Method, system and equipment for evaluating credibility of auxiliary driving system and medium

Abstract

The invention discloses an auxiliary driving system credibility evaluation method, system and device and a medium, and relates to the technical field of intelligent driving, and the auxiliary driving system credibility evaluation method comprises the following steps: obtaining the actual confidence of an auxiliary driving system in multiple dimensions; calculating a credibility index of the auxiliary driving system according to the actual confidence of the multiple dimensions; and determining the trust level of the auxiliary driving system according to the trust index of the auxiliary driving system. According to the invention, the operation state of the auxiliary driving system is quantified through the credibility index, so that a driver can accurately know the operation state of the auxiliary driving system in the use process.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, specifically to a method, system, device, and medium for evaluating the trustworthiness of an assisted driving system. Background Technology

[0002] With the widespread adoption of driver assistance technology in the automotive industry, the relationship between drivers and vehicles has shifted from "fully manual control" to "human-machine co-driving." Vehicles using driver assistance technology allow drivers to operate the vehicle, but also allow the built-in driver assistance system to actively control the vehicle's movement without driver intervention, enriching driving experiences and making vehicles more intelligent.

[0003] However, it is difficult for drivers to accurately understand the current state, capability boundaries, and limitations of the driver assistance system. The driver assistance technology is a "black box" system for the driver, who cannot accurately grasp the operating status of the system and is only reminded when it is necessary to take over. Summary of the Invention

[0004] This invention provides a method, system, device, and medium for evaluating the trust level of an assisted driving system, which can solve the problem in the prior art that the driver cannot accurately grasp the operating status of the system and is only reminded when it is necessary to take over.

[0005] In a first aspect, embodiments of the present invention provide a method for evaluating the trust level of an assisted driving system, comprising the following steps: Obtain the actual confidence levels of the driver assistance system across multiple dimensions; The trust index of the driver assistance system is calculated based on the actual confidence levels of multiple dimensions. The trust level of a driver assistance system is determined based on its trust index.

[0006] In conjunction with the first aspect, in one implementation, calculating the trust index of the driver assistance system based on actual confidence levels across multiple dimensions includes the following steps: Calculate the confidence scores of the actual confidence levels for multiple dimensions according to the preset quantification rules; The trust index of the driver assistance system is calculated based on the confidence scores of the actual confidence levels of multiple dimensions and their respective weights in the driver assistance system.

[0007] In conjunction with the first aspect, in one implementation, after determining the trust level of the driver assistance system based on the trust index of the driver assistance system, the following steps are included: Generate corresponding visual alert strategies based on the determined trust level of the driver assistance system.

[0008] In conjunction with the first aspect, in one implementation, obtaining the actual confidence level of the assisted driving system across multiple dimensions includes the following steps: Acquire confidence scores for multiple measurement perceptions, multiple measurement scenario complexity, multiple measurement map navigation, multiple measurement V2X, and multiple measurement driver state monitoring. The actual perception confidence, actual scenario complexity confidence, actual map navigation confidence, actual V2X confidence, and actual driver state monitoring confidence are calculated based on multiple measurement perception confidence, multiple measurement scenario complexity confidence, multiple measurement map navigation confidence, multiple measurement V2X confidence, and multiple measurement driver state monitoring confidence, respectively.

[0009] In conjunction with the first aspect, in one implementation, the step of calculating the actual perception confidence, actual scene complexity confidence, actual map navigation confidence, actual V2X confidence, and actual driver state monitoring confidence based on multiple measurement perception confidence, multiple measurement scene complexity confidence, multiple measurement map navigation confidence, multiple measurement V2X confidence, and multiple measurement driver state monitoring confidence respectively includes the following steps: Normal distribution statistics were performed on the acquired multiple measurement perception confidence scores and multiple measurement driver state monitoring confidence scores, respectively, and multiple measurement perception confidence scores and multiple measurement driver state monitoring confidence scores within the preset standard deviation range were selected. The actual perception confidence and the actual driver state monitoring confidence are calculated by using a weighted moving average statistical method for multiple measurement perception confidence and multiple measurement driver state monitoring confidence within the preset standard deviation range.

[0010] In conjunction with the first aspect, in one implementation, obtaining confidence scores for the complexity of multiple measurement scenarios includes the following steps: Time series information is added to the confidence scores of the complexity of the multiple measurement scenarios.

[0011] In conjunction with the first aspect, in one implementation, obtaining multiple measurement map navigation confidence scores further includes the following steps: Multiple measurement map navigation confidence scores are obtained based on multi-source map data.

[0012] Secondly, embodiments of the present invention provide a trust evaluation system for an assisted driving system, the assisted driving system trust evaluation system comprising: The acquisition module is used to acquire the actual confidence levels of the driver assistance system across multiple dimensions. The processing module is used to calculate the trust index of the driver assistance system based on the actual confidence levels of multiple dimensions. The execution module is used to determine the trust level of the driver assistance system based on the trust index of the driver assistance system.

[0013] Thirdly, embodiments of the present invention provide a trust evaluation device for an assisted driving system, the assisted driving system trust evaluation device including a processor, a memory, and an assisted driving system trust evaluation program stored in the memory and executable by the processor, wherein when the assisted driving system trust evaluation program is executed by the processor, it implements the steps of the assisted driving system trust evaluation method.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a driver assistance system trust evaluation program, wherein when the driver assistance system trust evaluation program is executed by a processor, it implements the steps of the driver assistance system trust evaluation method.

[0015] The beneficial effects of the technical solutions provided by the embodiments of the present invention include: This invention discloses a method, system, device, and medium for evaluating the trust level of an assisted driving system. The method includes the following steps: obtaining the actual confidence levels of the assisted driving system across multiple dimensions; calculating the trust index of the assisted driving system based on the actual confidence levels of the multiple dimensions; and determining the trust level of the assisted driving system based on the trust index. This invention quantifies the operating status of the assisted driving system through the trust index, enabling drivers to accurately understand the operating status of the assisted driving system during use. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an embodiment of the trust evaluation method for driver assistance systems of the present invention; Figure 2 For the present invention Figure 1 A detailed flowchart of step S2; Figure 3 This is a schematic diagram of the functional modules of an embodiment of the driver assistance system trust evaluation system of the present invention; Figure 4 This is a schematic diagram of the hardware structure of the trust evaluation device for the driver assistance system involved in the embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0019] With the widespread adoption of driver assistance technology in the automotive industry, the relationship between drivers and vehicles has shifted from "completely manual control" to "human-machine co-driving." However, drivers often struggle to accurately understand the current state, capabilities, and limitations of driver assistance systems. Driver assistance technology remains a "black box" for drivers, who cannot accurately grasp its operational status. This hinders users from accepting and confidently using driver assistance functions.

[0020] The main shortcomings of existing technologies include: 1. Coarse information granularity: Current driver assistance systems only provide feedback to the driver on the operation of the driver assistance system, but lack feedback on the driver's operational status and trustworthiness of the driver assistance system functions; 2. Passive rather than proactive: Current driver assistance systems are a passive "fault management" mode, only reminding the driver when takeover is needed, rather than a proactive and continuous "state sharing" mode, which cannot help the driver establish situational awareness.

[0021] like Figure 1 As shown, in a first aspect, embodiments of the present invention provide a method for evaluating the trust level of an assisted driving system, comprising the following steps: S1, obtain the actual confidence level of the driver assistance system in multiple dimensions; S2 calculates the trust index of the driver assistance system based on the actual confidence levels of multiple dimensions; S3 determines the trust level of the driver assistance system based on the trust index of the driver assistance system.

[0022] In the process of evaluating the trust level of driver assistance systems, the driver assistance system obtains actual confidence levels in multiple dimensions through multiple sensors, including: Based on the data quality of sensors such as cameras and radar, and the accuracy of algorithm output, a comprehensive confidence level of actual perception is generated.

[0023] Based on the identified road type, traffic density, weather conditions, lighting conditions, etc., assess the challenge level of the current scene to the system and generate the corresponding confidence level of the actual scene complexity.

[0024] Relying on the real-time updates of road conditions provided by navigation maps, actual map navigation confidence is generated before vehicles enter congested sections, accident-prone areas, complex intersections, or temporary construction zones.

[0025] Relying on V2X equipment deployed on vehicles / roadsides, it generates actual V2X confidence levels for complex and sudden scenarios at intersections.

[0026] By continuously monitoring driver fatigue, it is determined whether the driver has the ability to take over the vehicle at any time, and a confidence level for actual driver status monitoring is generated.

[0027] Of course, the actual confidence levels of the above-listed dimensions are only the dimensions used in one embodiment. In actual use, other dimensions can be added as needed to obtain actual confidence levels.

[0028] The trust index is calculated by obtaining the actual confidence levels of multiple dimensions and the corresponding weights for each dimension. The calculation formula is as follows: (Formula 1) During the test, Indicates the trust index. Indicates the first Dimensions Indicates the first Weights of each dimension Indicates the first The actual confidence level of each dimension.

[0029] The trust index can be designed to range from 0 to 1 or from 0 to 100, depending on the requirements. After quantifying the trust level of the driver assistance system, the specific trust index value can be used to determine the trust level of the system. Further, in one embodiment, the trust index is divided into three levels: high trust, medium trust, and low trust. The high trust index ranges from 0.7 to 1.0, the medium trust index ranges from 0.4 to 0.7, and the low trust index ranges from 0 to 0.4. Of course, this classification rule can be modified according to actual requirements.

[0030] During driving, the driver assistance system trust evaluation system acquires actual confidence levels across multiple dimensions through sensors and calculates the corresponding trust index. The trust level of the driver assistance system can then be determined based on the specific value of the trust index. This addresses the "trust black box" problem in existing driver assistance human-machine interactions by presenting the real-time confidence levels, capability boundaries, and potential risks of the driver assistance system's internal perception and decision-making modules to the driver in the form of a trust index. This eliminates the information gap between the driver and the driver assistance system, enhances the driver's situational awareness of the system, establishes reasonable trust, and enables smooth and efficient handover of responsibilities when necessary.

[0031] This invention quantifies the operating status of the driver assistance system through a trust index, enabling drivers to accurately understand the operating status of the driver assistance system during use.

[0032] like Figure 2 As shown, in one embodiment, calculating the trust index of the assisted driving system based on the actual confidence levels of multiple dimensions includes the following steps: S21, calculate the confidence scores of the actual confidence levels of multiple dimensions according to the preset quantification rules; S22, calculate the trust index of the driver assistance system based on the confidence scores of the actual confidence in multiple dimensions and their respective weights in the driver assistance system.

[0033] The process of quantifying the actual confidence levels of multiple dimensions according to preset quantization rules to obtain confidence scores is as follows: 1. Calculate the actual perceived confidence score using the following formula: (Formula 2) (Formula 3) In the formula, It is the actual perceived confidence score. It is a score generated based on image sharpness, contrast, and object detection neural networks. The score is generated based on factors such as target signal-to-noise ratio, target stability, and point cloud density. The score is generated based on point cloud density, reflectivity quality, etc. They represent the corresponding The weights, the and The value ranges from 0 to 1.

[0034] Furthermore, when there is no lidar in the driver assistance system, at this time The value is 0.

[0035] 2. The confidence score for the actual scenario complexity is calculated using the following method. This confidence score is a negative indicator; the higher the complexity, the lower the confidence score. The base score is 1.0, with deductions for: Weather (heavy rain / snow / fog: -0.4; light rain / fog: -0.2); Illumination (nighttime: -0.3; backlight: -0.2); Road type (congested urban roads: -0.3; national highways without medians: -0.4); Traffic density (extremely high: -0.3; moderate: -0.1). It equals the base score plus the score from all deductions, and its value is between 0 and 1.

[0036] 3. Calculate the actual map navigation confidence score using the following formula: (Formula 4) (Formula 5) In the formula, It is the actual map navigation confidence score. The score is generated based on the map update frequency; the newer the map, the higher the score. The score is generated based on the positioning error; the smaller the error, the higher the score. The score is generated based on the navigation path, which determines whether there are multiple forks in the road or complex ramps ahead. The higher the complexity, the lower the score. They represent the corresponding The weights, the and The value ranges from 0 to 1.

[0037] 4. Calculate the actual V2X confidence score using the following formula: (Formula 6) (Formula 7) In the formula, It is the actual V2X confidence score. The score is generated based on the map update frequency; the newer the map, the higher the score. The score is generated based on the density of V2V vehicles in the surrounding area and the consistency of information. They represent the corresponding The weights, the and The value ranges from 0 to 1.

[0038] 5. Calculate the confidence score for actual driver state monitoring using the following formula: (Formula 8) (Formula 9) In the formula, It is the confidence score of actual driver status monitoring. The score is generated based on the map update frequency; the newer the map, the higher the score. The score is generated by judging whether the hand is on the steering wheel using torque or capacitance sensors. They represent the corresponding The weights, the and The value ranges from 0 to 1.

[0039] This invention quantifies the scenarios encountered during driving by calculating the confidence scores of actual confidence in multiple dimensions and then calculating the corresponding trust index, which can intuitively reflect the trust level of the driver assistance system.

[0040] In one embodiment, after determining the trust level of the driver assistance system based on the trust index of the driver assistance system, the following steps are included: generating a corresponding visual reminder strategy based on the determined trust level of the driver assistance system.

[0041] During driving, the driver's attention is primarily focused on driving. To better convey the current trust level of the advanced driver assistance system (ADAS) and provide feedback to the driver, the trust level can be mapped to specific visual elements. This mapping can be integrated into the in-vehicle infotainment system and displayed prominently on the instrument panel, central control screen, or head-up display (HUD) to provide immediate reminders to the driver. In one reminder scheme, the visual interface is presented on the instrument panel, central control screen, or HUD using a "dynamic visual halo" method. The mapping relationship between different trust levels and the halo is as follows: High trust level: The halo displays a rich green glow that is stable and bright; Medium Trust Level: The halo color changes to amber, accompanied by a slow breathing effect; Low Trust Level: The halo turns red and flashes rapidly, accompanied by an audible alarm.

[0042] This invention generates corresponding visual reminder strategies based on the trust level of the driver assistance system, which can intuitively and conspicuously remind the driver of the current trust level of the driver assistance system.

[0043] In one embodiment, obtaining the actual confidence scores of the assisted driving system across multiple dimensions includes the following steps: obtaining multiple measurement perception confidence scores, multiple measurement scenario complexity confidence scores, multiple measurement map navigation confidence scores, multiple measurement V2X confidence scores, and multiple measurement driver state monitoring confidence scores; and calculating the actual perception confidence score, actual scenario complexity confidence score, actual map navigation confidence score, actual V2X confidence score, and actual driver state monitoring confidence score based on the multiple measurement perception confidence scores, multiple measurement scenario complexity confidence scores, multiple measurement map navigation confidence scores, multiple measurement V2X confidence scores, and multiple measurement driver state monitoring confidence scores, respectively.

[0044] In the process of collecting actual confidence scores across multiple dimensions, occasional inaccuracies may occur. To improve data quality, reduce the impact of abnormal data on the system's confidence score judgment, and enhance the robustness of the technical solution, multiple samplings can be performed on the measurement confidence score data for different dimensions, followed by noise reduction to obtain the actual confidence score for the first dimension.

[0045] This invention further increases the accuracy of trust evaluation by denoising the acquired measurement confidence levels to obtain accurate actual confidence levels across multiple dimensions.

[0046] In one embodiment, the step of calculating the actual perception confidence, actual scene complexity confidence, actual map navigation confidence, actual V2X confidence, and actual driver state monitoring confidence based on multiple measurement perception confidence, multiple measurement scene complexity confidence, multiple measurement map navigation confidence, multiple measurement V2X confidence, and multiple measurement driver state monitoring confidence includes the following steps: performing normal distribution statistics on the acquired multiple measurement perception confidence and multiple measurement driver state monitoring confidence, and filtering out multiple measurement perception confidence and multiple measurement driver state monitoring confidence within a preset standard deviation range; calculating the actual perception confidence and actual driver state monitoring confidence using a weighted moving average statistical method on the filtered multiple measurement perception confidence and multiple measurement driver state monitoring confidence within the preset standard deviation range.

[0047] Since the data sources for both actual perception confidence and actual driver state monitoring confidence are from in-vehicle and out-of-vehicle sensors, outlier removal and sliding window filtering algorithms can be introduced to preprocess multiple measured perception confidence and multiple measured driver state monitoring confidence from sensors such as cameras and radar, in order to improve the stability and anti-interference capability of their calculations. The specific process is as follows: Window definition: Set a sliding window with a fixed number of sampling times N to cache the data sequence of measurement perception confidence or measurement driver state monitoring confidence in a recent period: W={C1, C2, C3, ..., CN}, where Ci is the measurement perception confidence or measurement driver state monitoring confidence obtained from the i-th sampling; Outlier detection and removal: Within a sliding window, a standard deviation-based method is used to identify and remove abnormal measurement perception confidence data or driver state monitoring confidence data that may be caused by transient sensor interference, algorithm misjudgment, etc.: Calculate the mean μ and standard deviation σ of the data within the window, and set a threshold k. If a data point Ci satisfies |Ci-μ|>k*σ, it means that it exceeds the preset standard deviation range, and this data point is regarded as an outlier and removed from the current window.

[0048] Data filtering: Weighted moving average is used to filter the measured perception confidence or measured driver state monitoring confidence within the window to reduce the impact of noise.

[0049] This invention first uses normal distribution statistics to remove outliers from multiple acquired measurement perception confidence scores and multiple measurement driver state monitoring confidence scores, and then performs filtering to reduce the noise in the acquired multiple measurement perception confidence scores and multiple measurement driver state monitoring confidence scores. The calculation of actual perception confidence scores and actual driver state monitoring confidence scores using the processed measurement perception confidence scores and measurement driver state monitoring confidence scores is more accurate.

[0050] In one embodiment, obtaining multiple measurement scenario complexity confidence scores includes the following steps: adding time series information to the obtained multiple measurement scenario complexity confidence scores respectively.

[0051] To avoid drastic fluctuations in the confidence score of actual scene complexity due to sudden changes in the scene, which could affect the continuity of trust assessment and user experience of the assisted driving system, time series smoothing is introduced. By adding time series information to all collected signals, the signals collected at each moment are aligned using the time series information. The confidence score of the measured scene complexity is obtained based on the aligned signals, ensuring accurate acquisition of the confidence score of the measured scene complexity at each moment even during sudden changes in the scene. This processing is based on a sliding window and smoothing algorithm, which performs real-time filtering on the scene complexity score to ensure that changes in the confidence score of actual scene complexity are smooth and reasonable.

[0052] Window definition: Set a fixed sliding window N for acquiring the confidence score of the measurement scenario complexity. The average of the confidence scores of the most recent N measurement scenario complexities is used to calculate the confidence score. This method can effectively suppress short-term fluctuations.

[0053] Exponentially weighted average: An exponentially weighted moving average is used to process the confidence level of the measurement scenario complexity within the window, improving the sensitivity to recent data. The processing formula is as follows: (Formula 10) in, Indicates the first time, Indicates the first Real-world scenario complexity confidence level. Indicates the first Measure the confidence level of scene complexity at each moment, initially. , This represents the smoothing factor (0 < α < 1), and the smaller the value, the smaller the smoothing effect.

[0054] By introducing time series information, this invention effectively prevents errors caused by time series disorder in the obtained measurement scenario complexity confidence score, and further increases the accuracy of the obtained measurement scenario complexity confidence score.

[0055] In one embodiment, obtaining multiple measurement map navigation confidence scores further includes the following steps: obtaining multiple measurement map navigation confidence scores respectively based on multi-source map data.

[0056] To improve the accuracy and reliability of actual map navigation confidence, a multi-source map data comparison and redundancy verification mechanism is adopted. By integrating map information from different data sources and performing consistency verification and anomaly identification, the credibility of map data in complex environments is improved.

[0057] Multi-source map data definition: Data from multiple map data sources, including but not limited to: high-precision maps containing lane-level geometric features, traffic signs, and slope curvature; navigation maps with real-time traffic information and time-updated capabilities; and dynamic map information distributed by V2X or cloud platforms. Data comparison and consistency verification: Spatial and attribute consistency comparison of road topology, traffic events, location and map matching in the map.

[0058] This invention obtains the confidence level of the measured map navigation by using multi-source map data, which improves the reliability in complex environments and further enhances the accuracy of obtaining the confidence level of the actual map navigation.

[0059] like Figure 3As shown, in a second aspect, embodiments of the present invention also provide a trust evaluation system for an assisted driving system, the assisted driving system trust evaluation system comprising: an acquisition module, which is used to acquire the actual confidence levels of the assisted driving system in multiple dimensions; a processing module, which is used to calculate the trust index of the assisted driving system based on the actual confidence levels in multiple dimensions; and an execution module, which is used to determine the trust level of the assisted driving system based on the trust index of the assisted driving system.

[0060] The functions of each module in the aforementioned driver assistance system trust evaluation system correspond to the steps in the aforementioned driver assistance system trust evaluation method embodiment, and their functions and implementation processes will not be described in detail here.

[0061] Thirdly, embodiments of the present invention provide a trust evaluation device for driver assistance systems. The trust evaluation device for driver assistance systems can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0062] like Figure 4 As shown, Figure 4 This is a schematic diagram of the hardware structure of the driver assistance system trust evaluation device involved in the embodiment of the present invention. In this embodiment, the driver assistance system trust evaluation device may include a processor, a memory, a communication interface, and a communication bus.

[0063] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0064] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the driver assistance system trust evaluation device, as well as interfaces used for interconnecting the driver assistance system trust evaluation device with other devices (such as other computing devices or user devices). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user devices can be displays, keyboards, etc.

[0065] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0066] The processor can be a general-purpose processor, which can call the driver assistance system trust evaluation program stored in the memory and execute the driver assistance system trust evaluation method provided in the embodiments of the present invention. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the driver assistance system trust evaluation program is called can be referred to in various embodiments of the driver assistance system trust evaluation method of the present invention, and will not be described again here.

[0067] Those skilled in the art will understand that Figure 4 The hardware structure shown does not constitute a limitation of the invention and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0068] Fourthly, embodiments of the present invention also provide a computer-readable storage medium.

[0069] The present invention provides a computer-readable storage medium storing a trust evaluation program for an assisted driving system, wherein when the assisted driving system trust evaluation program is executed by a processor, it implements the steps of the assisted driving system trust evaluation method described above.

[0070] The method implemented when the driver assistance system trust evaluation procedure is executed can be referred to in various embodiments of the driver assistance system trust evaluation method of the present invention, and will not be repeated here.

[0071] It should be noted that the sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0072] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0073] In the description of the embodiments of the present invention, terms such as "exemplary," "for example," or "for instance" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary," "for example," or "for instance" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0074] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.

[0075] In some processes described in the embodiments of the present invention, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of the present invention, or may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of the present invention.

[0077] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for evaluating the trust level of a driver assistance system, characterized in that, Includes the following steps: Obtain the actual confidence levels of the driver assistance system across multiple dimensions; The trust index of the driver assistance system is calculated based on the actual confidence levels of multiple dimensions. The trust level of a driver assistance system is determined based on its trust index.

2. The method for evaluating the trust level of an assisted driving system according to claim 1, characterized in that, The process of calculating the trust index of the driver assistance system based on actual confidence levels across multiple dimensions includes the following steps: Calculate the confidence scores of the actual confidence levels for multiple dimensions according to the preset quantification rules; The trust index of the driver assistance system is calculated based on the confidence scores of the actual confidence levels of multiple dimensions and their respective weights in the driver assistance system.

3. The method for evaluating the trust level of an assisted driving system according to claim 1, characterized in that, After determining the trust level of the driver assistance system based on its trust index, the process includes the following steps: Generate corresponding visual alert strategies based on the determined trust level of the driver assistance system.

4. The method for evaluating the trust level of an assisted driving system according to claim 1, characterized in that, The process of obtaining the actual confidence level of the driver assistance system across multiple dimensions includes the following steps: Acquire confidence scores for multiple measurement perceptions, multiple measurement scenario complexity, multiple measurement map navigation, multiple measurement V2X, and multiple measurement driver state monitoring. The actual perception confidence, actual scenario complexity confidence, actual map navigation confidence, actual V2X confidence, and actual driver state monitoring confidence are calculated based on multiple measurement perception confidence, multiple measurement scenario complexity confidence, multiple measurement map navigation confidence, multiple measurement V2X confidence, and multiple measurement driver state monitoring confidence, respectively.

5. The method for evaluating the trust level of an assisted driving system according to claim 4, characterized in that, The process of calculating the actual perception confidence, actual scene complexity confidence, actual map navigation confidence, actual V2X confidence, and actual driver state monitoring confidence based on multiple measurement perception confidence, multiple measurement scene complexity confidence, multiple measurement map navigation confidence, multiple measurement V2X confidence, and multiple measurement driver state monitoring confidence includes the following steps: Normal distribution statistics were performed on the acquired multiple measurement perception confidence scores and multiple measurement driver state monitoring confidence scores, respectively, and multiple measurement perception confidence scores and multiple measurement driver state monitoring confidence scores within the preset standard deviation range were selected. The actual perception confidence and the actual driver state monitoring confidence are calculated by using a weighted moving average statistical method for multiple measurement perception confidence and multiple measurement driver state monitoring confidence within the preset standard deviation range.

6. The method for evaluating the trust level of an assisted driving system according to claim 4, characterized in that, The process of obtaining confidence scores for the complexity of multiple measurement scenarios includes the following steps: Time series information is added to the confidence scores of the complexity of the multiple measurement scenarios.

7. The method for evaluating the trust level of an assisted driving system according to claim 4, characterized in that, The process of obtaining multiple measurement map navigation confidence scores also includes the following steps: Multiple measurement map navigation confidence scores are obtained based on multi-source map data.

8. A trust evaluation system for driver assistance systems, characterized in that, The driver assistance system trust evaluation system includes: The acquisition module is used to acquire the actual confidence levels of the driver assistance system across multiple dimensions. The processing module is used to calculate the trust index of the driver assistance system based on the actual confidence levels of multiple dimensions. The execution module is used to determine the trust level of the driver assistance system based on the trust index of the driver assistance system.

9. A trust evaluation device for an assisted driving system, characterized in that, The driver assistance system trust evaluation device includes a processor, a memory, and a driver assistance system trust evaluation program stored in the memory and executable by the processor, wherein when the driver assistance system trust evaluation program is executed by the processor, it implements the steps of the driver assistance system trust evaluation 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 a trust evaluation program for an assisted driving system, wherein when the assisted driving system trust evaluation program is executed by a processor, it implements the steps of the assisted driving system trust evaluation method as described in any one of claims 1 to 7.

Images