Single index and performance evaluation method and system for longitudinal driving of intelligent automobile

Abstract

The invention discloses a single index and performance evaluation method and system for longitudinal driving of an intelligent automobile, and the method comprises the steps: obtaining a certain evaluation index for the longitudinal performance of the automobile for multiple times under the same scene and the same working condition, and obtaining the driving data of a mature driver, a beginner driver and the intelligent automobile; and respectively determining the driving characteristic probability distribution of the mature driver, the beginner driver and the energy automobile about the evaluation index by respectively carrying out probability statistical analysis on the driving data corresponding to the mature driver, the beginner driver and the energy automobile. And determining a high-score evaluation standard and a performance basic standard for calculating an index score corresponding to the evaluation index according to the driving characteristic probability distribution of the mature driver and the beginner driver about the evaluation index. And finally, based on the obtained high-score evaluation standard and the performance basic standard, according to the driving characteristic probability distribution of the intelligent automobile, quantitatively evaluating a single index score of the intelligent automobile about the evaluation index.

Description

Technical Field

[0001] The present invention relates to the technical field of computer-aided design of vehicles, and in particular to a single indicator, performance evaluation method and system for longitudinal driving of an intelligent vehicle. Background Art

[0002] Forward longitudinal driving control is the most basic capability of smart cars. At present, the main way to test and evaluate the driving performance of smart cars is in dedicated smart connected car test sites, open roads or vehicle-in-the-loop simulation. Testers generally conduct a comprehensive evaluation of the autonomous driving level of smart cars by setting up typical test scenarios and test conditions, such as deceleration conditions, slow driving conditions, emergency conditions, cut-in / cut-out, high-speed following, stop-and-go driving and other typical test conditions. The test evaluation stays at the "point" of specific conditions, and the evaluation results are scientific and reasonable.

[0003] However, the evaluation results of the driving performance of the autonomous driving system are mainly reflected in the functional aspects, and fail to fully reflect the overall performance level of the system. Moreover, the driving experience of the driving system is mainly presented through subjective evaluation. The test results are not quantitative enough, and subjective evaluation has high professional requirements for evaluators. The stability and consistency of the evaluation results are easily affected by factors such as the level and status of the evaluators. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention proposes a single indicator, performance evaluation method and system for the longitudinal driving of an intelligent vehicle, which can objectively and quantitatively evaluate the longitudinal driving performance of an intelligent vehicle. The specific technical solution is as follows:

[0005] In a first aspect, a method for evaluating a single indicator of longitudinal driving of an intelligent vehicle is provided. In a first implementable manner of the first aspect, the method includes:

[0006] Obtain multiple sets of driving data on evaluation indicators for experienced drivers, novice drivers, and smart cars under the same test scenarios and working conditions;

[0007] By performing statistical probability analysis on the corresponding driving data, respectively determining the driving characteristic probability distribution of the mature driver, the novice driver and the intelligent car with respect to the evaluation index;

[0008] Determine the high score evaluation standard and the basic performance standard corresponding to the evaluation index according to the characteristic values ​​corresponding to the driving characteristic probability distributions corresponding to the mature driver and the novice driver respectively;

[0009] Based on the high-score evaluation criteria and the basic performance criteria, and according to the probability distribution of the driving characteristics of the smart car, the individual indicator scores of the smart car with respect to the evaluation indicators are calculated.

[0010] In combination with the first implementable manner of the first aspect, in a second implementable manner of the first aspect, obtaining driving data on evaluation indicators of a mature driver, a novice driver, and an intelligent vehicle under the same test scenario and the same working conditions includes:

[0011] Obtain multiple sets of vehicle driving data for experienced drivers, novice drivers, and smart cars under the same test scenario;

[0012] The vehicle driving data corresponding to the mature driver, the novice driver and the smart car are clustered respectively to determine multiple groups of driving data corresponding to the mature driver, the novice driver and the smart car under different working conditions.

[0013] In combination with the first implementable method of the first aspect, in a third implementable method of the first aspect, the high-score evaluation criteria include the mean value and variance corresponding to the driving characteristic probability distribution corresponding to mature drivers and their corresponding score rate, and the basic performance criteria include the mean value and variance corresponding to the driving characteristic probability distribution corresponding to novice drivers and their corresponding score rate.

[0014] In combination with the first implementable manner of the first aspect, in a fourth implementable manner of the first aspect, calculating the single indicator score of the smart car with respect to the evaluation indicator includes:

[0015]

[0016] Among them, E i , σ i are the median and variance of the probability distribution of driving characteristics of intelligent vehicles with respect to evaluation index i, E bi , are the average values ​​of the probability distribution of driving characteristics corresponding to novice drivers and their corresponding score rates, E gi , σ gi , S σgi are the mean value, variance and corresponding score rate of the driving characteristics probability distribution corresponding to mature drivers, D JSi It is the JS discreteness of the probability distribution of driving characteristics and high performance indicators of smart cars.

[0017] In a second aspect, a method for evaluating the longitudinal driving performance of an intelligent vehicle is provided, comprising:

[0018] Using the intelligent vehicle longitudinal driving single index evaluation method as described in any one of the first to fourth possible implementations of the first aspect, calculating the single index scores of the intelligent vehicle for different evaluation indicators;

[0019] According to the individual indicator scores and weights corresponding to each evaluation indicator at the next level, the indicator scores corresponding to each evaluation indicator at the previous level are calculated step by step with weighted calculations, and finally the comprehensive score of the smart car is obtained.

[0020] In a third aspect, a method for evaluating the longitudinal driving performance of an intelligent vehicle is provided, comprising:

[0021] Obtain multiple sets of vehicle driving data for experienced drivers, novice drivers, and smart cars in different test scenarios;

[0022] The intelligent vehicle longitudinal driving performance evaluation method as described in the second aspect is adopted to determine the comprehensive score of the intelligent vehicle under different test scenarios and different working conditions.

[0023] In a fourth aspect, a single indicator evaluation system for longitudinal driving of an intelligent vehicle is provided, comprising:

[0024] An acquisition module is configured to respectively acquire multiple groups of driving data on evaluation indicators of a mature driver, a novice driver, and an intelligent vehicle under the same test scenario and the same working conditions;

[0025] A statistical module configured to determine the driving characteristic probability distribution of the mature driver, the novice driver and the intelligent car with respect to the evaluation index by performing statistical probability analysis on the corresponding driving data;

[0026] A standard module is configured to determine the high-score evaluation standard and the basic performance standard corresponding to the evaluation index according to the characteristic values ​​corresponding to the driving characteristic probability distributions corresponding to the mature driver and the novice driver respectively;

[0027] The evaluation module is configured to calculate the single indicator score of the smart car with respect to the evaluation index based on the high-score evaluation standard and the basic performance standard and according to the probability distribution of the driving characteristics of the smart car.

[0028] In a fifth aspect, a system for evaluating the longitudinal driving performance of an intelligent vehicle is provided, comprising:

[0029] A single evaluation module, configured to calculate single indicator scores of the smart car for different evaluation indicators by using the smart car longitudinal driving single indicator evaluation method as described in any one of the first to fourth implementation modes of the first aspect;

[0030] The comprehensive evaluation module is configured to calculate the indicator scores corresponding to the evaluation indicators of the previous level step by step according to the individual indicator scores and weights corresponding to the evaluation indicators of the next level, and finally obtain the comprehensive score of the smart car.

[0031] In a sixth aspect, a system for evaluating the longitudinal driving performance of an intelligent vehicle is provided, comprising:

[0032] A driving data module configured to obtain multiple sets of vehicle driving data of experienced drivers, novice drivers and smart cars under different test scenarios and different working conditions;

[0033] The performance evaluation module is configured to adopt the intelligent vehicle longitudinal driving performance evaluation method as described in the second aspect to determine the comprehensive score of the intelligent vehicle under different test scenarios and different working conditions.

[0034] Beneficial effects: By using the single index, performance evaluation method and system of the longitudinal driving of the intelligent vehicle of the present invention, the driving data of mature drivers and novice drivers obtained by multiple tests can be statistically analyzed to determine the driving characteristic probability distribution corresponding to mature drivers and novice drivers, and thereby determine the high-score evaluation standards and basic performance standards corresponding to various evaluation indicators for evaluating the longitudinal driving performance of the intelligent vehicle. Then, by performing statistical probability distribution on the driving data of the intelligent vehicle obtained by multiple tests, the driving characteristic probability distribution of the intelligent vehicle with respect to various evaluation indicators can be determined, and the performance of the intelligent vehicle with respect to various evaluation indicators can be quantitatively evaluated by combining the previously determined high-score evaluation standards and basic performance standards. Finally, the performance of the intelligent vehicle can be comprehensively and objectively evaluated by combining the performance corresponding to all evaluation indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific implementation of the present invention, the following will briefly introduce the drawings required for use in the specific implementation. In all the drawings, each element or part is not necessarily drawn according to the actual scale.

[0036] Figure 1 A flow chart of a method for evaluating a single index of longitudinal driving of an intelligent vehicle provided by an embodiment of the present invention;

[0037] Figure 2 A flow chart of a method for evaluating the longitudinal driving performance of an intelligent vehicle provided by an embodiment of the present invention;

[0038] Figure 3 A flow chart of a method for evaluating the longitudinal driving performance of an intelligent vehicle provided by an embodiment of the present invention;

[0039] Figure 4 A system block diagram of a single index evaluation system for longitudinal driving of an intelligent vehicle provided by an embodiment of the present invention;

[0040] Figure 5 A system block diagram of a smart car longitudinal driving performance evaluation system provided by an embodiment of the present invention;

[0041] Figure 6 This is a system block diagram of a smart car longitudinal driving performance evaluation system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0043] It should be understood that the essence of the longitudinal driving performance of smart cars is speed control, while the distance control, comfortable driving, etc. are the performance of driving requirements in different scenarios and working conditions. Therefore, in this embodiment, the evaluation of the longitudinal driving performance of the car can be divided into four dimensions: distance control, comfortable driving, comprehensive energy consumption and traffic efficiency.

[0044] The evaluation indicators for vehicle-to-vehicle distance control include system response time, stopping distance, and stable vehicle-to-vehicle distance at each speed range. The evaluation indicators for comfortable driving include the vehicle's system response time, acceleration, and jerk in test scenarios such as front vehicle acceleration, front vehicle deceleration, front vehicle cut-in, front vehicle cut-out, and curve driving.

[0045] When evaluating the longitudinal driving performance of a smart car, each single evaluation indicator may be scored respectively to determine the single indicator score corresponding to each single evaluation indicator, and then the longitudinal driving performance of the smart car may be comprehensively evaluated based on the single indicator scores corresponding to multiple single evaluation indicators.

[0046] like Figure 1 The flowchart of the single index evaluation method for longitudinal driving of an intelligent vehicle shown in FIG. 1 includes:

[0047] Step 1, obtaining multiple sets of driving data on evaluation indicators of experienced drivers, novice drivers and smart cars under the same test scenario and the same working conditions;

[0048] Step 2: Determine the driving characteristic probability distribution of the mature driver, the novice driver and the intelligent car with respect to the evaluation index by performing statistical probability analysis on the corresponding driving data;

[0049] Step 3, determining the high-score evaluation standard and the basic performance standard corresponding to the evaluation index according to the characteristic values ​​corresponding to the driving characteristic probability distributions corresponding to the mature driver and the novice driver respectively;

[0050] Step 4: Based on the high-score evaluation criteria and the basic performance criteria, and according to the driving characteristic probability distribution of the smart car, calculate the single indicator score of the smart car with respect to the evaluation indicator.

[0051] Specifically, first, the driving data of mature drivers, novice drivers and smart cars can be obtained by testing a certain evaluation index of vehicle longitudinal performance multiple times under the same scene and the same working conditions. Then, by performing probability statistical analysis on the driving data corresponding to mature drivers, novice drivers and smart cars, the probability distribution of driving characteristics of mature drivers, novice drivers and smart cars with respect to the evaluation index can be determined respectively.

[0052] After that, the high-score evaluation standard and basic performance standard used to calculate the index score corresponding to the evaluation index can be determined based on the probability distribution of the driving characteristics of mature drivers and novice drivers for the evaluation index. Finally, based on the obtained high-score evaluation standard and basic performance standard, the single index score of the smart car for the evaluation index can be quantitatively evaluated according to the probability distribution of the driving characteristics of the smart car. Avoid the influence of factors such as the level and status of the evaluator on the stability and consistency of the evaluation results of the longitudinal driving performance of the smart car.

[0053] In this embodiment, optionally, in step 1, driving data of the mature driver, the novice driver and the smart car on the evaluation index under the same test scenario and the same working condition are obtained, including:

[0054] Obtain multiple sets of vehicle driving data for experienced drivers, novice drivers, and smart cars under the same test scenario;

[0055] The vehicle driving data corresponding to the mature driver, the novice driver and the smart car are clustered respectively to determine multiple groups of driving data corresponding to the mature driver, the novice driver and the smart car under different working conditions.

[0056] Specifically, the vehicle driving data of mature and experienced drivers in the test scenario can be collected through the vehicle road test system collection system. The vehicle road test system includes the environmental perception measurement system (such as the perception and measurement system of the front target, the adjacent lane target, and the rear target), the vehicle dynamic parameter measurement system (such as speed, longitudinal acceleration / deceleration, lateral acceleration, time distance between vehicles, etc.); the laboratory vehicle-in-the-loop test system includes the front target simulation system (such as video simulation / injection, millimeter wave radar simulation, etc.), chassis dynamometer, continuous test scenario library, etc.

[0057] The collected vehicle driving data includes data corresponding to evaluation indicators such as headway, acceleration / deceleration, emergency lane change / braking timing, etc. It also includes driving data of mature drivers under different working conditions. By performing cluster analysis on all collected vehicle driving data, the driving data corresponding to mature drivers under different working conditions can be determined. By testing in the same test scenario multiple times, multiple sets of driving data corresponding to each evaluation indicator of mature drivers in the same test scenario and different working conditions can be obtained. From this, multiple sets of driving data corresponding to a certain evaluation indicator of mature drivers can be extracted.

[0058] Similarly, the same method can be used to obtain multiple sets of driving data of novice drivers and smart cars in the same scene and different working conditions. Through working condition matching, multiple sets of driving data corresponding to various evaluation indicators of mature drivers, novice drivers and smart cars in the same scene and the same working conditions can be determined for subsequent evaluation of the driving performance of smart cars.

[0059] In this embodiment, optionally, in step 3, the high-score evaluation criteria include the mean value and variance corresponding to the driving characteristic probability distribution corresponding to mature drivers and their corresponding score rate, and the basic performance criteria include the mean value and variance corresponding to the driving characteristic probability distribution corresponding to novice drivers and their corresponding score rate.

[0060] Specifically, after obtaining multiple sets of driving data corresponding to a certain evaluation index of mature drivers, statistical probability analysis can be performed on the obtained multiple sets of driving data to obtain the driving characteristics probability distribution of mature drivers for the evaluation index. Then, the scoring rate corresponding to the mean value and variance of the driving characteristics probability distribution is manually set, and finally, the high-score evaluation standard for evaluating the longitudinal driving performance of smart cars is composed of the mean value and variance of the driving characteristics probability distribution of mature drivers for the evaluation index, and the scoring rate corresponding to the mean value and variance. Similarly, the basic performance standard for evaluating the longitudinal driving performance of smart cars is composed of the mean value of the driving characteristics probability distribution of novice drivers for the evaluation index and the scoring rate corresponding to the mean value. Finally, the mean value and variance of the driving characteristics probability distribution of the smart car for the evaluation index are compared with the basic performance standard and the high-score evaluation standard, respectively, so as to quantitatively evaluate the single indicator score of the evaluation index of the smart car under the same test scenario and the same working conditions.

[0061] In this embodiment, optionally, calculating the score of a single indicator of the smart car with respect to the evaluation indicator includes:

[0062]

[0063] Among them, E i , σ iare the median and variance of the probability distribution of driving characteristics of intelligent vehicles with respect to evaluation index i, E bi , are the average values ​​of the probability distribution of driving characteristics corresponding to novice drivers and their corresponding score rates, E gi , σ gi , S σgi are the mean value, variance and corresponding score rate of the driving characteristics probability distribution corresponding to mature drivers, D JSi It is the JS discreteness of the probability distribution of driving characteristics and high performance indicators of smart cars.

[0064]

[0065] like Figure 2 The flowchart of the method for evaluating the longitudinal driving performance of an intelligent vehicle shown in FIG. 1 includes:

[0066] Step S1, using the above-mentioned intelligent vehicle longitudinal driving single index evaluation method to calculate the single index scores of the intelligent vehicle with respect to different evaluation indexes;

[0067] Step S2: According to the individual indicator scores and weights corresponding to the evaluation indicators of the next level, the indicator scores corresponding to the evaluation indicators of the previous level are weightedly calculated level by level, and finally the comprehensive score of the smart car is obtained.

[0068] Specifically, first, multiple sets of driving data on various evaluation indicators of mature drivers, novice drivers and smart cars under the same test scenarios and the same working conditions can be collected. And the above-mentioned smart car longitudinal driving single indicator evaluation method is used to determine the single indicator score of the smart car for each evaluation indicator. Then, each evaluation indicator can be graded according to the evaluation system, and the indicator score of the upper-level indicator can be weightedly calculated according to the single indicator score and weight corresponding to each evaluation indicator. By performing weighted calculations step by step, a comprehensive score of the longitudinal driving performance of the smart car can be obtained. Thereby achieving a comprehensive and objective quantitative evaluation of the longitudinal driving performance of the smart car. The specific calculation formula for the indicator score is as follows:

[0069]

[0070] Among them, S t Score the indicator of the previous level indicator, S i+1 and ε i+1 It is the indicator score and weight of each evaluation indicator at the next level corresponding to the indicator at the previous level.

[0071] The evaluation system is as follows:

[0072]

[0073]

[0074] For example, the above-mentioned single indicator evaluation method for longitudinal driving of intelligent vehicles can be first used to calculate the single indicator scores of the intelligent vehicle regarding evaluation indicators such as parking distance, system response time when the front vehicle accelerates, vehicle longitudinal acceleration, vehicle jerk, system response time when the front vehicle decelerates, vehicle longitudinal acceleration, and vehicle jerk.

[0075] Then, the indicator score of the second-level indicator to which the third-level indicator belongs can be calculated based on the corresponding third-level indicator. For example, the indicator score corresponding to the acceleration of the preceding vehicle can be calculated based on the individual indicator scores and weights corresponding to the system response time, vehicle longitudinal acceleration, and vehicle jerk under the acceleration of the preceding vehicle.

[0076] Afterwards, the index score of the first-level index to which the second-level index belongs can be calculated based on the index score of the corresponding second-level index. For example, the index score of the comfortable driving index can be calculated based on the index scores and weights corresponding to the acceleration of the front vehicle, the deceleration of the front vehicle, the cut-in of the front vehicle, the cut-out of the front vehicle, and the driving on a curve. For the second-level index without a third-level evaluation index, the above-mentioned single index evaluation method for longitudinal driving of intelligent vehicles can be directly used to calculate the corresponding index score. For example, based on the single index scores and weights corresponding to the parking spacing and the stable following time distance, the index score corresponding to the vehicle distance control index can be obtained by weighted calculation.

[0077] Finally, the comprehensive score of the longitudinal driving performance of the smart car is calculated based on the corresponding indicator scores and weights of all the first-level indicators. For example, the comprehensive score of the longitudinal driving performance of the smart car is calculated based on the corresponding indicator scores and weights of comfortable driving, vehicle distance control, comprehensive energy consumption and traffic efficiency.

[0078] like Figure 3 The flowchart of the method for evaluating the longitudinal driving performance of an intelligent vehicle is shown, and the evaluation method includes:

[0079] Step D1, obtaining multiple groups of vehicle driving data of experienced drivers, novice drivers and smart cars under different test scenarios;

[0080] Step D2: using the above-mentioned smart car longitudinal driving performance evaluation method to determine the comprehensive score of the smart car under different test scenarios and different working conditions.

[0081] Specifically, first, multiple sets of vehicle driving data of mature drivers, novice drivers and smart cars in different test scenarios can be obtained. Then, all the obtained vehicle driving data are clustered to determine the data sets corresponding to different test scenarios and different working conditions, and the data sets include multiple sets of driving data corresponding to mature drivers, novice drivers and smart cars. Then, the above-mentioned smart car longitudinal driving performance evaluation method is used to calculate the corresponding comprehensive scores according to the corresponding data sets in different scenarios and different working conditions. In this way, the longitudinal driving performance of smart cars in different scenarios and under different working conditions can be comprehensively and objectively quantitatively evaluated.

[0082] like Figure 4 The system block diagram of the intelligent vehicle longitudinal driving single index evaluation system shown in FIG. 1 includes:

[0083] An acquisition module is configured to respectively acquire multiple groups of driving data on evaluation indicators of a mature driver, a novice driver, and an intelligent vehicle under the same test scenario and the same working conditions;

[0084] A statistical module configured to determine the driving characteristic probability distribution of the mature driver, the novice driver and the intelligent car with respect to the evaluation index by performing statistical probability analysis on the corresponding driving data;

[0085] A standard module is configured to determine the high-score evaluation standard and the basic performance standard corresponding to the evaluation index according to the characteristic values ​​corresponding to the driving characteristic probability distributions corresponding to the mature driver and the novice driver respectively;

[0086] The evaluation module is configured to calculate the single indicator score of the smart car with respect to the evaluation index based on the high-score evaluation standard and the basic performance standard and according to the probability distribution of the driving characteristics of the smart car.

[0087] Specifically, the evaluation system includes an acquisition module, a statistical module, a standard module and an evaluation module. Among them, the acquisition module can obtain the driving data of mature drivers, novice drivers and smart cars by testing a certain evaluation index of vehicle longitudinal performance multiple times under the same scene and the same working conditions. The statistical module can determine the driving characteristic probability distribution of mature drivers, novice drivers and smart cars with respect to the evaluation index by performing probability statistical analysis on the driving data corresponding to mature drivers, novice drivers and smart cars respectively.

[0088] The standard module can determine the high-score evaluation standard and basic performance standard for calculating the index score corresponding to the evaluation index based on the driving characteristics probability distribution of mature drivers and novice drivers for the evaluation index. Based on the obtained high-score evaluation standard and basic performance standard, the evaluation module can quantitatively evaluate the single index score of the smart car for the evaluation index according to the driving characteristics probability distribution of the smart car. Avoid the influence of factors such as the level and status of the evaluators on the stability and consistency of the evaluation results of the longitudinal driving performance of the smart car.

[0089] like Figure 5 The system block diagram of the intelligent vehicle longitudinal driving performance evaluation system shown in FIG. 1 includes:

[0090] A single evaluation module is configured to use the above-mentioned intelligent vehicle longitudinal driving single indicator evaluation method to calculate the single indicator scores of the intelligent vehicle with respect to different evaluation indicators;

[0091] The comprehensive evaluation module is configured to calculate the indicator scores corresponding to the evaluation indicators of the previous level step by step according to the individual indicator scores and weights corresponding to the evaluation indicators of the next level, and finally obtain the comprehensive score of the smart car.

[0092] Specifically, the evaluation system includes a single evaluation module and a comprehensive evaluation module. Among them, the single evaluation module can collect multiple sets of driving data on various evaluation indicators for mature drivers, novice drivers and smart cars under the same test scenario and the same working conditions. And the above-mentioned smart car longitudinal driving single indicator evaluation method is used to determine the single indicator score of the smart car for each evaluation indicator. The comprehensive evaluation module can classify each evaluation indicator according to the evaluation system, and according to the single indicator score and weight corresponding to each evaluation indicator, weightedly calculate the indicator score of the upper level indicator. In this way, the comprehensive score of the longitudinal driving performance of the smart car can be obtained by weighted calculation step by step. Thereby achieving a comprehensive and objective quantitative evaluation of the longitudinal driving performance of the smart car.

[0093] like Figure 6 The system block diagram of the intelligent vehicle longitudinal driving performance evaluation system shown in FIG. 1 includes:

[0094] A driving data module configured to obtain multiple sets of vehicle driving data of experienced drivers, novice drivers and smart cars under different test scenarios and different working conditions;

[0095] The performance evaluation module is configured to adopt the above-mentioned intelligent vehicle longitudinal driving performance evaluation method to determine the comprehensive score of the intelligent vehicle under different test scenarios and different working conditions.

[0096] Specifically, the evaluation system includes a driving data module and a performance evaluation module. Among them, the driving data module can obtain multiple sets of vehicle driving data of mature drivers, novice drivers and smart cars under different test scenarios. And cluster all the acquired vehicle driving data to determine the data sets corresponding to different test scenarios and different working conditions, and the data sets include multiple sets of driving data corresponding to mature drivers, novice drivers and smart cars. The performance evaluation module can adopt the above-mentioned smart car longitudinal driving performance evaluation method, and calculate the corresponding comprehensive score according to the corresponding data sets under different scenarios and different working conditions. Thereby comprehensively and objectively quantifying and evaluating the longitudinal driving performance of smart cars in different scenarios and under public conditions.

[0097] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for evaluating a single index of longitudinal driving of an intelligent vehicle, characterized in that: include: Obtain multiple sets of driving data on evaluation indicators for experienced drivers, novice drivers, and smart cars under the same test scenarios and working conditions; By performing statistical probability analysis on the corresponding driving data, respectively determining the driving characteristic probability distribution of the mature driver, the novice driver and the intelligent car with respect to the evaluation index; Determine the high score evaluation standard and the basic performance standard corresponding to the evaluation index according to the characteristic values ​​corresponding to the driving characteristic probability distributions corresponding to the mature driver and the novice driver respectively; Based on the high-score evaluation criteria and the basic performance criteria, and according to the probability distribution of the driving characteristics of the smart car, the individual indicator scores of the smart car with respect to the evaluation indicators are calculated.

2. The method for evaluating a single index of longitudinal driving of an intelligent vehicle according to claim 1, characterized in that: Obtain driving data on evaluation indicators for experienced drivers, novice drivers, and smart cars under the same test scenarios and conditions, including: Obtain multiple sets of vehicle driving data for experienced drivers, novice drivers, and smart cars under the same test scenario; The vehicle driving data corresponding to the mature driver, the novice driver and the smart car are clustered respectively to determine multiple groups of driving data corresponding to the mature driver, the novice driver and the smart car under different working conditions.

3. The method for evaluating a single index of longitudinal driving of an intelligent vehicle according to claim 1, characterized in that: The high score evaluation criteria include the mean value and variance corresponding to the driving characteristic probability distribution corresponding to the mature driver and the corresponding score rate, and the basic performance criteria include the mean value and the corresponding score rate corresponding to the driving characteristic probability distribution corresponding to the novice driver.

4. The method for evaluating a single index of longitudinal driving of an intelligent vehicle according to claim 1, characterized in that: Calculating the individual indicator scores of the smart car with respect to the evaluation indicators includes: Among them, E i , σ i are the median and variance of the probability distribution of driving characteristics of intelligent vehicles with respect to evaluation index i, E bi , are the average values ​​of the probability distribution of driving characteristics corresponding to novice drivers and their corresponding score rates, E gi , σ gi , S σgi are the mean value, variance and corresponding score rate of the driving characteristics probability distribution corresponding to mature drivers, D JSi It is the JS discreteness of the probability distribution of driving characteristics and high performance indicators of smart cars.

5. A method for evaluating the longitudinal driving performance of an intelligent vehicle, characterized in that: include: Using the intelligent vehicle longitudinal driving single index evaluation method as described in any one of claims 1 to 4, calculating the single index scores of the intelligent vehicle with respect to different evaluation indicators; According to the individual indicator scores and weights corresponding to each evaluation indicator at the next level, the indicator scores corresponding to each evaluation indicator at the previous level are calculated step by step with weighted calculations, and finally the comprehensive score of the smart car is obtained.

6. A method for evaluating the longitudinal driving performance of an intelligent vehicle, characterized in that: include: Obtain multiple sets of vehicle driving data for experienced drivers, novice drivers, and smart cars in different test scenarios; The method for evaluating the longitudinal driving performance of an intelligent vehicle as claimed in claim 5 is used to determine the comprehensive score of the intelligent vehicle under different test scenarios and different working conditions.

7. A single index evaluation system for longitudinal driving of intelligent vehicles, characterized in that: include: An acquisition module is configured to respectively acquire multiple groups of driving data on evaluation indicators of a mature driver, a novice driver, and an intelligent vehicle under the same test scenario and the same working conditions; A statistical module configured to determine the driving characteristic probability distribution of the mature driver, the novice driver and the intelligent car with respect to the evaluation index by performing statistical probability analysis on the corresponding driving data; A standard module is configured to determine the high-score evaluation standard and the basic performance standard corresponding to the evaluation index according to the characteristic values ​​corresponding to the driving characteristic probability distributions corresponding to the mature driver and the novice driver respectively; The evaluation module is configured to calculate the single indicator score of the smart car with respect to the evaluation index based on the high-score evaluation standard and the basic performance standard and according to the probability distribution of the driving characteristics of the smart car.

8. A smart car longitudinal driving performance evaluation system, characterized in that: include: A single evaluation module, configured to use the intelligent vehicle longitudinal driving single index evaluation method as described in any one of claims 1 to 4 to calculate the single index scores of the intelligent vehicle with respect to different evaluation indexes; The comprehensive evaluation module is configured to calculate the indicator scores corresponding to the evaluation indicators of the previous level step by step according to the individual indicator scores and weights corresponding to the evaluation indicators of the next level, and finally obtain the comprehensive score of the smart car.

9. A smart car longitudinal driving performance evaluation system, characterized in that: include: A driving data module configured to obtain multiple sets of vehicle driving data of experienced drivers, novice drivers and smart cars under different test scenarios and different working conditions; The performance evaluation module is configured to use the intelligent vehicle longitudinal driving performance evaluation method as described in claim 5 to determine the comprehensive score of the intelligent vehicle under different test scenarios and different working conditions.

Images