Trustworthiness evaluation method and device, vehicle, program product and storage medium

Abstract

The present disclosure provides a trust evaluation method and device, a vehicle, a program product and a storage medium, and relates to the technical field of intelligent driving. The method comprises: obtaining subjective evaluation data of a driver in an automatic lane changing experience of a vehicle; obtaining an electroencephalogram signal of the driver in the automatic lane changing experience of the vehicle; and determining a trust degree of the driver to the automatic lane changing according to the subjective evaluation data and the electroencephalogram signal. The method reflects the invisible trust state of the driver to the automatic lane changing through the electroencephalogram signal, and makes up for the lag and subjective bias of the subjective evaluation data. Moreover, the trust degree of the automatic lane changing is evaluated from two aspects of the subjective evaluation data and the electroencephalogram signal, which can make up for the limitation of evaluating the trust degree of the automatic lane changing from a single dimension, more truly reflect the trust degree of the driver to the automatic lane changing from subjective and objective aspects, and improve the accuracy of the trust degree of the automatic lane changing.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to trust assessment methods, devices, vehicles, software products, and storage media. Background Technology

[0002] In autonomous driving scenarios, such as automatic lane changing, the driver's trust in the autonomous driving system can directly affect the safety of the system and the user experience.

[0003] Currently, trust levels are typically assessed solely based on the driver's subjective judgment, or by using skin sensory data obtained with the assistance of devices such as eye trackers. However, trust levels obtained through these methods are inaccurate. Summary of the Invention

[0004] This disclosure provides a trust assessment method, apparatus, vehicle, program product, and storage medium that can improve the accuracy of automatic lane change trust assessment.

[0005] In a first aspect, this application provides a trust assessment method for automatic lane changing of a vehicle, comprising: acquiring subjective evaluation data of the driver's experience with automatic lane changing of the vehicle; acquiring the driver's electroencephalogram (EEG) signals during the experience with automatic lane changing of the vehicle; and determining the driver's trust in automatic lane changing based on the subjective evaluation data and the EEG signals.

[0006] The trust assessment method provided in this disclosure uses electroencephalogram (EEG) signals to reflect the driver's implicit trust in automatic lane changing, thus compensating for the lag and subjective bias of subjective evaluation data. Furthermore, by assessing trust in automatic lane changing from both subjective evaluation data and EEG signals, it overcomes the limitations of evaluating trust in automatic lane changing from only a single dimension, providing a more realistic reflection of the driver's trust in automatic lane changing from both subjective and objective perspectives, thereby improving the accuracy of trust assessment.

[0007] In some possible implementations, the EEG signal includes a first full-process EEG signal generated by the driver during the automatic lane change process; determining the driver's trust level in the automatic lane change based on subjective evaluation data and the EEG signal includes: performing spectral analysis on the first full-process EEG signal to obtain a first spectral energy distribution index, which is used to characterize the frequency domain energy distribution characteristics of the driver's EEG during the automatic lane change process; performing correlation analysis on the first spectral energy distribution index and the subjective evaluation data, and determining the driver's trust level in the automatic lane change based on the correlation analysis results.

[0008] Based on this implementation method, by performing correlation analysis on EEG signals and subjective evaluation data, the correlation between subjective evaluation data and EEG signals can be obtained. This can quantitatively prove that subjective feelings are significantly related to brain activity, thereby giving EEG signals the semantic meaning of 'trust'. This provides a reliable basis for inferring the degree of trust using EEG signals, making the determined degree of trust more accurate.

[0009] In some possible implementations, spectral analysis is performed on the first full-range EEG signal to obtain a first spectral energy distribution index, including: estimating the power spectral density of the first full-range EEG signal to obtain the power spectral density; integrating the power spectral density according to preset frequency bands to obtain the spectral energy corresponding to multiple frequency bands; and determining the first spectral energy distribution index based on the proportion of the spectral energy corresponding to multiple frequency bands in the total spectral energy.

[0010] Based on this implementation method, the first spectrum energy distribution index is obtained by segmenting the first full-process EEG signal. This index can reflect the driver's feelings during the automatic lane change experience from a physiological and objective perspective. The driver's psychological activities are converted into a decomposable first spectrum energy distribution index, providing a data basis for subsequent correlation analysis.

[0011] In some possible implementations, subjective evaluation data includes interface evaluation data of the driver's experience with the automatic lane change human-machine interface, and EEG signals include a second full-process EEG signal generated by the driver during the preset duration of the automatic lane change human-machine interface experience. Determining the driver's trust level in the automatic lane change based on the subjective evaluation data and EEG signals includes: performing spectral analysis on the second full-process EEG signal to obtain a second spectral energy distribution index, which is used to characterize the driver's EEG frequency domain energy distribution characteristics of the automatic lane change human-machine interface; performing correlation analysis between the second spectral energy distribution index and the interface evaluation data, and determining the driver's trust level in the automatic lane change human-machine interface based on the correlation analysis results.

[0012] Based on this implementation method, by analyzing the correlation between the second full-process EEG signals and interface evaluation data, the usability of the human-computer interaction interface can be analyzed from the perspectives of subjective evaluation and objective physiological response, thereby obtaining the driver's trust in the automatic lane-changing human-computer interaction interface, making the determined trust level more credible.

[0013] In some possible implementations, the method further includes: obtaining the driver's level of trust in multiple automatic lane change human-machine interfaces; and determining a recommended human-machine interface based on the level of trust in the multiple automatic lane change human-machine interfaces.

[0014] Based on this implementation method, among different automatic lane changing human-machine interaction interfaces, the most suitable human-machine interaction interface can be recommended to the user, which can improve the user's driving experience and further enhance the user's trust in automatic lane changing.

[0015] In some possible implementations, the method further includes: acquiring a first EEG signal generated when the driver intends to change lanes and a second EEG signal generated when the vehicle automatically changes lanes during the driver's experience with automatic lane changing; analyzing the first and second EEG signals to obtain a phase synchronization difference index and a cortical activation difference index, wherein the phase synchronization difference index is used to characterize the difference in phase synchronization between different brain regions of the driver when the driver intends to change lanes and when the vehicle automatically changes lanes, and the cortical activation difference index is used to characterize the difference in the activation location and activation intensity of the driver's cerebral cortex when the driver intends to change lanes and when the vehicle automatically changes lanes; and determining the driver's level of trust in automatic lane changing based on the phase synchronization difference index and the cortical activation difference index.

[0016] Based on this implementation method, by performing brain function connectivity analysis and source tracing analysis on the first and second EEG signals, the location where the EEG signals are generated can be found directly from the source. Furthermore, the difference in the driver's trust in automatic lane changing in the two scenarios of manual lane changing and automatic lane changing can be determined from the source of the EEG signals. This compensates for the coupling caused by single-band analysis, making the trust level more accurate.

[0017] In some possible implementations, the first and second EEG signals are analyzed to obtain cortical activation difference indices, including: dividing the brain into regions according to a standard brain atlas to obtain multiple brain regions; extracting the first sub-EEG signal of each brain region from the first EEG signal; extracting the second sub-EEG signal of each brain region from the second EEG signal; and performing source tracing analysis on the multiple first sub-EEG signals and multiple second sub-EEG signals to obtain cortical activation difference indices.

[0018] Based on this implementation method, by conducting source analysis on different brain regions, it is possible to refine the specific differences in activation of different brain regions during automatic and manual lane changes, making the determined cortical activation difference indicators more accurate and the calculation of the confidence level of automatic lane changes more objective.

[0019] Secondly, this application provides a trust assessment device for automatic lane changing of a vehicle, comprising: a first acquisition module for acquiring subjective evaluation data of the driver's experience with automatic lane changing of the vehicle; a second acquisition module for acquiring the driver's electroencephalogram (EEG) signals during the experience with automatic lane changing of the vehicle; and a determination module for determining the driver's trust in automatic lane changing based on the subjective evaluation data and the EEG signals.

[0020] Thirdly, this application provides a control device, including: a memory and a processor; the memory and the processor are coupled; the memory is used to store a computer program; the processor executes the computer program to implement the trust evaluation method of any of the above embodiments.

[0021] Fourthly, this application provides a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the trust assessment method of any of the above embodiments.

[0022] Fifthly, this application provides a computer program product including computer program instructions that, when executed by a processor, implement the trust assessment method described in any of the above embodiments.

[0023] Sixthly, this application provides a vehicle including the control device of any of the preceding embodiments; or the computer-readable storage medium of any of the preceding embodiments; or the computer program product of any of the preceding embodiments. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in this disclosure, the accompanying drawings used in some embodiments of this disclosure will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings.

[0025] Figure 1 A schematic diagram illustrating an HMI display position according to an embodiment of this disclosure; Figure 2 This is a schematic diagram of the architecture of a trust assessment system provided in an embodiment of the present disclosure; Figure 3 This is a schematic diagram of a trust assessment method provided in an embodiment of the present disclosure; Figure 4 This is a schematic flowchart of an embodiment of electroencephalogram (EEG) signal preprocessing provided in this disclosure; Figure 5 A flowchart illustrating a method for determining the trust level of a human-computer interaction interface, provided as an embodiment of this disclosure; Figure 6 A schematic diagram of a process for determining the trust level of automatic lane changing, provided for an embodiment of this disclosure; Figure 7 This is a schematic diagram of the structure of a trust assessment device provided in an embodiment of the present disclosure; Figure 8 This is a schematic diagram of the structure of a control device provided in an embodiment of the present disclosure. Detailed Implementation

[0026] The technical solutions of this disclosure will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0027] It should be noted that, in this disclosure, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0028] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0029] In the description of this disclosure, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "more than one" means two or more.

[0030] As autonomous driving technology continues to develop, the level of trust drivers have in autonomous driving systems will directly affect driving safety.

[0031] However, existing methods for detecting driving trust largely rely on subjective judgment questions, Likert scales, eye trackers, and electrodermatology (EDS). Each of these methods has its limitations: detection based on a single sense (such as vision or skin perception) is not comprehensive enough and cannot be correlated with other senses in real time; while subjective judgment allows users to recall the driving process and record some behaviors, such recall often lags behind the actual experience and does not originate from the initial neural response. More importantly, most current driving trust testing methods are not directly linked to the specific scenario of automatic lane changing.

[0032] For example, physiological electrical signals are collected through eye trackers, skin conductance data, and psychological activity data to detect trust levels. However, this method does not consider the multi-channel fusion problem behind the physiological electrical signals. In fact, the frontal, occipital, temporal, and parietal lobes of the brain are interconnected in many cases. Some perceptions are often the result of the joint arousal of multiple physiological sites in the body. Only by comprehensively analyzing this joint arousal can the driver's trust state be more accurately determined. This requires multi-channel fusion analysis using advanced brain signals. Furthermore, although current trust detection for autonomous driving involves multiple modules such as vehicle braking, ambient lighting, intelligent fragrance, vibration strips, and virtual avatar projection, it does not cover the automatic lane-changing scenario.

[0033] In summary, although existing technologies can perform general tests of driving trust through eye trackers, electrodermal data, heart rate, and rating scales, they lack specific considerations for automatic lane-changing scenarios and also lack fusion analysis of the overall perception of multiple parts of the body at the EEG level.

[0034] At the same time, automatic lane changing technology still has many key issues that have not yet been verified through physiological electrophysiological analysis. For example, lane changing timing: how far in advance should the lane changing warning be issued; lane changing distance: how far in advance should the lane changing be initiated, and what should the system's trust / safe distance be set; vehicle speed factors: when automatically changing lanes, the vehicle speed during normal driving or in the process of changing lanes needs to be considered, as well as the impact of vehicle speed switching during the lane changing process on the driver's level of trust.

[0035] In addition, the information displayed by the human-machine interface (HMI) can also affect the driver's level of trust.

[0036] Currently, various types of driving information are gradually being presented on multiple screens of the human-machine interface (HMI). The HMI displays information on the instrument panel, head-up display (HUD), surrounding reality (SR) interface, and central control screen. Automatic lane changing, as one of the core driving behaviors executed by L2 / L3 level vehicles based on driver intention, requires its related information to be mapped to the aforementioned interfaces in real time. For example, Figure 1 This is a schematic diagram illustrating an HMI display position according to an embodiment of this disclosure. Figure 1 As shown, the HMI can be displayed on the instrument panel, central control screen, head-up display, and other locations.

[0037] However, a mismatch between the design of HMI display information and the driver's own perception or intention can lead to traffic accidents. For example, HMI display information design involves both visual and auditory interaction; different HMI interface designs can affect the driver's cognitive load, thereby impacting trust. Furthermore, if the timing of HMI display information prompts when the vehicle enters a ramp is too early or too late, it will directly affect the driver's trust in the system. In other words, the quality of HMI display information design directly affects the driver's level of trust in the system.

[0038] To address the aforementioned technical problems, this disclosure provides a trust assessment method. The method's approach is to assess the trust level of automatic lane changing based on two aspects: the driver's electroencephalogram (EEG) signals and subjective evaluation data during the vehicle's automatic lane changing experience, thereby improving the accuracy of the trust level assessment.

[0039] The trust assessment system provided in the embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0040] Figure 2 This is a schematic diagram of the architecture of a trust assessment system provided in an embodiment of this disclosure. Figure 2 As shown, the trust assessment system 200 includes a data acquisition module 201 and a controller 202.

[0041] The data acquisition module 201 is used to acquire the driver's subjective evaluation data and EEG signals during the vehicle's automatic lane changing experience. The controller 202 is used to determine the driver's level of trust in the automatic lane changing based on the subjective evaluation data and EEG signals.

[0042] Communication connection between data acquisition module 201 and controller 202.

[0043] For example, the data acquisition module 201 includes a subjective evaluation acquisition module and an electroencephalogram (EEG) signal acquisition module. The subjective evaluation acquisition module is used to acquire the driver's subjective evaluation data during the vehicle's automatic lane-changing experience; the EEG signal acquisition module is used to acquire the driver's EEG signals during the vehicle's automatic lane-changing experience.

[0044] For example, the subjective evaluation acquisition module loads a rating scale. This could be a Likert scale (e.g., 5-level, 7-level, or 10-level Likert), a trust scale, or a NASA scale. In response to the driver's input of this rating scale, the module acquires the driver's subjective evaluation data regarding the vehicle's automatic lane-changing experience.

[0045] For example, a vehicle is equipped with an EEG acquisition device, which is worn by the driver to collect the driver's brain signals during the vehicle's automatic lane-changing experience. This device can be 32-bit or 64-bit. The acquired brain signals are then sent to an EEG signal acquisition module.

[0046] The controller 202 is used to determine the driver's level of trust in automatic lane changing based on subjective evaluation data and EEG signals.

[0047] It is understood that the application scenarios of the embodiments of this disclosure are not limited. The system architecture and business scenarios described in the embodiments of this disclosure are for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of this disclosure. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this disclosure are also applicable to similar technical problems.

[0048] The trust assessment method provided in the embodiments of this disclosure will be described in detail below.

[0049] Figure 3 This is a schematic diagram of a trust assessment method provided in an embodiment of the present disclosure, such as... Figure 3 As shown, the method includes the following steps: S301. Obtain subjective evaluation data of the driver's experience with the vehicle's automatic lane changing.

[0050] For example, the automatic lane-changing experience of a vehicle can include experiences under different road types, driving scenarios, speeds, and interference conditions. For instance, a driver could experience automatic lane changing on different road types such as urban roads, suburban roads, and elevated roads. Alternatively, under the same external conditions, a driver could experience automatic and manual lane changing respectively, allowing for a more accurate evaluation of the automatic lane-changing performance through comparison. Furthermore, the vehicle's automatic lane-changing experience could include automatic lane changing in high-speed scenarios and automatic lane changing in low-speed scenarios. Finally, the vehicle's automatic lane-changing experience could include automatic lane changing under interference and automatic lane changing without interference.

[0051] For example, the aforementioned subjective evaluation data could be scores for different aspects of the vehicle's automatic lane-changing experience. For instance, scores could be given for the smoothness of the automatic lane-changing, the timing of the automatic lane-changing, the distance of the automatic lane-changing, and the level of trust in the automatic lane-changing. The aforementioned subjective evaluation data could also be a cognitive load score for the vehicle's automatic lane-changing experience. For instance, how much attention is required to understand the vehicle's automatic lane-changing, and whether one feels uneasy during automatic lane-changing, etc.

[0052] S302. Obtain the driver's brain signals during the vehicle's automatic lane-changing experience.

[0053] For example, the aforementioned EEG signal may refer to the EEG signal throughout the automatic lane change experience, or it may refer to the EEG signal during a certain period of the automatic lane change experience.

[0054] For example, with the visual stimulus presentation time as 0ms, the EEG signal from 1500ms before the stimulus to the end of the task is extracted as the full-process EEG signal.

[0055] For example, the entire EEG signal can be segmented to obtain multiple EEG signal segments. The duration of each EEG signal segment is uniform (e.g., 10 seconds) for comparison.

[0056] To facilitate subsequent processing of EEG signals, the duration of the EEG signal can be set to an integer. For example, if the duration of the automatic lane change experience is 10.3 seconds, the experience duration can be rounded down, meaning the EEG signal acquisition duration is set to 10 seconds.

[0057] S303. Determine the driver's level of trust in automatic lane changing based on subjective evaluation data and EEG signals.

[0058] The trust assessment method provided in this disclosure uses electroencephalogram (EEG) signals to reflect the driver's implicit trust in automatic lane changing, thus compensating for the lag and subjective bias of subjective evaluation data. Furthermore, by assessing trust in automatic lane changing from both subjective evaluation data and EEG signals, it overcomes the limitations of evaluating trust in automatic lane changing from only a single dimension, providing a more realistic reflection of the driver's trust in automatic lane changing from both subjective and objective perspectives, thereby improving the accuracy of trust assessment.

[0059] In some embodiments, determining the driver's trust level in automatic lane changing based on subjective evaluation data and EEG signals includes: preprocessing the EEG signals to obtain preprocessed EEG signals; and determining the driver's trust level in automatic lane changing based on subjective evaluation data and preprocessed EEG signals.

[0060] For example, EEG signals can be preprocessed using the ERPLAB and EEGLAB tools. Figure 4 This is a schematic flowchart illustrating an embodiment of electroencephalogram (EEG) signal preprocessing provided in this disclosure. Figure 4 As shown, the preprocessing process for the EEG signal includes: S401, performing localization, DC offset removal, filtering, and noise elimination on the EEG signal to obtain the preprocessed EEG signal; S402, exporting the preprocessed EEG signal.

[0061] Taking a 64-channel EEG signal as an example, the BESA 4-Shell Sphere model was used for electrode localization. The mean value of both mastoid processes was used as a rereference, and baseline correction was applied to remove DC offset, thus avoiding edge artifacts in the subsequent filtering process. Next, line noise was removed by sequentially applying a 0.1Hz high-pass and a 100Hz low-pass Butterworth filter, followed by a Parks-McClellan notch filter (50Hz). The EEG signal was then downsampled to 256Hz.

[0062] In some embodiments, the EEG signal includes a first full-range EEG signal generated by the driver during the automatic lane change process. The determination of the driver's trust in the automatic lane change based on subjective evaluation data and the EEG signal includes: performing spectral analysis on the first full-range EEG signal to obtain a first spectral energy distribution index, which characterizes the frequency domain energy distribution characteristics of the driver's EEG during the automatic lane change process; performing correlation analysis on the first spectral energy distribution index and the subjective evaluation data; and determining the driver's trust in the automatic lane change based on the correlation analysis results.

[0063] By performing correlation analysis on EEG signals and subjective evaluation data, the correlation between subjective evaluation data and EEG signals can be obtained. This can quantitatively prove that subjective feelings are significantly related to brain activity, thereby giving EEG signals the semantic meaning of 'trust'. This provides a reliable basis for inferring the degree of trust using EEG signals, making the determined degree of trust more accurate.

[0064] In some embodiments, the first full-range EEG signal is subjected to spectral analysis to obtain a first spectral energy distribution index, including: estimating the power spectral density of the first full-range EEG signal to obtain the power spectral density; integrating the power spectral density according to preset frequency bands to obtain the spectral energy corresponding to multiple frequency bands; and determining the first spectral energy distribution index based on the proportion of the spectral energy corresponding to multiple frequency bands in the total spectral energy.

[0065] For example, the power spectral density of the first full-process EEG signal is estimated based on the pWelch algorithm to obtain the power spectral density.

[0066] According to preset frequency bands, the first full-process EEG signal is divided into the δ (0.5-4Hz) band, θ (4-8Hz) band, α (8-13Hz) band, β (13-30Hz) band, and γ (30-45Hz) band. The spectral energy of each band is obtained by integration. Taking the δ band as an example, the proportion of the δ band in the total spectral energy is P(δ) / (P(δ)+P(θ)+P(α)+P(β)+P(γ)). Where P(δ) is the spectral energy of the δ band; P(θ) is the spectral energy of the θ band; P(α) is the spectral energy of the α band; P(β) is the spectral energy of the β band; and P(γ) is the spectral energy of the γ band. The corresponding proportion of each band is determined as the first spectral energy distribution index.

[0067] For example, when the first full-range EEG signal is a 64-channel EEG signal, the spectral energy of each frequency band is the average value of the spectral energy of the 64 channels.

[0068] The spectral energy values ​​of different frequency bands can be used to reflect different user states. For example, a higher relative spectral energy in the alpha band indicates that the user is relaxed and focused, undisturbed, meaning the subjective evaluation data obtained at this time is reliable. A higher relative spectral energy in the delta band indicates lower cognitive conflict for the driver during the automatic lane-changing experience, reflecting a higher level of trust in the automatic lane-changing experience. A higher relative spectral energy in the gamma band indicates a better overall perception of the automatic lane-changing experience by the driver, with active higher-level cognitive engagement; the subjective evaluation data obtained at this time is more likely to reflect the driver's true state. A lower relative spectral energy in the beta band indicates less operational anxiety and tension for the driver, meaning a higher level of trust in the automatic lane-changing experience. A lower relative spectral energy in the theta band indicates a lighter working memory load for the driver, with no additional cognitive effort due to confusion or frustration, indicating a better experience with the automatic lane-changing experience. For example, when drivers have lower trust in automatic lane-changing, the relative spectral energy of the gamma band in the temporal region is higher for women than for men.

[0069] Thus, by processing the first full-process EEG signal in frequency bands to obtain the first spectral energy distribution index, it is possible to truly reflect the driver's feelings during the automatic lane change experience from a physiological and objective perspective. The driver's psychological activities are converted into a decomposable first spectral energy distribution index, providing a data basis for subsequent correlation analysis.

[0070] In some embodiments, the first complete EEG signal consists of multiple data points, and the subjective evaluation data consists of multiple data points.

[0071] For example, multiple first full-process EEG signals and multiple subjective evaluation data can refer to the first full-process EEG signals and subjective evaluation data generated by each driver during the automatic lane-changing experience of multiple drivers in the vehicle.

[0072] For example, multiple first full-process EEG signals and multiple subjective evaluation data can refer to the first full-process EEG signals and subjective evaluation data generated by the same driver in each automatic lane change experience in multiple automatic lane change experiences of the vehicle.

[0073] To ensure the accuracy of the trust level, the number of EEG signals throughout the entire process was determined by estimating the sample size. That is, to determine the number of drivers, or the number of times the vehicle automatically changed lanes during the test.

[0074] For example, using G Power, combined with statistical testing methods (e.g., T-test, ANOVA, etc.), expected effect size, pre-specified significance level (e.g., α=0.05), and expected statistical power (e.g., Power≥0.8), determines the number of EEG signals in the first full-process EEG.

[0075] In addition, to ensure the accuracy of the drivers' trust in automatic lane changing, the above samples can be divided into experimental and control groups to determine the authenticity and accuracy of the trust.

[0076] The above-mentioned correlation analysis of the first spectrum energy distribution index and subjective evaluation data, and the determination of the driver's trust in automatic lane changing based on the correlation analysis results, includes: performing normal distribution verification on multiple first spectrum energy distribution indexes and multiple subjective evaluation data, and determining the driver's trust in automatic lane changing based on the normal distribution verification results.

[0077] In one possible implementation, when multiple first-spectrum energy distribution indicators and multiple subjective evaluation data satisfy a normal distribution, a product-moment correlation analysis is performed on the multiple first-spectrum energy distribution indicators and multiple subjective evaluation data to determine the driver's trust in automatic lane changing.

[0078] For example, the results of product-difference correlation analysis of multiple first-spectrum energy distribution indicators and multiple subjective evaluation data are used to determine the driver's confidence in automatic lane changing.

[0079] In another possible implementation, when multiple first-spectrum energy distribution indicators do not meet a normal distribution, or multiple subjective evaluation data do not meet a normal distribution, a rank correlation analysis is performed on the multiple first-spectrum energy distribution indicators and multiple subjective evaluation data to determine the driver's trust in automatic lane changing.

[0080] For example, the results of a graded correlation analysis of multiple first-spectrum energy distribution indicators and multiple subjective evaluation data are used to determine the driver's trust in automatic lane changing.

[0081] In product-moment correlation analysis or rank correlation analysis, the statistical significance threshold is set to p<0.05.

[0082] In some embodiments, subjective evaluation data includes interface evaluation data of the driver's experience with the automatic lane change human-machine interface, and EEG signals include second full-process EEG signals generated by the driver during the preset duration of the automatic lane change human-machine interface experience.

[0083] For example, the human-machine interface experience for automatic lane changing can be an experience in a real driving environment or a virtual experience in a laboratory environment.

[0084] Furthermore, this human-machine interface can be integrated into the central control screen, instrument panel, HUD, etc. Moreover, the aforementioned automatic lane-changing human-machine interface experience can interact with the driver through multiple modalities, including visual, auditory, and tactile senses.

[0085] For example, to ensure that the second full-process EEG signal collected is only the EEG signal generated by the automatic lane-changing human-computer interaction interface 2, and to avoid inaccurate results due to the introduction of other variables, the preset duration can be set to a duration of 5 to 10 seconds.

[0086] Figure 5 This is a schematic flowchart illustrating a method for determining the trust level of a human-computer interaction interface, provided as an embodiment of this disclosure. Figure 5 As shown, the driver's trust in automatic lane changing was determined based on subjective evaluation data and EEG signals, including: S501. Perform spectral analysis on the second full-process EEG signal to obtain the second spectral energy distribution index.

[0087] Among them, the second spectral energy distribution index is used to characterize the frequency domain energy distribution characteristics of the driver's interaction with the automatic lane change human-machine interface.

[0088] In some possible implementations, the above-mentioned spectral analysis of the second full-range EEG signal to obtain the second spectral energy distribution index includes: estimating the power spectral density of the second full-range EEG signal to obtain the second power spectral density; integrating the second power spectral density according to preset frequency bands to obtain the spectral energy corresponding to multiple frequency bands; and determining the second spectral energy distribution index based on the proportion of the spectral energy corresponding to multiple frequency bands in the total spectral energy.

[0089] The process of determining the second spectral energy distribution index can be referred to the process of determining the first spectral energy distribution index, and will not be repeated here.

[0090] S502. Perform correlation analysis between the second spectrum energy distribution index and the interface evaluation data, and determine the driver's trust level in the automatic lane change human-machine interface based on the correlation analysis results.

[0091] In some possible implementations, the aforementioned second full-process EEG signal is multiple, and the interface evaluation data is multiple.

[0092] For example, multiple second full-process EEG signals and multiple interface evaluation data can refer to the second full-process EEG signals and interface evaluation data generated by each driver during the human-machine interaction experience of multiple drivers in automatic lane changing.

[0093] For example, multiple second full-process EEG signals and multiple interface evaluation data can refer to the second full-process EEG signals and interface evaluation data generated by the same driver in each automatic lane change human-machine interaction interface experience during multiple automatic lane change human-machine interaction interface experiences.

[0094] The above-mentioned correlation analysis between the second spectrum energy distribution index and the interface evaluation data, and the determination of the driver's trust in the automatic lane change human-machine interface based on the correlation analysis results, includes: performing normal distribution verification on multiple second spectrum energy distribution indexes and multiple interface evaluation data, and determining the driver's trust in the automatic lane change human-machine interface based on the normal distribution verification results.

[0095] In one possible implementation, when multiple second-spectrum energy distribution indicators and multiple interface evaluation data satisfy a normal distribution, a product-moment correlation analysis is performed on the multiple second-spectrum energy distribution indicators and multiple interface evaluation data to determine the driver's trust in the automatic lane-changing human-machine interface.

[0096] For example, the results of product-difference correlation analysis of multiple second-spectrum energy distribution indicators and multiple interface evaluation data can be used to determine the driver's level of trust in the automatic lane-changing human-machine interface.

[0097] In another possible implementation, when multiple second-spectrum energy distribution indicators do not meet a normal distribution, or multiple interface evaluation data do not meet a normal distribution, a rank correlation analysis is performed on the multiple second-spectrum energy distribution indicators and multiple interface evaluation data to determine the driver's trust in automatic lane changing.

[0098] For example, the results of a graded correlation analysis of multiple second-spectrum energy distribution indicators and multiple interface evaluation data are used to determine the driver's level of trust in the automatic lane-changing human-machine interface.

[0099] Understandably, different human-computer interaction interfaces (HCIs) have varying degrees of usability, and users generate different EEG signals when experiencing different HCIs. For example, when the usability of an HCI is high, the relative spectral energy of the alpha band from the frontal lobe, parietal lobe, and parieto-occipital region increases, indicating that the user is relaxed and focused, and is not disturbed by the HCI. The relative spectral energy of the delta band from the frontal lobe increases, indicating that the HCI causes less cognitive conflict to the user. The relative spectral energy of the gamma band from the C3 point increases, indicating that the user has a good overall perception of the HCI and is actively engaged in higher cognitive processes. At the same time, the relative spectral energy of the beta band from the left central region decreases, indicating that the user has less operational anxiety and tension. The relative spectral energy of the theta band from the frontal lobe and parieto-occipital region decreases, indicating that the user's working memory burden is light and there is no additional cognitive effort due to confusion or frustration.

[0100] Thus, by analyzing the correlation between the second full-process EEG signals and interface evaluation data, the usability of the human-computer interaction interface can be analyzed from the perspectives of subjective evaluation and objective physiological response, thereby obtaining the driver's trust in the automatic lane-changing human-computer interaction interface, making the determined trust level more credible.

[0101] In some embodiments, the method further includes: obtaining the driver's trust level in multiple automatic lane changing human-machine interfaces; and determining a recommended human-machine interface based on the trust level of the multiple automatic lane changing human-machine interfaces.

[0102] For example, different human-computer interaction interfaces differ in display location, information richness, modality, and other aspects.

[0103] For example, the recommended human-computer interaction interface is the one with the highest level of trust.

[0104] Recommending the most suitable human-machine interface for users among different automatic lane changing human-machine interfaces can improve the user's driving experience and further enhance the user's trust in automatic lane changing.

[0105] Figure 6 This is a schematic diagram illustrating a process for determining the trust level of automatic lane changing, provided as an embodiment of this disclosure. Figure 6 As shown, the above method also includes: S601. Acquire the first EEG signal generated when the driver intends to change lanes and the second EEG signal generated when the vehicle automatically changes lanes during the driver's automatic lane change experience.

[0106] For example, when a driver intends to change lanes, they press a button (e.g., a mouse button, a screen button, etc.), and in response to the driver's button input, the system begins to collect the driver's first EEG signal.

[0107] For example, the first and second EEG signals mentioned above can be two EEG signals collected during the same automatic lane change process, or they can be the first and second EEG signals collected separately during manual lane change and automatic lane change.

[0108] For example, the first EEG signal is the EEG signal generated when the driver believes it is safe to change lanes. The second EEG signal is the EEG signal generated by the driver when the automatic lane-changing system automatically changes lanes. As another example, the first EEG signal is the EEG signal generated when the driver believes it is safe to change lanes at a certain speed. The second EEG signal is the EEG signal generated by the driver when the automatic lane-changing system determines it is safe to change lanes at a certain speed. Yet another example: when there is an obstacle ahead or a merging ramp, the first EEG signal is the EEG signal generated by the driver believing it is safe to change lanes at a certain distance. The second EEG signal is the EEG signal generated by the driver when the automatic lane-changing system determines it is safe to change lanes at a certain distance.

[0109] S602. Analyze the first and second EEG signals to obtain the phase synchronization difference index and the cortical activation difference index.

[0110] Among them, the phase synchronization difference index is used to characterize the difference in phase synchronization between different brain regions of the driver when the driver intends to change lanes and when the vehicle automatically changes lanes. The cortical activation difference index is used to characterize the difference in the location and intensity of activation in the driver's cerebral cortex when the driver intends to change lanes and when the vehicle automatically changes lanes.

[0111] In one possible implementation, the above-mentioned analysis of the first and second EEG signals to obtain a phase synchronization difference index includes performing brain functional connectivity analysis on the first and second EEG signals to obtain the phase synchronization difference index.

[0112] For example, the above-mentioned brain functional connectivity analysis of the first EEG signal and the second EEG signal to obtain the phase synchronization difference index includes: performing a Hilbert transform on the first EEG signal to obtain a first phase-locked value; performing a Hilbert transform on the second EEG signal to obtain a second phase-locked value; and determining the phase synchronization difference index based on the difference between the first phase-locked value and the second phase-locked value.

[0113] Phase locking value (PLV), also known as average phase coherence, is used to characterize undirected brain functional connectivity. PLV measures the phase synchronization between the first and second EEG signals, quantifies the phase difference retained over time, and can also be used to characterize time-related activity connectivity metrics.

[0114] For example, the phase-locked value is the corrected imaginary phase-locked value (ciPLV). Compared to PLV, ciPLV can suppress false synchronization caused by volumetric conduction in brain functional connectivity analysis.

[0115] For example, taking the first EEG signal as an example, the first EEG signal is segmented according to a preset frequency band to obtain multiple frequency bands of the first EEG signal. A Hilbert transform is then performed on each frequency band of the first EEG signal to obtain the first ciPLV. Similarly, the calculation process for the second ciPLV can refer to the calculation process for the first ciPLV, and will not be repeated here.

[0116] When there are multiple first EEG signals and multiple second EEG signals, after obtaining the differences between multiple first phase-locked values ​​and multiple second phase-locked values, a nonparametric permutation test (e.g., a two-tailed t-test with 1000 randomizations) is performed on these differences to determine the significance index of differences between each brain connection. The significance index is then corrected for the false discovery rate (FDR) to obtain the corrected significance index. Based on the corrected significance index, a phase synchronization difference index is determined.

[0117] In addition, the significance index after correction is judged to be less than the preset value (e.g., 0.05, 0.01, etc.) in order to distinguish whether the differences in brain functional connectivity are significant.

[0118] The driver's level of trust in automatic lane changing affects their attentional resource allocation, situational monitoring, and risk perception. The brain's connectivity varies under different levels of trust. In other words, the phase synchronization difference index can objectively and intuitively reflect the driver's level of trust in automatic lane changing.

[0119] For example, when trust is high, the driver's frontal lobe alpha and beta bands exhibit strong functional connectivity. When trust is low, the driver's temporal lobe gamma band shows strong functional connectivity. Furthermore, compared to a sudden driving crisis, the phase-locked values ​​of the delta and alpha bands increase under normal driving conditions, indicating that the driver is relaxed and under low cognitive stress; while under conditions of perceptual uncertainty, such as foggy weather, the phase-locked values ​​of the delta, theta, and beta bands increase significantly, indicating a lack of trust in the surrounding environment. Through analysis of brain functional connectivity in EEG signals, the discriminative power of brain functional connectivity in different driving scenarios can be directly reflected.

[0120] In one possible implementation, the above analysis of the first and second EEG signals to obtain cortical activation difference indices includes: performing source analysis on the first and second EEG signals to obtain cortical activation difference indices.

[0121] Extensive neuroimaging evidence suggests that human trust in others or other systems is not a singular emotion, but rather a cognitive appraisal process involving the prefrontal-limbic-striatal network. Trust studies based on facial expressions and appearance consistently find that trust is primarily associated with the anterior frontal lobe (frontal pole, orbitofrontal cortex, anterior cingulate cortex) and reward-related basal ganglia structures (caudate nucleus, putamen), reflecting positive anticipation and reward processing. Distrust, on the other hand, stably activates the right amygdala, insula (temporal lobe), and superior temporal sulcus (STS), forming a "threat-aversion-risk" appraisal loop. The amygdala plays a crucial role in fear and defensive responses, while the insula is significantly activated when perceiving uncertainty and aversion.

[0122] However, neural feedback in these areas is difficult to collect directly. Although EEG signals have high temporal resolution, they are affected by volumetric conduction, making it impossible to accurately locate changes in activity in these deep frontal and temporal lobe structures. Source analysis of EEG signals accurately transforms EEG signals collected from the skin layer into neural connectivity responses within the cerebral cortex. This source analysis overcomes the spatial ambiguity of the scalp and uses cortical activation difference indicators to accurately and intuitively reflect the driver's level of trust in autonomous driving.

[0123] S603. Based on the phase synchronization difference index and the cortical activation difference index, determine the driver's confidence in automatic lane changing.

[0124] For example, the driver's confidence in automatic lane changing can be obtained by weighted summation of the phase synchronization difference index and the cortical activation difference index.

[0125] Because the acquired EEG signals are the result of mixing whole-brain activity, it is easy to misjudge which brain region is actually active. For example, EEG signals acquired by frontal lobe electrodes may not be generated by the frontal lobe itself, but rather "transmitted" from other areas such as the parietal lobe through functional connectivity. If only spectral analysis is performed, "received signals" may be mistaken for "originating signals," failing to reveal deeper neural origins. By performing brain functional connectivity analysis and source tracing analysis on the first and second EEG signals, the location where the EEG signals are generated can be directly identified at the root. Furthermore, by determining the root cause of the EEG signal generation, the difference in drivers' trust in automatic lane changing scenarios between manual and automatic lane changing can be determined, compensating for the coupling limitations of single-band analysis and making trust assessment more accurate.

[0126] In some embodiments, the above-described analysis of the first and second EEG signals to obtain a cortical activation difference index includes: dividing the brain into regions according to a standard brain atlas to obtain multiple brain regions; extracting a first sub-EEG signal from each brain region from the first EEG signal; extracting a second sub-EEG signal from each brain region from the second EEG signal; and performing source tracing analysis on the multiple first and second sub-EEG signals to obtain a cortical activation difference index.

[0127] Taking the first EEG signal as an example, Brainstorm was used to calculate the noise covariance of the first EEG signal to distinguish it from noise. A three-layer head model was established using OpenMEEG based on magnetic resonance imaging (MRI). Based on this three-layer head model and an automated anatomical labeling (AAL) brain atlas, the upper, middle, and lower regions of the left (L.1, L.2, L.3) and right (R.1, R.2, R.3) regions of the frontal or occipital lobes, and the upper and lower regions of the left (L.1, L.2, L.3) and right (R.1, R.2, R.3) regions of the parietal and temporal lobes were selected as brain regions. The first sub-EEG signal of each brain region was extracted to achieve equal comparison of multiple brain regions.

[0128] In one possible implementation, the above-mentioned source analysis of multiple first sub-EEG signals and multiple second sub-EEG signals to obtain a cortical activation difference index includes: performing dynamic statistical parameter mapping analysis on multiple first sub-EEG signals to obtain a first mapping value; performing dynamic statistical parameter mapping analysis on the second EEG signals to obtain a second mapping value; and determining the cortical activation difference index based on the difference between the first mapping value and the second mapping value.

[0129] Taking multiple first sub-EEG signals as an example, dynamic statistical parameter analysis is performed on multiple first sub-EEG signals to obtain multiple mapping values, and the average value of multiple mapping values ​​is taken as the first mapping value.

[0130] In addition, multiple sub-EEG signals can also be obtained by segmenting the EEG signal according to time windows of 10, 20 or 30 seconds.

[0131] By analyzing the origins of different brain regions, we can refine the specific differences in the activation of different brain regions during automatic and manual lane changes, making the determined cortical activation difference indicators more accurate and the calculation of the confidence level of automatic lane changes more objective.

[0132] In some embodiments, the method further includes: adjusting the automatic lane change parameters of the automatic lane change system when the phase synchronization difference index is greater than a first threshold and / or the cortical activation difference index is greater than a second threshold.

[0133] For example, automatic lane changing parameters include automatic lane changing time, automatic lane changing speed, and automatic lane changing distance.

[0134] In some embodiments, there are multiple drivers, and the method further includes: classifying drivers according to their type; and determining the level of trust in automatic lane changing among the multiple types of drivers based on subjective evaluation data and multiple EEG signals.

[0135] For example, driver types include: driver's gender, driver's age, driver's driving experience duration, driver's occupation, driver's education level, etc.

[0136] In this disclosure, the vehicle's operating mode in the automatic lane changing experience includes at least one of the following: hybrid, separate, and random.

[0137] In addition, to more accurately determine the driver's level of trust in automatic lane changing, an interview can be arranged with the driver after the autonomous driving experience.

[0138] The foregoing primarily describes the solutions of the embodiments of this disclosure from a methodological perspective. It is understood that, in order to achieve the aforementioned functions, the trust assessment device includes at least one of the hardware structures and software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure.

[0139] This disclosure embodiment can divide the trust assessment device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one functional module. The integrated module can be implemented in hardware or software. It should be noted that the module division in this disclosure embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the example of dividing each function into a separate functional module.

[0140] Figure 7 This is a schematic diagram of a trust assessment device provided in an embodiment of this disclosure. This trust assessment device is applied to the automatic lane changing of vehicles and can execute the trust assessment method provided in the above-described method embodiments. Figure 7 As shown, the trust assessment device 700 includes: a first acquisition module 701, used to acquire the driver's subjective evaluation data in the vehicle's automatic lane changing experience; a second acquisition module 702, used to acquire the driver's brain signals in the vehicle's automatic lane changing experience; and a determination module 703, used to determine the driver's trust in automatic lane changing based on the subjective evaluation data and brain signals.

[0141] In some embodiments, the EEG signal includes a first full-process EEG signal generated by the driver during the automatic lane change process; the determining module 703 is specifically used to: perform spectral analysis on the first full-process EEG signal to obtain a first spectral energy distribution index, the first spectral energy distribution index being used to characterize the frequency domain energy distribution characteristics of the driver's EEG during the automatic lane change process; perform correlation analysis on the first spectral energy distribution index and the subjective evaluation data, and determine the driver's trust level in the automatic lane change based on the correlation analysis results.

[0142] In some embodiments, the determining module 703 is used to: estimate the power spectral density of the first full-range EEG signal to obtain the power spectral density; integrate the power spectral density according to preset frequency bands to obtain the spectral energy corresponding to multiple frequency bands; and determine the first spectral energy distribution index based on the proportion of the spectral energy corresponding to multiple frequency bands in the total spectral energy.

[0143] In some embodiments, the subjective evaluation data includes interface evaluation data of the driver's experience with the automatic lane change human-machine interface, and the EEG signal includes a second full-process EEG signal generated by the driver during the preset duration of the automatic lane change human-machine interface experience; the determining module 703 is used to: perform spectral analysis on the second full-process EEG signal to obtain a second spectral energy distribution index, the second spectral energy distribution index being used to characterize the frequency domain energy distribution characteristics of the driver's experience with the automatic lane change human-machine interface; perform correlation analysis between the second spectral energy distribution index and the interface evaluation data, and determine the driver's level of trust in the automatic lane change human-machine interface based on the correlation analysis results.

[0144] In some embodiments, the apparatus further includes: a third acquisition module, configured to acquire the driver's trust level in multiple automatic lane changing human-machine interfaces; and a recommendation module, configured to determine a recommended human-machine interface based on the trust level in the multiple automatic lane changing human-machine interfaces.

[0145] In some embodiments, the above-mentioned device further includes: a fourth acquisition module, used to acquire a first EEG signal generated when the driver intends to change lanes and a second EEG signal generated when the vehicle automatically changes lanes during the driver's automatic lane-changing experience; a first analysis module, used to analyze the first EEG signal and the second EEG signal to obtain a phase synchronization difference index and a cortical activation difference index, wherein the phase synchronization difference index is used to characterize the phase synchronization difference between different brain regions of the driver when the driver intends to change lanes and when the vehicle automatically changes lanes, and the cortical activation difference index is used to characterize the difference in the activation location and activation intensity of the driver's cerebral cortex when the driver intends to change lanes and when the vehicle automatically changes lanes; and a determination module 703, used to determine the driver's level of trust in automatic lane changing based on the phase synchronization difference index and the cortical activation difference index.

[0146] In some embodiments, the first analysis module is used to: divide the brain into regions according to a standard brain atlas to obtain multiple brain regions; extract a first sub-EEG signal for each brain region from a first EEG signal; extract a second sub-EEG signal for each brain region from a second EEG signal; and perform source analysis on the multiple first sub-EEG signals and multiple second sub-EEG signals to obtain a cortical activation difference index.

[0147] In the case of implementing the functions of the integrated modules described above in hardware, this disclosure provides a possible structure for the control device involved in the above embodiments. Figure 8 This is a schematic diagram of a control device provided in an embodiment of this disclosure. Figure 8 As shown, the control device 800 includes a processor 802 and a bus 804. Optionally, the control device may also include a memory 801; optionally, the control device 800 may also include a communication interface 803.

[0148] Processor 802 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 802 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 802 may also be a combination of functions implementing computational capabilities, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0149] The communication interface 803 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0150] The memory 801 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0151] In one possible implementation, the memory 801 can exist independently of the processor 802. The memory 801 can be connected to the processor 802 via a bus 804 and is used to store instructions or program code. When the processor 802 calls and executes the instructions or program code stored in the memory 801, it can implement the trust assessment method provided in this embodiment. In another possible implementation, the memory 801 can also be integrated with the processor 802.

[0152] The 804 bus can be an extended industry standard architecture (EISA) bus, etc. The 804 bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0153] Some embodiments of this disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) storing computer program instructions that, when executed on a processor, cause the processor to perform a trust assessment method as described in any of the above embodiments.

[0154] Exemplary examples show that the aforementioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical discs (e.g., compact disks (CDs), digital versatile disks (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROMs), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this disclosure may represent one or more devices for storing information and / or other machine-readable storage media. The term "machine-readable storage media" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0155] This disclosure provides a computer program product containing instructions that, when run on a processor, cause the processor to execute the trust assessment method described in any of the above embodiments.

[0156] This disclosure provides a vehicle including the control device of any of the preceding embodiments; or the computer-readable storage medium of any of the preceding embodiments; or the computer program product of any of the preceding embodiments.

[0157] The vehicle provided in this application may be a passenger vehicle or a freight vehicle, and may also be an electric vehicle or a hybrid vehicle. This application does not limit the specific purpose or power type of the vehicle, and the choice can be made according to actual needs.

[0158] In some examples, a vehicle consists of a body and wheels. The body is used for passengers and for carrying goods, while the wheels are mounted underneath the body to support it and allow it to roll on the road surface, thus enabling the vehicle to move.

[0159] In some possible examples, the vehicle is equipped with a control system, which typically adopts a layered distributed architecture. From the bottom layer to the top layer, it can be roughly divided into a perception layer, a control layer, a coordination layer, and an interaction layer. The layers communicate with each other through an in-vehicle network.

[0160] The perception layer mainly consists of various sensors distributed inside and outside the vehicle, including but not limited to external environment cameras, millimeter-wave radar, lidar, ultrasonic sensors, in-vehicle driver monitoring cameras, microphone arrays, and various vehicle status sensors (such as wheel speed sensors, inertial measurement units, temperature sensors, etc.). The perception layer is responsible for collecting multi-dimensional data such as the vehicle's own operating status, driver behavior, and external driving environment in real time.

[0161] The control layer consists of dozens to hundreds of electronic control units (ECUs), distributed across multiple functional domains including powertrain, chassis, body, intelligent driving, and infotainment. Each ECU embeds real-time control software that performs closed-loop control of the vehicle's actuators based on preset control strategies or upper-level commands, and generates corresponding alarm signals when abnormal conditions are detected. Typical ECUs include the engine control unit, transmission control unit, brake control unit, steering control unit, vehicle stability control unit, airbag control unit, intelligent driving domain controller, and in-vehicle infotainment unit.

[0162] The coordination layer typically exists in the form of a domain controller or a central computing platform, responsible for cross-domain data fusion, global state management, and collaborative decision-making. The coordination layer centrally processes and schedules the sensing data and control commands that were originally scattered across various functional domains, connecting downwards to various electronic control units and supporting human-machine interaction functions upwards.

[0163] The interaction layer mainly includes in-cabin display devices (such as instrument panel, central control screen, head-up display), voice interaction system, haptic feedback device, etc., which are responsible for presenting vehicle status, warning information and driving suggestions to the driver in the form of visual, auditory or tactile, while receiving the driver's touch, voice and other input commands.

[0164] Data transmission and interaction between different layers are achieved through the vehicle bus network. Common vehicle bus protocols include CAN (Controller Area Network), CAN FD (CAN with Flexible Data-Rate), LIN (Local Interconnect Network), FlexRay, and vehicle Ethernet, which supports high-bandwidth data transmission. Among these, CAN and CAN FD buses are widely used for communication in real-time control domains such as powertrain and chassis, while vehicle Ethernet is gradually being applied to high-bandwidth sensor data transmission in the intelligent driving domain and multimedia interaction scenarios in the cockpit domain.

[0165] In some possible examples, the intelligent driving domain controller, as the core of the in-vehicle computing platform, is configured with a processor and memory to execute the trust assessment method provided in the embodiments of this application.

[0166] For example, the control device of this application is arranged in the intelligent driving domain controller.

[0167] For example, the intelligent driving domain controller has multiple functional modules deployed to perform the various method steps.

[0168] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A trust assessment method, characterized in that, An automatic lane-changing method applied to vehicles, the method comprising: Obtain subjective evaluation data from drivers regarding their experience with the vehicle's automatic lane changing function; Acquire the driver's electroencephalogram (EEG) signals during the vehicle's automatic lane-changing experience; The driver's level of trust in the automatic lane change is determined based on the subjective evaluation data and the electroencephalogram (EEG) signals.

2. The method according to claim 1, characterized in that, The EEG signal includes the first full-process EEG signal generated by the driver during the automatic lane change of the vehicle. The step of determining the driver's level of trust in the automatic lane change based on the subjective evaluation data and the electroencephalogram (EEG) signals includes: Spectral analysis is performed on the first full-process EEG signal to obtain a first spectral energy distribution index. The first spectral energy distribution index is used to characterize the EEG frequency domain energy distribution characteristics of the driver during the automatic lane change process. A correlation analysis is performed on the first spectral energy distribution index and the subjective evaluation data, and the driver's trust in the automatic lane change is determined based on the correlation analysis results.

3. The method according to claim 2, characterized in that, The step of performing spectral analysis on the first full-process EEG signal to obtain the first spectral energy distribution index includes: The power spectral density of the first full-process EEG signal is estimated to obtain the power spectral density. Integrate the power spectral density according to the preset frequency bands to obtain the spectral energy corresponding to multiple frequency bands; The first spectral energy distribution index is determined based on the proportion of spectral energy corresponding to the multiple frequency bands in the total spectral energy.

4. The method according to claim 1, characterized in that, The subjective evaluation data includes the driver's evaluation data of the automatic lane change human-machine interface experience, and the EEG signal includes the second full-process EEG signal generated by the driver during the preset duration experience of the automatic lane change human-machine interface. The step of determining the driver's level of trust in the automatic lane change based on the subjective evaluation data and the electroencephalogram (EEG) signals includes: Spectral analysis is performed on the second full-process EEG signal to obtain a second spectral energy distribution index. The second spectral energy distribution index is used to characterize the EEG frequency domain energy distribution characteristics of the driver's interaction with the automatic lane-changing human-machine interface. The second spectral energy distribution index is correlated with the interface evaluation data, and the driver's trust in the automatic lane-changing human-machine interface is determined based on the correlation analysis results.

5. The method according to claim 4, characterized in that, The method further includes: Assess the driver's level of trust in multiple automatic lane change human-machine interfaces; Based on the level of trust in the multiple automatic lane change human-machine interaction interfaces, a recommended human-machine interaction interface is determined.

6. The method according to claim 1, characterized in that, The method further includes: Acquire the first EEG signal generated when the driver intends to change lanes and the second EEG signal generated when the vehicle automatically changes lanes during the automatic lane change experience. The first EEG signal and the second EEG signal are analyzed to obtain the phase synchronization difference index and the cortical activation difference index. The phase synchronization difference index is used to characterize the phase synchronization difference between different brain regions of the driver when the driver intends to change lanes and when the vehicle automatically changes lanes. The cortical activation difference index is used to characterize the difference in the activation location and activation intensity of the driver's cerebral cortex when the driver intends to change lanes and when the vehicle automatically changes lanes. The driver's level of trust in the automatic lane change is determined based on the phase synchronization difference index and the cortical activation difference index.

7. The method according to claim 6, characterized in that, The analysis of the first and second EEG signals to obtain cortical activation difference indices includes: The brain regions were divided according to the standard brain atlas, resulting in multiple brain regions. Extract the first sub-EEG signal from each of the brain regions from the first EEG signal; Extract the second sub-EEG signal from each of the brain regions from the second EEG signal; Source analysis was performed on multiple first sub-EEG signals and multiple second sub-EEG signals to obtain cortical activation difference indices.

8. A trust assessment device, characterized in that, An automatic lane-changing device for vehicles, comprising: The first acquisition module is used to acquire the driver's subjective evaluation data on the vehicle's automatic lane changing experience; The second acquisition module is used to acquire the driver's brain signals during the vehicle's automatic lane-changing experience; The determination module is used to determine the driver's level of trust in the automatic lane change based on the subjective evaluation data and the electroencephalogram (EEG) signals.

9. A control device, characterized in that, The control device includes: a memory and a processor; the memory and the processor are coupled; the memory is used to store instructions executable by the processor; when the processor executes the instructions, it performs the trust assessment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on an electronic device, cause the electronic device to perform the trust assessment method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, Includes a computer program; when the computer program is executed, it is capable of implementing the trust assessment method as described in any one of claims 1 to 7.

12. A vehicle, characterized in that, It includes the control device as claimed in claim 9; or the computer-readable storage medium as claimed in claim 10; or the computer program product as claimed in claim 11.

Images