Design method and device for human-machine interface of autonomous vehicle

Abstract

This invention discloses a method and apparatus for designing a human-machine interface (HMI) for autonomous vehicles, relating to the field of automotive technology. The invention determines the reasonableness of each driver feedback based on the confidence level of the autonomous driving system and the driver's feedback status to the autonomous driving function, obtaining a large number of combinations of the reasonableness of driver feedback and the actual display intensity of HMI information. Based on these combinations, a target display intensity of the HMI information that maximizes driver feedback is determined. By setting each piece of information in the HMI according to the target display intensity, the most reasonable HMI for driver feedback can be obtained, thus improving the reasonableness of the HMI and enabling the driver to use the vehicle's autonomous driving function appropriately.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and more particularly to a method and apparatus for designing human-machine interfaces for autonomous vehicles. Background Technology

[0002] The human-machine interface (HMI) of autonomous vehicles significantly impacts the utilization rate of their autonomous driving functions. A well-designed HMI fosters driver trust and proper use of these functions, while a poorly designed HMI can lead to either distrust or over-trust. Distrust can result in the system being abandoned, while over-trust can lead to its misuse. Therefore, to ensure proper driver use of autonomous driving functions, it is crucial to consider how to improve the HMI of autonomous vehicles. Summary of the Invention

[0003] This invention solves the technical problem of how to make the human-machine interface of autonomous vehicles more reasonable by providing a design method and device for human-machine interface of autonomous vehicles.

[0004] On the one hand, the present invention provides the following technical solution:

[0005] A method for designing a human-machine interface for autonomous vehicles includes:

[0006] Acquire the confidence level of the autonomous driving system during each autonomous driving process, the driver's feedback status to the autonomous driving function each time, and the actual display intensity of each type of information in each version of the human-machine interface;

[0007] The reasonableness of each driver's feedback is determined based on the confidence level and the feedback status;

[0008] The target display intensity for each type of information is determined based on multiple degrees of reasonableness and the corresponding actual display intensity to make the driver's feedback most reasonable.

[0009] Optionally, the confidence level represents the system state, including good system state, average system state, system may be about to exit, system exit or is preparing to exit.

[0010] Optionally, the feedback state includes no feedback, supervised state, active takeover state, and passive takeover state.

[0011] Optionally, the information includes autonomous driving-related information, takeover alert information, and driver-related information.

[0012] Optionally, determining the reasonableness of each driver feedback based on the confidence level and the feedback status includes:

[0013] Determine the reasonableness value corresponding to each combination of the confidence level and the corresponding feedback state;

[0014] The degree of reasonableness is calculated based on multiple reasonableness values.

[0015] Optionally, a target display intensity for each piece of information that makes the driver's feedback most reasonable is determined based on multiple degrees of reasonableness and the corresponding actual display intensity, including:

[0016] Determine the expression between each of the stated degrees of reasonableness and the corresponding actual display intensity;

[0017] The target display intensity is determined based on multiple of the stated expressions.

[0018] Optionally, the target display intensity is determined based on a plurality of the expressions, including:

[0019] Machine learning is performed based on multiple of the expressions to calculate the target display intensity.

[0020] On the other hand, the present invention also provides the following technical solution:

[0021] A human-machine interface design device for autonomous vehicles, comprising:

[0022] The acquisition module is used to acquire the confidence level of the autonomous driving system during each autonomous driving process of the vehicle, the driver's feedback status to the autonomous driving function each time, and the actual display intensity of each type of information in each version of the human-machine interface.

[0023] A determination module is used to determine the reasonableness of each feedback from the driver based on the confidence level and the feedback status;

[0024] The target display intensity for each type of information is determined based on multiple degrees of reasonableness and the corresponding actual display intensity to make the driver's feedback most reasonable.

[0025] On the other hand, the present invention also provides the following technical solution:

[0026] A computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any autonomous vehicle human-machine interface design method.

[0027] On the other hand, the present invention also provides the following technical solution:

[0028] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a human-machine interface design method for any autonomous vehicle.

[0029] One or more technical solutions provided by this invention have at least the following technical effects or advantages:

[0030] This invention determines the reasonableness of each driver feedback based on the confidence level of the autonomous driving system and the driver's feedback status to the autonomous driving function. It obtains a large number of combinations of the reasonableness of driver feedback and the actual display intensity of human-machine interface information. Based on the combination of the reasonableness of driver feedback and the actual display intensity of human-machine interface information, it determines the target display intensity of human-machine interface information that makes the driver's feedback most reasonable. After setting each piece of information of the human-machine interface based on the target display intensity of each piece of information, the human-machine interface that makes the driver's feedback most reasonable can be obtained, which improves the reasonableness of the human-machine interface and enables the driver to use the vehicle's autonomous driving function reasonably. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is a flowchart of the human-machine interface design method for autonomous vehicles in an embodiment of the present invention;

[0033] Figure 2 This is a schematic diagram of the human-machine interface design device for autonomous vehicles in an embodiment of the present invention. Detailed Implementation

[0034] The embodiments of the present invention provide a method and apparatus for designing human-machine interfaces for autonomous vehicles, thereby solving the technical problem of how to make the human-machine interface of autonomous vehicles more reasonable.

[0035] To better understand the technical solution of the present invention, the technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0036] like Figure 1 As shown, the human-machine interface design method for autonomous vehicles according to an embodiment of the present invention includes:

[0037] Step S1: Obtain the confidence level of the autonomous driving system, the driver's feedback status to the autonomous driving function each time, and the actual display intensity of each type of information in each version of the human-machine interface during each autonomous driving process.

[0038] Step S2: Determine the reasonableness of each driver's feedback based on the confidence level of the autonomous driving system and the driver's feedback status;

[0039] Step S3: Determine the target display intensity of each piece of information in the human-machine interface that makes the driver's feedback most reasonable based on multiple levels of reasonableness and the corresponding actual display intensity.

[0040] The confidence level represents the state of the autonomous driving system, namely its reliability and robustness. The system state represented by the confidence level can include: good system state, average system state, system likely to disengage, system disengagement or preparing to disengage. The confidence level of the autonomous driving system is used as a known value during each autonomous driving process. For example, a confidence level of A represents a good system state, B represents an average system state, C represents a system likely to disengage, and D represents a system disengagement or preparing to disengage. The confidence level of the autonomous driving system can be obtained from the in-vehicle infotainment system (IVI).

[0041] During an autonomous driving process, the driver may provide feedback to the autonomous driving function multiple times. Each feedback will result in a feedback status, which can include no feedback, supervised status, active takeover status, and passive takeover status. The supervised status indicates that the driver has monitored the autonomous driving function; the active takeover status indicates that the driver has actively taken over the vehicle; and the passive takeover status indicates that the driver has been passively taken over the vehicle. For example, feedback status E represents no feedback, F represents supervised status, G represents active takeover status, and H represents passive takeover status. The driver's no-feedback and supervised statuses can be identified by the Driver Monitoring System (DMS), while the active and passive takeover statuses can be identified by steering wheel angle signals and accelerator / brake pedal signals.

[0042] The information displayed in the human-machine interface can include autonomous driving-related information, takeover warning information, and driver-related information. Autonomous driving-related information can include vehicle location information, weather information, lane line information, pedestrian and vehicle information around the vehicle, vehicle speed information, and information on the vehicle's next action (such as braking, steering, U-turn, lane change), etc. Takeover warning information can include visual warning information, auditory warning information, and tactile warning information, and driver-related information can include driver status information (normal, fatigued, or distracted), driver takeover information (whether the driver is holding the steering wheel, whether the driver actively brakes), and non-driving input information input by the driver (including infotainment, voice input, etc.).

[0043] In a human-computer interface (HCI), the display intensity of information represents whether the information is displayed and its intensity. The display intensity of visual cues is the prominence of the displayed content; the display intensity of auditory cues is the volume and frequency of the sound; and the display intensity of tactile cues is the amplitude and frequency of the vibration. For example, a display intensity of 0 means the information is not displayed, and a display intensity of 1 represents the maximum display intensity. Let 'i' represent the information's sequence number, and 'wi' represent the actual display intensity of the i-th piece of information, with 'wi' ranging from 0 to 1. Once each version of the HCI is determined, the actual display intensity of each type of information in the HCI is determined, and the display result 'f' of that version of the HCI can be obtained. HMI = w1 + w2 + ... + wn, where n is the total number of information types.

[0044] Step S2 may include: determining the reasonableness value corresponding to each combination of confidence level and corresponding feedback state; and calculating the degree of reasonableness based on multiple reasonableness values. In this embodiment of the invention, there are 4 types of confidence levels, 4 types of feedback states, and 16 combinations of confidence levels and feedback states. Only when the combination of confidence level and feedback state is AE, BF, CG, or DH does the driver's feedback represent reasonableness; the other combinations represent unreasonable feedback. Of course, reasonable and unreasonable feedback are also graded. For example, the reasonableness value can range from -10 to 10, and the reasonableness value of a reasonable feedback combination can range from 1 to 10. The higher the reasonableness value of a reasonable feedback combination, the more reasonable the feedback. The reasonableness value of an unreasonable feedback combination can range from -1 to -10, and the lower the reasonableness value of an unreasonable feedback combination, the more unreasonable the feedback. The reasonableness values ​​corresponding to the 16 combinations of confidence levels and feedback states are shown in Table 1.

[0045] Table 1

[0046]

[0047]

[0048] In Table 1, combinations 1-12 represent unreasonable feedback, while combinations 13-16 represent reasonable feedback. It can be seen that when the confidence level of the autonomous driving system is at its normal state, the most reasonable feedback state for the driver is a supervised state; conversely, when the confidence level of the autonomous driving system is at its exit or preparation for exit, the least reasonable feedback state for the driver is no feedback. Let j represent the combination number of confidence level and feedback state, yj represent the reasonableness value corresponding to the j-th combination, and Y represent the reasonableness of the corresponding feedback. Then, Y = y1 + y2 + y3 + ... + y15 + y16. The smaller Y is, the more reasonable the driver's feedback.

[0049] After extensive experimentation, the display results for each human-computer interface can be obtained. HMIIf the driver's feedback is deemed reasonable to a certain degree (Y), then step S3 can select the display result f corresponding to the smallest Y value from a large number of reasonableness levels (Y). HMI As the target display intensity for various information in the required human-machine interface, setting each piece of information in the human-machine interface based on the target display intensity of each piece of information yields the human-machine interface that provides the most reasonable feedback to the driver, thus improving the rationality of the human-machine interface. Of course, step S3 can also include: determining the expression between each level of rationality and the corresponding actual display intensity; and determining the target display intensity based on multiple expressions. Specifically, determining the target display intensity based on multiple expressions includes: performing machine learning based on multiple expressions to calculate the target display intensity. The expression between the level of rationality and the corresponding actual display intensity can be set as Y = f HMI +w0, obtain each f HMI After finding the corresponding Y, we can calculate the corresponding w0 and obtain the f. HMI The expression between Y and the corresponding Y, a large number of Y = f HMI The +w0 expression forms a knowledge graph for human-computer interface design, which can be used for machine learning based on a large number of expressions to calculate the target display intensity of each type of information in the human-computer interface.

[0050] As described above, the autonomous vehicle human-machine interface design method of this invention determines the reasonableness of each driver feedback based on the confidence level of the autonomous driving system and the driver's feedback status to the autonomous driving function. This results in a large number of combinations of the reasonableness of driver feedback and the actual display intensity of human-machine interface information. Based on these combinations, a target display intensity of human-machine interface information that makes the driver's feedback most reasonable is determined. After setting each piece of information in the human-machine interface based on the target display intensity of each piece of information, the human-machine interface that makes the driver's feedback most reasonable can be obtained. This improves the reasonableness of the human-machine interface and enables the driver to use the vehicle's autonomous driving function reasonably.

[0051] like Figure 2 As shown, embodiments of the present invention also provide a human-machine interface design device for autonomous vehicles, comprising:

[0052] The acquisition module is used to acquire the confidence level of the autonomous driving system during each autonomous driving process of the vehicle, the driver's feedback status to the autonomous driving function each time, and the actual display intensity of each type of information in each version of the human-machine interface.

[0053] The determination module is used to determine the reasonableness of each driver's feedback based on confidence level and feedback status;

[0054] The target display intensity for each type of information is determined based on multiple levels of reasonableness and the corresponding actual display intensity to ensure the most reasonable feedback from the driver.

[0055] Furthermore, the confidence level can represent the system state as follows: the system is in a good state, the system is in a normal state, the system may be about to exit, or the system has exited or is preparing to exit.

[0056] Furthermore, the feedback status can include no feedback, supervised status, active takeover status, and passive takeover status.

[0057] Furthermore, the information includes information related to autonomous driving, takeover alerts, and driver-related information.

[0058] Furthermore, the determination module can also be used for:

[0059] Determine the reasonableness value corresponding to each combination of confidence level and corresponding feedback state;

[0060] The degree of reasonableness is calculated based on multiple reasonableness values.

[0061] Furthermore, the determination module can also be used for:

[0062] Determine the expression between each level of reasonableness and the corresponding actual display intensity;

[0063] The target display intensity is determined based on multiple expressions.

[0064] Furthermore, the determination module can also be used for:

[0065] Machine learning is performed based on multiple expressions to calculate the target display intensity.

[0066] Based on the same inventive concept as the aforementioned autonomous vehicle human-machine interface design method, this embodiment of the invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the aforementioned autonomous vehicle human-machine interface design methods.

[0067] The bus architecture (represented by a bus) can include any number of interconnected buses and bridges, linking various circuits including one or more processors (represented by a processor) and memory (represented by memory). The bus can also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface between the bus and receivers and transmitters. Receivers and transmitters can be the same element, a transceiver, providing a unit for communicating with various other devices over a transmission medium. The processor is responsible for managing the bus and general processing, while memory can be used to store data used by the processor during operation.

[0068] Since the computer device described in this embodiment of the invention is the computer device used to implement the autonomous vehicle human-machine interface design method of this invention, those skilled in the art can understand the specific implementation methods and various variations of the computer device in this embodiment of the invention based on the autonomous vehicle human-machine interface design method described in this embodiment of the invention. Therefore, how the computer device implements the method in this embodiment of the invention will not be described in detail here. Any computer device used by those skilled in the art to implement the autonomous vehicle human-machine interface design method of this invention falls within the scope of protection of this invention.

[0069] Based on the same inventive concept as the above-mentioned autonomous vehicle human-machine interface design method, the present invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of any of the aforementioned autonomous vehicle human-machine interface design methods.

[0070] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0073] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0074] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for designing a human-machine interface for an autonomous vehicle, characterized in that, include: The system acquires the confidence level of the autonomous driving system during each autonomous driving process, the driver's feedback status to the autonomous driving function each time, and the actual display intensity of each type of information in each version of the human-machine interface; the system state represented by the confidence level includes system state good, system state average, system may exit, system exit or prepare to exit. The reasonableness of each driver's feedback is determined based on the confidence level and the feedback status; Determine the expression between each of the stated degrees of reasonableness and the corresponding actual display intensity; Machine learning is performed on multiple of the aforementioned expressions to calculate the target display intensity for each type of information that makes the driver's feedback most reasonable. Each piece of information in the human-computer interface is set based on the target display intensity of each type of information.

2. The human-machine interface design method for autonomous vehicles as described in claim 1, characterized in that, The feedback states include no feedback, supervised state, active takeover state, and passive takeover state.

3. The human-machine interface design method for autonomous vehicles as described in claim 1, characterized in that, The information includes information related to autonomous driving, takeover alerts, and driver information.

4. The human-machine interface design method for autonomous vehicles as described in claim 1, characterized in that, Determining the reasonableness of each driver feedback based on the confidence level and the feedback status includes: Determine the reasonableness value corresponding to each combination of the confidence level and the corresponding feedback state; The degree of reasonableness is calculated based on multiple reasonableness values.

5. A human-machine interface design device for autonomous vehicles, characterized in that, include: The acquisition module is used to acquire the confidence level of the autonomous driving system, the driver's feedback status to the autonomous driving function each time, and the actual display intensity of each type of information in each version of the human-machine interface during each autonomous driving process of the vehicle; the system state represented by the confidence level includes system state good, system state average, system may exit, system exit or prepare to exit. A determination module is used to determine the reasonableness of each feedback from the driver based on the confidence level and the feedback status; Determine the expression between each of the stated degrees of reasonableness and the corresponding actual display intensity; Machine learning is performed on multiple of the aforementioned expressions to calculate the target display intensity for each type of information that makes the driver's feedback most reasonable. Each piece of information in the human-computer interface is set based on the target display intensity of each type of information.

6. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1-4.

Images