Automatic driving takeover method and system based on road impedance in intelligent network connection environment

Abstract

The invention belongs to the field of road vehicle control systems, and relates to an automatic driving takeover method and system based on road impedance in an intelligent network connection environment, and the system comprises a car following model, an impedance value calculation model, a takeover interval determination module, and a man-machine interaction module. The car-following model is used for determining motion modes of the vehicle in different road environments; the impedance value calculation model is used for quantifying the interference of the road environment on the automatic driving vehicle and converting the complex road environment into a computable impedance value; the takeover interval determination module determines a manual takeover speed interval by analyzing the change rate of the impedance value along with the average speed of the vehicles on the road; the man-machine interaction module is used for reminding a driver to take over when the speed reaches a threshold value of a manual take-over speed interval; the system can update the speed interval of manual takeover in real time according to the road environment, and timely remind a driver to perform takeover operation at the takeover node, so that the user experience of the driver and the reliability of the automatic driving vehicle are improved.

Description

Technical Field

[0001] The present invention belongs to the field of road vehicle control systems, relates to the takeover of autonomous vehicles, and particularly relates to a method and system for autonomous driving takeover based on road impedance in an intelligent networked environment. Background Art

[0002] Autonomous driving technology is still at the L3 level (conditional autonomous driving), and in L3-level autonomous driving, the driver still needs to take over. Taking over refers to the process in which when the vehicle encounters a road environment that it cannot handle, the human driver needs to temporarily take over the vehicle control right. In order to improve the reliability of autonomous vehicles and the user experience of drivers, a takeover system is needed to determine the speed range for the driver to take over.

[0003] Traditional takeover systems set the torque corresponding to the steering wheel according to different road environments or judge takeover performance to ensure the stable operation of autonomous vehicles. This method has the following disadvantages and deficiencies: (1) Lack of real-time performance. When the traffic condition suddenly changes, the torque cannot be adjusted in advance; (2) Reaction lag. Judging the driver's state through takeover performance may miss the best takeover opportunity; (3) Lack of real-time feedback. After determining manual takeover, due to the lack of human-machine interaction hardware (tactile feedback, visual warning, and sound prompt), the takeover efficiency will be affected.

[0004] In an intelligent networked environment, autonomous vehicles can monitor the road environment in real time, obtain the running conditions of surrounding vehicles, which not only improves the perception and decision-making capabilities, but also provides a basis for the vehicle's driving strategy. Therefore, it is necessary to provide an autonomous driving takeover system that can receive road information data in real time. Summary of the Invention

[0005] In view of the above technical problems and deficiencies, the purpose of the present invention is to provide a method for autonomous driving takeover based on road impedance in an intelligent networked environment. This takeover method calculates the impedance value of the road through the road environment data obtained in real time, determines the running efficiency of autonomous vehicles in different road environments according to the impedance value, thereby determining the manual takeover speed range, improving the reliability of autonomous driving takeover and the user experience of drivers, and providing technical support for the development of intelligent transportation systems.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: A method for autonomous driving takeover based on road impedance in an intelligent networked environment, the method comprising the following steps: Step 1. Build a car-following model to determine the motion patterns of human-driven vehicles and autonomous vehicles under different road environments through the car-following model; the car-following model includes the car-following model of human-driven vehicles and the car-following model of autonomous vehicles; the car-following model of human-driven vehicles is used to represent the motion pattern of human-driven vehicles, and the expression is: ; ; In the formula, is the acceleration of the following vehicle at the current moment, is the sensitivity coefficient, is the speed of the following vehicle at the current moment, is the undetermined coefficient, is the speed of the leading vehicle at the current moment, is the weight coefficient of the distance term, is the position of the leading vehicle at the current moment, is the position of the following vehicle at the current moment, is the desired following distance of the following vehicle, and are undetermined coefficients; The car-following model of the autonomous vehicle is used to represent the motion pattern of the autonomous vehicle; Step 2. Determine the average speed of the vehicles on the road according to the current road environment, and determine the vehicle density of the road based on the car-following model of human-driven vehicles and the car-following model of autonomous vehicles; ; In the formula, is the desired headway of the autonomous vehicle, is the length of the autonomous vehicle, is the minimum safety distance, is the proportion of human-driven vehicles, is the proportion of autonomous vehicles, , is the average speed of the vehicles on the road; Step 3. Calculate the impedance value of the road based on the average speed of the vehicles on the road and the vehicle density of the current road, and the expression is: ; In the formula, is the impedance value, and are weight coefficients, , is the average speed of the vehicles on the road, is the maximum average speed of the vehicles on the road, is the vehicle density of the current road, is the maximum vehicle density of the current road; Step 4. Analyze the change rate of the impedance value with the average speed of the vehicles on the road, so as to determine the speed range for the autonomous vehicle to perform manual takeover; Step 5. When the average speed of the vehicles on the road reaches the threshold of the speed range for manual takeover, remind the driver to take over through the human-machine interaction module.

[0007] As an optimization of the present invention, the following car-following model of the autonomous vehicle is used to represent the movement mode of the autonomous vehicle, and the expression is: ; ; In the formula, is the speed of the autonomous vehicle at moment, is the time step, taking 0.01 s, is the speed of the autonomous vehicle at the current moment, is the spacing error control parameter, is the error between the actual headway of the autonomous vehicle at the current moment and the desired headway, is the undetermined coefficient, is the derivative with respect to time , is the headway between the autonomous vehicle and the vehicle in front, is the length of the autonomous vehicle, is the minimum safety distance, is the desired headway time of the autonomous vehicle.

[0008] As an optimization of the present invention, the dynamic change coefficients in the car-following model of the manually driven vehicle and the car-following model of the autonomous vehicle are obtained by parameter fitting of the historical data stored in the database and the vehicle data obtained in real time, so as to obtain the car-following models of the manually driven vehicle and the autonomous vehicle under different road conditions. The dynamic change coefficients in the car-following model of the manually driven vehicle include the sensitivity coefficient , the undetermined coefficient , the undetermined coefficient and , the weight coefficient of the distance term; the dynamic change coefficients in the car-following model of the autonomous vehicle include the spacing error control parameter , the undetermined coefficient , the desired headway time of the autonomous vehicle.

[0009] As an optimization of the present invention, the weight coefficients and is a dynamic change coefficient. In order to enable the calculated impedance value to be normally used in all current road environments, the weight coefficient and are determined as follows: Step a. First, fix and the value of the ratio of autonomous driving vehicles to human-driven vehicles to obtain the minimum impedance value in the first road environment; Step b. Change the value of the ratio of autonomous driving vehicles to human-driven vehicles to obtain the minimum impedance value in the second road environment; Step c. Repeat the operation of Step b to obtain the minimum impedance values in all road environments under the current value; Step d. According to the minimum impedance values in all road environments under the current value, obtain the average value of the minimum impedance values when is fixed and the ratio of autonomous driving vehicles to human-driven vehicles changes; Step e. Change the value and repeat the operations of Steps a to d to obtain a new average value of the minimum impedance values; Step f. Take the maximum average value of the minimum impedance values as the objective function to ensure the stability of the impedance value calculation, and finally obtain the value.

[0010] As an optimization of the present invention, when analyzing the change rate of the impedance value with the average speed of the vehicles on the road in Step 4, if the change rate < 0.5%, it is considered that the driving efficiency of the autonomous driving vehicle is relatively stable in the speed range where the change rate < 0.5%. Conversely, if the change rate ≥ 0.5%, it is considered that the driving efficiency of the autonomous driving vehicle is relatively low in the speed range where the change rate ≥ 0.5%, and the driver is allowed to take over driving in the speed range where the change rate ≥ 0.5%.

[0011] The present invention also provides an autonomous driving takeover system based on road impedance in an intelligent networked environment. The system includes a following model, an impedance value calculation model, a takeover interval determination module, and a human-machine interaction module; Among them, the following model is used to determine the motion modes of human-driven vehicles and autonomous driving vehicles in different road environments; the following model includes a following model of human-driven vehicles and a following model of autonomous driving vehicles; the following model of human-driven vehicles is used to represent the motion mode of human-driven vehicles, and the expression is: ; ; In the formula, is the acceleration of the following vehicle at the current moment, is the sensitivity coefficient, is the speed of the following vehicle at the current moment, is a coefficient to be determined, is the speed of the leading vehicle at the current moment, is the weight coefficient of the distance term, is the position of the leading vehicle at the current moment, is the position of the following vehicle at the current moment, is the expected following distance of the following vehicle, and are coefficients to be determined; The following model of the autonomous vehicle is used to represent the motion mode of the autonomous vehicle; The impedance value calculation model is used to quantify the interference of the road environment on the autonomous vehicle and convert the complex road environment into a computable impedance value. The expression is: ; In the formula, is the impedance value, and are weight coefficients, , is the average speed of the vehicles on the road, is the maximum average speed of the vehicles on the road, is the vehicle density of the current road, is the maximum vehicle density of the current road; The vehicle density K of the current road is determined based on the following model of the human-driven vehicle and the following model of the autonomous vehicle. The expression is: ; In the formula, is the expected headway of the autonomous vehicle, is the length of the autonomous vehicle, is the minimum safety distance, is the proportion of the human-driven vehicles, is the proportion of the autonomous vehicles, , is the average speed of the vehicles on the road; The takeover interval determination module obtains the operation efficiency of the autonomous vehicle at different average speeds by analyzing the change rate of the impedance value with respect to the average speed of the vehicles on the road, and thus determines the speed interval for the autonomous vehicle to perform manual takeover; The human-machine interaction module is used to remind the driver to take over when the average speed of the vehicles on the road reaches the threshold of the takeover speed interval, so as to ensure the reliability of the autonomous vehicle.

[0012] As a preferred embodiment of the present invention, the system further comprises a computing platform, and the computing platform is used to calculate the dynamic change coefficients in each model according to historical data and data acquired in real time, so as to determine the car-following model and the impedance value calculation model.

[0013] As a preferred embodiment of the present invention, the human-computer interaction module includes a tactile feedback module, a visual warning module and a sound prompt module. The tactile feedback module reminds the driver to take over manually by vibration; the visual warning module reminds the driver of the speed range for manual takeover and the average speed of vehicles on the current road through a display, so that the driver can understand the urgency of the takeover requirement; the sound prompt module reminds the driver to take over manually by voice broadcast.

[0014] The advantages and beneficial effects of the present invention are: (1) The present invention takes into account that in an intelligent network environment, data on the road environment can be obtained in real time, and proposes an automatic driving takeover system based on road impedance in an intelligent network environment. The system can update the speed range for manual takeover in real time according to the road environment, and promptly remind the driver to take over at the takeover node, thereby improving the driver's user experience and the reliability of the automatic driving vehicle.

[0015] (2) The takeover system provided by the present invention can, with the help of a high-performance computing platform, efficiently process various data in the autonomous driving process in real time, thereby accurately determining whether the autonomous driving vehicle needs to be taken over in the current road environment, so as to avoid missing the best takeover opportunity, and at the same time facilitate the realization of a higher level of autonomous driving functions.

[0016] (3) The takeover system provided by the present invention is based on human-computer interaction hardware, and realizes real-time feedback of driving status through a multimodal interaction channel. When confirming to take over, it can promptly remind the driver to perform the takeover operation through tactile feedback, visual warnings and sound prompts, thereby improving the fault tolerance of the automatic driving system and enabling the vehicle to maintain reliable operation under system extreme conditions.

[0017] (4) The takeover system provided by the present invention can define the speed range for manual takeover. In different road environments, the system can also adjust the speed range in real time. The existing takeover system does not quantify the triggering conditions for manual takeover. The takeover system provided by the present invention specifies the nodes at which the autonomous driving vehicle should be manually taken over in various road environments, thereby promoting the development of autonomous driving technology.

[0018] (5) The car-following model of the manually driven vehicle provided by the present invention is obtained by improving the GM car-following model. The stimulation term of the original GM car-following model only includes speed, which may lead to too large or too small distances between two vehicles and is not conducive to calculating the impedance value. Therefore, the present invention adjusts the stimulation term and expression of the GM car-following model. The improved GM car-following model does not consider time delay, and the stimulation is jointly determined by speed and spacing. The stimulation generated by the spacing also takes into account the desired headway. Such a design is conducive to calculating the impedance value of the road, and the degree of interference of the driving of the autonomous vehicle by the road environment is represented by the impedance value. Description of the Drawings

[0019] Figure 1 is the logical block diagram of the autonomous driving takeover system based on road impedance in the intelligent networked environment; Figure 2 is the road impedance value diagram for all proportional combinations of autonomous driving vehicles and manually driven vehicles; Figure 3 is the change rate diagram of the road impedance value; Detailed Embodiment

[0020] To enable those skilled in the art to better understand the technical solutions and their advantages of the present invention, the present application will be described in detail below with reference to the accompanying drawings, but it is not intended to limit the protection scope of the present invention.

[0021] Figure 1 is the logical block diagram of an autonomous driving takeover system based on road impedance provided by the present invention. As Figure 1 shown, an autonomous driving takeover system based on road impedance provided in this embodiment includes: a car-following model, an impedance value calculation model, a takeover interval determination module, and a human-machine interaction module; Among them, the car-following model is used to determine the movement modes of manually driven vehicles and autonomous driving vehicles in different road environments; the car-following model includes a car-following model of a manually driven vehicle and a car-following model of an autonomous driving vehicle; In this embodiment, the car-following model of the manually driven vehicle is used to represent the movement mode of the manually driven vehicle, and the movement mode of the manually driven vehicle is: ; ; In the formula, is the acceleration of the following vehicle at the current moment, is the sensitivity coefficient, is the speed of the following vehicle at the current moment, is the undetermined coefficient, is the speed of the leading vehicle at the current moment, is the weight coefficient of the distance term, is the position of the leading vehicle at the current moment, is the position of the following vehicle at the current moment, is the desired following distance of the following vehicle, and are undetermined coefficients, which are determined by parameter fitting of the position information of the leading and following vehicles and the speed information of the following vehicle on the road; The following - distance model of the autonomous vehicle is used to represent the motion mode of the autonomous vehicle. The motion mode of the autonomous vehicle is: ; ; In the formula, is the speed of the autonomous vehicle at moment, is the time step, taking 0.01 s, is the speed of the autonomous vehicle at the current moment, is the spacing error control parameter, is the error between the actual head - to - head spacing and the desired head - to - head spacing of the autonomous vehicle at the current moment, is an undetermined coefficient, is the derivative with respect to time, is the head - to - head spacing (following distance) between the autonomous vehicle and the leading vehicle, is the length of the autonomous vehicle, is the minimum safety distance, is the desired headway of the autonomous vehicle; The vehicle density of the road represents the number of vehicles per unit length. Since the following distances of human - driven vehicles and autonomous vehicles are different, usually the following distance of autonomous vehicles is shorter, so there will be different average vehicle speeds and vehicle densities in different road environments. The driving of autonomous vehicles will be interfered by the road environment, and this interference can be expressed by the impedance value of the road. Therefore, the present invention designs an impedance - value calculation model. The impedance - value calculation model is used to quantify the interference of the road environment on autonomous vehicles. It converts the complex road environment into a computable impedance value and obtains the impedance value of autonomous vehicles when driving at different speeds. The expression is: ; In the formula, is the impedance value, and are weight coefficients, , is the average speed of vehicles (autonomous vehicles and human - driven vehicles) on the road, is the maximum average speed of vehicles on the road, is the vehicle density of the current road, is the maximum vehicle density of the current road; In this embodiment, the vehicle density K of the current road is determined based on the car-following model of human-driven vehicles and the car-following model of autonomous vehicles, and the expression is: ; In the formula, is the desired headway of autonomous vehicles, is the length of autonomous vehicles, is the minimum safety distance, is the proportion of human-driven vehicles, is the proportion of autonomous vehicles, , is the average speed of vehicles on the road; The takeover interval determination module obtains the operating efficiency of autonomous vehicles at different average speeds by analyzing the change rate of the impedance value with respect to the average speed of vehicles on the road, and thus determines the speed interval for autonomous vehicles to perform manual takeover, and this speed interval is the appropriate takeover interval; The human-machine interaction module is used to remind the driver to take over when the average speed of vehicles on the road reaches the threshold of the speed interval for manual takeover, so as to ensure the reliability of autonomous vehicles.

[0022] In this example, the dynamic change coefficients in the car-following model of human-driven vehicles and the car-following model of autonomous vehicles are obtained by parameter fitting of historical data stored in the database and vehicle data obtained in real time, so as to obtain the car-following model of human-driven vehicles and the car-following model of autonomous vehicles under different roads. The dynamic change coefficients in the car-following model of human-driven vehicles include the sensitivity coefficient , undetermined coefficient , undetermined coefficient and , the weight coefficient of the distance term ; The dynamic change coefficients in the car-following model of autonomous vehicles include the spacing error control parameter , undetermined coefficient , the desired headway of autonomous vehicles ; In addition, the weight coefficients and during impedance value calculation are also dynamic change coefficients.

[0023] Furthermore, in this example, the system further includes a high-performance computing platform, and the high-performance computing platform is used to calculate the dynamic change coefficients in each model according to historical data and data obtained in real time, so as to determine the car-following model and the impedance value calculation model.

[0024] In this example, the human-machine interaction module includes a tactile feedback module, a visual warning module, and an audio prompt module. The tactile feedback module reminds the driver to take over manually by vibrating. The visual warning module reminds the driver of the speed range for manual takeover and the average speed of the vehicles on the current road through a display, facilitating the driver to grasp the urgency of the takeover requirement. The audio prompt module reminds the driver to take over manually through voice broadcast, ensuring that the autonomous vehicle interacts with the driver in real time.

[0025] In this example, the autonomous vehicle stores the trajectory data of human-driven vehicles and autonomous vehicles in different road environments. At the same time, the autonomous vehicle can also obtain the trajectory data of surrounding vehicles in real time under the intelligent networked environment, and fit the parameters of the car-following model in real time through these trajectory data, so as to obtain the car-following models of human-driven vehicles and autonomous vehicles in different road environments.

[0026] Specifically, taking the dataset as an example of the NGSIM (Next Generation Simulation) project; specific road environment: vehicle data on Highway 101 in Los Angeles, California, USA. When calculating the values of the dynamic change parameters of the car-following model of human-driven vehicles, a high-performance computing platform is used to fit this dataset, and the determined values of the dynamic change parameters are: 6, , , , .

[0027] In this embodiment, the parameter values of the car-following model of the autonomous vehicle can be determined by fitting through a high-performance computing platform. Of course, existing publicly reported models can also be directly adopted; for example, take 45, , , , .

[0028] In this embodiment, the parameters in the impedance value calculation model are determined according to the maximum speed of the actual road. For example, if the highway speed limit is 120 km / h, then theoretically the average speed of the vehicle is between 0 and 120, and the maximum average speed is 120 km / h; of course, different roads have different speed limits, and it can also be 26.27 m / s (the maximum vehicle speed in the NGSIM dataset is 26.27 m / s), that is, the maximum average vehicle speed on the road is 26.27 m / s.

[0029] can be obtained by theoretical derivation. In this embodiment, when the road vehicles are running stably, the acceleration of all vehicles is 0 m / s2 , at this time, the expected headway (following distance) of the human-driven vehicle is , and the expected headway of the autonomous vehicle is ; the vehicle density K of the road represents the number of vehicles per unit length, and the calculation formula is as follows: ; In the formula, is the proportion of human-driven vehicles, is the proportion of autonomous vehicles, where , represents the average speed of the vehicles on the road.

[0030] From 's calculation formula, when takes 0 m / s, takes 1 (when all the vehicles on the road are autonomous vehicles), takes the maximum value, and the maximum value is .

[0031] In this embodiment, the proportion of autonomous vehicles and human-driven vehicles on the road is uncertain, and the vehicle density of the road will change under different proportions; in order to enable the impedance value calculation model to be used normally in all environments of the current road, the values of and are obtained through the robustness principle. The specific method is as follows: Step a. First, fix and the value of the proportion of autonomous vehicles to human-driven vehicles to obtain the minimum impedance value in the first road environment; Step b. Change the value of the proportion of autonomous vehicles to human-driven vehicles to obtain the minimum impedance value in the second road environment; Step c. Repeat the operation of step b to obtain the minimum impedance values in all road environments under the current value; Step d. According to the minimum impedance values in all road environments under the current value, obtain the average value of the minimum impedance values when remains fixed and the proportion of autonomous vehicles to human-driven vehicles changes; Step e. Change the value of , and repeat the operations of steps a to d to obtain a new average value of the minimum impedance value; Step f. Take the maximum average value of the minimum impedance value as the objective function to ensure the stability of the impedance value calculation module, and finally obtain 's value.

[0032] In this embodiment, the finally obtained 's value is 0.33, because , so takes the value of 0.67; among them, the larger the impedance value, the higher the efficiency of autonomous driving.

[0033] In this embodiment, the takeover interval determination module calculates the change rate of the impedance value of the autonomous vehicle at each speed (the average speed of the vehicles on the road) through the impedance function. If the change rate is small (less than 0.5%), it is considered that the driving efficiency of the autonomous vehicle is relatively stable in this speed interval; if the change rate is large, it is considered that the driving efficiency of the autonomous vehicle is low in this speed interval, and the driver is required to take over the driving in this speed interval; Figure 2 Schematically shows the impedance values of autonomous vehicles and manually driven vehicles under all proportional combinations. Through Figure 2 It can be seen that the operating efficiency of autonomous vehicles is poor when the speed (the average speed of the vehicles on the road) is too large or too small; among them, Figure 2 The shaded part represents the impedance values of autonomous vehicles and manually driven vehicles at different proportions. The lower limit curve of the shaded part corresponds to the situation with the lowest operating efficiency; by analyzing Figure 2 the change rate of the impedance value of the lower limit curve of the shaded part, a change rate diagram of the impedance value can be obtained (as Figure 3 shown), through Figure 3 It can be seen that in the speed (the average speed of the vehicles on the road) interval from 4.88 m / s to 15.81 m / s, the change rate of the impedance value is low, and the change amplitude is less than 0.5%; therefore, the manual driving intervals of the autonomous vehicle are from 0 m / s to 4.88 m / s and from 15.81 m / s to 26.27 m / s.

[0034] In this example, the takeover interval determination module has a corresponding database in different road environments. The high-performance computing platform performs parameter fitting on the car-following models of manually driven vehicles and autonomous vehicles through the database and the vehicle data obtained in real time, and then uses the car-following models (different car-following models have different α and maximum densities) to obtain the impedance functions in different road environments, so as to determine the corresponding manual takeover speed interval; the human-machine interaction module timely reminds the driver to take over according to the manual takeover speed interval to ensure the reliability of the autonomous vehicle.

[0035] This embodiment also provides an autonomous driving takeover method based on road impedance in an intelligent networked environment. This method includes the following steps: Step 1. Construct a car-following model, and determine the movement modes of manually driven vehicles and autonomous vehicles in different road environments through the car-following model; the car-following model includes the car-following model of manually driven vehicles and the car-following model of autonomous vehicles; the car-following model of manually driven vehicles is used to represent the movement mode of manually driven vehicles, and the expression is: ; ; In the formula, is the acceleration of the following vehicle at the current moment, is the sensitivity coefficient, is the speed of the following vehicle at the current moment, is the undetermined coefficient, is the speed of the leading vehicle at the current moment, is the weight coefficient of the distance term, is the position of the leading vehicle at the current moment, is the position of the following vehicle at the current moment, is the expected following distance of the following vehicle, and are undetermined coefficients, which are determined by parameter fitting of the position information of the leading and following vehicles in stable following and the speed information of the following vehicle on the road; The following model of the autonomous vehicle is used to represent the motion mode of the autonomous vehicle; Step 2. Determine the average speed of the vehicles on the road according to the current road environment, and determine the vehicle density of the road based on the following model of the human-driven vehicle and the following model of the autonomous vehicle; ; Among them, is the expected headway of the autonomous vehicle, is the length of the autonomous vehicle, is the minimum safety distance, is the proportion of human-driven vehicles, is the proportion of autonomous vehicles, , represents the average speed of the road vehicles; Step 3. Calculate the impedance value of the road based on the average speed of the vehicles on the road and the vehicle density of the current road. The expression is: ; In the formula, is the impedance value, and are weight coefficients, , is the average speed of the vehicles on the road, is the maximum average speed of the vehicles on the road, is the vehicle density of the current road, is the maximum vehicle density of the current road, that is, the vehicle density when all the vehicles on the road are autonomous vehicles; Step 4. Analyze the change rate of the impedance value with the average speed of the vehicles on the road, so as to determine the speed range for the autonomous vehicle to perform manual takeover; Step 5. When the average speed of the vehicles on the road reaches the threshold of the speed range for manual takeover, the driver is reminded to take over through the human-machine interaction module.

[0036] The above uses specific examples to elaborate on the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the technical field to which the present invention pertains, based on the idea of the present invention, several simple deductions, deformations or substitutions can also be made. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An automatic driving takeover method based on road impedance in an intelligent networked environment, characterized in that, Including the following steps: Step 1. Construct a car-following model to determine the movement patterns of human-driven vehicles and autonomous vehicles in different road environments through the car-following model. The car-following model includes the car-following model of human-driven vehicles and the car-following model of autonomous vehicles; The car-following model of human-driven vehicles is used to represent the movement pattern of human-driven vehicles, and the expression is: ； ； Wherein, is the acceleration of the following vehicle at the current moment, is the sensitivity coefficient, is the speed of the following vehicle at the current moment, is the undetermined coefficient, is the speed of the leading vehicle at the current moment, is the weight coefficient of the distance term, is the position of the leading vehicle at the current moment, is the position of the following vehicle at the current moment, is the expected following distance of the following vehicle, and are undetermined coefficients; The car-following model of autonomous vehicles is used to represent the movement pattern of autonomous vehicles; Step 2. Determine the average speed of the vehicles on the road according to the current road environment, and determine the vehicle density of the road based on the car-following model of human-driven vehicles and the car-following model of autonomous vehicles; ； wherein, is the desired time headway of the autonomous vehicle, is the length of the autonomous vehicle, is the minimum safety distance, is the proportion of human-driven vehicles, is the proportion of autonomous vehicles, , is the average speed of vehicles on the road; Step 3. Calculate the impedance value of the road based on the average speed of the vehicles on the road and the vehicle density of the current road, and the expression is: ； Wherein, is the impedance value, and are the weight coefficients, , is the average speed of vehicles on the road, is the maximum average speed of vehicles on the road, is the vehicle density of the current road, is the maximum vehicle density of the current road; Step 4. Analyze the change rate of the impedance value with respect to the average speed of the vehicles on the road to determine the speed range for the autonomous vehicle to perform manual takeover; Step 5. When the average speed of the vehicles on the road reaches the threshold of the speed range for manual takeover, remind the driver to take over through the human-machine interaction module.

2. The method for autonomous driving takeover based on road impedance in an intelligent networked environment according to claim 1, wherein The car-following model of the autonomous vehicle is used to represent the movement pattern of the autonomous vehicle, and the expression is: ； ； Wherein, is the speed of the autonomous vehicle at moment, is the time step, taking 0.01 s, is the speed of the autonomous vehicle at the current moment, is the spacing error control parameter, is the error between the actual headway of the autonomous vehicle and the desired headway at the current moment, is the undetermined coefficient, is the derivative of with respect to time, is the headway between the autonomous vehicle and the vehicle in front, is the length of the autonomous vehicle, is the minimum safety distance, is the desired headway time of the autonomous vehicle.

3. The method for autonomous driving takeover based on road impedance in an intelligent networked environment according to claim 2, wherein The dynamic change coefficients in the car-following model of the human-driven vehicle and the car-following model of the autonomous vehicle are obtained by parameter fitting using historical data stored in the database and vehicle data obtained in real time, so as to obtain the car-following models of the human-driven vehicle and the autonomous vehicle under different road environments. The dynamic change coefficients in the car-following model of the human-driven vehicle include the sensitivity coefficient , undetermined coefficient , undetermined coefficient and , the weight coefficient of the distance term ; the dynamic change coefficients in the car-following model of the autonomous vehicle include the spacing error control parameter , undetermined coefficient , the desired time headway of the autonomous vehicle .

4. The method for autonomous driving takeover based on road impedance in an intelligent networked environment according to claim 2, characterized in that, Weighting coefficient during impedance value calculation and are dynamic change coefficients. To enable the calculated impedance value to be normally used in all current road environments, the determination method of the weighting coefficient and is as follows: Step a. First, fix and the value of the ratio of autonomous vehicles to human-driven vehicles to obtain the minimum impedance value in the first road environment; Step b. Change the value of the ratio of autonomous vehicles to human-driven vehicles to obtain the minimum impedance value in the second road environment; Step c. Repeat the operation of step b to obtain the minimum impedance value under all road environments at the current value; Step d. According to the minimum impedance values under all road environments at the current value, obtain the average value of the minimum impedance values when it is fixed and the ratio of autonomous vehicles to human-driven vehicles changes; Step e. Change the value of, repeat the operations in steps a to d to obtain the average value of the new minimum impedance value; Step f. Taking the maximum average value of the minimum impedance values as the objective function to ensure the stability of impedance value calculation, and finally obtaining the value of 5. The method for autonomous driving takeover based on road impedance in an intelligent networked environment according to claim 2, wherein When analyzing the change rate of the impedance value with respect to the average speed of the vehicles on the road in Step 4, if the change rate < 0.5%, it is considered that the driving efficiency of the autonomous vehicle is relatively stable in the speed range where the change rate < 0.5%. Conversely, if the change rate ≥ 0.5%, it is considered that the driving efficiency of the autonomous vehicle is relatively low in the speed range where the change rate ≥ 0.5%, and the driver is allowed to take over driving in the speed range where the change rate ≥ 0.5%.

6. An automatic driving takeover system based on road impedance in an intelligent networked environment, characterized in that, Including a car-following model, an impedance value calculation model, a takeover interval determination module, and a human-machine interaction module; Among them, the car-following model is used to determine the movement patterns of human-driven vehicles and autonomous vehicles in different road environments. The car-following model includes the car-following model of human-driven vehicles and the car-following model of autonomous vehicles. The car-following model of human-driven vehicles is used to represent the movement pattern of human-driven vehicles, and the expression is: ； ； Wherein, is the acceleration of the following vehicle at the current moment, is the sensitivity coefficient, is the speed of the following vehicle at the current moment, is the undetermined coefficient, is the speed of the leading vehicle at the current moment, is the weight coefficient of the distance term, is the position of the leading vehicle at the current moment, is the position of the following vehicle at the current moment, is the expected following distance of the following vehicle, and are undetermined coefficients; The car-following model of the autonomous vehicle is used to represent the movement pattern of the autonomous vehicle; The impedance value calculation model is used to quantify the interference of the road environment on the autonomous vehicle and convert the complex road environment into a computable impedance value, and the expression is: ； wherein, is the impedance value, and are the weight coefficients, , is the average speed of vehicles on the road, is the maximum average speed of vehicles on the road, is the vehicle density on the current road, is the maximum vehicle density on the current road; The vehicle density K of the current road is determined based on the car-following model of human-driven vehicles and the car-following model of autonomous vehicles, and the expression is: ； Wherein, is the desired time headway of the autonomous vehicle, is the length of the autonomous vehicle, is the minimum safety distance, is the proportion of human-driven vehicles, is the proportion of autonomous vehicles, , is the average speed of vehicles on the road; The takeover interval determination module analyzes the change rate of the impedance value with respect to the average speed of the vehicles on the road to obtain the operating efficiency of the autonomous vehicle at different average speeds, so as to determine the speed range for the autonomous vehicle to perform manual takeover; The human-machine interaction module is used to remind the driver to take over when the average speed of the vehicles on the road reaches the threshold of the speed range for manual takeover.

7. The automatic driving takeover system based on road impedance in the intelligent networked environment according to claim 6, characterized in that, The described automatic driving takeover system further includes a computing platform, which is used to calculate the dynamic change coefficients in each model according to historical data and real-time acquired data, so as to determine the following model and the impedance value calculation model.

8. The automated driving takeover system based on road impedance in an intelligent networked environment according to claim 6, wherein The human-computer interaction module includes a tactile feedback module, a visual warning module, and a voice prompt module. The tactile feedback module reminds the driver to perform manual takeover by vibration; the visual warning module reminds the driver of the speed range for manual takeover and the average speed of vehicles on the current road through a display; the voice prompt module reminds the driver to perform manual takeover by voice broadcast.

Images