Driver driving behavior evaluation method and device, electronic equipment and storage medium

Abstract

The present application relates to a kind of driver driving behavior evaluation method, device, electronic equipment and storage medium based on improved artificial potential field.The method includes: obtaining the first driving data of target vehicle and the second driving data of vehicle around target vehicle;According to the driving risk potential field and the driving efficiency potential field of each vehicle, the first driving data and the second driving data of each vehicle are established according to the data of each vehicle itself;The driving behavior of driver on target vehicle is evaluated based on the driving risk potential field and the driving efficiency potential field.The present application improves artificial potential field, and perfects the evaluation system of contemporary driving behavior evaluation.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method, device, electronic device, and storage medium for evaluating driver behavior based on an improved artificial potential field. Background Technology

[0002] Analyzing emergency maneuvers ("three urgent behaviors") is a common method in evaluating driver behavior. However, these behaviors only consider safety during driving and do not address driving efficiency. A driver's performance should be evaluated by considering both safety and efficiency. Furthermore, emergency maneuvers are outcome-oriented evaluations, meaning they assess a driver based on sensor data after the initial driving session. Relying solely on this data makes it difficult to accurately and comprehensively assess the specific circumstances of the driving process.

[0003] Currently, many companies and academic papers are attempting to refine and enrich the indicators of the three urgent needs behaviors, or to conduct big data intelligent algorithm analysis on these indicators, but none of these efforts can solve the fundamental problems of these behaviors. The artificial potential field method treats a vehicle as a point mass surrounded by multiple artificial potential fields, such as obstacles or endpoints. Each potential field exerts a force on the vehicle, and the vehicle moves due to the resultant force of these multiple potential fields. That is, when two vehicles are too close, the resultant force manifests as a repulsive force, requiring the following vehicle to slow down or the preceding vehicle to accelerate to ensure safety. When two cars in a following relationship are too far apart, the resultant force manifests as an attractive force, requiring the following vehicle to accelerate; or, if the car is always acting as a destination under the influence of gravity, it needs to arrive as quickly as possible to ensure driving efficiency.

[0004] Currently, artificial potential field methods are mostly used for path planning in intelligent vehicles, but have not yet been applied to driver behavior evaluation. Therefore, how to establish risk and efficiency potential fields based on collected driving information to reflect the game situation of vehicles in the current driving scenario and improve the evaluation of driver behavior is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] In view of this, it is necessary to provide an improved method, device, electronic device and storage medium for evaluating driver behavior in an artificial potential field, so as to improve the accuracy of current driver behavior evaluation.

[0006] To achieve the above objectives, in a first aspect, the present invention provides an improved method for evaluating driver behavior in an artificial potential field, comprising:

[0007] Acquire the first driving data of the target vehicle and the second driving data of the vehicles surrounding the target vehicle;

[0008] The driving risk potential field and driving efficiency potential field of each vehicle are established based on the vehicle's own data, the first driving data and the second driving data.

[0009] The driving behavior of the driver in the target vehicle is evaluated based on the driving risk potential field and the driving efficiency potential field.

[0010] Furthermore, the individual data for each vehicle includes vehicle width and vehicle length;

[0011] The first driving data includes the target vehicle's speed and acceleration;

[0012] The second driving data includes the distance between the target vehicle and surrounding vehicles, the speed and acceleration of surrounding vehicles, and the lane width.

[0013] Furthermore, a driving risk potential field for each vehicle is established based on its own data, first driving data, and second driving data, including:

[0014] Based on the length and width of each vehicle, create a top-view ellipse for the body of each vehicle.

[0015] Based on the speed and acceleration of each vehicle relative to surrounding vehicles, determine the longitudinal safety distance between each vehicle and the vehicles in front and behind, as well as the lateral safety distance between each vehicle and the vehicles to the left and right. Based on the longitudinal safety distance and the lateral safety distance, determine the bottom shape of the driving risk potential field of each vehicle.

[0016] Lamé curves are used to fit the longitudinal safety distance, lateral safety distance, and risk potential field value to establish a surface function of the risk potential energy field for each vehicle. The risk potential field value is 0 on the bottom surface shape of the driving risk potential field of each vehicle, and the risk potential field value is 1 on the top-view ellipse of the vehicle body.

[0017] Furthermore, the step of establishing the driving efficiency potential field for each vehicle based on its own data, the first driving data, and the second driving data includes:

[0018] Set the lane width to the driving efficiency potential field width for each vehicle;

[0019] The distance from the rear end of the driving risk potential field of each vehicle to the driver's visible distance point is set as the driving efficiency potential field length of each vehicle. The visible distance refers to the distance between two vehicles when the driver can see the vehicle in front in the same lane under the current environment.

[0020] Using the quadratic function form of the gravitational potential field, a function of the driving efficiency potential field for each vehicle is established based on the width and length of the driving efficiency potential field. When the vehicle speed is less than the road speed limit, the vehicle's efficiency potential field value gradually decreases from the rear end to the visible distance point. When the vehicle speed is equal to the road speed limit, the vehicle's efficiency potential field value is always 1.

[0021] Furthermore, the evaluation of the driver's driving behavior on the target vehicle based on the driving risk potential field and the driving efficiency potential field includes:

[0022] The coordinates of the target vehicle in the coordinate system of the vehicle in front are determined based on the artificial potential field corresponding to the target vehicle and the vehicle in front of it. The artificial potential field includes the driving risk potential field and the driving efficiency potential field. The coordinates are the coordinates of the points on the top view of the target vehicle that have the shortest distance to the top view of the vehicle in front.

[0023] Based on the coordinate values, the risk index and efficiency index of the target vehicle are calculated, and the risk index and efficiency index are converted to time to determine the duration of the target vehicle's action under the risk potential field and efficiency potential field of the vehicle in front.

[0024] The average risk index of the target vehicle under the risk potential field of the vehicle in front is calculated based on the risk index of the target vehicle and the action time of the target vehicle under the risk potential field of the vehicle in front. The average efficiency index of the target vehicle under the risk potential field of the vehicle in front is calculated based on the efficiency index of the target vehicle and the action time of the target vehicle under the efficiency potential field of the vehicle in front.

[0025] The weight values ​​are determined based on the current traffic scenario, and the first driving behavior score of the target vehicle driver under the artificial potential field of the preceding vehicle is calculated using the average risk index, the average efficiency index, and the weight values.

[0026] Furthermore, the evaluation of the driver's driving behavior on the target vehicle based on the driving risk potential field and the driving efficiency potential field also includes:

[0027] Calculate the second driving behavior score of the target vehicle driver under the artificial potential field of surrounding vehicles during the current driving process.

[0028] Furthermore, the traffic scenario includes urban road conditions and highway road conditions, with urban road conditions having a greater weight than highway road conditions.

[0029] Secondly, the present invention also provides a driver behavior assessment device based on an improved artificial potential field, comprising:

[0030] The acquisition module is used to acquire the first driving data of the target vehicle and the second driving data of the vehicles surrounding the target vehicle.

[0031] The potential field establishment module is used to establish the driving risk potential field and driving efficiency potential field of each vehicle based on the vehicle's own data, the first driving data and the second driving data.

[0032] The evaluation module is used to evaluate the driving behavior of the driver in the target vehicle based on the driving risk potential field and the driving efficiency potential field.

[0033] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the above-described method for evaluating driver behavior based on an improved artificial potential field.

[0034] Fourthly, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, implements the steps in the above-described method for evaluating driver behavior based on an improved artificial potential field.

[0035] The beneficial effects of the above embodiments are as follows: This invention acquires driving data and road information of the target vehicle and surrounding vehicles through vehicle-mounted sensors, and then establishes a risk potential field and an efficiency potential field that reflect the driving scenario and vehicle game situation at that time through the acquired driving data. Compared with the traditional artificial potential field, it can better reflect the game situation of vehicles in the driving scenario at that time and has more practical application value. Furthermore, the driver driving behavior evaluation method proposed based on this can provide a comprehensive evaluation of the driver's driving behavior in terms of driving safety and driving efficiency in real time, filling the gap in this field in China and solving the limitation of existing evaluation methods that emphasize driving safety but ignore driving efficiency, effectively filling the gap in contemporary driving behavior evaluation.

[0036] Furthermore, this assessment method can be combined with other driving behavior assessment methods, such as the currently mainstream outcome-oriented assessment of the three urgent behaviors (urgent needling, quick waking, and quick waking), or with in-vehicle driver fatigue and distraction detection systems. This allows outcome-based and process-based assessments, as well as in-vehicle driver detection and external driving environment assessment, to complement each other, making the driver behavior assessment system more comprehensive and complete. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating an embodiment of the driver behavior assessment method based on an improved artificial potential field provided by the present invention.

[0038] Figure 2(a) is a top-view elliptical schematic diagram of a vehicle body according to an embodiment of the present invention;

[0039] Figure 2(b) is a schematic diagram of the bottom surface shape of a risk potential field provided in an embodiment of the present invention;

[0040] Figure 2(c) is a top view of a vehicle risk potential field provided in an embodiment of the present invention;

[0041] Figure 2(d) is a schematic diagram of a vehicle risk potential field provided in an embodiment of the present invention;

[0042] Figure 3 This invention provides a risk potential field distribution diagram of all vehicles on a road segment in a vehicle-to-everything (V2X) environment, as an embodiment of the present invention.

[0043] Figure 4 This is a schematic diagram of an artificial potential field for a car provided in an embodiment of the present invention;

[0044] Figure 5 A flowchart illustrating a driver behavior assessment method based on an improved artificial potential field, provided for another embodiment of the present invention;

[0045] Figure 6 A schematic diagram of an artificial potential field for a two-vehicle game provided in an embodiment of the present invention;

[0046] Figure 7 A schematic diagram of the structure of an embodiment of the driver behavior evaluation device based on an improved artificial potential field provided by the present invention;

[0047] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0048] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0049] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, "a plurality of" means two or more, unless otherwise explicitly specified. References to "embodiment" herein mean that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0050] This invention provides a method, device, electronic device, and storage medium for evaluating driver behavior based on an improved artificial potential field. The risk and efficiency potential fields established using collected driving information, compared to traditional artificial potential fields, better reflect the game-theoretic dynamics of the vehicle in the given driving scenario, thus possessing greater practical application value. The proposed driver behavior evaluation method can provide a more contextualized assessment of driver safety and efficiency in relation to the specific driving situation. Combining this method with other driver behavior evaluation methods can effectively fill the gaps in contemporary driver behavior assessment.

[0051] The specific embodiments are described in detail below:

[0052] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the driver behavior assessment method based on an improved artificial potential field provided by the present invention. A specific embodiment of the present invention discloses a driver behavior assessment method based on an improved artificial potential field, comprising:

[0053] Step S101: Obtain the first driving data of the target vehicle and the second driving data of the vehicles surrounding the target vehicle;

[0054] Step S102: Establish the driving risk potential field and driving efficiency potential field for each vehicle based on its own data, the first driving data and the second driving data.

[0055] Step S103: Evaluate the driving behavior of the driver in the target vehicle based on the driving risk potential field and the driving efficiency potential field.

[0056] First, it's important to clarify that the "three hasty actions" (urgent driving, slow driving, and slow speeding) consider driver safety, not driving efficiency. A driver's behavior should be evaluated by considering both safety and efficiency. A slow driver has a significant negative impact on traffic flow efficiency. Worse still, while ensuring their own safety, they influence the strategic decisions of other vehicles, further affecting them and creating a chain reaction that can lead to safety issues between neighboring vehicles.

[0057] Secondly, the "three-urgent behavior" evaluation is outcome-oriented, meaning it assesses the driver after they have completed a segment of driving based on sensor data. However, relying solely on this data makes it difficult to accurately and comprehensively evaluate the driving scenario at that moment. While some researchers have used changes in vehicle speed and GPS-recorded latitude and longitude coordinates to infer the driving scenario, traffic conditions on the same road segment change in real time, thus limiting the effectiveness of this method. Alternatively, reviewing surveillance footage or dashcam recordings based on the timing of abnormal data occurrences is an undeniably labor-intensive approach. Current process-oriented driver behavior evaluations include in-vehicle driver fatigue monitoring and distraction detection, but they do not yet address the external vehicle's driving status and the driving scenario.

[0058] This invention acquires driving data and road information of the target vehicle and surrounding vehicles through onboard sensors. Then, it establishes risk and efficiency potential fields based on the acquired driving data, reflecting the driving scenario and vehicle interaction at that time. Compared with traditional artificial potential fields, this better reflects the vehicle interaction situation in the driving scenario and has greater practical application value. Furthermore, the driver behavior assessment method proposed based on this invention can provide a comprehensive assessment of the driver's driving behavior in terms of driving safety and driving efficiency in real time, filling a gap in this field in China and solving the limitation of existing assessment methods that emphasize driving safety but ignore driving efficiency, effectively filling the gap in contemporary driving behavior assessment.

[0059] In one embodiment of the present invention, the individual data of each vehicle includes vehicle width and vehicle length;

[0060] The first driving data includes the target vehicle's speed and acceleration;

[0061] The second driving data includes the distance between the target vehicle and surrounding vehicles, the speed and acceleration of surrounding vehicles, and the lane width.

[0062] Understandably, acquiring driving data for each vehicle involves using the vehicle's onboard sensors to obtain data on the vehicle itself and surrounding vehicles, and extracting road information. However, to ensure that the established artificial potential field's functional distribution accurately reflects the interaction between the vehicle and its surroundings, and thus accurately reflects the driving scenario, the data source must originate from real-time data acquired by the vehicle's sensors. For example, GPS can be used to obtain the vehicle's speed and acceleration values, while radar or cameras can be used to detect the distance between the vehicle and surrounding vehicles, the speed and acceleration of surrounding vehicles, and lane width.

[0063] Furthermore, in order to solve the problem of acquiring massive amounts of driving data, modern vehicle-to-everything (V2X) communication technology can be used to enable the vehicle to easily obtain the distribution of artificial potential fields of all vehicles within the communication range on the road during the current driving process, making the driver's driving behavior score more accurate, comprehensive, and complete.

[0064] In one embodiment of the present invention, a driving risk potential field for each vehicle is established based on its own data, first driving data, and second driving data, including:

[0065] Based on the length and width of each vehicle, create a top-view ellipse for the body of each vehicle.

[0066] Based on the speed and acceleration of each vehicle relative to surrounding vehicles, determine the longitudinal safety distance between each vehicle and the vehicles in front and behind, as well as the lateral safety distance between each vehicle and the vehicles to the left and right. Based on the longitudinal safety distance and the lateral safety distance, determine the bottom shape of the driving risk potential field of each vehicle.

[0067] Lamé curves are used to fit the longitudinal safety distance, lateral safety distance, and risk potential field value to establish a surface function of the risk potential energy field for each vehicle. The risk potential field value is 0 on the bottom surface shape of the driving risk potential field of each vehicle, and the risk potential field value is 1 on the top-view ellipse of the vehicle body.

[0068] It is understandable that the vehicle body can be visualized as a rectangle based on its length and width. However, in driving risk assessment and risk warning, a certain safety margin must be reserved. Therefore, the vehicle body's top-view ellipse is established using the relationship of the largest inscribed rectangle of an ellipse, and this is used as the inner elliptical part of the risk potential field. This part includes the rectangular area occupied by the vehicle itself and four crescent-shaped redundant areas with a risk index of 1. As shown in Figure 2(a), Figure 2(a) is a schematic diagram of a vehicle body's top-view ellipse provided by an embodiment of the present invention. Once surrounding vehicles touch this part, it indicates that the risk of a collision is quite high.

[0069] The relationship between the major axis A1 and minor axis B1 of the ellipse and the vehicle length L and width W is as follows: The equation of the ellipse is:

[0070] Then, based on the data obtained by the sensor, the shape of the bottom surface of the risk potential field is determined. Please refer to Figure 2(b). Figure 2(b) is a schematic diagram of the bottom surface shape of the risk potential field provided in an embodiment of the present invention.

[0071] The vehicle's speed and acceleration, obtained from GPS, radar, or cameras, are used to calculate the optimal longitudinal distance between the vehicle and the vehicle in front, according to the expected distance calculation formula in the IDM (Intelligent Driver Model). The optimal longitudinal distance between the vehicle and the vehicle behind is also calculated, reflecting the game-theoretic relationship between the vehicle and the vehicles in front and behind. The formula for calculating the expected distance in the IDM model is shown below:

[0072] In this formula, Let s be the desired longitudinal distance between the two vehicles. L0 Let T be the safe distance between two vehicles when they are stationary, T be the driver's reaction time, and v be the vehicle's speed. f Let 'a' be the speed of the vehicle in front, 'a' be the maximum acceleration of your own vehicle, and 'b' be the comfortable deceleration of your own vehicle.

[0073] When two vehicles are traveling adjacent to each other on a road, it is desirable for both vehicles to be in the middle of their respective lanes, at which point the lateral distance between them is considered optimal. The optimal lateral distance between the two vehicles is determined by sensors detecting the width of the lanes at this point and the width of the nearest vehicle in the adjacent lanes. The calculation formula is as follows:

[0074] In this formula, Let w be the desired lateral distance between the two vehicles, w be the lane width of the road segment, and W be the width of the vehicle itself. r / l The width of the adjacent right or left vehicle.

[0075] Then, the front and rear longitudinal axis values ​​A of the risk potential field generated by the vehicle can be obtained. 11 A 12 and the left and right horizontal axis values ​​B 11 B 12 :

[0076] The bottom surface of the risk potential field in this invention is designed as an elliptical shape composed of four quarter ellipses. With the vehicle's forward direction as the positive x-axis and the left side of the forward direction as the positive y-axis, the expression is as follows:

[0077] However, as can be seen from this formula, when a car is in the edge lane or a vehicle in a certain direction is beyond the sensor's sensing range, the bottom part of the ellipse will be missing; if there are only vehicles in the front and rear directions or only vehicles in the left and right directions, the bottom of the risk potential field will not be a closed loop shape.

[0078] It is understandable that the probability of a collision or other risky accident between two vehicles does not exhibit a simple linear relationship with the distance between them. Instead, the risk index increases sharply in an exponential manner as the distance between the two vehicles decreases. To better quantify and evaluate the risk index, this invention sets its value between 0 and 1, and to approximate the exponential increase. Therefore, a Lamy curve in the first quadrant is used to fit the relationship between vehicle distance and the risk index. The Lamy curve function expression is as follows:

[0079] In the formula, α and β are the semi-diameters of the curve, and n is a parameter that takes a value between 0 and 1. Within this range, the Lame curve will exhibit a shape that grows in an exponential manner. Furthermore, in this invention, the value n affects the growth trend of the risk index with the change in vehicle spacing, and is related to the mass, shape, driving conditions, and road surface adhesion of the two vehicles.

[0080] Then, the surface function of the risk potential energy field for each vehicle is established, as shown in Figures 2(c) and 2(d). Figure 2(c) is a top view of a vehicle risk potential field provided in an embodiment of the present invention, and Figure 2(d) is a schematic diagram of a vehicle risk potential field provided in an embodiment of the present invention. When the bottom surface is at an elliptical boundary, the risk index is 0, and as the distance d between the two vehicles decreases, the risk index increases in the form of a Lame curve. When it touches the top-view ellipse of the vehicle body, the risk index reaches 1. Based on the method of establishing the equation of the solid external surface with known parallel sections, and by adjusting some parameters to make the surface continuous, the surface function of the risk potential field is constructed. Let the front longitudinal axis A be... 11 If the value is greater than the values ​​of the other four axes, then the surface function expression is as follows:

[0081]

[0082] The region containing the aforementioned surface function is defined as D1, and the surface function is normalized; the risk potential field value within the top-view ellipse of the vehicle body is defined as 1, and this region is defined as D2, i.e.:

[0083]

[0084] Furthermore, modern vehicle-to-everything (V2X) communication technologies can be used to enable each vehicle to easily obtain the potential energy field distribution of all vehicles within communication range on the road during the driving process. Please refer to [link / reference]. Figure 3 , Figure 3 This invention provides a risk potential field distribution map of all vehicles on a road segment in a vehicle-to-everything (V2X) environment, as an embodiment of the present invention.

[0085] In one embodiment of the present invention, establishing the driving efficiency potential field of each vehicle based on its own data, first driving data, and second driving data includes:

[0086] Set the lane width to the driving efficiency potential field width for each vehicle;

[0087] The distance from the rear end of the driving risk potential field of each vehicle to the driver's visible distance point is set as the driving efficiency potential field length of each vehicle. The visible distance refers to the distance between two vehicles when the driver can see the vehicle in front in the same lane under the current environment.

[0088] Using the quadratic function form of the gravitational potential field, a function of the driving efficiency potential field for each vehicle is established based on the width and length of the driving efficiency potential field. When the vehicle speed is less than the road speed limit, the vehicle's efficiency potential field value gradually decreases from the rear end to the visible distance point. When the vehicle speed is equal to the road speed limit, the vehicle's efficiency potential field value is always 1.

[0089] Please see Figure 4 , Figure 4 This is a schematic diagram of an artificial potential field for a vehicle according to an embodiment of the present invention. It is understood that the efficiency potential field addresses vehicle driving efficiency. However, when a vehicle is used as a reference vehicle, the efficiency of vehicles to its left, right, and in front is not relevant. Therefore, the efficiency potential field generated by a vehicle is defined to be effective only for vehicles behind it in the same lane, and the vehicle is also only affected by the efficiency potential fields of vehicles in front of it in the same lane. The width of the efficiency potential field is set to be the same as the lane width, and its longitudinal length is defined as the value starting from the rear endpoint of the risk potential field (x = -A). 12 The line extends all the way to the point of visibility for the driver behind. The visible distance s here v This refers to the distance between two vehicles when, under current conditions, the driver can begin to clearly see the vehicle ahead in the same lane. Then, it employs the quadratic function form commonly used in classical artificial potential fields, specifically the gravitational potential field. That is, when the vehicle behind is within the efficient potential field generated by its own vehicle, and the speed of the vehicle behind is less than the road speed limit v. l Then, the efficiency potential field value is defined as decaying from 1 at the endpoint of the risk potential field according to a quadratic function until it becomes 0 at the visible distance point. However, due to road speed limits, when the speed of a vehicle behind equals the road speed limit, regardless of the vehicle's position, the efficiency potential field value is 1. Using the vehicle's own coordinate system as a reference, its efficiency potential field expression is as follows:

[0090] In one embodiment of the present invention, please refer to Figure 5 , Figure 5 This is a flowchart illustrating a driver behavior assessment method based on an improved artificial potential field, provided as another embodiment of the present invention.

[0091] Step S501: Determine the coordinates of the target vehicle in the coordinate system of the vehicle in front based on the artificial potential field corresponding to the target vehicle and the vehicle in front of it. The artificial potential field includes the driving risk potential field and the driving efficiency potential field. The coordinates are the coordinates of the points on the top view of the target vehicle that have the shortest distance to the top view of the vehicle in front of it.

[0092] Step S502: Calculate the risk index and efficiency index of the target vehicle based on the coordinate values, and convert the risk index and efficiency index into time to determine the duration of the target vehicle's action under the risk potential field and efficiency potential field of the vehicle in front.

[0093] Step S503: Calculate the average risk index of the target vehicle under the risk potential field of the vehicle in front based on the risk index of the target vehicle and the action time of the target vehicle under the risk potential field of the vehicle in front; calculate the average efficiency index of the target vehicle under the risk potential field of the vehicle in front based on the efficiency index of the target vehicle and the action time of the target vehicle under the efficiency potential field of the vehicle in front.

[0094] Step S504: Determine the weight value based on the current traffic scenario, and use the average risk index, the average efficiency index and the weight value to calculate the first driving behavior score of the target vehicle driver under the artificial potential field of the preceding vehicle;

[0095] Step S505: Calculate the second driving behavior score generated by the target vehicle driver under the artificial potential field of surrounding vehicles during the current driving process.

[0096] Understandably, taking the target vehicle's position within the artificial potential field generated by the vehicle in front as an example, a driver behavior evaluation method based on risk and efficiency potential fields is established. First, the target vehicle's position (x, y) in the coordinate system of the vehicle in front is determined by establishing the risk and efficiency potential fields of the vehicle in front. The position coordinates are defined as the coordinates of the points on the top view of the target vehicle that have the shortest distance to the top view of the vehicle in front.

[0097] Then, based on the coordinate values, the risk index E of the target vehicle under the risk potential field and efficiency potential field of the preceding vehicle is calculated. risk (x,y) or efficiency index E efficiency (x,y), transform it into the form E where time is the independent variable. risk (t) and E efficiency (t), obtain the time T during which the target vehicle interacts with the risk potential field and efficiency potential field of the vehicle in front. risk and T efficiency .

[0098] Next, the average risk index E of the target vehicle in the artificial potential field of the vehicles in front is obtained. risk and average efficiency index E efficiencyThe first driving behavior score of the target vehicle driver, obtained from the artificial potential field generated by the vehicle in front, is obtained through a weighted method. The formula is as follows:

[0099]

[0100]

[0101] It should be noted that the weight λ here is related to the traffic scenario at the time. When driving safety is the priority in complex urban traffic conditions, the value of λ is larger (>0.5); when driving efficiency is the priority in highway conditions, the value of λ is smaller (<0.5).

[0102] Understandably, by using the same method to calculate the second driving behavior score of the target vehicle within the artificial potential field of all surrounding vehicles during this driving process, weights are allocated according to the duration of the artificial potential field's influence, and the weighted average is calculated to obtain the driver's second driving behavior score for this driving process. The final driver's behavior score is the second driving behavior score, and the first driving behavior score is a component of the second driving behavior score. The formula is as follows:

[0103]

[0104] To better understand the invention, for example, on a single-lane road, such as... Figure 6 As shown, Figure 6 This is a schematic diagram of an artificial potential field for a two-vehicle game according to an embodiment of the present invention. Vehicle A's front is located 45m directly behind vehicle B in the coordinate system. Vehicle A travels at a constant speed of 10m / s, while vehicle B travels at a constant speed of 8m / s. The artificial potential field generated by vehicle A in this driving scenario is evaluated, and the first driving behavior score obtained by vehicle A after 20s of two-vehicle game is shown in Table 1. Table 1 lists the parameter values ​​required for this calculation.

[0105] Table 1 shows the parameter values ​​required for the calculation.

[0106]

[0107] Based on the above specific values ​​and the IDM model, the optimal longitudinal distance between the two vehicles is calculated to be 8.4051m, and the optimal following point is located at (-10.7801, 0, 0) in vehicle B's coordinate system. During the 20-second game between the two vehicles, vehicle A is in the efficiency potential field generated by vehicle B for the first 17.1095 seconds, and in the risk potential field generated by vehicle B for the next 2.8095 seconds. Since vehicle B is only engaging in driving games with vehicle A at this time, as mentioned above, the risk potential field generated by vehicle B is simply a surface that grows along a Lame curve.

[0108] Based on the calculation steps for driver behavior scoring, the average efficiency index of driver A is calculated to be 0.7778 during the time period from 0s to 17.1095s, and the average risk index is calculated to be 0.3955 during the time period from 17.1095s to 20s. Assuming the traffic scenario is an urban road and λ is taken as 0.6, the driver's driving behavior score for this driving process can be obtained as 67.382 points.

[0109] The above examples are only for better illustrating the implementation process of the present invention. However, in actual implementation, the vehicle operation scenario will be more complex, the required driving data will be more extensive, the same vehicle will engage in complex game interactions with multiple vehicles, and the shape and size of the risk potential field and efficiency potential field will also change in real time.

[0110] To better implement the driver behavior assessment method based on improved artificial potential field in the embodiments of the present invention, based on the driver behavior assessment method based on improved artificial potential field, please refer to the corresponding... Figure 7 , Figure 7 This is a schematic diagram of an embodiment of the driver driving behavior assessment device based on an improved artificial potential field provided by the present invention. The embodiment of the present invention provides a driver driving behavior assessment device 700 based on an improved artificial potential field, comprising:

[0111] The acquisition module 701 is used to acquire the first driving data of the target vehicle and the second driving data of the vehicles surrounding the target vehicle.

[0112] The potential field establishment module 702 is used to establish the driving risk potential field and driving efficiency potential field of each vehicle based on the vehicle's own data, the first driving data and the second driving data.

[0113] The evaluation module 703 is used to evaluate the driving behavior of the driver in the target vehicle based on the driving risk potential field and the driving efficiency potential field.

[0114] It should be noted that the device 700 provided in the above embodiments can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding content in the above method embodiments, and will not be repeated here.

[0115] Based on the above-described driver behavior assessment method based on an improved artificial potential field, this invention also provides an electronic device, including: a processor and a memory, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, it implements the steps in the driver behavior assessment method based on an improved artificial potential field as described in the above embodiments.

[0116] Figure 8The diagram shows a structural schematic of an electronic device 800 suitable for implementing embodiments of the present invention. The electronic device in the embodiments of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0117] The electronic device includes a memory and a processor, wherein the processor may be referred to as processing device 801 below, and the memory may include at least one of read-only memory (ROM) 802, random access memory (RAM) 803 and storage device 808 below, as detailed below:

[0118] like Figure 8 As shown, the electronic device 800 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device 800. The processing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0119] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 An electronic device 800 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0120] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by a processing device 801, it performs the functions defined in the methods of the embodiments of the present invention.

[0121] Based on the above-described driver behavior assessment method based on an improved artificial potential field, this invention also provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps in the driver behavior assessment method based on an improved artificial potential field as described in the above embodiments.

[0122] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0123] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating driver behavior based on an improved artificial potential field, characterized in that, include: Acquire the first driving data of the target vehicle and the second driving data of the vehicles surrounding the target vehicle; The driving risk potential field and driving efficiency potential field of each vehicle are established based on the vehicle's own data, the first driving data, and the second driving data. The vehicle's own data includes the vehicle width and vehicle length; the first driving data includes the target vehicle's speed and acceleration; and the second driving data includes the target vehicle's distance from surrounding vehicles, the speed and acceleration of surrounding vehicles, and the lane width. The driving behavior of the driver in the target vehicle is evaluated based on the driving risk potential field and the driving efficiency potential field. A driving risk potential field for each vehicle is established based on its own data, first driving data, and second driving data, including: Based on the length and width of each vehicle, create a top-view ellipse for the body of each vehicle. Based on the speed and acceleration of each vehicle relative to surrounding vehicles, determine the longitudinal safety distance between each vehicle and the vehicles in front and behind, as well as the lateral safety distance between each vehicle and the vehicles to the left and right. Based on the longitudinal safety distance and the lateral safety distance, determine the bottom shape of the driving risk potential field of each vehicle. Lamé curves are used to fit the longitudinal safety distance, lateral safety distance, and risk potential field value to establish a surface function of the risk potential energy field for each vehicle. The risk potential field value is 0 on the bottom surface shape of the driving risk potential field of each vehicle, and the risk potential field value is 1 on the top-view ellipse of the vehicle body.

2. The driver behavior assessment method based on an improved artificial potential field according to claim 1, characterized in that, The step of establishing the driving efficiency potential field for each vehicle based on its own data, first driving data, and second driving data includes: Set the lane width to the driving efficiency potential field width for each vehicle; The distance from the rear end of the driving risk potential field of each vehicle to the driver's visible distance point is set as the driving efficiency potential field length of each vehicle. The visible distance refers to the distance between two vehicles when the driver can see the vehicle in front in the same lane under the current environment. Using the quadratic function form of the gravitational potential field, a function of the driving efficiency potential field for each vehicle is established based on the width and length of the driving efficiency potential field. When the vehicle speed is less than the road speed limit, the vehicle's efficiency potential field value gradually decreases from the rear end to the visible distance point. When the vehicle speed is equal to the road speed limit, the vehicle's efficiency potential field value is always 1.

3. The driver behavior assessment method based on an improved artificial potential field according to claim 1, characterized in that, The evaluation of the driver's driving behavior on the target vehicle based on the driving risk potential field and the driving efficiency potential field includes: The coordinates of the target vehicle in the coordinate system of the vehicle in front are determined based on the artificial potential field corresponding to the target vehicle and the vehicle in front of it. The artificial potential field includes the driving risk potential field and the driving efficiency potential field. The coordinates are the coordinates of the points on the top view of the target vehicle that have the shortest distance to the top view of the vehicle in front. Based on the coordinate values, the risk index and efficiency index of the target vehicle are calculated, and the risk index and efficiency index are converted to time to determine the duration of the target vehicle's action under the risk potential field and efficiency potential field of the vehicle in front. The average risk index of the target vehicle under the risk potential field of the vehicle in front is calculated based on the risk index of the target vehicle and the action time of the target vehicle under the risk potential field of the vehicle in front. The average efficiency index of the target vehicle under the risk potential field of the vehicle in front is calculated based on the efficiency index of the target vehicle and the action time of the target vehicle under the efficiency potential field of the vehicle in front. The weight values ​​are determined based on the current traffic scenario, and the first driving behavior score of the target vehicle driver under the artificial potential field of the preceding vehicle is calculated using the average risk index, the average efficiency index, and the weight values.

4. The driver behavior assessment method based on an improved artificial potential field according to claim 3, characterized in that, The evaluation of the driver's driving behavior on the target vehicle based on the driving risk potential field and the driving efficiency potential field further includes: Calculate the second driving behavior score of the target vehicle driver under the artificial potential field of surrounding vehicles during the current driving process.

5. The driver behavior assessment method based on an improved artificial potential field according to claim 3, characterized in that, The traffic scenarios include urban road conditions and highway road conditions, with urban road conditions having a greater weight than highway road conditions.

6. A driver behavior evaluation device based on an improved artificial potential field, characterized in that, include: The acquisition module is used to acquire the first driving data of the target vehicle and the second driving data of the vehicles surrounding the target vehicle. The potential field establishment module is used to establish the driving risk potential field and driving efficiency potential field of each vehicle based on the vehicle's own data, the first driving data and the second driving data. The vehicle's own data includes the vehicle width and vehicle length; the first driving data includes the target vehicle's speed and acceleration; the second driving data includes the target vehicle's distance from surrounding vehicles, the surrounding vehicles' speed and acceleration, and the lane width. An evaluation module is used to evaluate the driving behavior of the driver in the target vehicle based on the driving risk potential field and the driving efficiency potential field. A driving risk potential field for each vehicle is established based on its own data, first driving data, and second driving data, including: Based on the length and width of each vehicle, create a top-view ellipse for the body of each vehicle. Based on the speed and acceleration of each vehicle relative to surrounding vehicles, determine the longitudinal safety distance between each vehicle and the vehicles in front and behind, as well as the lateral safety distance between each vehicle and the vehicles to the left and right. Based on the longitudinal safety distance and the lateral safety distance, determine the bottom shape of the driving risk potential field of each vehicle. Lamé curves are used to fit the longitudinal safety distance, lateral safety distance, and risk potential field value to establish a surface function of the risk potential energy field for each vehicle. The risk potential field value is 0 on the bottom surface shape of the driving risk potential field of each vehicle, and the risk potential field value is 1 on the top-view ellipse of the vehicle body.

7. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory is used to store a program; and the processor is coupled to the memory to execute the program stored in the memory to implement the steps in the driver driving behavior assessment method based on an improved artificial potential field according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, are capable of implementing the steps in the driver behavior assessment method based on an improved artificial potential field as described in any one of claims 1 to 5.

Images