Calibration method, device, equipment and vehicle for trustworthiness of autonomous driving system

Abstract

The embodiment of the present application discloses a calibration method, device, equipment and vehicle for the trust of an autonomous driving system. The calibration method may include: obtaining status information of a user in the vehicle, the status information including behavioral information and / or physiological information; determining a target trust index corresponding to the user according to the status information, the target trust index being used to characterize the user's trust in the vehicle's autonomous driving system; and executing a target operation for adjusting the trust according to the target trust index. By implementing the method, the user's trust in the vehicle's autonomous driving system can be calibrated in a timely manner.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method, device, equipment and vehicle for calibrating the trustworthiness of an autonomous driving system. Background Art

[0002] With the advancement of autonomous driving technology, users need to spend less time on car control and road observation, and spend more time on non-driving-related behaviors (NDRT), such as watching movies, playing games, using mobile phones, chatting, and sleeping. The premise of this phenomenon is that users have a proper sense of trust in the vehicle's autonomous driving system. Summary of the invention

[0003] The embodiments of the present application provide a method, device, equipment and vehicle for calibrating the trust of an autonomous driving system, which can timely calibrate the user's trust in the vehicle's autonomous driving system.

[0004] A first aspect of an embodiment of the present application provides a method for calibrating the trustworthiness of an autonomous driving system, comprising:

[0005] Acquiring status information of a user in the vehicle, wherein the status information includes behavioral information and / or physiological information;

[0006] Determining, according to the state information, a target trust index corresponding to the user, wherein the target trust index is used to represent the degree of trust of the user in the automatic driving system of the vehicle;

[0007] According to the target trust index, a target operation for adjusting the trust level is performed.

[0008] A second aspect of an embodiment of the present application provides a device for calibrating the trustworthiness of an autonomous driving system, including:

[0009] A state acquisition unit, used to acquire state information of a user in the vehicle, wherein the state information includes behavior information and / or physiological information;

[0010] a trust calculation unit, configured to determine a target trust index corresponding to the user according to the state information, wherein the target trust index is used to represent the degree of trust the user has in the automatic driving system of the vehicle;

[0011] The trust calibration unit is used to perform a target operation for adjusting the trust level according to the target trust index.

[0012] A third aspect of the embodiments of the present application provides an electronic device, including:

[0013] A memory storing executable program code;

[0014] and a processor coupled to the memory;

[0015] The processor calls the executable program code stored in the memory, and when the executable program code is executed by the processor, the processor implements the method described in the first aspect of the embodiment of the present application.

[0016] A fourth aspect of an embodiment of the present application provides a vehicle, which includes the electronic device described in the third aspect of an embodiment of the present application.

[0017] A fifth aspect of the embodiments of the present application provides a computer-readable storage medium having executable program code stored thereon. When the executable program code is executed by a processor, the method described in the first aspect of the embodiments of the present application is implemented.

[0018] A sixth aspect of the embodiments of the present application discloses a computer program product. When the computer program product runs on a computer, the computer executes any one of the methods disclosed in the first aspect of the embodiments of the present application.

[0019] A seventh aspect of an embodiment of the present application discloses an application publishing platform, which is used to publish a computer program product. When the computer program product runs on a computer, the computer executes any one of the methods disclosed in the first aspect of the embodiment of the present application.

[0020] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0021] In an embodiment of the present application, status information of a user in a vehicle is obtained, the status information including behavioral information and / or physiological information; based on the status information, a target trust index corresponding to the user is determined, the target trust index being used to characterize the degree of trust the user has in the vehicle's autonomous driving system; based on the target trust index, a target operation for adjusting the degree of trust is performed.

[0022] By implementing this method, the user's trust level in the vehicle's autonomous driving system can be determined in real time based on the user's status information in the vehicle, and then the corresponding target operation can be performed based on the trust level, so as to achieve the purpose of real-time calibration of the user's trust level in the vehicle's autonomous driving system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments and the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained based on these drawings.

[0024] Figure 1It is a schematic diagram of an application scenario disclosed in an embodiment of the present application;

[0025] Figure 2 It is a flowchart of a method for calibrating the trustworthiness of an autonomous driving system disclosed in an embodiment of the present application;

[0026] Figure 3 is another flowchart of a method for calibrating the trustworthiness of an autonomous driving system disclosed in an embodiment of the present application;

[0027] Figure 4 It is a structural diagram of a device for calibrating the trustworthiness of an autonomous driving system disclosed in an embodiment of the present application;

[0028] Figure 5 It is a structural diagram of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The embodiments of the present application provide a method, device, equipment and vehicle for calibrating the trust of an autonomous driving system, which can timely calibrate the user's trust in the vehicle's autonomous driving system.

[0030] In order to make the technical personnel in the technical field better understand the scheme of the present application, the technical scheme in the embodiment of the present application will be described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, they should all fall within the scope of protection of the present application.

[0031] The technical solution disclosed in the embodiments of the present application is applied to autonomous driving vehicles, which may include but are not limited to two-wheeled vehicles, three-wheeled vehicles, four-wheeled vehicles, hybrid vehicles, or other driving energy-driven vehicles with autonomous driving capabilities. When the autonomous driving vehicle executes the autonomous driving agent, the user in the vehicle can perform non-driving related behaviors (Non-Driving-Relayed Task, NDRT) in the vehicle, and can also monitor the vehicle at any time. It should be noted that the user in the vehicle can be the driver, operator, supervisor of the autonomous driving vehicle, or an ordinary passenger.

[0032] Figure 1 This is a schematic diagram of an application scenario disclosed in the embodiment of this application. Figure 1The application scenario diagram shown includes a vehicle 10. With the advancement of autonomous driving technology, users in the vehicle 10 spend less time on vehicle control and road observation, and more time on NDRT, such as watching movies, playing games, using mobile phones, chatting, and sleeping. The premise of this phenomenon is that users have a proper degree of trust in the autonomous driving system of the vehicle 10. Therefore, how to calibrate the degree of trust users have in the autonomous driving system of the vehicle has become a technical problem that the industry needs to solve urgently.

[0033] In the prior art, the method for calibrating the user's trust in the vehicle's autonomous driving system is usually to obtain reports on the trust in the vehicle's autonomous driving system subjectively reported by users in the vehicle 10 over a period of time, perform measurements based on the obtained reports, and perform calibration based on the measurement results. This calibration method has poor real-time performance.

[0034] In the technical solution disclosed in the embodiment of the present application, the user's trust level in the automatic driving system of the vehicle 10 can be determined in real time based on the status information of the user in the vehicle 10, and then the corresponding target operation can be performed based on the trust level, thereby achieving the purpose of real-time calibration of the user's trust level in the automatic driving system of the vehicle 10.

[0035] See also Figure 2 , Figure 2 FIG. 1 is a flowchart of a method for calibrating the trustworthiness of an autonomous driving system disclosed in an embodiment of the present application. Figure 2 The calibration method shown may include the following steps:

[0036] 201. Obtain status information of a user in a vehicle, where the status information includes behavior information and / or physiological information.

[0037] In the embodiment of the present application, the status information of the user in the vehicle can be obtained through the sensor system of the vehicle. The sensor system may include but is not limited to the following devices: gaze detector, camera, microphone, wearable device and other physiological signal measuring device. The gaze detector and camera can be used to obtain the behavior information of the user in the vehicle, and the wearable device and other physiological signal measuring device can be used to obtain the physiological information of the user in the vehicle.

[0038] In some embodiments, the behavior information may include at least one of the following: posture information, expression information, eye movement information, etc. Physiological information may include at least one of the following: electrocardiogram, heart rate, pressure, skin temperature, blood oxygen saturation, blood pressure, respiratory rate, skin electricity, myoelectricity, and brain electricity, etc.

[0039] 202. Determine a target trust index corresponding to the user based on the state information, where the target trust index is used to represent the user's trust level in the vehicle's automatic driving system.

[0040] Among them, when there is only one user in the vehicle, the target trust index represents the user's trust in the vehicle's automatic driving system, and the target trust index can be obtained based on the user's status information. When there are multiple users in the vehicle, the target trust index can represent the overall trust of the multiple users in the vehicle's automatic driving system, and the target trust index can be obtained based on the status information of each user.

[0041] Among them, the target trust index can be proportional to the above-mentioned trust level. The larger the target trust index is, the higher the user's trust in the vehicle's autonomous driving system.

[0042] 203. Execute a target operation for adjusting the trust level according to the target trust index.

[0043] In some embodiments, performing a target operation for adjusting the trust level according to the target trust index may include:

[0044] When the target trust index is less than a first index threshold, performing a first operation for improving the trust level; and / or,

[0045] When the target trust index is greater than a second index threshold, a second operation for reducing the trust level is performed.

[0046] By implementing this method, when the target trust index is less than the first index threshold, a first operation for increasing the trust level is performed, and when the target trust index is greater than the second index threshold, a second operation for decreasing the trust level is performed. In this way, the user can maintain an appropriate level of trust in the vehicle's autonomous driving system, so that the user can not only effectively benefit from the autonomous driving system, but also maintain appropriate driving alertness and reduce the probability of accidents.

[0047] In some embodiments, executing a target operation for adjusting the degree of trust according to a target trust index may include: executing a target operation for adjusting the degree of trust through an onboard device of a vehicle according to the target trust index.

[0048] The vehicle-mounted equipment may include at least one of the following: a vehicle-mounted screen, a speaker, a vibration actuator, a scent generator, and a cabin light controller, etc.

[0049] In some embodiments, performing the first operation may include at least one of the following:

[0050] Output weather information via the vehicle screen and / or speakers;

[0051] Outputting food recommendation information via the vehicle screen and / or speakers;

[0052] Output attraction recommendation information via the on-board screen and / or speakers;

[0053] Play soothing music through the speakers;

[0054] Display interesting visual advertisements through the in-car screen;

[0055] Control the cockpit lighting to be in a soothing atmosphere mode;

[0056] Control the scent generator to emit a soothing aroma.

[0057] In some embodiments, performing the second operation may include at least one of the following:

[0058] Outputting vehicle status information through the vehicle screen and / or speaker; wherein the vehicle status information may include at least one of the following: vehicle speed, vehicle current position, driving mode, etc.;

[0059] Outputting vehicle surrounding environment information through the vehicle screen and / or speaker; wherein the vehicle surrounding environment information may include at least one of the following: other vehicles, pedestrians, traffic lights and traffic signs near the vehicle, etc.;

[0060] Outputting vehicle decision information through the vehicle screen and / or speaker, etc.; wherein the vehicle decision information may include at least one of the following: acceleration, deceleration, emergency stop and lane change, etc.;

[0061] Control the cabin lighting to be in strong atmosphere mode;

[0062] Control the scent generator to emit an uplifting scent;

[0063] Control the vibration actuator to vibrate greatly.

[0064] By implementing this method, the information used to adjust the trust level is not limited to vision, but can also include touch, hearing and smell, and the calibration method is richer.

[0065] By implementing the above method, the user's trust level in the vehicle's autonomous driving system can be determined in real time based on the user's status information in the vehicle, and corresponding target operations can be performed based on the trust level, so as to achieve the purpose of real-time calibration of the user's trust level in the vehicle's autonomous driving system.

[0066] See also Figure 3 , Figure 3 FIG. 1 is another flowchart of a method for calibrating the trustworthiness of an autonomous driving system disclosed in an embodiment of the present application. Figure 3 The calibration method shown may include the following steps:

[0067] 301. Obtain status information of a user in a vehicle, where the status information includes behavior information and / or physiological information.

[0068] For more information about status information, please refer to Figure 2 The description below step 201 is not repeated here.

[0069] 302. Determine a target trust index corresponding to the user based on the state information, where the target trust index is used to represent the user's trust level in the vehicle's automatic driving system.

[0070] In some embodiments, the vehicle's current driving scene information can also be identified based on the environmental information around the vehicle.

[0071] Furthermore, determining a target trust index corresponding to the user based on the state information may include: determining a target trust index corresponding to the user based on the state information and current driving scene information of the vehicle.

[0072] In some embodiments, there are multiple users in the vehicle, and determining the target trust index corresponding to the user based on the status information can include: determining the trust index corresponding to each user based on the status information of each user in the vehicle; and using the smallest trust index among the trust indexes corresponding to each user as the target trust index corresponding to the user in the vehicle.

[0073] In some embodiments, the status information includes behavioral information and physiological information, and the users in the vehicle include a first user; determining the trust index corresponding to the first user based on the status information of the first user may include: determining a first trust index based on the behavioral information of the first user; determining a second trust index based on the physiological information of the first user; determining a trust index corresponding to the first user based on the first trust index and the second trust index.

[0074] In some embodiments, determining the first trust index based on the behavior information of the first user may include: determining the first trust index based on the behavior information of the first user and current driving scene information of the vehicle.

[0075] In some embodiments, the behavior information includes posture information, expression information, and eye movement information. The first trust index is determined according to the behavior information of the first user and the current driving scene information of the vehicle, including but not limited to the following methods:

[0076] Method 1: Determine the first sub-trust index, the second sub-trust index and the third sub-trust index according to the posture information, expression information and eye movement information of the first user respectively; adjust the first sub-trust index, the second sub-trust index and the third sub-trust index respectively according to the current driving scene information of the vehicle; determine the first trust index according to the adjusted first sub-trust index, the second sub-trust index and the third sub-trust index.

[0077] In some embodiments, determining the first sub-trust index based on the posture information of the first user may include: determining the posture ease level of the first user based on the posture information of the first user; using the trust index corresponding to the posture ease level of the first user in the first trust index table as the first sub-trust index; wherein the posture ease level indicates that the easier the posture of the first user is, the higher the corresponding trust index is.

[0078] In some embodiments, adjusting the first sub-trust index according to the vehicle's current driving scene information may include: when the vehicle's current driving scene information indicates that the vehicle is in a complex driving scene, adjusting the first sub-trust index using a first coefficient; when the vehicle's current driving scene information indicates that the vehicle is in a simple driving scene, adjusting the first sub-trust index using a second coefficient.

[0079] In some embodiments, the first coefficient is greater than 1 and the second coefficient is less than 1.

[0080] Exemplarily, complex driving scenarios include driving scenarios with complex road conditions and driving scenarios with large passenger flow. Simple driving scenarios include driving scenarios with simple road conditions and driving scenarios with small passenger flow.

[0081] In some embodiments, determining the posture ease level of the first user based on the posture information of the first user may include: processing the posture information of the first user by a first level classifier to obtain the posture ease level of the first user. The first level classifier may be pre-trained using a variety of sample posture information.

[0082] Exemplarily, when the posture information of the first user indicates that the first user sits upright, grasps an object, and has a small movement amplitude, the ease level of the first user is determined to be the first level;

[0083] When the posture information of the first user indicates that the first user is sitting upright and holding an object, determining that the posture ease level of the first user is the second level;

[0084] When the posture information of the first user indicates that the first user is sitting upright, determining that the posture ease level of the first user is the third level;

[0085] When the posture information of the first user indicates that the first user is lying lazily, determining that the posture ease level of the first user is the fourth level;

[0086] When the posture information of the first user indicates that the first user is lying lazily and the movement amplitude is large, determining that the posture ease level of the first user is the fifth level;

[0087] It should be noted that the posture of the first user becomes increasingly relaxed from the first level to the fifth level.

[0088] In some embodiments, determining the second sub-trust index based on the facial expression information of the first user may include: determining the first user's facial expression emotion level based on the first user's facial expression information; using the trust index corresponding to the first user's facial expression emotion level in the second trust index table as the second sub-trust index; wherein the more positive the first user's emotion represented by the facial expression emotion level is, the higher the corresponding trust index is.

[0089] Among them, regarding the method of adjusting the second sub-trust index, reference can be made to the above-mentioned method of adjusting the first sub-trust index, which will not be repeated here.

[0090] In some embodiments, the expression information may include facial expression data of the first user, and determining the first user's expression emotion level based on the first user's expression information may include: inputting the first user's facial expression data into a second level classifier to obtain the first user's expression emotion level. The second level classifier may be pre-trained using a variety of sample facial expression data.

[0091] In some embodiments, the eye movement information may include a gaze duration ratio, which can be obtained by dividing the gaze duration of one's own NDRT task (watching movies, playing with mobile phones, reading, playing games, etc.) by a specified duration, or by dividing the gaze duration of the display system in the vehicle by a specified duration, or by dividing the gaze duration of the vehicle's external environment (pedestrians, vehicles, roads, surrounding trees) by a specified duration.

[0092] Further, determining the third sub-trust index according to the eye movement information may include: searching a third sub-trust index corresponding to the gaze duration in a third trust index table.

[0093] Among them, when the gaze time is obtained by dividing the gaze time of one's own NDRT task (watching movies, playing with mobile phones, reading, playing games, etc.) by the specified time, or when the gaze time is obtained by dividing the gaze time of the vehicle's external environment (pedestrians, vehicles, roads, surrounding trees) by the specified time, the longer the gaze time, the stronger the trust represented by the third sub-trust index. When the gaze time is obtained by dividing the gaze time of the display system in the vehicle (displaying driving maps, displaying vehicle driving information, etc.) by the specified time, the shorter the gaze time, the stronger the trust represented by the third sub-trust index.

[0094] Among them, regarding the method of adjusting the third sub-trust index, reference can be made to the above-mentioned method of adjusting the first sub-trust index, which will not be repeated here.

[0095] In some embodiments, the first trust index is determined according to the adjusted first sub-trust index, the second sub-trust index, and the third sub-trust index, including but not limited to the following methods:

[0096] The largest trust index among the adjusted first sub-trust index, the adjusted second sub-trust index and the adjusted third sub-trust index is used as the first trust index;

[0097] or,

[0098] The average of the adjusted first sub-trust index, the adjusted second sub-trust index and the adjusted third sub-trust index is used as the first trust index;

[0099] or,

[0100] The smallest trust index among the adjusted first sub-trust index, the adjusted second sub-trust index and the adjusted third sub-trust index is used as the first trust index.

[0101] Method 2: Determine the first sub-trust index, the second sub-trust index and the third sub-trust index according to the posture information, expression information and eye movement information of the first user respectively; determine the third trust index according to the first sub-trust index, the second sub-trust index and the third sub-trust index; adjust the third trust index according to the current driving scene information of the vehicle to obtain the first trust index.

[0102] Among them, the calculation method of the first sub-trust index, the second sub-trust index and the third sub-trust index can be referred to the above description and will not be repeated here.

[0103] In some embodiments, the third trust index is determined according to the first sub-trust index, the second sub-trust index and the third sub-trust index, which may include but is not limited to the following methods:

[0104] The largest trust index among the first sub-trust index, the second sub-trust index and the third sub-trust index is used as the third trust index;

[0105] or,

[0106] The average of the first sub-trust index, the second sub-trust index and the third sub-trust index is used as the third trust index;

[0107] or,

[0108] The smallest trust index among the first sub-trust index, the second sub-trust index and the third sub-trust index is used as the third trust index.

[0109] Among them, regarding the adjustment method of the third trust index, reference can be made to the above-mentioned method of adjusting the first sub-trust index, which will not be repeated here.

[0110] In some embodiments, the method of determining the second trust index according to the physiological information of the first user may specifically include: processing the physiological information of the first user through a fourth level classifier to obtain the physiological emotion level of the first user; wherein the fourth level classifier may be pre-trained by multiple sample physiological information; and using the trust index in the fourth trust index table that matches the physiological emotion level of the first user as the second trust index. wherein the physiological emotion level represents that the more nervous the emotion of the first user is, the stronger the trust represented by the corresponding second trust index is.

[0111] In some embodiments, the method of determining the second trust index based on the physiological information of the first user may specifically include: processing the physiological information of the first user through a fourth-level classifier to obtain the physiological-emotional level of the first user; wherein the fourth-level classifier may be pre-trained by multiple sample physiological information; obtaining a trust index in the fourth trust index table that matches the physiological-emotional level of the first user; and adjusting the trust index that matches the physiological-emotional level of the first user according to the current driving scene information of the vehicle to obtain a second trust index.

[0112] In some embodiments, determining the trust index corresponding to the first user according to the first trust index and the second trust index may include but is not limited to the following methods:

[0113] The largest trust index between the first trust index and the second trust index is used as the trust index corresponding to the first user;

[0114] or,

[0115] Taking the average of the first trust index and the second trust index as the trust index corresponding to the first user;

[0116] or,

[0117] The smallest trust index between the first trust index and the second trust index is used as the trust index corresponding to the first user.

[0118] 303. Identify a target reminder mode corresponding to the target user.

[0119] When the number of users in the vehicle is 1, the target user is this user; when the number of users in the vehicle includes multiple users, the target user is the user who has the lowest level of trust in the vehicle's autonomous driving system among the multiple users.

[0120] In some embodiments, the target reminder mode includes at least one of the following: a visual reminder mode, an auditory reminder mode, a tactile reminder mode, and an olfactory reminder mode.

[0121] In some embodiments, identifying the target reminder mode corresponding to the target user may include: identifying the target reminder mode corresponding to the target user according to behavior information of the target user.

[0122] In some embodiments, identifying the target reminder mode corresponding to the target user according to the behavior information of the target user may include:

[0123] When the behavior information of the target user indicates that the target user is sitting with eyes open, determining that the target reminder mode is a visual reminder mode;

[0124] When the behavior information of the target user indicates that the target user has closed eyes, the gaze point of the target user's eyes is outside the vehicle window, or the target user is lying flat, determining the target reminder mode to be at least one of the following: an auditory reminder mode, a tactile reminder mode, and an olfactory reminder mode;

[0125] When the behavior information of the target user indicates that the target user wears headphones, determining the target reminder mode to be at least one of the following: a visual reminder mode, a tactile reminder mode, and an olfactory reminder mode;

[0126] 304. Determine, from at least one in-vehicle device of the vehicle, an in-vehicle device that matches the target reminder pattern.

[0127] Among them, the reminder mode corresponding to the vehicle screen is the visual reminder mode, the reminder mode corresponding to the speaker is the auditory reminder mode, the reminder mode corresponding to the vibrator is the tactile reminder mode, and the reminder mode corresponding to the odor generator is the olfactory reminder mode.

[0128] 305. According to the target trust index, the vehicle-mounted device matched with the target reminder mode executes a target operation for adjusting the trust level.

[0129] In some embodiments, the number of vehicle-mounted devices that match the target reminder mode is one or more.

[0130] When there are multiple in-vehicle devices that match the target reminder pattern, the target operation for adjusting the trust level is performed by the in-vehicle devices that match the target reminder pattern according to the target trust index, which may include but is not limited to the following methods:

[0131] Method 1: Use the vehicle-mounted device with the highest priority among the vehicle-mounted devices matching the target reminder pattern as the target device; and perform a target operation for adjusting the trust level through the target device according to the target trust index.

[0132] In some embodiments, based on the target trust index, performing a target operation for adjusting the degree of trust through a target device may include: when the target trust index is less than a first index threshold, performing a first operation for increasing the degree of trust through the target device; and / or, when the target trust index is greater than a second index threshold, performing a second operation for reducing the degree of trust through the target device.

[0133] Method 2: When the target trust index is less than a first index threshold, the driving experience index of the target user is obtained, and the driving experience index is used to characterize the driving proficiency of the target user; the vehicle-mounted device corresponding to the driving experience index among the vehicle-mounted devices matching the target reminder mode is used as the target device; wherein, the lower the driving experience index, the less visual interference the corresponding vehicle-mounted device has on the target user; and a first operation for improving the degree of trust is performed through the target device.

[0134] In some embodiments, multiple index ranges may be preset, and each index range corresponds to a different vehicle-mounted device. The vehicle-mounted device corresponding to the driving experience index includes: the vehicle-mounted device corresponding to the index range in which the target user's driving experience index is located.

[0135] Exemplarily, four index ranges are pre-set, including the first index range, the second index range, the third index range and the fourth index range. Among them, the driving proficiency represented by the first index range is less than the driving proficiency represented by the second index range, the driving proficiency represented by the second index range is less than the driving proficiency represented by the third index range, and the driving proficiency represented by the third index range is less than the driving proficiency represented by the fourth index range. The vehicle-mounted device corresponding to the first index range is a smell generator, the vehicle-mounted device corresponding to the second index range is a vibration actuator, the vehicle-mounted device corresponding to the third index range is a speaker, and the vehicle-mounted device corresponding to the fourth index range is a vehicle-mounted screen.

[0136] By implementing this method, when users with less driving experience lack trust in the vehicle, they can try to give priority to calibrating in a way that does not increase their workload, and the calibration method is more in line with user needs.

[0137] The following is a further explanation of the above steps with a scenario example:

[0138] Example 1: When the user in the vehicle pays attention to the external information of the vehicle for a long time and the body posture is tense, it is judged that the user has low trust in the vehicle's autonomous driving system and calibration is required. In order to calibrate the user's trust in the vehicle's autonomous driving system, the appearance of pedestrians or text information that the vehicle stops and waits is highlighted on the in-vehicle map display system that the user pays attention to, and the user can also be prompted with voice to such information, so that the user can be more comfortable and focused on the current NDRT.

[0139] Example 2: The user is overly immersed in the NDRT task, and the visual gaze stays on non-navigation information for a long time, not paying attention to the vehicle situation. At this time, the driving scene is relatively complex, and it is judged that the user's trust in the vehicle's autonomous driving system is too high and needs to be calibrated. In order to calibrate the user's trust in the vehicle's autonomous driving system, voice and cabin vibration are used to remind the user to pay attention to the environmental information around the vehicle's driving and the vehicle's driving decision information.

[0140] Example 3: During the driving process, the user sleeps for too long and does not pay attention to the vehicle information for a long time. At this time, the driving scene is relatively simple. It is judged that the user's trust in the vehicle's automatic driving system is too high and needs to be calibrated. In order to calibrate the user's trust in the vehicle's automatic driving system, music is played, voice broadcasts are made at regular intervals, or scents are emitted to improve the atmosphere in the car, so that the user can stay awake to a certain extent and understand the vehicle's condition.

[0141] By implementing the above method, the user's trust in the vehicle's automatic driving system can be determined in real time based on the status information of the user in the vehicle, and the corresponding target operation can be performed according to the trust level, so as to achieve the purpose of real-time calibration of the user's trust in the vehicle's automatic driving system. Furthermore, the vehicle-mounted device that matches the target reminder mode can be determined from the vehicle-mounted devices, and the target operation for adjusting the trust level can be performed through the vehicle-mounted device that matches the target reminder mode, which can be quickly perceived by the user in the vehicle and better meet the user's needs.

[0142] See also Figure 4 , Figure 4 1 is a structural diagram of a calibration device for the trustworthiness of an autonomous driving system disclosed in an embodiment of the present application. Figure 4 The calibration device shown may include a state acquisition unit 401, a trust calculation unit 402 and a trust calibration unit 403; wherein:

[0143] A state acquisition unit 401 is used to acquire state information of a user in the vehicle, where the state information includes behavior information and / or physiological information;

[0144] A trust calculation unit 402 is used to determine a target trust index corresponding to the user according to the state information, where the target trust index is used to represent the degree of trust the user has in the automatic driving system of the vehicle;

[0145] The trust calibration unit 403 is used to perform a target operation for adjusting the trust level according to a target trust index.

[0146] In some embodiments, there are multiple users in the vehicle, and the trust calculation unit 402 is used to determine the target trust index corresponding to the user based on the status information, which may specifically include: the trust calculation unit 402 is used to determine the trust index corresponding to each user based on the status information of each user in the vehicle; the smallest trust index among the trust indexes corresponding to each user is used as the target trust index corresponding to the user in the vehicle.

[0147] In some embodiments, the status information includes behavioral information and physiological information, and the users in the vehicle include a first user; the trust calculation unit 402 is used to determine the trust index corresponding to the first user based on the status information of the first user, which may specifically include: the trust calculation unit 402 is used to determine the first trust index based on the behavioral information of the first user, and the behavioral information includes at least one of the following: posture information, expression information and eye movement information; and, determine the second trust index based on the physiological information of the first user, and the physiological information includes at least one of the following: electrocardiogram, heart rate, pressure, skin temperature, blood oxygen saturation, blood pressure, respiratory rate, skin electricity, myoelectricity, and electroencephalogram; and, determine the trust index corresponding to the first user based on the first trust index and the second trust index.

[0148] In some embodiments, the trust calculation unit 402 is used to determine the target trust index corresponding to the user based on the status information, which may specifically include: the trust calculation unit 402 is used to determine the target trust index corresponding to the user based on the status information and the current driving scene information of the vehicle.

[0149] In some embodiments, the trust calibration unit 403 is used to perform a target operation for adjusting the degree of trust based on a target trust index, which may specifically include: the trust calibration unit 403 is used to identify a target reminder pattern corresponding to a target user; and, from at least one on-board device of the vehicle, determine an on-board device that matches the target reminder pattern; and, based on the target trust index, perform a target operation for adjusting the degree of trust through the on-board device that matches the target reminder pattern.

[0150] In some embodiments, when the number of users in the vehicle is 1, the target user is that user; when the number of users in the vehicle includes multiple users, the target user is the user who has the lowest level of trust in the vehicle's autonomous driving system among the multiple users.

[0151] In some embodiments, there are multiple vehicle-mounted devices that match the target reminder pattern, and the trust calibration unit 403 is used to perform a target operation for adjusting the degree of trust through the vehicle-mounted devices that match the target reminder pattern according to the target trust index. Specifically, the trust calibration unit 403 is used to use the vehicle-mounted device with the highest priority among the vehicle-mounted devices that match the target reminder pattern as the target device; and, according to the target trust index, perform a target operation for adjusting the degree of trust through the target device.

[0152] In some embodiments, there are multiple vehicle-mounted devices that match the target reminder pattern, and the trust calibration unit 403 is used to perform a target operation for adjusting the degree of trust through the vehicle-mounted devices that match the target reminder pattern according to the target trust index. Specifically, the method may include: when the target trust index is less than a first index threshold, obtaining a driving experience index of the target user, the driving experience index being used to characterize the driving proficiency of the target user; and, among the vehicle-mounted devices that match the target reminder pattern, the vehicle-mounted device corresponding to the driving experience index is used as a target device; wherein, the lower the driving experience index, the less visual interference the corresponding vehicle-mounted device has on the target user; and, through the target device, performing a first operation for improving the degree of trust.

[0153] In some embodiments, the target reminder mode includes at least one of the following: a visual reminder mode, an auditory reminder mode, a tactile reminder mode, and an olfactory reminder mode.

[0154] In some embodiments, the trust calibration unit 403 is used to perform a target operation for adjusting the degree of trust based on a target trust index, which may specifically include: the trust calibration unit 403 is used to perform a first operation for improving the degree of trust when the target trust index is less than a first index threshold; and / or, when the target trust index is greater than a second index threshold, to perform a second operation for reducing the degree of trust.

[0155] See also Figure 5 , Figure 5 FIG. 1 is a structural diagram of an electronic device disclosed in an embodiment of the present application. Figure 5 The electronic device shown may include a memory 501 storing executable program codes, and a processor 502 coupled to the memory.

[0156] In the embodiment of the present application, the processor 502 also has the following functions:

[0157] Acquiring status information of a user in the vehicle, the status information including behavioral information and / or physiological information;

[0158] Determine a target trust index corresponding to the user according to the state information, where the target trust index is used to represent the user's trust in the vehicle's automatic driving system;

[0159] According to the target trust index, a target operation for adjusting the trust level is performed.

[0160] In the embodiment of the present application, there are multiple users in the vehicle, and the processor 502 also has the following functions:

[0161] Determine the trust index corresponding to each user according to the status information of each user in the vehicle;

[0162] The minimum trust index among the trust indexes corresponding to each user is used as the target trust index corresponding to the users in the vehicle.

[0163] In the embodiment of the present application, the state information includes behavior information and physiological information, and the user in the vehicle includes the first user; the processor 502 also has the following functions:

[0164] Determining a first trust index according to behavior information of the first user, where the behavior information includes at least one of the following: posture information, expression information, and eye movement information;

[0165] Determine a second trust index according to physiological information of the first user, where the physiological information includes at least one of the following: electrocardiogram, heart rate, pressure, skin temperature, blood oxygen saturation, blood pressure, respiratory rate, electrodermal conductivity, electromyography, and electroencephalogram;

[0166] A trust index corresponding to the first user is determined according to the first trust index and the second trust index.

[0167] In the embodiment of the present application, the processor 502 also has the following functions:

[0168] According to the status information and the current driving scene information of the vehicle, the target trust index corresponding to the user is determined.

[0169] In the embodiment of the present application, the processor 502 also has the following functions:

[0170] Identify the target reminder mode corresponding to the target user;

[0171] Determining, from at least one in-vehicle device of the vehicle, an in-vehicle device that matches the target reminder pattern;

[0172] According to the target trust index, a target operation for adjusting the trust level is performed by the vehicle-mounted device matched with the target reminder pattern.

[0173] In an embodiment of the present application, when the number of users in the vehicle is 1, the target user is this user; when the number of users in the vehicle includes multiple users, the target user is the user who has the lowest level of trust in the vehicle's automatic driving system among the multiple users.

[0174] In the embodiment of the present application, there are multiple vehicle-mounted devices that match the target reminder mode, and the processor 502 also has the following functions:

[0175] The vehicle-mounted device with the highest priority among the vehicle-mounted devices matching the target reminder mode is used as the target device;

[0176] According to the target trust index, a target operation for adjusting the trust level is performed by the target device.

[0177] In the embodiment of the present application, there are multiple vehicle-mounted devices that match the target reminder mode, and the processor 502 also has the following functions:

[0178] When the target trust index is less than the first index threshold, obtaining a driving experience index of the target user, where the driving experience index is used to characterize the driving proficiency of the target user;

[0179] The in-vehicle device corresponding to the driving experience index among the in-vehicle devices matching the target reminder mode is used as the target device; wherein the lower the driving experience index, the less visual interference the corresponding in-vehicle device has on the target user;

[0180] By the target device, a first operation for increasing the trust level is performed.

[0181] In an embodiment of the present application, the target reminder mode includes at least one of the following: a visual reminder mode, an auditory reminder mode, a tactile reminder mode, and an olfactory reminder mode.

[0182] In the embodiment of the present application, the processor 502 also has the following functions:

[0183] When the target trust index is less than a first index threshold, performing a first operation for improving the trust level; and / or,

[0184] When the target trust index is greater than a second index threshold, a second operation for reducing the trust level is performed.

[0185] An embodiment of the present application discloses a vehicle, which includes the electronic device in the above embodiment.

[0186] An embodiment of the present application discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor implements part or all of the steps executed by the electronic device in the above embodiment.

[0187] The embodiment of the present application discloses a computer program product. When the computer program product is run on a computer, the computer executes part or all of the steps executed by the electronic device in the above embodiment.

[0188] An embodiment of the present application discloses an application publishing platform, which is used to publish a computer program product. When the computer program product runs on a computer, the computer executes part or all of the steps executed by the electronic device in the above embodiment.

[0189] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0190] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server, or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server, a data center, etc. that includes one or more available media integration. Available media can be magnetic media, (e.g., floppy disk, disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state disk Solid State Disk (SSD)), etc.

[0191] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0192] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0193] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0194] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0195] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc. Various media that can store program codes.

[0196] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for calibrating the trustworthiness of an autonomous driving system, characterized in that: include: Acquiring status information of users in the vehicle, the status information including behavior information and physiological information, and the number of users in the vehicle is multiple; Determine the trust index corresponding to each user according to the status information of each user in the vehicle; use the minimum trust index among the trust indexes corresponding to each user as the target trust index corresponding to the user in the vehicle, wherein the target trust index is used to represent the degree of trust of the user in the automatic driving system of the vehicle; According to the target trust index, performing a target operation for adjusting the trust level; The users in the vehicle include a first user, and a trust index corresponding to the first user is determined based on the status information of the first user, including: determining a first trust index based on the behavior information of the first user; determining a second trust index based on the physiological information of the first user; and determining a trust index corresponding to the first user based on the first trust index and the second trust index.

2. The method according to claim 1, characterized in that The behavioral information includes at least one of the following: posture information, expression information and eye movement information; the physiological information includes at least one of the following: electrocardiogram, heart rate, pressure, skin temperature, blood oxygen saturation, blood pressure, respiratory rate, electrodermal electricity, electromyography, and electroencephalogram.

3. The method according to claim 1, characterized in that: Determining a first trust index according to the behavior information of the first user includes: The first trust index is determined according to the behavior information of the first user and the current driving scene information of the vehicle.

4. The method according to claim 1, characterized in that: The performing a target operation for adjusting the degree of trust according to the target trust index includes: Identify the target reminder mode corresponding to the target user; Determining, from at least one on-board device of the vehicle, an on-board device that matches the target reminder pattern; According to the target trust index, a target operation for adjusting the trust level is performed by the vehicle-mounted device matched with the target reminder pattern.

5. The method according to claim 4, characterized in that The target user is a user who has the lowest degree of trust in the automatic driving system of the vehicle among multiple users included in the vehicle.

6. The method according to claim 4, characterized in that There are multiple in-vehicle devices that match the target reminder pattern, and performing a target operation for adjusting the trust level through the in-vehicle devices that match the target reminder pattern according to the target trust index includes: Using the vehicle-mounted device with the highest priority among the vehicle-mounted devices matching the target reminder pattern as the target device; According to the target trust index, a target operation for adjusting the trust level is performed by the target device.

7. The method according to claim 4, characterized in that There are multiple in-vehicle devices that match the target reminder pattern, and performing a target operation for adjusting the trust level through the in-vehicle devices that match the target reminder pattern according to the target trust index includes: When the target trust index is less than a first index threshold, obtaining a driving experience index of the target user, where the driving experience index is used to characterize the driving proficiency of the target user; The vehicle-mounted device corresponding to the driving experience index among the vehicle-mounted devices matching the target reminder pattern is used as the target device; wherein the lower the driving experience index, the less visual interference the corresponding vehicle-mounted device causes to the target user; A first operation for improving the trust level is performed through the target device.

8. The method according to any one of claims 4 to 7, characterized in that: The target reminder mode includes at least one of the following: a visual reminder mode, an auditory reminder mode, a tactile reminder mode, and an olfactory reminder mode.

9. The method according to claim 1, characterized in that: The performing a target operation for adjusting the degree of trust according to the target trust index includes: When the target trust index is less than a first index threshold, performing a first operation for improving the trust level; and / or, When the target trust index is greater than a second index threshold, a second operation for reducing the trust level is performed.

10. A device for calibrating the trustworthiness of an autonomous driving system, characterized in that: include: A state acquisition unit, used to acquire state information of a user in the vehicle, the state information including behavior information and physiological information, and the number of users in the vehicle is multiple; a trust calculation unit, configured to determine a trust index corresponding to each user according to the status information of each user in the vehicle; and use the minimum trust index among the trust indexes corresponding to each user as a target trust index corresponding to the user in the vehicle, wherein the target trust index is used to represent the degree of trust of the user in the automatic driving system of the vehicle; a trust calibration unit, configured to perform a target operation for adjusting the trust level according to the target trust index; The users in the vehicle include a first user, and the trust calculation unit is specifically used to determine a first trust index based on the behavior information of the first user; determine a second trust index based on the physiological information of the first user; and determine a trust index corresponding to the first user based on the first trust index and the second trust index.

11. An electronic device, characterized in that: include: A memory storing executable program code; and a processor coupled to the memory; The processor calls the executable program code stored in the memory, and when the executable program code is executed by the processor, the processor implements the method according to any one of claims 1 to 9.

12. A vehicle comprising the electronic device according to claim 11.

Images