vehicle 1, "What is the vehicle speed at which ACC can be activated?", the answer generation unit 133 generates a voice response stating the vehicle speed at which ACC can be activated (20 miles per hour (approximately 32.2 km / h) or higher), as well as a voice response explaining the name of ACC used by the automobile manufacturer that produced vehicle 1. The answer generation unit 133 also generates a voice response explaining the driver's actions required to activate ACC and the corresponding operation of HMI6 (e.g., the display screen of HMI6). Furthermore, the answer generation unit 133 generates a voice response explaining the conditions for activating ACC in vehicle 1, the distance control performed while ACC is in operation, etc.
[0018] In the third example of the processing performed in a vehicle 1 to which the driver assistance system 10 of the first embodiment is applied, measures are taken to address the fact that the name ACC differs among automobile manufacturers, similar to the second example described above. In the third example, the vehicle 1 does not need to be equipped with a GPS unit 3 and a map information unit 4. In the third example, when the HMI6 receives the voice question, "I'm driving on the △△ Expressway at 80 km / h. Can I activate ACC now?", the response generation unit 133 generates a voice response indicating that ACC can be activated while driving on the △△ Expressway at 80 km / h, and also generates a voice response explaining the name of ACC used by the automobile manufacturer that produced vehicle 1. The response generation unit 133 also generates a voice response explaining the necessary actions of the vehicle 1 driver to activate ACC and the corresponding operation of the HMI6 (e.g., the HMI6 display screen). Furthermore, the response generation unit 133 generates a voice response explaining the change in the behavior of vehicle 1 (acceleration) in response to changes in the behavior of a slow-moving preceding vehicle (lane change, acceleration) while ACC is activated. Finally, the response generation unit 133 generates a voice response explaining the conditions for activating ACC in vehicle 1, the distance control performed while ACC is activated, and the driver's obligations while ACC is activated.
[0019] In the fourth example of processing performed in a vehicle 1 to which the driver assistance device 10 of the first embodiment is applied, the vehicle 1 does not need to be equipped with a GPS unit 3 and a map information unit 4, similar to the third example described above. In the fourth example, when HMI6 receives the voice question "I'm moving vehicle 1 in the parking lot. Can I activate ACC at 5 km / h?" from the driver of vehicle 1, the response generation unit 133 generates a voice response explaining that the maximum vehicle speed at which ACC can be activated for vehicle 1 is 20 miles per hour (approximately 32.2 km / h), and also generates a voice response explaining the name of ACC used by the automobile manufacturer that produced vehicle 1. Furthermore, the response generation unit 133 generates a voice response stating that ACC cannot be activated at 5 km / h.
[0020] In a fifth example of processing performed in a vehicle 1 to which the driver assistance system 10 of the first embodiment is applied, similar to the second example described above, information indicating the ACC designation of each automobile manufacturer is pre-stored in the memory 12, for example, at the time of manufacturing of the vehicle 1. When HMI6 receives a voice question from the driver of Vehicle 1, such as "What operations are required to activate ACC?", and the voice question uses the term for ACC used by a different automobile manufacturer than the one that manufactured Vehicle 1, the response generation unit 133 generates a voice response explaining that the term for ACC used by the driver is not the term for ACC used by the automobile manufacturer that manufactured Vehicle 1, but rather the term for ACC used by another automobile manufacturer. Furthermore, the response generation unit 133 generates a voice response that provides useful advice to the driver who has become a user of Vehicle 1 from a user of a vehicle manufactured by another automobile manufacturer (advice to help the driver easily distinguish between the ACC function of Vehicle 1 and the ACC function of a vehicle manufactured by another automobile manufacturer).
[0021] In the sixth example of processing performed in a vehicle 1 to which the driver assistance device 10 of the first embodiment is applied, when the HMI6 receives a voice question from the driver of vehicle 1, "What operation is required to turn off road sign assist (a function that displays road signs recognized by a camera mounted on vehicle 1 on the screen of HMI6)?", the answer generation unit 133 generates a voice response that explains the operation required by the driver of vehicle 1 to turn off road sign assist, and the corresponding operation of the HMI6 (e.g., the display screen of the HMI6), based on the question from the driver of vehicle 1 and the explanation of the operation required to turn off road sign assist contained in the user manual.
[0022] In the seventh example of processing performed in a vehicle 1 to which the driver assistance device 10 of the first embodiment is applied, when the HMI 6 receives an audio question from the driver of vehicle 1, "If the ABS is not operational, the ACC cannot be activated? What is the problem?", the answer generation unit 133 generates an audio response stating that the ACC cannot be activated when the ABS is not operational, based on the question from the driver of vehicle 1 and the conditions for activating the ACC of vehicle 1 contained in the user manual ("the ABS must be operational," etc.), and also generates an audio response explaining the name of the ACC used by the automobile manufacturer that manufactured vehicle 1. Furthermore, the answer generation unit 133 generates an audio response explaining why the ACC cannot be activated when the ABS is not operational. In addition, the answer generation unit 133 generates audio responses explaining each of the multiple conditions for activating the ACC of vehicle 1.
[0023] In the eighth example of processing performed in a vehicle 1 to which the driver assistance device 10 of the first embodiment is applied, not only the data from the user manual of vehicle 1 but also the data from the user manual of the old model of vehicle 1 are stored in the memory 12. When the HMI 6 receives a voice question from the driver of vehicle 1, such as "I have switched from the old model of vehicle 1 to vehicle 1 (current model). What are the new things I need to know?", the answer generation unit 133 extracts the updated functions (new functions) in vehicle 1 (current model) based on the question from the driver of vehicle 1, the user manual of vehicle 1 (current model), and the user manual of the old model of vehicle 1, and generates a voice answer that explains the extracted functions.
[0024] In the ninth example of processing performed in a vehicle 1 to which the driver assistance system 10 of the first embodiment is applied, the HMI 6 receives a voice question from the driver operating the vehicle 1, "What is the vehicle speed range in which lane change assist (one of the functions of ADAS) can be operated?", and the acquisition unit 131 acquires the voice question. The voice recognition unit 132 recognizes the voice question acquired by the acquisition unit 131. In detail, the voice recognition unit 132 performs text conversion of the voice question. The answer generation unit 133 acquires the question converted into text by the voice recognition unit 132. When HMI6 receives a voice question, the acquisition unit 131 retrieves data from the user manual stored in memory 12. The user manual describes the operating conditions for the lane change assist of vehicle 1, such as the vehicle speed of vehicle 1 being approximately 85 to 130 km / h. The answer generation unit 133 retrieves this data from the user manual. In other examples, the operating conditions for the lane change assist of vehicle 1 may differ from those described above.
[0025] In the ninth example, the response generation unit 133 uses a large-scale language model to generate an audio response to the driver's question, "What is the vehicle speed range in which lane change assist can be operated?", based on the driver's question and the user manual. Specifically, the response generation unit 133 generates an audio response that explains the vehicle speed range in which lane change assist can be operated (approximately 85-130 km / h).
[0026] Figure 4 is a flowchart illustrating an example of a process performed by the driver assistance device 10 of the first embodiment. The process shown in Figure 4 is performed, for example, while the vehicle 1 is in motion (specifically, when the vehicle speed of the vehicle 1 is greater than zero). In the example shown in Figure 4, in step S10, the acquisition unit 131 acquires voice questions from the driver of vehicle 1 regarding ADAS. In step S11, the acquisition unit 131 acquires the vehicle status signal. In step S12, the acquisition unit 131 acquires the location information of vehicle 1. In step S13, the acquisition unit 131 acquires data from the user manual. In step S14, the voice recognition unit 132 recognizes the voice question about ADAS from the driver of vehicle 1 acquired in step S10 and performs text conversion of the voice question. In step S15, the response generation unit 133 uses a large-scale language model to generate an audio response corresponding to the audio question about ADAS asked by the driver of vehicle 1 in step S10, based on the textualized question about ADAS from the driver of vehicle 1 in step S14, the vehicle status signal acquired in step S11, the location information of vehicle 1 acquired in step S12, and the user manual indicated by the data acquired in step S13. Specifically, the response generation unit 133 generates a textual response corresponding to the audio question about ADAS from the driver of vehicle 1 acquired in step S10, and then generates an audio response corresponding to the audio question about ADAS from the driver of vehicle 1 by converting the textual response into audio.
[0027] <Second Embodiment> A vehicle 1 to which the driver assistance device 10 of the second embodiment is applied is configured in the same way as a vehicle 1 to which the driver assistance device 10 of the first embodiment is applied, except for the points described later.
[0028] Figure 5 shows an example of a vehicle 1 to which the driver assistance device 10 of the second embodiment is applied. Figure 6 shows an example of the flow of data, etc., in a vehicle 1 to which the driver assistance device 10 of the second embodiment is applied. In the examples shown in Figures 5 and 6, the vehicle 1 is equipped with a communication device 7 that communicates with the outside of the vehicle 1. The response generation unit 133 generates voice responses to voice questions about ADAS recognized by the voice recognition unit 132 by using a large-scale language model located outside the vehicle 1, for example, on a server. Specifically, the response generation unit 133 acquires the question transcribed into text by the speech recognition unit 132 and instructs the communication device 7 to transmit the question to a large-scale language model outside of the vehicle 1. The response generation unit 133 also acquires the vehicle status signal generated by the vehicle status sensor 2 and instructs the communication device 7 to transmit the vehicle status signal to a large-scale language model outside of the vehicle 1. Furthermore, the response generation unit 133 acquires location information indicating the position of the vehicle 1 identified by the GPS unit 3 and the map information unit 4 and instructs the communication device 7 to transmit this location information to a large-scale language model outside of the vehicle 1. Finally, the response generation unit 133 acquires the user manual data stored in the memory 12 and instructs the communication device 7 to transmit this data to a large-scale language model outside of the vehicle 1. Furthermore, the response generation unit 133 causes the communication device 7 to perform processing to receive the processing results of a large-scale language model outside of the vehicle 1, and uses these processing results to generate voice responses corresponding to voice questions from the driver of the vehicle 1. In detail, the response generation unit 133 generates text information of the response corresponding to the voice question from the driver of the vehicle 1, and then generates voice responses by performing speech conversion of that text information.
[0029] In an example of processing performed in a vehicle 1 to which the driver assistance device 10 of the second embodiment is applied, when the HMI 6 receives a voice question from the driver of vehicle 1, such as "What operations are necessary for an OTA (Over-The-Air) update (the communication device 7 performs data transmission and reception via wireless communication with the outside of vehicle 1 to update the in-vehicle software, etc.)?", the answer generation unit 133 generates a voice response explaining the operations that the driver of vehicle 1 needs to perform for the OTA update, based on the question from the driver of vehicle 1 and the explanation of operations necessary for an OTA update included in the user manual.
[0030] As described above, embodiments of the driver assistance device, driver assistance method, and program of this disclosure have been explained with reference to the drawings. However, the driver assistance device, driver assistance method, and program of this disclosure are not limited to the embodiments described above, and can be modified as appropriate without departing from the spirit of this disclosure. The configurations of each example of the embodiments described above may be combined as appropriate. The program stored in the memory 12 of the driver assistance device 10 (the program that realizes the functions of the processor 13 of the driver assistance device 10) may be recorded on a computer-readable storage medium such as a semiconductor memory, magnetic recording medium, or optical recording medium (non-temporary storage medium) and provided or distributed. [Explanation of Symbols]
[0031] 1...Vehicle, 2...Vehicle status sensor, 3...GPS unit, 4...Map information unit, 5...Driver monitor camera, 6...HMI, 7...Communication device, 10...Driving assistance device, 11...Communication interface, 12...Memory, 13...Processor, 131...Acquisition unit, 132...Voice recognition unit, 133...Answer generation unit, 134...Update unit
Claims
1. An acquisition unit that acquires voice questions regarding ADAS (Advanced Driver-Assistance Systems) received from the driver while the vehicle is in operation, A voice recognition unit that recognizes voice questions related to ADAS acquired by the acquisition unit, The system includes a response generation unit that uses large language models (LLMs) to generate speech responses corresponding to speech questions about the ADAS recognized by the speech recognition unit, The acquisition unit acquires, when the vehicle speed of the vehicle is greater than zero, an audio question received from the driver asking whether the ADAS function, which cannot be operated when the vehicle speed is below a threshold, is in a state where it can be operated; information indicating the state of the vehicle at the time the audio question asking whether the ADAS function is in a state where it can be operated was received from the driver; location information of the vehicle at the time the audio question asking whether the ADAS function is in a state where it can be operated was received from the driver; and information describing the conditions for operating the ADAS function. The voice recognition unit recognizes a voice question obtained by the acquisition unit asking whether the ADAS function is in an operational state, A driver assistance device in which the response generation unit generates an audio response corresponding to the audio question asking whether the ADAS function is in a state where it can be activated, based on an audio question obtained by the acquisition unit asking whether the ADAS function is in a state where it can be activated, information indicating the state of the vehicle, the location information of the vehicle, and information describing the conditions for activating the ADAS function, when the vehicle speed of the vehicle is greater than zero.
2. An acquisition unit that acquires voice questions regarding ADAS received from a driver while the vehicle is in operation, A voice recognition unit that recognizes voice questions related to ADAS acquired by the acquisition unit, The system includes a large-scale language model and an answer generation unit that generates voice responses corresponding to voice questions about the ADAS recognized by the voice recognition unit, The ADAS functions include lane change assist, A driver assistance device in which, when the acquisition unit receives an audio question from a driver operating the vehicle regarding the range of vehicle speeds in which the lane change assist can be operated, the answer generation unit generates an audio answer explaining the range of vehicle speeds in which the lane change assist can be operated.
3. An acquisition step in which the driver assistance device acquires an audio question regarding ADAS received from the driver while the vehicle is in operation, The aforementioned driving assistance device includes a voice recognition step in which it recognizes a voice question related to the ADAS acquired in the acquisition step, The driver assistance device includes a response generation step which uses a large-scale language model to generate a voice response corresponding to a voice question about the ADAS recognized in the voice recognition step, In the acquisition step, the following are acquired: an audio question received from the driver when the vehicle speed is greater than zero, asking whether the ADAS function, which cannot be activated when the vehicle speed is below a threshold, is in a state where it can be activated; information indicating the state of the vehicle at the time the driver gives the audio question asking whether the ADAS function is in a state where it can be activated; location information of the vehicle at the time the driver gives the audio question asking whether the ADAS function is in a state where it can be activated; and information describing the conditions for activating the ADAS function. In the aforementioned speech recognition step, a voice question is recognized asking whether the ADAS function acquired in the acquisition step is in an operational state. A driver assistance method in which, in the response generation step, a voice question asking whether the ADAS function acquired in the acquisition step is in a state where it can be activated, information indicating the state of the vehicle, location information of the vehicle, and information describing the conditions for activating the ADAS function are generated when the vehicle speed is greater than zero, a voice response corresponding to the voice question asking whether the ADAS function is in a state where it can be activated, and, if the ADAS function is in a state where it can be activated, a voice response explaining the driver's operation necessary to activate the ADAS function are generated.
4. An acquisition step in which the driver assistance device acquires an audio question regarding ADAS received from the driver while the vehicle is in operation, The aforementioned driving assistance device includes a voice recognition step in which it recognizes a voice question related to the ADAS acquired in the acquisition step, The driver assistance device includes a response generation step which uses a large-scale language model to generate a voice response corresponding to a voice question about the ADAS recognized in the voice recognition step, The ADAS functions include lane change assist, A driving assistance method in which, when an audio question regarding the range of vehicle speeds in which the lane change assist can be operated is received from the driver while the vehicle is in operation, the response generation step generates an audio response that explains the range of vehicle speeds in which the lane change assist can be operated.
5. The processor includes: The acquisition step involves obtaining voice questions about ADAS received from the driver while the vehicle is in operation, and A speech recognition step that recognizes the voice question related to the ADAS acquired in the acquisition step, A program for executing a response generation step that uses a large-scale language model to generate a speech response corresponding to a speech question about ADAS recognized in the speech recognition step, In the acquisition step, the following are acquired: an audio question received from the driver when the vehicle speed is greater than zero, asking whether the ADAS function, which cannot be activated when the vehicle speed is below a threshold, is in a state where it can be activated; information indicating the state of the vehicle at the time the driver gives the audio question asking whether the ADAS function is in a state where it can be activated; location information of the vehicle at the time the driver gives the audio question asking whether the ADAS function is in a state where it can be activated; and information describing the conditions for activating the ADAS function. In the aforementioned speech recognition step, a voice question is recognized asking whether the ADAS function acquired in the acquisition step is in an operational state. A program that, in the response generation step, generates an audio response corresponding to the audio question asking whether the ADAS function is operational, and, if the ADAS function is operational, an audio response explaining the driver's operation required to activate the ADAS function, based on an audio question asking whether the ADAS function is operational, information indicating the vehicle's status, the vehicle's location information, and information describing the conditions for activating the ADAS function, when the vehicle's speed is greater than zero.
6. The processor includes: The acquisition step involves obtaining voice questions about ADAS received from the driver while the vehicle is in operation, and A speech recognition step that recognizes the voice question related to the ADAS acquired in the acquisition step, A program for executing a response generation step that uses a large-scale language model to generate a speech response corresponding to a speech question about ADAS recognized in the speech recognition step, The ADAS functions include lane change assist, A program in which, when an audio question regarding the range of vehicle speeds in which the lane change assist can operate is received from a driver operating the vehicle while the vehicle is in motion, is obtained in the acquisition step, the answer generation step generates an audio answer that explains the range of vehicle speeds in which the lane change assist can operate.