A vehicle control method and system considering vehicle-non-vehicle conflict

Abstract

The present invention belongs to the field of road vehicle control systems and relates to a vehicle control method and system that considers vehicle-non-motor vehicle conflicts. The method first obtains non-motor vehicle driving state information and environmental status data, and based on the obtained data, perceives the risk of abrupt lane changes, red light running, wrong-way driving, and loss of control. It then perceives the risk of side collisions and frontal collisions based on the driving state information of the non-motor vehicle and surrounding motor vehicles and the non-motor vehicle's abrupt lane changes. Comprehensively covering all potential conflict scenarios between motor vehicles and non-motor vehicles, the method then uses an improved frequency statistics method to calculate the weights of different risk factors. Based on these different risk factors and weights, it calculates the overall risk level. Finally, the overall risk level is graded and different control strategies are adopted. This method achieves accurate prediction of potential conflicts and then proactively intervenes based on the prediction results, effectively reducing conflict risks and ensuring driving safety.

Description

Technical Field

[0001] The present invention belongs to the field of road vehicle control systems, and in particular relates to a vehicle control method and system taking into account vehicle-non-vehicle conflicts. Background Art

[0002] In recent years, with the acceleration of urbanization and the rapid growth of travel demand, the number of both non-motorized vehicles and motorized vehicles has increased dramatically, leading to increasingly prominent traffic congestion and becoming a common challenge in urban transportation management. As an important means of transportation, non-motorized vehicles are highly favored by those traveling short and medium distances due to their advantages of labor-saving, speed, flexibility, convenience, efficiency, practicality, environmental friendliness, and economy. According to statistics, the number of electric bicycles in my country has exceeded 400 million, and they occupy a vital position in the road transportation systems of cities at all levels of economic development.

[0003] However, the widespread use of non-motorized vehicles has also led to a series of traffic safety issues. Non-motorized vehicles are characterized by their relatively high speed, high flexibility, difficulty in control, and sensitivity to interference. This, combined with the low cost of violating regulations and the inadequate safety equipment of riders, has led to frequent non-motorized vehicle accidents and an increasingly severe traffic safety situation. Furthermore, non-motorized vehicles and motor vehicles often share lanes, leading to traffic chaos and reducing traffic efficiency while exacerbating collisions between motor vehicles and non-motorized vehicles. The loss of life and economic losses caused by these accidents are far greater than those caused by other types of non-motorized vehicle accidents.

[0004] Currently, the main methods for resolving conflicts between motor vehicles and non-motor vehicles include optimizing traffic planning and design, strengthening management, encouraging public participation, and improving infrastructure. While these measures can reduce accident rates and improve road safety and traffic efficiency to a certain extent, they still have limitations. In particular, when the risk of accidents is high, effective measures to avoid them are often not taken in advance.

[0005] In the existing technology, relevant patents mostly focus on traffic status identification and warning, but lack the accurate prediction of collision risks between non-motor vehicles and motor vehicles and the active control of vehicles, which cannot effectively reduce accident risks. For example, Chinese patent CN 115171383 discloses a "vehicle-road collaborative warning system for dangerous road sections" and proposes a vehicle-road collaborative warning system based on millimeter-wave radar and LORA communication modules. It can detect the position, direction and speed of pedestrians, non-motor vehicles and motor vehicles in real time, and transmit data through a low-power, anti-interference wireless communication module. However, non-motor vehicles have strong flexibility and are prone to sudden lane changes, rollovers and loss of control. Detecting the position, direction and speed of pedestrians, non-motor vehicles and motor vehicles alone cannot effectively predict the collision risk between non-motor vehicles and motor vehicles, and cannot proactively provide effective control strategies for vehicles to reduce accident risks. Chinese patent CN 116704199 A discloses a "multi-task traffic panoramic perception method, device and computer equipment". It obtains target driving area, lane lines, target object positioning and motion status information through feature extraction and target detection models, determines traffic panoramic perception information, and improves perception speed and dimension. Although this method can determine traffic panoramic perception information, it has not yet disclosed how to accurately predict the collision risk between non-motor vehicles and motor vehicles based on the obtained traffic panoramic perception information. Therefore, it is still impossible to actively provide an effective control strategy for the vehicle; Chinese patent CN 110867081A discloses a "wireless radio frequency identification electric vehicle safety driving device and its working process". It focuses on monitoring dangerous driving behaviors of electric non-motor vehicles and motor vehicles, and transmits warning information through wireless signals. It lacks accurate prediction of collision risks between non-motor vehicles and motor vehicles.

[0006] While existing technologies have made some progress in traffic state perception and early warning, they still have significant shortcomings in proactively controlling vehicles to avoid accidents, as they cannot accurately predict the risk of collisions between non-motorized vehicles and motor vehicles in mixed traffic lanes. Therefore, there is an urgent need to develop an active vehicle control method based on accurate and reliable prediction of vehicle-vehicle collisions, which is of great practical significance for preventing and reducing traffic accidents. Summary of the Invention

[0007] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a vehicle control method that takes into account motor vehicle and non-motor vehicle conflicts. This method collects and analyzes the dynamic behavior data of motor vehicles and non-motor vehicles in real time, combines intelligent algorithms, and realizes accurate prediction of potential conflicts. It then actively intervenes based on the prediction results, thereby effectively reducing the risk of conflict and ensuring driving safety.

[0008] To achieve the above object, the present invention adopts the following technical solutions:

[0009] A vehicle control method considering vehicle-to-vehicle conflict, the method comprising the following steps:

[0010] Step 1. Obtain non-motor vehicle driving status information and environmental status data, and perceive dangerous behaviors and the degree of danger based on the driving status information and environmental status data. The dangerous behaviors include abrupt lane changes. SLC The degree of danger includes the degree of danger of running a red light , the degree of danger of driving against traffic , the degree of risk of loss of control ;

[0011] Step 2: Based on the driving status information of non-motor vehicles and surrounding motor vehicles and the abrupt lane-changing behavior of non-motor vehicles SLC , perceive the risk of side collision At the same time, the safety distance D to prevent rear-end collision is calculated based on the driving status information of the non-motor vehicle and the rear motor vehicle, and the degree of front collision risk is perceived based on the safety distance D and the distance between the front non-motor vehicle and the rear motor vehicle. ;

[0012] Step 3. Calculate the risk level of red light running based on the probability and severity coefficient of red light running, wrong-way driving, loss of control, side collision, and front collision in historical data. , the degree of danger of driving against traffic , the degree of risk of loss of control , side collision risk , forward collision risk The weight of

[0013] Step 4. Use a weighted scoring model to add the weights of each risk factor and the current risk level to obtain a comprehensive risk level score;

[0014] Step 5. Determine the danger level of the current driving situation based on the comprehensive danger level score. Different danger level intervals correspond to different control strategies.

[0015] As a preferred embodiment of the present invention, a method for sensing the degree of danger of running a red light is:

[0016] Step a. Obtain the video stream collected by the visual module on the non-motor vehicle driver's smart helmet;

[0017] Step b. Use the YOLO-v8 model to perceive the status information of the traffic lights in the collected video stream;

[0018] Step c. Calculate the focal length f of the visual module and the imaging height of the traffic light pixel W p The ratio of

[0019] Step d. Based on the current status of the signal light and Danger level of running red lights for non-motor vehicles Make a judgment:

[0020] ;

[0021] in, is the corrected threshold, and the calculation formula is:

[0022] ;

[0023] in, v is the speed of non-motor vehicles, α is the empirical coefficient, v max is the maximum driving speed, is the threshold value, which is 0.2.

[0024] As a preferred embodiment of the present invention, the method for sensing the degree of danger of reverse driving is as follows: obtaining the current position data of the non-motor vehicle and the position data of the non-motor vehicle at the next moment through the GPS module, and at the same time obtaining the center line position information of the road where the non-motor vehicle is currently traveling; sensing the degree of danger of reverse driving of the non-motor vehicle based on the principle of vector product method, and when a non-motor vehicle is detected to be reverse driving, the degree of danger of reverse driving is detected. ,otherwise .

[0025] As a preferred embodiment of the present invention, when perceiving sudden lane change behavior, a static inclination angle threshold or a dynamic lane reference model is selected based on the lane line to make a judgment. If the lane line is clear and it is a straight road, the static inclination angle threshold model is used for calculation; if the lane is not straight or the lane line cannot be accurately detected, the dynamic lane reference model is used for calculation.

[0026] As a preferred embodiment of the present invention, the risk of loss of control is determined by the lateral acceleration and turning radius of the non-motor vehicle in combination with the road conditions, and the expression is:

[0027] ;

[0028] in, is the radial acceleration of the non-motor vehicle, ; is the current speed of the non-motor vehicle; is the turning radius of non-motor vehicles, is the coefficient of friction of the road surface.

[0029] As a preferred embodiment of the present invention, the method for sensing the risk of lateral collision based on the abrupt lane change behavior of non-motor vehicles is as follows: first, the lateral distance between the motor vehicle and the adjacent non-motor vehicle is calculated. , correct the lateral distance based on the abrupt lane change behavior, in, for The corrected lateral distance between the motor vehicle and the adjacent non-motor vehicle, is the distance correction coefficient, which is set to 0.2. The degree of lateral collision risk is determined based on the corrected lateral distance between the motor vehicle and the adjacent non-motor vehicle. The expression is:

[0030] As a preferred embodiment of the present invention, when sensing the risk of a front collision, the safe distance to prevent rear-end collision is first determined based on the running state of the non-motor vehicle. Calculate and then compare the distance S between the front non-motor vehicle and the rear motor vehicle with the safety distance Compare and judge the degree of risk of front collision , the expression is: .

[0031] As a preferred embodiment of the present invention, the method for determining the weight coefficient in step 3 is:

[0032] First, calculate the probability of the jth risk factor appearing in the historical data :

[0033] ;

[0034] Where, For the j The number of occurrences of risk factors, is the total number of samples; risk factors include running a red light, driving against traffic, loss of control, side collision, and front collision;

[0035] Then, the weight of each risk factor is calculated, and the weight formula is:

[0036] ;

[0037] in, is the weight of the j-th risk factor;

[0038] However, the introduction of severity coefficient , the weight is modified, and the final weight formula is:

[0039] ;

[0040] in, is the weight of the j-th risk factor after correction.

[0041] As a preferred embodiment of the present invention, in step 5, the comprehensive risk level score is used. The size of the danger is divided into four levels. For low risk, the driver is reminded by early warning; for relatively low risk, the deceleration and power output are controlled while the early warning is given; for medium risk, the driver is warned while the formula is used Dynamically adjust deceleration, provide steering suggestions, and control power output; for high-risk situations, it triggers stepped emergency braking while issuing warnings, synchronously activates the electric power steering system, automatically performs obstacle avoidance actions under the constraint of lateral acceleration ≤ 0.3g, and completely cuts off power output.

[0042] As a preferred embodiment of the present invention, when the non-motor vehicle ahead is stationary, the safe distance to prevent rear-end collision is The expression is:

[0043] ；

[0044] When the non-motorized vehicle in front is in a state of constant speed or constant acceleration, the motor vehicle behind is During the time period Always reduce the speed to the same as the vehicle in front, to avoid rear-end collision The expression is:

[0045] ； Otherwise, a safe distance to prevent rear-end collisions The expression is:

[0046] ;

[0047] When the non-motor vehicle in front is in a decelerating state, keep a safe distance to prevent rear-end collision The expression is:

[0048] ;

[0049] in, and are the speeds of the non-motor vehicle in front and the motor vehicle behind, and are the accelerations of the non-motor vehicle in front and the motor vehicle behind, is the reaction time of the motor vehicle driver, is the braking response time, is the braking time when the speed of the non-motor vehicle in front is the same as that of the motor vehicle behind. The minimum safe distance.

[0050] As a further preferred embodiment of the present invention, when calculating the static tilt angle threshold model, the steering angle and radial acceleration are used for judgment. When the following two conditions are met at the same time, it is considered that an abrupt lane change has occurred:

[0051] and ;

[0052] in, is the angle between the actual non-motor vehicle and the lane line, is the radial acceleration of the non-motor vehicle, is the threshold value, which is 0.4g. is the threshold value, which is 20°;

[0053] The specific steps for calculating the dynamic lane benchmark model are as follows:

[0054] Step a. Dynamically construct the lane benchmark model;

[0055] First, lane lines are detected and road boundaries are extracted using LiDAR point clouds. B-spline curve fitting is then used to fit the detected lane lines or road boundary points into lane benchmarks. B-spline curve fitting uses cubic uniform B-splines, and the number of control points is dynamically adjusted based on the road curvature.

[0056] Step b. The lateral displacement change rate of the non-motor vehicle relative to the lane reference Perform calculations;

[0057] Step c. According to the lane curvature Adaptive adjustment of the maximum allowable deviation rate , the expression is:

[0058] ;

[0059] in, is the basic threshold, is the curvature compensation coefficient, is the lane curvature threshold;

[0060] Step d. Abrupt lane change behavior for non-motor vehicles SLC Make a judgment, if , it is considered that the non-motor vehicle has made an abrupt lane change. ,otherwise .

[0061] As a further preferred embodiment of the present invention, the control points are optimized by weighted least squares method with Tikhonov regularization, and the objective function is:

[0062] ;

[0063] in, is the weighted least squares term, Q represents the coordinate matrix of the road feature points obtained by the sensor, B is the matrix composed of B-spline basis functions, C is the coordinate matrix of the control points to be solved, and the weight matrix W is a diagonal matrix whose diagonal elements are assigned according to the detection confidence of each feature point;

[0064] is the Tikhonov regularization term. L usually adopts a second-order difference operator matrix to constrain the change range of the control points. The value range of the regularization coefficient λ is set to 0.1 to 0.3.

[0065] The present invention also provides a vehicle control system that considers non-motor vehicle conflicts and is used to implement the above-mentioned control method. The system includes an information collection module, a road feature perception module, a vehicle parameter perception module, a non-motor vehicle driving behavior perception module, a danger level perception module, a danger level determination module, and a warning and control module. The information collection module is used to obtain driving status information and environmental status data of motor vehicles and non-motor vehicles.

[0066] The road feature perception module is used to obtain road-related information, including road center lines, lane lines, lane curvatures, and road boundary points, based on the environmental status data collected by the information collection module;

[0067] The vehicle parameter perception module is used to obtain various dynamic parameters of the interaction between the motor vehicle and the non-motor vehicle during the driving process, including driving speed, acceleration, and steering angle, based on the driving status information of the motor vehicle and the non-motor vehicle collected by the information collection module;

[0068] The non-motor vehicle driving behavior perception module is used to perceive dangerous behaviors and the degree of danger during the non-motor vehicle driving process based on the non-motor vehicle driving state data and the environmental state data;

[0069] The danger level perception module is used to determine the danger level of a front collision and the danger level of a side collision based on the dynamic parameters obtained by the vehicle parameter perception module and the dangerous behavior perceived by the non-motor vehicle driving behavior perception module;

[0070] The danger level determination module is used to calculate the comprehensive danger level based on the danger levels of front collision, side collision, loss of control, running a red light and wrong-way driving, and classify the danger level of the current traffic situation in combination with preset thresholds;

[0071] The early warning and control module is used to take corresponding early warning and control measures according to the results of the danger level determination module.

[0072] Advantages and beneficial effects of the present invention:

[0073] (1) The present invention collects and analyzes the dynamic behavior data of motor vehicles and non-motor vehicles in real time, and combines it with intelligent algorithms to achieve accurate prediction of potential conflicts and improve the reliability of detection results.

[0074] (2) In order to break through the dependence of existing technologies on scenarios, the present invention avoids using a single data source or parameters that are easily affected by environmental interference. Instead, it integrates multi-dimensional data to construct a universal conflict detection model suitable for complex urban road environments, ensuring the stability and adaptability of the system in different scenarios.

[0075] (3) The present invention establishes a multi-type conflict model, which not only covers behaviors such as running red lights in traditional scenarios, but also further expands to more complex and dangerous behaviors such as driving against traffic and changing lanes, comprehensively covering all types of potential conflict scenarios between motor vehicles and non-motor vehicles, thereby significantly improving the system's prediction accuracy of potential conflicts.

[0076] (4) To solve the problem that existing technologies only provide early warning but lack active intervention, the present invention combines intelligent transportation and vehicle-mounted communication technologies to send warning information to the driver and dynamically coordinate the driving status of the motor vehicle based on the predicted risk level, conduct active intervention, effectively reduce the risk of conflict, and ensure driving safety.

[0077] (5) The present invention detects abrupt lane-changing behavior and predicts the degree of lateral collision risk based on the abrupt lane-changing behavior, thereby making the prediction of the degree of lateral collision risk more accurate.

[0078] (6) The present invention calculates the safe distance to prevent rear-end collision based on the running status of the non-motor vehicle in front, and predicts the degree of risk of front collision based on the safe distance and the distance between the non-motor vehicle in front and the motor vehicle behind. This method can produce accurate and reliable prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] By referring to the following description in conjunction with the accompanying drawings, and with a more complete understanding of the present invention, other objects and results of the present invention will become more clear and easy to understand. In the accompanying drawings:

[0080] Figure 1 A flow chart of a vehicle control method considering machine-non-conflict provided by the present invention;

[0081] Figure 2 This is a structural block diagram of a vehicle control system that takes into account machine-non-conflicts provided by the present invention. DETAILED DESCRIPTION

[0082] In order to enable those skilled in the art to better understand the technical solutions and advantages of the present invention, the present application is described in detail below with reference to the accompanying drawings, but this is not intended to limit the scope of protection of the present invention.

[0083] Example 1:

[0084] like Figure 1 As shown, this embodiment provides a vehicle control method considering vehicle-non-vehicle conflict, the method comprising the following steps:

[0085] Step 1. Obtain non-motor vehicle driving status information and environmental status data, and perceive dangerous behaviors and the degree of danger based on the driving status information and environmental status data. The dangerous behaviors include abrupt lane changes. SLC The degree of danger includes the degree of danger of running a red light , the degree of danger of driving against traffic , the degree of risk of loss of control ;

[0086] Step 2: Based on the driving status information of non-motor vehicles and surrounding motor vehicles and the abrupt lane-changing behavior of non-motor vehicles SLC , perceive the risk of side collision At the same time, the safety distance D to prevent rear-end collision is calculated based on the driving status information of the non-motor vehicle and the rear motor vehicle, and the degree of risk of front collision is perceived based on the safety distance D and the distance between the front non-motor vehicle and the rear motor vehicle. ;

[0087] Step 3. Calculate the risk level of red light running based on the probability and severity coefficient of red light running, wrong-way driving, loss of control, side collision, and front collision in historical data. , the degree of danger of driving against traffic , the degree of risk of loss of control , side collision risk , forward collision risk The weight of

[0088] Step 4. Use a weighted scoring model to add the weights of each risk factor and the current risk level to obtain a comprehensive risk level score;

[0089] Step 5. Determine the danger level of the current driving situation based on the comprehensive danger level score. Different danger level intervals correspond to different control strategies.

[0090] In this embodiment, a visual module (camera) and a GPS module are installed on the smart helmet of a non-motor vehicle driver. The driver's smart helmet is linked with the vehicle-mounted networking facilities to obtain the driving status information of the non-motor vehicle during driving through the vehicle-mounted networking facilities, and perceive dangerous behaviors and risk levels based on the driving status information.

[0091] In this embodiment, the process of sensing the risk level of running a red light while a non-motor vehicle is driving is as follows:

[0092] Step a. Obtain the video stream (resolution) collected by the visual module (camera) on the non-motor vehicle driver's smart helmetH × W ,focal length f );

[0093] Step b. Use the YOLO-v8 model to perceive the status information of the traffic lights in the collected video stream;

[0094] Specifically, by modifying the format of the output header of the YOLO-v8 model, the YOLO-v8 model synchronously generates the following information:

[0095]

[0096] in: (x,y) is the coordinate of the center point of the traffic light, (w,h) The width and height of the traffic light's bounding box, color prob is the probability of a red light (Sigmoid output); y top , y bottom for The top and bottom ordinates of the traffic light's bounding box.

[0097] Through the generated information, the traffic light status S Make a judgment:

[0098]

[0099] in, S ∈{0 (green light), 1 (red light)};

[0100] Step c. Based on the principle of monocular ranging, calculate the focal length f of the visual module (camera) and the imaging height of the traffic light pixel W p The ratio k reflects the relative distance between non-motor vehicles and traffic lights;

[0101] because:

[0102]

[0103] in, W p is the pixel imaging height of the traffic light, extracted by the target detection model, W r Physical height of traffic lights ； As the distance d decreases, Continuously increasing, Continuously decrease, when it decreases to the threshold value determined by the experiment When the vehicle is driving on a highway, it can be considered that a red light running behavior has occurred.

[0104] Since there are situations where high-speed non-motor vehicles cannot brake in time, it is necessary to adjust the threshold Make corrections so that it can provide early warning and control of other motor vehicles:

[0105]

[0106] in, v is the speed of non-motor vehicles, α is the empirical coefficient, and its value is 0.2; v max is the maximum travel speed, which is 15 m / s; The value is 0.2.

[0107] Step d. The degree of danger of non-motor vehicles running red lights based on the current state of the traffic light and the ratio k Make a judgment:

[0108]

[0109] in, is the corrected threshold.

[0110] In this embodiment, when a non-motor vehicle is detected running a red light, the danger level of running a red light is ,otherwise .

[0111] In this embodiment, the process of sensing the degree of danger of a non-motor vehicle traveling in the wrong direction (reverse driving) is as follows:

[0112] In the perception of the danger level of reverse driving, the current location data of non-motor vehicles is obtained through the GPS module The location data of non-motor vehicles at the next moment At the same time, the centerline position information of the road where the non-motor vehicle is currently traveling is obtained through the vehicle networking facilities Based on the principle of vector product method, the danger level of non-motor vehicles driving against traffic is perceived. The specific modeling method is as follows:

[0113] Step a. Coordinate system conversion (WGS84 to plane coordinates):

[0114] The WGS84 coordinate system is a global three-dimensional coordinate system widely used in geolocation, surveying and mapping standards, and the Global Positioning System (GPS). This method converts WGS84 longitude and latitude into planar coordinates. This method can convert coordinates returned by a map API (map application programming interface) into planar coordinates for use in vector cross products, avoiding errors caused by the Earth's curvature.

[0115] Specifically, the present invention uses the transverse Mercator projection formula, and the core formula is:

[0116]

[0117]

[0118] in: is latitude and longitude, The UTM scale factor is 0.9996. The UTM (Universal Transverse Mercator) projection is a conformal cylindrical projection that projects the earth's surface onto a cylinder and then unfolds it into a plane. is the meridian arc length integral formula, is the first eccentricity, is the semi-major axis of the Earth ellipsoid, is the semi-minor axis of the Earth ellipsoid, is the radius of curvature of the Maoyou circle, is the second eccentricity of the Earth, ( x,y ) is the coordinate of the plane coordinate system after transformation;

[0119] Step b. Projection method and closest point algorithm:

[0120] The projection method can optimize the search for the coordinates of the perpendicular point from the driver's position to the road centerline at time t, and enhance the accuracy of judgment in conditions such as curved roads. The specific formula is as follows:

[0121] Given a line segment endpoint and non-motorized vehicle coordinates :

[0122]

[0123]

[0124] in, represents the proportional position of the foot of the perpendicular on line segment AB, Represents the vertical point of the center line Non-motorized vehicle location The direction vector, Represents the vertical point of the center line with endpoint The direction vector, Represents the vertical point of the center line with endpoint direction vector;

[0125] Step c. Determine the degree of retrograde risk using the two-dimensional vector cross multiplication method :

[0126]

[0127] in, For the same, is the displacement vector of non-motor vehicles during this period.

[0128] In this embodiment, when a non-motor vehicle is detected to be traveling in the wrong direction, the degree of danger of traveling in the wrong direction is ,otherwise .

[0129] In this embodiment, the process of sensing a sudden lane change during non-motor vehicle driving is as follows:

[0130] To reduce computational complexity and provide faster early warning and proactive intervention control for vehicles, the present invention uses either a static inclination angle threshold or a dynamic lane reference model for SLC detection, depending on the lane markings. If the lane markings are clear and the road is straight, the static inclination angle threshold model is used for calculation. If the lane is not straight or the lane markings cannot be accurately detected, the dynamic lane reference model is used for calculation. The specific situations are as follows:

[0131] (1) Static tilt threshold model calculation:

[0132] The model is mainly judged by two variables: steering angle and radial acceleration.

[0133] When the driver changes lanes suddenly, the steering angle α and the angle β between the non-motor vehicle and the lane line are complementary in value:

[0134]

[0135] in, is the steering angle of the vehicle; is the angle between the actual non-motor vehicle and the lane line;

[0136] Due to perspective, the angle calculated in the image Not equal to the actual angle , needs to be corrected by top view transformation:

[0137]

[0138] Transform represents the process of converting the lane lines in the image into a top-down view and then calculating the actual angle.

[0139] when Less than the experimentally determined threshold At the same time, the IMU module is used to detect the radial acceleration of non-motor vehicles. ; When the radial acceleration is detected Greater than the threshold set by the experiment When , it is considered that the vehicle has a large radial acceleration.

[0140] An abrupt lane change is considered to have occurred when both of the following conditions are met:

[0141] and

[0142] in, The value is 0.4g, The value is 20°;

[0143] (2) Dynamic lane benchmark model calculation:

[0144] First, the lane benchmark model is dynamically constructed;

[0145] Specifically, the lane lines are detected using camera visual perception, and the road boundaries are extracted using LiDAR point clouds. Subsequently, B-spline curve fitting is used to fit the detected lane lines or road boundary points into a virtual benchmark (lane benchmark), and its function is expressed as:

[0146]

[0147] in, is the B-spline basis function, is the control point, is a parameter, n is the number of collection points, For B-spline curves with parameters In the specific implementation of the dynamic lane benchmark model, the system first constructs road features through multi-sensor data fusion. Specifically, the camera captures images at a 60Hz frame rate and uses a deep learning-based segmentation network to extract lane feature points. At the same time, the 64-line LiDAR obtains the three-dimensional coordinates of the road boundary through point cloud clustering. After the two types of data are aligned in time and space, they are uniformly processed in the vehicle coordinate system.

[0148] In this embodiment, the B-spline curve fitting uses cubic uniform B-spline, and the number of control points is dynamically adjusted according to the road curvature. The control points are optimized by weighted least squares method with Tikhonov regularization, and the objective function is:

[0149]

[0150] in, is the weighted least squares term, Q represents the coordinate matrix of the road feature points obtained by the sensor, B is the matrix composed of B-spline basis functions, C is the coordinate matrix of the control points to be solved, and the weight matrix W is a diagonal matrix whose diagonal elements are assigned according to the detection confidence of each feature point.

[0151] is the Tikhonov regularization term. L usually adopts a second-order difference operator matrix to constrain the change range of the control points. The value range of the regularization coefficient λ is set to 0.1 to 0.3. By adjusting this parameter, the relationship between curve fitting accuracy and smoothness can be balanced.

[0152] Then, Cholesky decomposition is used to efficiently solve the problem. The normal equation corresponding to the objective function is: .

[0153] Then, based on the calculation results, the lateral displacement change rate of the vehicle (non-motor vehicle) relative to the lane reference (virtual reference) is calculated. Calculation is performed to reflect the urgency of lane change for non-motor vehicles:

[0154]

[0155] in, Unit time The lateral distance change between the inner vehicle and the lane benchmark.

[0156] Afterwards, according to the lane curvature Adaptive adjustment of the maximum allowable deviation rate , the expression is:

[0157]

[0158] in, is the basic threshold, the value is 0.7m / s, is the curvature compensation coefficient, which is set to 0.2. is the lane curvature threshold, which is 0.03 .

[0159] Finally, the sudden lane change behavior of non-motor vehicles SLC Make a judgment:

[0160]

[0161] In this embodiment, if , it is considered that the non-motor vehicle has made an abrupt lane change. ,otherwise .

[0162] In this embodiment, the risk level of a lateral collision is perceived based on the abrupt lane change behavior of a non-motor vehicle. The specific situation is as follows:

[0163] For side collision risk, the present invention considers the distance between the motor vehicle and the adjacent non-motor vehicle and the non-motor vehicle's driving behavior, particularly the dangers of lane changes. The risk of side collision is assessed by measuring the lateral distance and determining whether a sudden lane change occurs.

[0164] The lateral distance between a motor vehicle and an adjacent non-motor vehicle is calculated as follows:

[0165]

[0166] Where, is the lateral distance between the motor vehicle and the adjacent non-motor vehicle (m); , is the horizontal and vertical coordinates of the current motor vehicle; , are the horizontal and vertical coordinates of the adjacent non-motor vehicles.

[0167] At the same time, if a non-motor vehicle makes an abrupt lane change, the risk of a side collision will increase, so the lateral distance needs to be corrected:

[0168]

[0169] Among them, SLC is the marker variable of acute lane change behavior, is the distance correction coefficient, which is taken as 0.2 here.

[0170] Side collision risk The evaluation looks like this:

[0171]

[0172] In this embodiment, when there is a risk of side collision, =1, otherwise, =0.

[0173] In this embodiment, the process of sensing the degree of front collision risk during the non-motor vehicle driving is as follows:

[0174] To determine the degree of frontal collision risk, the present invention uses ultrasonic sensors to sense the speed and relative speed of non-motor vehicle drivers, constructs a safety distance model, determines the values ​​of each parameter in the model, and adopts different safety distances for different situations. The safety distance calculation formula of the rear-end collision risk perception module is:

[0175]

[0176] in, To prevent rear-end collisions, keep a safe distance. and are the distances traveled by the front vehicle (non-motor vehicle) and the rear vehicle (motor vehicle) during the braking process, It is the minimum safety distance, which is 2m.

[0177] The car is currently stationary:

[0178]

[0179]

[0180] in, is the speed of the preceding vehicle (non-motor vehicle), is the acceleration of the preceding vehicle (non-motor vehicle), is the reaction time of the motor vehicle driver, is the braking response time;

[0181] The current vehicle is in a state of constant speed or constant acceleration:

[0182] The relative speed of the two cars is relatively small, and the rear car is A moment in a time period The speed is reduced to the same as that of the vehicle ahead. During the time period, the deceleration of the following vehicle is directly proportional to time;

[0183]

[0184] in, and are the speeds of the front and rear vehicles, is the reaction time of the motor vehicle driver, is the braking response time, is the braking time when the speed of the rear vehicle is the same as that of the front vehicle;

[0185] The relative speed of the vehicles is relatively high. After the deceleration of the rear vehicle reaches its maximum value, its speed is still higher than that of the front vehicle. At this time, the maximum braking deceleration needs to be maintained for a period of time before the rear vehicle can slow down to the same speed as the front vehicle.

[0186]

[0187] The current car is in a decelerating state:

[0188] Since the front car is in a decelerating state, as long as either of the two cars is still moving, the distance between the two cars will continue to shrink. Therefore, the moment when the speed of the rear car and the front car is reduced to zero (both stop) is the most dangerous moment.

[0189]

[0190] in, and are the speeds of the front and rear vehicles, and are the accelerations of the front and rear vehicles, is the reaction time of the motor vehicle driver, is the brake response time.

[0191] Forward collision risk The evaluation can be judged by the safety distance D to prevent rear-end collision, as shown below.

[0192]

[0193] in, S It is the distance between the non-motor vehicle in front and the motor vehicle behind.

[0194] In this embodiment, the process of sensing the risk of loss of control during the driving of a non-motor vehicle is as follows:

[0195] The risk of loss of control is usually related to factors such as the speed, turning angle, and road friction coefficient of the non-motor vehicle. The present invention predicts the possibility of loss of control by judging the lateral acceleration and turning radius of the non-motor vehicle and combining it with the road conditions. The expression is:

[0196]

[0197] in, is the radial acceleration of non-motor vehicles (m / s 2 ), ; is the current speed of the non-motor vehicle (m / s); is the turning radius of non-motor vehicles (m), is the friction coefficient of the road surface, In normal weather conditions, the value is 0.7; in rainy days, the value is 0.3; and in snowy days, the value is 0.1.

[0198] To comprehensively assess the risk , using a weighted scoring model, the weights of each risk factor and the current risk level are weighted and summed to obtain a comprehensive risk level score. However, due to the risk level vector It is a binary variable of 0-1. The common entropy weight method may fail to calculate each risk factor. Therefore, the present invention uses an improved frequency statistics method to calculate the weight of each risk factor. The specific situation is:

[0199] First, calculate the probability of the jth risk factor appearing in the historical data :

[0200]

[0201] Where, For the j The number of occurrences of risk factors, is the total number of samples;

[0202] Then, the weight of each risk factor is calculated. The higher the frequency of the risk, the lower its weight should be. Conversely, rare but high-risk events should be given a higher weight. Therefore, the weight formula is:

[0203]

[0204] in, is the weight of the j-th risk factor;

[0205] However, considering that some risks may occur infrequently but have serious consequences, the weights need to be modified based on expert knowledge, so the severity coefficient is introduced. , the final weight formula is:

[0206]

[0207] in, is the weight of the j-th risk factor after correction;

[0208] Finally, the comprehensive risk score It can be expressed as:

[0209] ;

[0210] in, 、 、 、 、 are the weights of the revised risk factors of running a red light, driving against traffic, rear-end collision, side collision and loss of control.

[0211] In this embodiment, the danger level of the current driving situation is determined based on the size of the comprehensive danger level score, as follows:

[0212] A: ;

[0213] B: ;

[0214] C: ;

[0215] D: .

[0216] In this embodiment, different risk level intervals correspond to different control strategies, specifically:

[0217] (1) Low risk - D range:

[0218] Provide minimum warning: a short horn sound, the corresponding warning icon on the instrument panel flashes slightly three times; the accelerator pedal damping is increased by 20% as a tactile reminder, but it does not affect the actual power output.

[0219] (2) Lower risk - Zone C:

[0220] Preventive measures are the main focus: a comfortable braking strategy is adopted, with deceleration controlled within the range of 0.5-1m / s²; a yellow floating warning box appears on the instrument panel display to indicate the estimated collision time; the accelerator pedal applies pulsed vibration feedback (each lasting 200ms), and power output is gradually reduced to 50%; if the driver is detected to have braked more than three times within three minutes, the intervention intensity is automatically reduced by 30% to avoid disrupting the driving rhythm.

[0221] (3) Medium risk - Zone B:

[0222] Implementing progressive defense: Braking system by formula Dynamically adjust deceleration; the steering system provides 5°~10° steering suggestions based on TTC (time to collision), and works with ESP (electronic stability program) to maintain stability; power output is limited to 30% opening, the orange warning area of ​​the instrument panel display screen continues to flash, accompanied by a voice prompt of "Danger! Please brake"; when it detects that the driver continues to step on the accelerator, the steering wheel will generate 5Hz damping feedback.

[0223] (4) High risk - Zone A:

[0224] Immediately initiate the highest level of intervention: first trigger the stepped emergency braking, use 2m / s² slow braking for the first 0.5 seconds to avoid drifting, then decelerate according to the formula The system dynamically increases deceleration based on real-time distance; simultaneously activates the electric power steering system, automatically executing obstacle avoidance maneuvers within the lateral acceleration constraint of ≤0.3g; completely cuts power to the powertrain, and simultaneously activates a multi-modal alarm. A full-screen red countdown is projected onto the windshield, the seats vibrate at a 10Hz frequency, and a 2000Hz high-frequency beeping sound is emitted. The system's response latency is strictly controlled within 100ms, ensuring a vehicle speed reduction of at least 60% within 1 second.

[0225] The present invention uses external precise timing interrupts to achieve timed data collection and storage for smart helmets, and transmits data on dangerous behaviors and levels of danger of non-motor vehicles to nearby motor vehicles through the V2X (Vehicle-to-Everything) technology of the Internet of Vehicles, facilitating motor vehicles to analyze the level of danger and control the motor vehicles based on the analysis results to avoid collision risks.

[0226] Example 2:

[0227] like Figure 2As shown, the present invention also provides a vehicle control system that considers vehicle-non-motor vehicle conflicts, the system comprising an information acquisition module, a road feature perception module, a vehicle parameter perception module, a non-motor vehicle driving behavior perception module, a danger level perception module, a danger level determination module, and a warning and control module; wherein the information acquisition module is used to obtain driving status information of motor vehicles and non-motor vehicles and environmental status data;

[0228] The road feature perception module is used to obtain road-related information, including road center lines, lane lines, lane curvatures, road boundary points, etc., based on the environmental status data collected by the information collection module;

[0229] The vehicle parameter perception module is used to obtain various dynamic parameters of the interaction between the motor vehicle and the non-motor vehicle during the driving process, including parameters such as driving speed, acceleration, and steering angle, based on the driving status information of the motor vehicle and the non-motor vehicle collected by the information collection module;

[0230] The non-motor vehicle driving behavior perception module is used to perceive dangerous behaviors and the degree of danger during the non-motor vehicle driving process based on the non-motor vehicle driving state data and the environmental state data;

[0231] The danger level perception module is used to determine the danger level of a front collision and the danger level of a side collision based on the dynamic parameters obtained by the vehicle parameter perception module and the dangerous behavior perceived by the non-motor vehicle driving behavior perception module;

[0232] The danger level determination module is used to calculate the comprehensive danger level based on the danger levels of front collision, side collision, loss of control, running a red light and wrong-way driving, and classify the danger level of the current traffic situation in combination with preset safety standards and thresholds;

[0233] The early warning and control module is used to take corresponding early warning and control measures according to the results of the danger level determination module.

[0234] Furthermore, in this embodiment, the information collection module includes a visual module (camera) installed on the non-motor vehicle driver's smart helmet, a GPS module, and vehicle-mounted sensors installed on the non-motor vehicle, the vehicle-mounted sensors including an IMU module, etc.; it also includes vehicle-mounted sensors installed on motor vehicles, etc.

[0235] In this embodiment, the system also includes a memory, and the data obtained by the road feature perception module and the vehicle parameter perception module are stored in the corresponding memory 1; the judgment result of the danger level judgment module is stored in the memory 2 for use by the subsequent warning and control module.

[0236] The present invention also provides an electronic device, comprising: one or more processors and a memory; wherein the memory is used to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the vehicle control method described above.

[0237] The present invention also provides a computer-readable medium having a computer program stored thereon, wherein the computer program implements the above-mentioned vehicle control method when executed by a processor.

[0238] Those skilled in the art will appreciate that all or part of the functions of the various methods / modules in the above embodiments may be implemented via hardware or via computer programs. When all or part of the functions in the above embodiments are implemented via computer programs, the program may be stored in a computer-readable storage medium, which may include a read-only memory, random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to implement the above functions. For example, the program may be stored in a memory of a device, and when the program in the memory is executed by a processor, all or part of the above functions may be implemented.

[0239] In addition, when all or part of the functions in the above-mentioned embodiments are implemented by means of a computer program, the program can also be stored in a storage medium such as a server, another computer, a disk, an optical disk, a flash drive or a mobile hard disk, and saved to the memory of a local device by downloading or copying, or the system of the local device is updated. When the program in the memory is executed by the processor, all or part of the functions in the above-mentioned embodiments can be implemented.

[0240] The above description of the present invention using specific examples is intended only to facilitate understanding of the present invention and is not intended to limit the present invention. A person skilled in the art of the present invention may make several simple deductions, modifications, or substitutions based on the principles of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A vehicle control method considering vehicle-non-vehicle conflicts, characterized in that: The method comprises the following steps: Step 1. Obtain non-motor vehicle driving state information and environmental state data, and perceive dangerous behaviors and danger levels based on the driving state information and environmental state data. The dangerous behaviors include sudden lane change behavior SLC, and the danger levels include red light running danger level R RRL , the risk level of retrograde driving R CTF , risk level of loss of control R loss ; The method of perceiving the danger level of running a red light is as follows: Step a. Obtain the video stream collected by the visual module on the non-motor vehicle driver's smart helmet; Step b. Use the YOLO-v8 model to perceive the status information of the traffic lights in the collected video stream; Step c. Calculate the focal length f of the visual module and the imaging height W of the traffic light pixel p The ratio of Step d. Based on the current status of the signal light and Danger level R for non-motor vehicles running red lights RRL Make a judgment: Wherein, the traffic light state S=1 represents the red light, k0′ is the corrected threshold, and the calculation formula is: Among them, v is the speed of non-motor vehicles, α is the empirical coefficient, and v max is the maximum driving speed, k0 is the threshold value, and its value is 0.2; When sensing a sudden lane change, the system uses either a static inclination threshold or a dynamic lane reference model based on the lane markings. If the lane markings are clear and the road is straight, the static inclination threshold model is used. If the lane is not straight or the lane markings cannot be accurately detected, the dynamic lane reference model is used. The static tilt threshold model is calculated based on two variables: steering angle and radial acceleration. An abrupt lane change is considered to have occurred when both of the following conditions are met: β<β0 and a r >a0; Among them, β is the angle between the actual non-motor vehicle and the lane line, a r is the radial acceleration of the non-motor vehicle, a0 is the threshold value, which is 0.4g, β0 is the threshold value, which is 20°; The specific steps for calculating the dynamic lane benchmark model are as follows: Step a. Dynamically construct the lane benchmark model; First, lane lines are detected and road boundaries are extracted using LiDAR point clouds. B-spline curve fitting is then used to fit the detected lane lines or road boundary points into lane benchmarks. B-spline curve fitting uses cubic uniform B-splines, and the number of control points is dynamically adjusted based on the road curvature. The control points are optimized by weighted least squares method with Tikhonov regularization, and the objective function is: in, is the weighted least squares term, Q represents the coordinate matrix of the road feature points obtained by the sensor, B is the matrix composed of B-spline basis functions, C is the coordinate matrix of the control points to be solved, and the weight matrix W is a diagonal matrix whose diagonal elements are assigned according to the detection confidence of each feature point; is the Tikhonov regularization term, L uses a second-order difference operator matrix to constrain the change range of the control points; the value range of the regularization coefficient λ is set to 0.1 to 0.3; Step b. The lateral displacement change rate v of the non-motor vehicle relative to the lane reference lat Perform calculations; Step c. Adaptively adjust the maximum allowable deviation rate according to the lane curvature k The expression is: Among them, v0 is the basic threshold, λ is the curvature compensation coefficient, and κ0 is the lane curvature threshold; Step d. Determine the SLC of the non-motor vehicle's sudden lane change behavior. If If the non-motor vehicle has an abrupt lane change, SLC = 1; otherwise, SLC = 0; Step 2: Based on the driving status information of the non-motor vehicle and surrounding motor vehicles and the non-motor vehicle's sudden lane change behavior SLC, the side collision risk level R is perceived. side At the same time, the safety distance D to prevent rear-end collision is calculated based on the driving status information of the non-motor vehicle and the rear motor vehicle, and the front collision risk level R is perceived based on the safety distance D and the distance between the front non-motor vehicle and the rear motor vehicle. front ; When the non-motor vehicle in front is stationary, the expression for the safety distance D to prevent rear-end collision is: When the non-motorized vehicle in front is traveling at a constant speed or with a constant acceleration, and the motorized vehicle behind reduces its speed to the same as that of the vehicle in front at time t2 within the time period t2, the expression for the safety distance D to prevent rear-end collision is: Otherwise, the expression of the safety distance D to prevent rear-end collision is: When the non-motorized vehicle ahead is in a decelerating state, the safe distance D to prevent rear-end collision is expressed as: Among them, V a and V b are the speeds of the non-motor vehicle in front and the motor vehicle behind, respectively, a A with a B are the accelerations of the non-motor vehicle in front and the motor vehicle behind, t1 is the reaction time of the motor vehicle driver, t2 is the braking response time, t′2 is the braking time when the speeds of the non-motor vehicle in front and the motor vehicle behind are the same, and S0 is the minimum safe distance; Step 3. Calculate the risk level R of running a red light based on the probability and severity coefficient of running a red light, driving against traffic, losing control, side collision, and front collision in the historical data. RRL , the risk level of retrograde driving R CTF , risk level of loss of control R loss , Side collision risk level R side , forward collision risk level R front The weight of the weight is determined as follows: First, calculate the probability p of the jth risk factor appearing in the historical data j : Where N j is the number of occurrences of the jth risk factor, and N is the total number of samples; risk factors include running a red light, driving against traffic, loss of control, side collision, and front collision; Then, the weight of each risk factor is calculated, and the weight formula is: Among them, ω j is the weight of the j-th risk factor; Then, the severity coefficient s is introduced j , s j ∈*(0.5,1.5), the weight is modified, and the final weight formula is: in, is the weight of the j-th risk factor after correction; Step 4: Use the weighted scoring model to sum the weights of each risk factor and the current risk level to obtain a comprehensive risk level score. The comprehensive risk level score S danger Expressed as: in, are the weights of the revised risk factors of running a red light, driving against traffic, rear-end collision, side collision, and loss of control; Step 5. Determine the danger level of the current driving situation based on the comprehensive danger level score. Different danger level intervals correspond to different control strategies.

2. The vehicle control method considering non-machine conflicts according to claim 1, characterized in that: The method for sensing the degree of danger of reverse driving is as follows: the current position data of the non-motor vehicle and the position data of the non-motor vehicle at the next moment are obtained through the GPS module, and the center line position information of the road where the non-motor vehicle is currently traveling is obtained at the same time; the degree of danger of reverse driving of the non-motor vehicle is sensed based on the vector product principle. When a non-motor vehicle is detected to be driving in the opposite direction, the degree of danger of reverse driving R is detected. CTF =1, otherwise R CTF =0; The risk of loss of control is determined by the lateral acceleration and turning radius of the non-motor vehicle in combination with the road conditions. The expression is: Among them, a r is the radial acceleration of the non-motor vehicle, V is the current speed of the non-motor vehicle; r is the turning radius of the non-motor vehicle, and μ is the friction coefficient of the road surface.

3. The vehicle control method considering non-machine conflicts according to claim 1, characterized in that: The method for perceiving the risk of lateral collision based on the abrupt lane change behavior of non-motor vehicles is as follows: first calculate the lateral distance d between the motor vehicle and the adjacent non-motor vehicle. l , correct the lateral distance based on the abrupt lane change behavior, in, is the corrected lateral distance between the motor vehicle and the adjacent non-motor vehicle, ∈ is the distance correction coefficient, which is 0.2; the lateral collision risk level R is determined based on the corrected lateral distance between the motor vehicle and the adjacent non-motor vehicle. side , the expression is: When sensing the risk of a front collision, the safe distance D to prevent rear-end collision is first calculated based on the running status of the non-motor vehicle. Then, the distance S between the non-motor vehicle in front and the motor vehicle behind is compared with the safe distance D to determine the risk of a front collision R. front , the expression is:

4. The vehicle control method considering non-machine conflicts according to claim 1, characterized in that: In step 5, the comprehensive risk score S danger The risk is divided into four levels. For low risk, the driver is reminded by early warning; for relatively low risk, the deceleration and power output are controlled while the early warning is given; for medium risk, the driver is reminded by the formula a=2+10(S danger -0.5) dynamically adjusts deceleration, provides steering advice, and controls power output. For high-risk situations, it simultaneously triggers stepped emergency braking with a warning and activates the electric power steering system, automatically executing obstacle avoidance maneuvers within the constraint of lateral acceleration ≤0.3g, completely cutting off power output.

5. A vehicle control system considering non-conflict for implementing the control method according to any one of claims 1 to 4, characterized in that: The system includes an information collection module, a road feature perception module, a vehicle parameter perception module, a non-motor vehicle driving behavior perception module, a danger level perception module, a danger level determination module, and an early warning and control module; wherein the information collection module is used to obtain driving status information of motor vehicles and non-motor vehicles and environmental status data; The road feature perception module is used to obtain road-related information, including road center lines, lane lines, lane curvatures, and road boundary points, based on the environmental status data collected by the information collection module; The vehicle parameter perception module is used to obtain various dynamic parameters of the interaction between the motor vehicle and the non-motor vehicle during the driving process, including driving speed, acceleration, and steering angle, based on the driving status information of the motor vehicle and the non-motor vehicle collected by the information collection module; The non-motor vehicle driving behavior perception module is used to perceive dangerous behaviors and the degree of danger during the non-motor vehicle driving process based on the non-motor vehicle driving state data and the environmental state data; The danger level perception module is used to determine the danger level of a front collision and the danger level of a side collision based on the dynamic parameters obtained by the vehicle parameter perception module and the dangerous behavior perceived by the non-motor vehicle driving behavior perception module; The danger level determination module is used to calculate the comprehensive danger level based on the danger levels of front collision, side collision, loss of control, running a red light and wrong-way driving, and classify the danger level of the current traffic situation in combination with preset thresholds; The early warning and control module is used to take corresponding early warning and control measures according to the results of the danger level determination module.

Images