Automatic driving comfort evaluation method and device, electronic equipment and storage medium

Abstract

The invention discloses an automatic driving comfort evaluation method and device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring automatic driving data of a vehicle in each of a plurality of driving scenes and a comfort reference index corresponding to each driving scene; wherein the comfort level reference index is determined according to active driving data in each driving scene in the vehicle driving process of the driver; according to the automatic driving data in each driving scene, determining an automatic driving comfort evaluation score of each driving scene; and determining an automatic driving comfort evaluation result of the vehicle according to the comfort reference indexes of the plurality of driving scenes and the automatic driving comfort evaluation scores. According to the method provided by the invention, the accuracy of the determined automatic driving comfort evaluation result is relatively high.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and more specifically, to an autonomous driving comfort evaluation method, device, electronic device, and computer-readable storage medium. Background Technology

[0002] With the continuous development of autonomous driving technology, a large number of vehicles equipped with autonomous driving functions have entered the market. Comfort is one of the important factors affecting users' acceptance of autonomous driving functions, and comfort evaluation has become an important evaluation dimension for autonomous driving functions.

[0003] Currently, the main method for evaluating autonomous driving functions is to rely on drivers' subjective evaluations of the vehicles and to synthesize the subjective evaluations from multiple drivers. However, this method has a low accuracy rate in evaluating autonomous driving functions. Summary of the Invention

[0004] This application proposes a method, apparatus, electronic device, and computer-readable storage medium for evaluating the comfort of autonomous driving, in order to improve the aforementioned deficiencies.

[0005] In a first aspect, embodiments of this application provide a method for evaluating the comfort of autonomous driving, the method comprising:

[0006] Acquire autonomous driving data for the vehicle in each of multiple driving scenarios, as well as the corresponding comfort benchmark index for each driving scenario; the comfort benchmark index is determined based on the active driving data of the driver in each driving scenario during the vehicle's operation.

[0007] Based on the autonomous driving data in each driving scenario, determine the autonomous driving comfort evaluation score for each driving scenario;

[0008] The autonomous driving comfort evaluation result of the vehicle is determined based on the comfort benchmark indicators of multiple driving scenarios and the autonomous driving comfort evaluation score.

[0009] Secondly, embodiments of this application also provide an autonomous driving comfort evaluation device, the device comprising:

[0010] The acquisition module is used to acquire autonomous driving data of the vehicle in each of multiple driving scenarios and the corresponding comfort benchmark index for each driving scenario; wherein, the comfort benchmark index is determined based on the active driving data of the driver in each driving scenario during the driving process;

[0011] The first determining module is used to determine the autonomous driving comfort evaluation score for each driving scenario based on the autonomous driving data in each driving scenario.

[0012] The second determining module is used to determine the autonomous driving comfort evaluation result of the vehicle based on the comfort benchmark indicators of multiple driving scenarios and the autonomous driving comfort evaluation score.

[0013] Thirdly, embodiments of this application also provide an electronic device, characterized in that the electronic device includes: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to perform the above-described methods.

[0014] Fourthly, embodiments of this application also provide a computer-readable storage medium storing processor-executable program code, which, when executed by the processor, causes the processor to perform the above-described method.

[0015] Fifthly, embodiments of this application also provide a computer program product, including computer-readable instructions, which, when executed by a processor, constitute the above-described method.

[0016] This application provides a method, device, electronic device, and computer-readable storage medium for evaluating the comfort of autonomous driving. In this application, the comfort benchmark index for a driving scenario is determined based on active driving data acquired during the driver's operation of the vehicle. This active driving data is obtained when the driver drives according to their own needs, thus accurately indicating the driver's satisfactory driving behavior. Therefore, the comfort benchmark index determined based on the active driving data of the driving scenario accurately indicates the driver's level of satisfaction. Simultaneously, based on the autonomous driving data for each driving scenario, an autonomous driving comfort evaluation score is determined for each driving scenario. Then, by combining the comfort benchmark index and the autonomous driving comfort evaluation score from multiple driving scenarios, the autonomous driving comfort evaluation result for the autonomous driving function is determined. This evaluation of the autonomous driving comfort score using the comfort benchmark index yields an autonomous driving comfort evaluation result that takes into account user satisfaction, making the autonomous driving comfort evaluation result more accurate. This eliminates the need for the driver's subjective evaluation to determine the autonomous driving comfort evaluation result, effectively reducing the possibility of inaccurate autonomous driving comfort evaluation results due to the high degree of subjective bias in subjective evaluations by different drivers.

[0017] Other features and advantages of the embodiments of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the embodiments of this application. The objects and other advantages of the embodiments of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart of an autonomous driving comfort evaluation method according to an embodiment of this application is shown.

[0020] Figure 2 A schematic diagram of the evaluation process for an autonomous driving function in an embodiment of this application is shown.

[0021] Figure 3 It shows Figure 1 The flowchart of step S120 in one embodiment is shown below.

[0022] Figure 4 It shows Figure 1 The flowchart of the steps preceding step S110 in the corresponding embodiment is shown in one embodiment.

[0023] Figure 5 The diagram shows a structural block diagram of an autonomous driving comfort evaluation device according to an embodiment of this application.

[0024] Figure 6 A structural block diagram of an electronic device provided according to an embodiment of this application is shown. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. The components of the embodiments of the present application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without inventive effort are within the scope of protection of the present application.

[0026] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] Please see Figure 1 , Figure 1 A flowchart of an autonomous driving comfort evaluation method according to an embodiment of this application is shown, for an electronic device, the method comprising:

[0028] S110: Acquire autonomous driving data of the vehicle in each of multiple driving scenarios and the corresponding comfort benchmark index for each driving scenario.

[0029] The comfort benchmark index is determined based on active driving data in each driving scenario during the driver's operation of the vehicle; that is, active driving data is acquired during the driver's operation of the vehicle, while autonomous driving data is acquired during the vehicle's autonomous driving operation.

[0030] The vehicle in this embodiment can be an electric vehicle or a gasoline-powered vehicle, or it can be a sedan, SUV, bus, or truck, etc. The autonomous driving function can be an autonomous driving function built into the vehicle, which allows the vehicle to drive autonomously.

[0031] It is easy to understand that the autonomous driving comfort evaluation method in this application is used to evaluate the autonomous driving function of a vehicle. Therefore, the autonomous driving data obtained is the data under the control of the vehicle's autonomous driving function. In other words, the autonomous driving data is the data obtained by the vehicle during the process of controlling the vehicle's autonomous driving based on the autonomous driving function.

[0032] It is understandable that the vehicle used to acquire active driving data and the vehicle used to acquire autonomous driving data can be the same vehicle or different vehicles of the same model. This ensures that the active driving vehicle and the autonomous driving vehicle have the same data about the vehicle itself, except for the driver, making the obtained active driving data and autonomous driving data more accurate.

[0033] Driving scenario can refer to the environment in which the vehicle is driving. In this embodiment, driving scenario is used to indicate at least one of the four main scenario dimensions: light, traffic flow density, road type, and driving behavior at the location where the vehicle is driving.

[0034] For example, light can be divided into daytime light and nighttime light. By detecting the current time, the light at the vehicle's location in the driving scenario can be determined. Traffic flow density can be sparse, medium, or dense, which can be determined by sensing the number of traffic participants through the vehicle's sensors (radar or camera). Road type can include highways, expressways, national roads, urban roads, and ramp interchanges, which can be comprehensively judged through high-precision maps and perception recognition results. Driving behavior can include stopping, starting, changing lanes, going straight, turning left, turning right, making a U-turn, splitting, and merging, which can be comprehensively judged by detecting information such as vehicle speed, steering wheel angle, lane lines, and stop line positions.

[0035] A driving scenario can refer to the result of combining information from at least one of the aforementioned main scenario dimensions. For example, a driving scenario could be driving on a busy city road during the day (in which case, the driving scenario involves the aforementioned four main scenario dimensions), or driving on a busy road at night (in which case, the driving scenario involves the aforementioned four main scenario dimensions: light and traffic density).

[0036] To facilitate the labeling of driving scenarios, different labels can be added to specific information under different main scenario dimensions, thereby indicating different driving scenarios through labels. For example, the labels added to the aforementioned information are shown in Table 1, as follows:

[0037] Table 1

[0038]

[0039]

[0040] At this point, the combined label A1 B1 C1 D1 represents the driving scenario of parking on a highway with sparse traffic flow during the day.

[0041] To make the driving scenarios more accurate, each driving scenario in this application involves the aforementioned four main scenario dimensions. Accordingly, if the main scenario dimensions include the specific information shown in Table 1, the number of driving scenarios involved can be 2×3×5×9=270.

[0042] During vehicle operation, data such as lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate can be collected to create an active driving dataset. This dataset is then segmented according to the driving scenario to obtain active driving data for each scenario, and labeled with a combination of tags corresponding to each scenario. Similarly, during autonomous driving, data such as lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate can be collected to create an autonomous driving dataset. This dataset is also segmented according to the driving scenario to obtain autonomous driving data for each scenario, and labeled with a combination of tags corresponding to each scenario.

[0043] In this embodiment, the driving scenario to which the autonomous driving data belongs can be determined based on each autonomous driving data in the autonomous driving dataset, and the autonomous driving data belonging to the same driving scenario can be divided into a set to obtain the autonomous driving data under that driving scenario; similarly, the driving scenario to which the active driving data belongs can be determined based on each active driving data in the active driving dataset, and the active driving data belonging to the same driving scenario can be divided into a set to obtain the active driving data under that driving scenario.

[0044] It is understood that the aforementioned active driving data can be acquired in real time during the driver's operation of the vehicle, or it can be stored in the cloud after the vehicle has collected the active driving data, and the electronic device retrieves the active driving data collected by the vehicle from the cloud when executing the method of this application. The cloud can refer to a server, cloud server, server cluster, or distributed system that is communicatively connected to the electronic device.

[0045] In some implementations, the active driving data includes the vehicle's active driving lateral acceleration, active driving longitudinal acceleration, active driving longitudinal acceleration rate of change, and active driving yaw rate. For each driving scenario, a comfort benchmark index for the driving scenario can be determined based on the active driving data for that driving scenario, including the active driving lateral acceleration, active driving longitudinal acceleration, active driving longitudinal acceleration rate of change, and active driving yaw rate.

[0046] For example, the active driving data can be obtained by weighted summing of the active driving lateral acceleration, active driving longitudinal acceleration, active driving longitudinal acceleration rate of change, and active driving yaw rate. The weights of these components can be set according to requirements and are not limited in this application.

[0047] S120. Based on the autonomous driving data in each driving scenario, determine the autonomous driving comfort evaluation score for each driving scenario.

[0048] As mentioned above, autonomous driving data includes the vehicle's lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate. For each driving scenario, the autonomous driving comfort evaluation score can be determined based on the autonomous driving data for that driving scenario, including the lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate.

[0049] In some implementations, the autonomous driving data, including the lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate, can be weighted and summed to obtain the autonomous driving data including the lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate. The weights of these components can be set based on requirements and are not limited in this application.

[0050] S130. Based on the comfort benchmark indicators of multiple driving scenarios and the autonomous driving comfort evaluation score, determine the autonomous driving comfort evaluation result of the vehicle.

[0051] After obtaining the comfort benchmark index and autonomous driving comfort evaluation score for each driving scenario, the autonomous driving comfort evaluation score of the autonomous driving function can be determined by combining the comfort benchmark index and autonomous driving comfort evaluation score for multiple driving scenarios.

[0052] In some implementations, S130 may include: for each driving scenario, calculating the ratio of the autonomous driving comfort evaluation score to the comfort benchmark index in that driving scenario, and then summing the ratios corresponding to multiple driving scenarios as the autonomous driving comfort evaluation result of the autonomous driving function.

[0053] In some implementations, S130 may also include: determining the score rate of each driving scenario based on the comfort benchmark index and the autonomous driving comfort evaluation score for each driving scenario; obtaining the scenario weights of multiple driving scenarios; the scenario weights of driving scenarios are used to indicate the frequency of occurrence of driving scenarios in multiple driving scenarios; and determining the autonomous driving comfort evaluation result of the vehicle based on the score rates and scenario weights of multiple driving scenarios.

[0054] The frequency of each driving scenario among multiple driving scenarios can be determined as the scenario weight. For example, in the process of collecting autonomous driving data or active driving data, if 1000 driving scenarios are involved, and driving scenario A appears 200 times, then the frequency of driving scenario A is 0.2, and the corresponding scenario weight of driving scenario A is 0.2.

[0055] In this application, the score rate for driving scenarios can be calculated according to Formula 1, which is as follows:

[0056]

[0057] Among them, S i Let I be the score rate for driving scenario i, and e be the natural constant. i The score represents the comfort level of autonomous driving in driving scenario i. This serves as the benchmark for comfort in driving scenario i.

[0058] Then, according to Formula 2, the scores of multiple driving scenarios can be weighted and summed to obtain the autonomous driving comfort evaluation result. Formula 2 is as follows:

[0059]

[0060] Where S represents the autonomous driving comfort evaluation result, and K i Let be the scene weight corresponding to driving scene i, and m be the number of driving scenes.

[0061] In this embodiment, after determining the comfort benchmark index, autonomous driving comfort evaluation score, and score rate based on the aforementioned steps S110-S130, a record table can also be generated, as shown in Table 2. Table 2 is as follows:

[0062] Table 2

[0063]

[0064] For example, such as Figure 2As shown, driving data can be collected during the driver's operation of the vehicle. Then, the collected data can be sliced ​​using a driving scenario slicing tool to obtain active driving data for each driving scenario. Simultaneously, driving data can be collected during the driver's operation of the vehicle, and the collected data can be sliced ​​using the driving scenario slicing tool to obtain active driving data for each driving scenario. Furthermore, when a vehicle is equipped with autonomous driving functionality, driving data can be collected during the vehicle's operation using this function, and the collected data can be sliced ​​using the driving scenario slicing tool to obtain autonomous driving data for each driving scenario.

[0065] Then, based on autonomous driving data and active driving data, model evaluation processing is performed: Following the methods described in S110-S120 above, comfort benchmark indicators and autonomous driving comfort evaluation scores for each driving scenario are determined. Then, combining the comfort benchmark indicators and autonomous driving comfort evaluation scores for each driving scenario, the autonomous driving comfort evaluation result for the autonomous driving function is determined, and based on the autonomous driving comfort evaluation result, it is determined whether the target has been achieved. Achieving the target may mean that the autonomous driving comfort evaluation result reaches a preset threshold, where the preset threshold can be set based on demand; this application does not impose any limitations.

[0066] If the goal is achieved, and the autonomous driving function is deemed to provide a high level of user comfort, then the autonomous driving function is deemed qualified and released. If the goal is not achieved, and the autonomous driving function is deemed to provide a low level of user comfort, then the autonomous driving function is deemed unqualified and needs to be improved. The improved autonomous driving function will then be evaluated in the aforementioned manner until the goal is achieved, at which point the autonomous driving function will be released.

[0067] The autonomous driving function in this application can be integrated into autonomous driving software, and the vehicle can be equipped with the autonomous driving software to drive itself.

[0068] In this embodiment, the comfort benchmark index for driving scenarios is determined based on active driving data. Active driving data is acquired during the driver's operation of the vehicle; that is, it is driving data obtained when the driver drives according to their own needs. Therefore, active driving data can accurately indicate the driver's satisfactory driving behavior, allowing the comfort benchmark index determined based on the active driving data of driving scenarios to accurately indicate the driver's level of satisfaction. Simultaneously, based on the autonomous driving data for each driving scenario, an autonomous driving comfort evaluation score is determined for each driving scenario. Then, by combining the comfort benchmark index and the autonomous driving comfort evaluation score from multiple driving scenarios, the autonomous driving comfort evaluation result for the autonomous driving function is determined. Thus, the autonomous driving comfort evaluation result is obtained by evaluating the autonomous driving comfort evaluation score using the comfort benchmark index. This ensures that the obtained autonomous driving comfort evaluation result takes into account the user's satisfaction level, making the autonomous driving comfort evaluation result more accurate. This eliminates the need for the driver's subjective evaluation to determine the autonomous driving comfort evaluation result, effectively reducing the possibility of inaccurate autonomous driving comfort evaluation results due to the high degree of subjective bias in subjective evaluations by different drivers.

[0069] Meanwhile, both autonomous driving data and active driving data involve lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate. These parameters can accurately indicate the vehicle's driving status, enabling the autonomous driving comfort evaluation score determined based on autonomous driving data to accurately reflect the autonomous driving situation. Furthermore, this makes the comfort benchmark index determined based on active driving data more consistent with the actual driving behavior of the driver, thereby improving the accuracy of the autonomous driving comfort evaluation results determined based on the comfort benchmark index and the autonomous driving comfort evaluation score.

[0070] In one embodiment, the autonomous driving data includes the vehicle's autonomous driving lateral acceleration, autonomous driving longitudinal acceleration, autonomous driving longitudinal acceleration rate of change, and autonomous driving yaw rate; the autonomous driving lateral acceleration includes the autonomous driving lateral acceleration at multiple first time points; the autonomous driving longitudinal acceleration includes the autonomous driving longitudinal and lateral acceleration at multiple first time points; the autonomous driving longitudinal acceleration rate of change includes the autonomous driving longitudinal acceleration rate of change at multiple first time points; the autonomous driving yaw rate in the driving scenario includes the autonomous driving yaw rate at multiple first time points; such as Figure 3 As shown, S120 includes:

[0071] S210. Based on the lateral acceleration of autonomous driving at multiple first time points in the driving scenario, determine the lateral acceleration index of autonomous driving at each of the multiple first time points in the driving scenario.

[0072] S220. Based on the longitudinal acceleration of autonomous driving at multiple first time points in the driving scenario, determine the longitudinal acceleration index of autonomous driving at each of the multiple first time points in the driving scenario.

[0073] S230. Based on the rate of change of longitudinal acceleration of autonomous driving at multiple first time points in the driving scenario, determine the respective indicators of the rate of change of longitudinal acceleration of autonomous driving at multiple first time points in the driving scenario.

[0074] S240. Based on the yaw rate of autonomous driving at multiple first time points in the driving scenario, determine the yaw rate index of autonomous driving at each of the multiple first time points in the driving scenario.

[0075] S250. For each first time point, determine the time point evaluation score corresponding to the first time point in the driving scenario based on the weights of the autonomous driving lateral acceleration index, the autonomous driving longitudinal acceleration index, the autonomous driving longitudinal acceleration change rate index, the autonomous driving yaw rate index, and the autonomous driving lateral acceleration index, the autonomous driving longitudinal acceleration index, the autonomous driving longitudinal acceleration change rate index, and the autonomous driving yaw rate index for each first time point in the driving scenario.

[0076] S260. Based on the time point evaluation scores corresponding to multiple first time points in the driving scenario, determine the autonomous driving comfort evaluation score of the driving scenario.

[0077] The lateral acceleration of autonomous driving at each first time point in a driving scenario can be squared and logarithmically calculated, with the result serving as the lateral acceleration index for that first time point. Similarly, the longitudinal acceleration of autonomous driving at each first time point in a driving scenario can be squared and logarithmically calculated, with the result serving as the longitudinal acceleration index for that first time point. The rate of change of longitudinal acceleration of autonomous driving at each first time point in a driving scenario can also be squared and logarithmically calculated, with the result serving as the rate of change of longitudinal acceleration for that first time point. Finally, the yaw rate of autonomous driving at each first time point in a driving scenario can be squared and logarithmically calculated. The calculation results are used as the autonomous driving yaw rate index for each first time point in the driving scenario. Then, for each first time point, the autonomous driving lateral acceleration index, autonomous driving longitudinal acceleration index, autonomous driving longitudinal acceleration rate of change index, and autonomous driving yaw rate index are weighted and summed according to their respective weights. The sum is used as the time point evaluation score for each first time point in the driving scenario. Finally, the autonomous driving comfort evaluation score for the driving scenario is determined by combining the time point evaluation scores for multiple first time points in the driving scenario.

[0078] The first time point can be any point in time during the vehicle's operation. The time point can refer to the time point used to collect autonomous driving data of the vehicle. The interval between the time points can be the same. For example, the interval between the time points is 0.02s, that is, autonomous driving data is collected once every 0.02s.

[0079] Among them, the weights of the autonomous driving lateral acceleration index, the autonomous driving longitudinal acceleration index, the autonomous driving longitudinal acceleration change rate index, and the autonomous driving yaw rate index can be set according to requirements. For example, the weights of the autonomous driving lateral acceleration index, the autonomous driving longitudinal acceleration index, the autonomous driving longitudinal acceleration change rate index, and the autonomous driving yaw rate index are all 0.25.

[0080] In some implementations, the target time point corresponds to multiple second time points; the multiple second time points corresponding to the target time point are time points that are no later than the target time point among multiple first time points; the target time point is any one of the first time points; the aforementioned S210 may include: determining the autonomous driving lateral acceleration index corresponding to the target time point in the driving scenario based on the automatic lateral acceleration of the multiple second time points corresponding to the target time point in the driving scenario.

[0081] Accordingly, S220 may include: determining the autonomous driving longitudinal acceleration index corresponding to the target time point in the driving scenario based on the automatic longitudinal acceleration at multiple second time points corresponding to the target time point in the driving scenario;

[0082] S230 may include: determining the automatic longitudinal acceleration change rate index corresponding to the target time point in the driving scenario based on the automatic longitudinal acceleration change rate at multiple second time points corresponding to the target time point in the driving scenario;

[0083] S240 may include: determining the autonomous driving yaw rate index corresponding to the target time point in the driving scenario based on the automatic yaw rate of multiple second time points corresponding to the target time point in the driving scenario.

[0084] For each first time point, the autonomous driving lateral acceleration index, autonomous driving longitudinal acceleration index, autonomous driving longitudinal acceleration rate of change index, and autonomous driving yaw rate index corresponding to each first time point in the driving scenario can be determined by following the process described in S210-S240.

[0085] In this context, the multiple second time points corresponding to a target time point (any first time point) are first time points no later than the target time point. That is, the multiple second time points corresponding to a target time point can include first time points before the target time point and the target time point itself. For example, if autonomous driving data is collected every 0.02 seconds, the multiple second time points corresponding to the 1st second of the target time point can include the 0.94th second, the 0.96th second, the 0.98th second, and the 1st second.

[0086] Specifically, the autonomous driving lateral acceleration index, autonomous driving longitudinal acceleration index, autonomous driving longitudinal acceleration rate of change index, and autonomous driving yaw rate index corresponding to the first time point in the driving scenario can be determined according to Formula 3, as follows:

[0087]

[0088] in, The lateral acceleration index for autonomous driving at the target time point. For the longitudinal acceleration index of autonomous driving at the target time point, Jerk RMS ω represents the rate of change of longitudinal acceleration for autonomous driving at the target time point. RMS The yaw rate index for autonomous driving at the target time point. The automatic lateral acceleration at the j-th second time point corresponding to the target time point. For the automatic longitudinal acceleration at the j-th second time point corresponding to the target time point, Jerk jLet ω be the rate of change of automatic longitudinal acceleration at the j-th second time point corresponding to the target time point. j Let $\frac{j}{j}$ be the automatic yaw rate at the j-th second time point corresponding to the target time point.

[0089] For any driving scenario, after obtaining the autonomous driving lateral acceleration index, autonomous driving longitudinal acceleration index, autonomous driving longitudinal acceleration rate of change index, and autonomous driving yaw rate index at the first time point in the driving scenario, the evaluation score corresponding to the first time point in the driving scenario can be determined according to Formula 4, based on the weights of the autonomous driving lateral acceleration index, autonomous driving longitudinal acceleration index, autonomous driving longitudinal acceleration rate of change index, and autonomous driving yaw rate index, as well as the respective autonomous driving lateral acceleration index, autonomous driving longitudinal acceleration index, autonomous driving longitudinal acceleration rate of change index, and autonomous driving yaw rate index at the first time point in the driving scenario. Formula 4 is as follows:

[0090]

[0091] Where I represents the evaluation score at the first time point. C1, C2, C3, and C4 are the weights of the autonomous driving lateral acceleration index, the autonomous driving longitudinal acceleration index, the autonomous driving longitudinal acceleration rate of change index, and the autonomous driving yaw rate index, respectively. These can be set based on requirements, and this application does not impose any restrictions.

[0092] By obtaining the time-point evaluation score corresponding to the first time point in the driving scenario, and combining the time-point evaluation scores corresponding to multiple first time points in the driving scenario, the autonomous driving comfort evaluation score of the driving scenario can be determined.

[0093] In some embodiments, multiple first time points are located in multiple evaluation periods; S260 may include: for each evaluation period, taking the maximum value of the time point evaluation scores corresponding to multiple first time points in the evaluation period under the driving scenario as the time period evaluation score corresponding to the evaluation period under the driving scenario; averaging the time period evaluation scores corresponding to multiple evaluation periods under the driving scenario to obtain the autonomous driving comfort evaluation score of the driving scenario.

[0094] Generally speaking, a driving scenario involves multiple first time points, and multiple evaluation periods can be determined for these multiple first time points. Each evaluation period belongs to the driving scenario, and the first time points in different evaluation periods can be different. For example, for driving scenario A, which involves 100 first time points, 10 evaluation periods can be determined, and each evaluation period includes 10 first time points.

[0095] Generally speaking, the time period during which a driving scenario occurs in the autonomous driving process is considered as an evaluation period. For example, the driving scenario is: parking on a highway with sparse traffic flow during the day. When the vehicle completes the process of parking on a highway with sparse traffic flow during the day in an autonomous driving process, the multiple first time points involved in this process belong to the same evaluation period.

[0096] In other words, multiple first time points are determined within each evaluation period. The maximum value of the time point evaluation scores corresponding to the multiple first time points within the evaluation period is taken as the time period evaluation score for the driving scenario. Then, the average of the time period evaluation scores corresponding to the multiple evaluation periods in the driving scenario is calculated to obtain the autonomous driving comfort evaluation score for the driving scenario.

[0097] The aforementioned process for determining the autonomous driving comfort evaluation score for a driving scenario can be summarized as Formula 5, which is as follows:

[0098]

[0099] in, Max.I represents the comfort score for autonomous driving in driving scenario i. q,i Let q be the time period evaluation score for the q-th evaluation period in driving scenario i, where Q is the number of evaluation periods in driving scenario i.

[0100] In this embodiment, the autonomous driving comfort evaluation score is determined by combining the lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate at multiple time points. This avoids the situation where the accuracy of the determined autonomous driving comfort evaluation score is low due to missing data when only one time point is selected for the lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate, thus improving the accuracy of the autonomous driving comfort evaluation score.

[0101] In addition, each driving scenario corresponds to multiple evaluation periods. The autonomous driving comfort evaluation score of the driving scenario is determined by combining the evaluation scores of multiple evaluation periods. This makes the autonomous driving comfort evaluation score take into account the driving conditions of multiple evaluation periods, avoiding the situation where the autonomous driving comfort evaluation score is inaccurate due to sudden changes in the autonomous driving data during only one evaluation period. This improves the accuracy of the autonomous driving comfort evaluation score.

[0102] In one embodiment, the active driving data includes the vehicle's active driving lateral acceleration, active driving longitudinal acceleration, active driving longitudinal acceleration rate of change, and active driving yaw rate; the active driving lateral acceleration includes the active driving lateral acceleration at multiple first time points; the active driving longitudinal acceleration includes the active driving longitudinal and lateral acceleration at multiple first time points; the active driving longitudinal acceleration rate of change includes the active driving longitudinal acceleration rate of change at multiple first time points; the active driving yaw rate in the driving scenario includes the active driving yaw rate at multiple first time points; such as Figure 4 As shown, before S110, the method further includes:

[0103] S310. Based on the active driving lateral acceleration at multiple third time points in the driving scenario, determine the active driving lateral acceleration index for each of the multiple third time points in the driving scenario.

[0104] S320. Based on the longitudinal acceleration of active driving at multiple third time points in the driving scenario, determine the benchmark index of the longitudinal acceleration of active driving at each of the multiple third time points in the driving scenario.

[0105] S330. Based on the rate of change of longitudinal acceleration of active driving at multiple third time points in the driving scenario, determine the benchmark index of the rate of change of longitudinal acceleration of active driving at each of the multiple third time points in the driving scenario.

[0106] S340. Based on the active driving yaw rate at multiple third time points in the driving scenario, determine the active driving yaw rate benchmark index for each of the multiple third time points in the driving scenario.

[0107] S350. For each third time point, determine the time point benchmark score corresponding to the third time point in the driving scenario based on the weights of the active driving lateral acceleration benchmark index, the active driving longitudinal acceleration benchmark index, the active driving longitudinal acceleration rate of change benchmark index, the active driving yaw rate benchmark index, and the active driving lateral acceleration benchmark index, the active driving longitudinal acceleration benchmark index, the active driving longitudinal acceleration rate of change benchmark index, and the active driving yaw rate benchmark index for each third time point in the driving scenario.

[0108] S360 determines the comfort benchmark index for driving scenarios based on the benchmark scores of multiple third time points in the driving scenario.

[0109] The lateral acceleration of active driving at each third time point in a driving scenario can be squared and logarithmically calculated, and the result can be used as a benchmark index for the lateral acceleration of active driving at each third time point in the driving scenario. Similarly, the longitudinal acceleration of active driving at each third time point in a driving scenario can be squared and logarithmically calculated, and the result can be used as a benchmark index for the longitudinal acceleration of active driving at each third time point in the driving scenario. The rate of change of longitudinal acceleration of active driving at each third time point in a driving scenario can be squared and logarithmically calculated, and the result can be used as a benchmark index for the rate of change of longitudinal acceleration of active driving at each third time point in the driving scenario. The yaw rate of active driving at each third time point in a driving scenario can also be squared and logarithmically calculated, and the result can be used as a benchmark index for the yaw rate of active driving at each third time point in the driving scenario. The calculated results are used as the active driving yaw rate benchmark index for each third time point in the driving scenario. Then, for each third time point, the active driving lateral acceleration benchmark index, active driving longitudinal acceleration benchmark index, active driving longitudinal acceleration rate of change benchmark index, and active driving yaw rate benchmark index are weighted and summed according to their respective weights. This summation is used as the time point benchmark score for each third time point in the driving scenario. Finally, the comfort benchmark index for the driving scenario is determined by combining the time point benchmark scores for multiple third time points in the driving scenario.

[0110] The third time point can be any collection point during the vehicle's operation. The collection time point can refer to the time point used to collect the vehicle's active driving data. The interval between collection time points can be the same. For example, the interval between collection time points is 0.02s, that is, active driving data is collected once every 0.02s.

[0111] Among them, the weights of the active driving lateral acceleration benchmark index, the active driving longitudinal acceleration benchmark index, the active driving longitudinal acceleration change rate benchmark index, and the active driving yaw rate benchmark index can be set according to requirements. For example, the weights of the active driving lateral acceleration benchmark index, the active driving longitudinal acceleration benchmark index, the active driving longitudinal acceleration change rate benchmark index, and the active driving yaw rate benchmark index can all be 0.25.

[0112] In some implementations, a specified time point corresponds to multiple fourth time points; the multiple fourth time points corresponding to the specified time point are time points that are no later than the specified time point among multiple third time points; the specified time point is any one of the third time points; the aforementioned S310 may include: determining the active driving lateral acceleration benchmark index corresponding to the specified time point in the driving scenario based on the active lateral acceleration of the multiple fourth time points corresponding to the specified time point in the driving scenario.

[0113] Accordingly, S320 may include: determining the active driving longitudinal acceleration benchmark index corresponding to the specified time point in the driving scenario based on the active longitudinal acceleration at multiple fourth time points corresponding to the specified time point in the driving scenario;

[0114] S330 may include: determining the active driving longitudinal acceleration change rate benchmark index corresponding to a specified time point in a driving scenario based on the active longitudinal acceleration change rate at multiple fourth time points corresponding to a specified time point in a driving scenario;

[0115] S340 may include: determining the active driving yaw rate benchmark index corresponding to a specified time point in a driving scenario based on the active yaw rate of multiple fourth time points corresponding to a specified time point in the driving scenario.

[0116] For each third time point, the active driving lateral acceleration benchmark, active driving longitudinal acceleration benchmark, active driving longitudinal acceleration rate of change benchmark, and active driving yaw rate benchmark can be determined according to the aforementioned process S310-S340 for each third time point in the driving scenario.

[0117] In this context, the multiple fourth time points corresponding to a specified time point (any third time point) are third time points no later than the specified time point. That is, the multiple fourth time points corresponding to a specified time point can include third time points before the specified time point and the specified time point itself. For example, if active driving data is collected every 0.02 seconds, the multiple fourth time points corresponding to the specified time point 1 second can include 0.94s, 0.96s, 0.98s, and 1s.

[0118] Specifically, according to Formula 3 mentioned above, the active driving lateral acceleration benchmark, active driving longitudinal acceleration benchmark, active driving longitudinal acceleration change rate benchmark, and active driving yaw rate benchmark corresponding to the third time point in the driving scenario can be determined, which will not be elaborated here.

[0119] For any driving scenario, after obtaining the active driving lateral acceleration benchmark, active driving longitudinal acceleration benchmark, active driving longitudinal acceleration rate of change benchmark, and active driving yaw rate benchmark for the third time point in the driving scenario, the benchmark score for the third time point in the driving scenario can be determined according to Formula 4, based on the weights of the active driving lateral acceleration benchmark, active driving longitudinal acceleration benchmark, active driving longitudinal acceleration rate of change benchmark, and active driving yaw rate benchmark, as well as the respective active driving lateral acceleration benchmark, active driving longitudinal acceleration benchmark, active driving longitudinal acceleration rate of change benchmark, and active driving yaw rate benchmark for the third time point in the driving scenario. This will not be elaborated further here. The weights of the active driving lateral acceleration benchmark, active driving longitudinal acceleration benchmark, active driving longitudinal acceleration rate of change benchmark, and active driving yaw rate benchmark can be set based on requirements, and this application does not impose any limitations on them.

[0120] By obtaining the benchmark score for the third time point in a driving scenario, and combining the benchmark scores for multiple third time points in the driving scenario, the comfort benchmark index for the driving scenario can be determined.

[0121] In some embodiments, multiple third time points are located in multiple specified time periods; S360 may include: for each specified time period, taking the maximum value of the time point benchmark scores corresponding to multiple third time points within the specified time period in the driving scenario as the time period benchmark score corresponding to the specified time period in the driving scenario; averaging the time period benchmark scores corresponding to multiple specified time periods in the driving scenario to obtain the comfort benchmark index of the driving scenario.

[0122] Generally speaking, a driving scenario involves multiple third time points. Multiple specified time periods can be determined for these multiple third time points. Each specified time period belongs to the driving scenario, and the third time points in different specified time periods can be different. For example, for driving scenario A, which involves 100 third time points, 10 specified time periods can be determined, and each specified time period includes 10 third time points.

[0123] Generally speaking, the time period during which a driving scenario occurs in the process of autonomous driving is defined as a designated time period. For example, an autonomous driving scenario is: parking on a highway with high traffic density in the rain. When the vehicle autonomously completes a parking process on a highway with high traffic density in the rain, the multiple third time points involved in this process belong to the same designated time period.

[0124] In other words, multiple third time points are determined within each specified time period. The maximum value of the time point benchmark scores corresponding to the multiple third time points within the specified time period is taken as the time period benchmark score for the specified time period in the driving scenario. Then, the average of the time period benchmark scores corresponding to the multiple specified time periods in the driving scenario is calculated to obtain the comfort benchmark index for the driving scenario.

[0125] In this embodiment, the active driving comfort benchmark score is determined by combining the lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate at multiple time points. This avoids the situation where the accuracy of the determined comfort benchmark index is low due to missing data when only one time point is selected for lateral acceleration, longitudinal acceleration, rate of change of longitudinal acceleration, and yaw rate, thus improving the accuracy of the comfort benchmark index.

[0126] In addition, each driving scenario corresponds to multiple specified time periods. The comfort benchmark index of the driving scenario is determined by combining the benchmark scores of multiple specified time periods. This allows the comfort benchmark index to comprehensively consider the driving conditions of multiple specified time periods, avoiding the inaccuracy of the comfort benchmark index caused by sudden changes in the active driving data of only one specified time period, thus improving the accuracy of the comfort benchmark index.

[0127] See appendix Figure 5 , Figure 5 This illustration shows a structural block diagram of an autonomous driving comfort evaluation device according to an embodiment of this application. For use in electronic devices, the device 800 includes:

[0128] The acquisition module 810 is used to acquire autonomous driving data of the vehicle in each of multiple driving scenarios and the corresponding comfort benchmark index for each driving scenario; wherein, the comfort benchmark index is determined based on the active driving data of the driver in each driving scenario during the driving process.

[0129] The first determining module 820 is used to determine the autonomous driving comfort evaluation score for each driving scenario based on the autonomous driving data in each driving scenario.

[0130] The second determining module 830 is used to determine the autonomous driving comfort evaluation result of the vehicle based on the comfort benchmark indicators of multiple driving scenarios and the autonomous driving comfort evaluation score.

[0131] Optionally, the autonomous driving data includes the vehicle's autonomous driving lateral acceleration, autonomous driving longitudinal acceleration, autonomous driving longitudinal acceleration change rate, and autonomous driving yaw rate; the first determining module 820 is further configured to determine the autonomous driving comfort evaluation score of the driving scenario based on the autonomous driving lateral acceleration, autonomous driving longitudinal acceleration, autonomous driving longitudinal acceleration change rate, and autonomous driving yaw rate in the driving scenario.

[0132] Optionally, the autonomous driving lateral acceleration includes the autonomous driving lateral acceleration at multiple first time points; the autonomous driving longitudinal acceleration includes the autonomous driving longitudinal and lateral acceleration at multiple first time points; the autonomous driving longitudinal acceleration change rate includes the autonomous driving longitudinal acceleration change rate at multiple first time points; the autonomous driving yaw rate in the driving scenario includes the autonomous driving yaw rate at multiple first time points; the first determining module 820 is further configured to determine the autonomous driving lateral acceleration index at multiple first time points in the driving scenario based on the autonomous driving lateral acceleration at multiple first time points in the driving scenario; determine the autonomous driving longitudinal acceleration index at multiple first time points in the driving scenario based on the autonomous driving longitudinal acceleration at multiple first time points in the driving scenario; and determine the autonomous driving yaw rate at multiple first time points in the driving scenario based on the autonomous driving longitudinal acceleration change rate. The system defines the longitudinal acceleration change rate index for autonomous driving at multiple first time points in a given driving scenario; it also determines the yaw rate index for autonomous driving at each of these first time points based on the yaw rate index; for each first time point, it determines the corresponding time-point evaluation score based on the weights of the autonomous driving lateral acceleration index, longitudinal acceleration index, longitudinal acceleration change rate index, and yaw rate index, as well as the respective autonomous driving lateral acceleration index, longitudinal acceleration index, longitudinal acceleration change rate index, and yaw rate index at each first time point in the driving scenario; and finally, it determines the autonomous driving comfort evaluation score for the driving scenario based on the time-point evaluation scores corresponding to the multiple first time points in the driving scenario.

[0133] Optionally, multiple first time points are located in multiple evaluation periods; the first determining module 820 is further configured to, for each evaluation period, take the maximum value of the time point evaluation scores corresponding to multiple first time points in the evaluation period under the driving scenario as the time period evaluation score corresponding to the evaluation period under the driving scenario; and average the time period evaluation scores corresponding to multiple evaluation periods under the driving scenario to obtain the autonomous driving comfort evaluation score of the driving scenario.

[0134] Optionally, the target time point corresponds to multiple second time points; the multiple second time points corresponding to the target time point are time points that are no later than the target time point among multiple first time points; the target time point is any one of the first time points; the first determining module 820 is further used to determine the autonomous driving lateral acceleration index corresponding to the target time point in the driving scenario based on the automatic lateral acceleration of the multiple second time points corresponding to the target time point in the driving scenario.

[0135] Optionally, the second determining module 830 is further configured to determine the score rate of each driving scenario based on the comfort benchmark index and the autonomous driving comfort evaluation score for each driving scenario; obtain the scenario weights of each of the multiple driving scenarios; the scenario weights of the driving scenarios are used to indicate the frequency of occurrence of the driving scenario in the multiple driving scenarios; and determine the autonomous driving comfort evaluation result of the vehicle based on the score rates and scenario weights of each of the multiple driving scenarios.

[0136] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0137] Furthermore, the functions in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module.

[0138] Furthermore, the functions in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module.

[0139] Please refer to Figure 6 This document illustrates a structural block diagram of an electronic device 500 according to an embodiment of this application. The electronic device 500 can be a smartphone, tablet computer, e-reader, vehicle, or other electronic device capable of running applications. The electronic device 500 in this application may include one or more of the following components: a processor 510, a memory 520, and one or more applications. One or more applications may be stored in the memory 520 and configured to be executed by one or more processors 510, and the one or more applications are configured to perform the methods described in the foregoing method embodiments.

[0140] Processor 510 may include one or more processing cores. Processor 510 connects to various parts within the electronic device 500 using various interfaces and lines, and performs various functions and processes data of the electronic device 500 by running or executing instructions, programs, code sets, or instruction sets stored in memory 520, and by calling data stored in memory 520. Optionally, processor 510 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 510 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 510 and may be implemented separately using a communication chip.

[0141] The memory 520 may include random access memory (RAM) or read-only memory (ROM). The memory 520 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 520 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created by the electronic device 500 during use (such as phonebook data, audio and video data, chat log data, etc.).

[0142] Furthermore, the functions in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module.

[0143] On the other hand, this application also provides a computer-readable storage medium storing program code that can be called by a processor to execute the methods described in the above method embodiments.

[0144] Computer-readable storage media can be electronic storage devices such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or a cluster of ROMs. Optionally, computer-readable storage media include non-transitory computer-readable storage media. The computer-readable storage medium has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code can be compressed, for example, in a suitable form.

[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. An automatic driving comfort evaluation method characterized by comprising: The method comprises: obtaining automatic driving data of a vehicle in each of a plurality of driving scenes and a comfort reference index corresponding to each of the driving scenes; wherein the comfort reference index is determined according to active driving data in each of the driving scenes during driving of the vehicle by a driver; determining an automatic driving comfort evaluation score of each of the driving scenes according to the automatic driving data in each of the driving scenes; determining an automatic driving comfort evaluation result of the vehicle according to the comfort reference index and the automatic driving comfort evaluation score of the plurality of driving scenes.

2. The method of claim 1, wherein, The automatic driving data comprises automatic driving lateral acceleration, automatic driving longitudinal acceleration, automatic driving longitudinal acceleration change rate and automatic driving yaw rate of the vehicle; The determination of the automatic driving comfort evaluation score of each of the driving scenes according to the automatic driving data in each of the driving scenes comprises: determining the automatic driving comfort evaluation score of the driving scene according to the automatic driving lateral acceleration in the driving scene, the automatic driving longitudinal acceleration in the driving scene, the automatic driving longitudinal acceleration change rate in the driving scene and the automatic driving yaw rate in the driving scene.

3. The method of claim 2, wherein, The automatic driving lateral acceleration comprises automatic driving lateral acceleration at a plurality of first time points; the automatic driving longitudinal acceleration comprises automatic driving longitudinal acceleration at a plurality of first time points; the automatic driving longitudinal acceleration change rate comprises automatic driving longitudinal acceleration change rate at a plurality of first time points; and the automatic driving yaw rate in the driving scene comprises automatic driving yaw rate at a plurality of first time points; The determination of the automatic driving comfort evaluation score of the driving scene according to the automatic driving lateral acceleration in the driving scene, the automatic driving longitudinal acceleration in the driving scene, the automatic driving longitudinal acceleration change rate in the driving scene and the automatic driving yaw rate in the driving scene comprises: determining an automatic driving lateral acceleration index of each of the plurality of first time points in the driving scene according to the automatic driving lateral acceleration of the plurality of first time points in the driving scene; determining an automatic driving longitudinal acceleration index of each of the plurality of first time points in the driving scene according to the automatic driving longitudinal acceleration of the plurality of first time points in the driving scene; determining an automatic driving longitudinal acceleration change rate index of each of the plurality of first time points in the driving scene according to the automatic driving longitudinal acceleration change rate of the plurality of first time points in the driving scene; determining an automatic driving yaw rate index of each of the plurality of first time points in the driving scene according to the automatic driving yaw rate of the plurality of first time points in the driving scene; For each of the first time points, a time point evaluation score corresponding to the first time point in the driving scene is determined according to the automatic driving lateral acceleration index weight, the automatic driving longitudinal acceleration index weight, the automatic driving longitudinal acceleration change rate index weight, the automatic driving yaw rate index weight, and the respective automatic driving lateral acceleration index, the automatic driving longitudinal acceleration index, the automatic driving longitudinal acceleration change rate index, and the automatic driving yaw rate index of the first time point in the driving scene. An automatic driving comfort evaluation score of the driving scene is determined based on the time point evaluation scores corresponding to the plurality of first time points in the driving scene.

4. The method of claim 3, wherein, The plurality of first time points are located in a plurality of evaluation periods. The automatic driving comfort evaluation score of the driving scene is determined based on the time point evaluation scores corresponding to the plurality of first time points in the driving scene, including: For each of the evaluation periods, a period evaluation score corresponding to the evaluation period in the driving scene is determined as a maximum value of the time point evaluation scores corresponding to the plurality of first time points in the evaluation period in the driving scene. The automatic driving comfort evaluation score of the driving scene is obtained by averaging the period evaluation scores corresponding to the plurality of evaluation periods in the driving scene.

5. The method of claim 3, wherein, A plurality of second time points correspond to a target time point; the plurality of second time points corresponding to the target time point are time points in the plurality of first time points that are not later than the target time point; and the target time point is any one of the first time points. The automatic driving lateral acceleration index of the driving scene is determined according to the automatic driving lateral acceleration of the plurality of first time points in the driving scene, including: The automatic driving lateral acceleration index of the driving scene corresponding to the target time point is determined according to the automatic lateral acceleration of the plurality of second time points corresponding to the target time point in the driving scene.

6. The method of claim 1, wherein, The automatic driving comfort evaluation result of the vehicle is determined according to the comfort reference index and the automatic driving comfort evaluation score of the plurality of driving scenes, including: A score rate of each driving scene is determined according to the comfort reference index and the automatic driving comfort evaluation score of each driving scene. A scene weight of each driving scene is obtained; the scene weight of the driving scene is used to indicate the frequency of occurrence of the driving scene in the plurality of driving scenes. The automatic driving comfort evaluation result of the vehicle is determined according to the score rate and the scene weight of each driving scene.

7. The method according to any one of claims 1 to 6, characterized in that, The driving scene is used to indicate at least one of light, traffic flow density, road type, and driving behavior at a position where the vehicle travels.

8. An automatic driving comfort level evaluation device characterized by comprising: The device includes: An acquisition module is configured to acquire automatic driving data of a vehicle in each of a plurality of driving scenes and a comfort reference index corresponding to each of the driving scenes; wherein the comfort reference index is determined according to active driving data in each of the driving scenes during driving of the vehicle by a driver. The first determining module is configured to determine an autonomous driving comfort evaluation score of each driving scene according to the autonomous driving data in each driving scene. The second determining module is configured to determine an autonomous driving comfort evaluation result of the vehicle according to the comfort benchmark index and the autonomous driving comfort evaluation score of the plurality of driving scenes.

9. An electronic device, comprising: The computer program product comprises: one or more processors; a memory; one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores processor-executable program code, and the processor-executable program code, when executed by the processor, causes the processor to execute the method according to any one of claims 1-7.

11. A computer program product, characterised in that, The computer readable instructions, when executed by the processor, implement the method according to any one of claims 1-7.

Images