An intelligent driving system based on camera and radar preview information

Abstract

The application discloses an intelligent driving system based on camera and radar preview information, which comprises a driving data collection module, a preview information analysis module, a driving force adjustment module and an adjustment efficiency judging module. The driving data collection module is used for collecting data of a vehicle during driving; the preview information analysis module analyzes and calculates various index parameters about vehicle driving according to information collected by a camera and a radar installed on the vehicle; the driving force adjustment module is used for selecting a driving force adjustment mode of the vehicle according to a driving force evaluation total parameter K calculated by the preview information analysis module; the adjustment efficiency judging module comprises a performance index calculation module and an adjustment effect judging module, the performance index calculation module is used for calculating an adjustment performance index, and the adjustment effect judging module is used for judging a working state of the intelligent driving system based on camera and radar preview information according to the adjustment performance index.

Description

Technical Field

[0001] This invention relates to an intelligent driving system based on camera and radar pre-aiming information. Background Technology

[0002] Camera and radar technologies are crucial perception technologies in intelligent driving systems. They provide key information about the vehicle's surrounding environment, enhancing the driver's perception of the driving environment and supporting real-time vehicle perception, decision-making, and control. Current development of related functions largely focuses on environmental perception, path planning, and decision-making control, with little consideration given to the integration of camera and radar technologies with the drive system. Furthermore, the evaluation metrics for the degree of drive force adjustment are relatively singular. Adjusting the drive force based on camera and radar pre-aiming information can significantly improve vehicle performance. Therefore, how to adjust the vehicle's drive force to improve driving safety, smoothness, and driver comfort has become a pressing technical problem for the applicant. To address these issues, this invention proposes an intelligent drive system based on camera and radar pre-aiming information. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent driving system based on camera and radar pre-aiming information to solve the problems encountered in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: an intelligent driving system based on camera and radar pre-aiming information includes a driving data acquisition module, a pre-aiming information analysis module, a driving force adjustment module, and an adjustment efficiency determination module;

[0005] The driving data acquisition module is used to collect data of the vehicle during driving, including the total mass of the vehicle m, the speed of the vehicle v, the width of the road B, and the wheelbase of the vehicle L.

[0006] The pre-aiming information analysis module analyzes and calculates various parameters related to vehicle driving based on information collected by cameras and radar installed on the vehicle, including:

[0007] S1. Establish a driving force model for the vehicle during driving, where the vehicle's driving force F is... t Satisfying the formula:

[0008]

[0009] Among them, F f F represents the rolling resistance of a vehicle. w F represents the air resistance of a vehicle. i The vehicle's slope resistance is represented by δ, the vehicle's rotational mass conversion factor is represented by m, the vehicle's total mass is represented by v, the vehicle's speed is represented by t, and time is represented by m.

[0010] S2. Calculate the evaluation parameters for each influencing driving force according to the following formulas, including:

[0011] S2.1 Calculate the road sign sub-parameter K1 according to the following formula,

[0012]

[0013] Where w1, w2, and w3 represent weighting coefficients;

[0014] k 11 This represents the speed limit sign coefficient. When the camera and radar detect a speed limit sign ahead and the vehicle's speed exceeds the limit, k... 11 =0.8, when the camera detects a speed limit sign ahead and the vehicle speed does not exceed the limit, k 11 =1.0, when the camera does not detect a speed limit sign ahead, k 11 =1.2;

[0015] k 12 This indicates the speed limit cancellation factor. When a vehicle is traveling in a speed-limited section and the camera and radar detect a speed limit cancellation sign ahead, k... 12 =1.2, in other cases, k 12 =1.0;

[0016] k 13 k represents the highway exit coefficient. When a vehicle is traveling on a highway and a camera or radar detects a highway exit sign, k... 13 =0.9, in other cases, k 13 =1.0;

[0017] k 14 k represents the highway entrance coefficient, which is the coefficient used when cameras and radar detect a highway entrance sign. 14 =1.1, other cases,

[0018] k 14 =1.0;

[0019] k 15 k represents the special area sign coefficient, which is used when cameras and radar detect construction zone signs, school zone signs, and pedestrian crossing signs ahead. 15 =0.8, in other cases, k 15 =1.0;

[0020] k 16 k represents the curve coefficient, which is used when cameras and radar detect a level curve in the road. 16 =0.9, when the camera and radar detect that the road is a perpendicular curve, k 16 =0.8, in other cases, k16 =1.0;

[0021] k 17 k represents the gradient coefficient, which is used when cameras and radar detect that the road has a longitudinal slope. 17 =0.9, when the camera and radar detect that the road is a transverse slope, k 17 =0.8, in other cases, k 17 =1.0;

[0022] S2.2 Calculate the camera blind spot detection sub-parameter K2 according to the following formula.

[0023]

[0024] Where w4 and w5 represent weighting coefficients;

[0025] k 21 k represents the automatic white balance coefficient, and its value depends on the camera's automatic white balance capability. When the camera can provide accurate white balance under different lighting conditions, k... 21 =1.2, in other cases, k 21 =1.0;

[0026] k 22 This represents the vertical field of view spread factor, the value of which depends on the vertical field of view extension factor of the camera. Where Angv0 represents the driver's vertical field of view, and Angv represents the sum of the vertical field of view angles of all cameras, when... At that time, k 22 =0.5, when At that time, k 22 =1.1, when At that time, k 22 =1.2;

[0027] k 23 This represents the horizontal field-of-view spread factor, the value of which depends on the horizontal field-of-view extension factor of the camera. Where Angh0 represents the driver's horizontal field of view, and Angh represents the sum of the horizontal field of view angles of all cameras. At that time, k 23 =0.5, when At that time, k 23 =1.1, when At that time, k 23 =1.2;

[0028] k 24 This represents the field of view expansion factor, the value of which depends on the percentage of blind spot coverage captured by the camera. Where Area0 represents the driver's blind spot area, and Area represents the blind spot area captured by all cameras. When ψ1 < 60%, k 24 =1.2, when ψ1≥60%, k 24 =1.3;

[0029] k 25 This represents the field of view expansion accuracy coefficient, the value of which depends on the percentage of blind spot accuracy captured by the camera. Where Area represents the blind spot area captured by all cameras, Area1 represents the blind spot area correctly identified by all cameras, and when ψ2 < 85%, k 25 =0.8, when ψ2≥85%, k 25 =1.2;

[0030] S2.3 Calculate the traffic environment monitoring sub-parameter K3 according to the following formula.

[0031]

[0032] Where w6 and w7 represent weighting coefficients;

[0033] k 31 k represents the pedestrian visibility coefficient, which is the coefficient used when cameras and radar detect pedestrians engaging in behaviors that affect vehicle movement or exhibiting a tendency to do so. 31 =0.7, in other cases, k 31 =1.0;

[0034] k 32 k represents the coefficient of surrounding traffic violations. It is calculated when cameras and radar detect traffic violations or trends of violations by surrounding drivers. 32 =0.8, in other cases, k 32 =1.0;

[0035] k 33 This represents the roadside emergency coefficient, indicating when cameras and radar detect an emergency event in the surrounding area. Emergency events include, but are not limited to, road collapses, traffic accidents, and sudden braking of the vehicle in front. k 33 =0.5, otherwise, k 33 =1.0;

[0036] k 34 This represents the road width coefficient, the value of which depends on the relationship between the road width B detected by cameras and radar and the vehicle wheelbase L. At that time, k 34 =0.7, when At that time, k 34 =1.0, when At that time, k 34 =1.3;

[0037] k 35 k represents the road slipperiness coefficient, which is the coefficient of slipperiness detected by cameras and radar when there is water, snow, or oil on the road. 35 =0.8, in other cases, k 35 =1.0;

[0038] S2.4 Calculate the driver state component parameter K4 according to the following formula.

[0039]

[0040] Where w8 and w9 represent weighting coefficients;

[0041] k 41 This represents the driver's head movement coefficient, the value of which depends on the frequency Δf of the driver's head tilting as captured by the in-vehicle camera. Where, N act T represents the number of times the driver looks down within a certain period of time. act f represents the observation duration. ave This indicates a reference value for the frequency of a driver looking down while driving in a safe manner. At that time, there is a potential for driver inattention and fatigue. 41 =0.8, when At that time, k 41 =1.0;

[0042] k 42 This represents the driver's hand movement coefficient. When the in-vehicle camera captures frequent hand movements, hands leaving the steering wheel, or excessive gripping of the steering wheel, it indicates a potential for driver inattention, mental stress, or fatigue. (k) 42 =0.8, in other cases, k 42 =1.0;

[0043] k 43 This represents the driver's eye movement coefficient. When the in-vehicle camera captures excessively long eye closure, significantly increased blinking frequency, and bloodshot eyes, the driver may be experiencing inattention or fatigue. 43 =0.8, in other cases, k 43 =1.0;

[0044] k 44 This represents the impact coefficient of road traffic volume. When cameras and radar detect high road traffic volume, it may cause drivers to feel nervous and anxious. 44 =0.9, in other cases, k 44 =1.0;

[0045] k 45 k represents the coefficient of change in driving behavior. When cameras and radar detect frequent lane changes, fluctuations in vehicle speed, and unstable lane keeping, it indicates a potential for driver inattention and fatigue. 45 =0.8, in other cases, k 45 =1.0;

[0046] k 46 This represents the driver's facial expression coefficient. When the in-vehicle camera captures the driver with their mouth tightly closed, brows furrowed, and forehead sweating for a period of time, it indicates a potential for the driver to drive under stress. 46 =0.9, in other cases, k 46 =1.0;

[0047] S2.5 Calculate the surrounding vehicle state sub-parameter K5 according to the following formula.

[0048]

[0049] Among them, w 10 w 11 Indicates the weighting coefficient;

[0050] k 51 This represents the headlight status coefficient of the vehicle ahead. When the camera and radar detect that the turn signal of the vehicle ahead is on, k... 51 =0.8, when the brake lights of the vehicle in front are detected to be on, k 51 =0.6, in other cases, k 51 =1.0;

[0051] k 52 This represents the following vehicle status coefficient, k, which is calculated when the camera and radar detect that the following vehicle has activated its left turn signal, indicating an intention to overtake. 52 =0.8, when the camera and radar detect a decrease in the relative distance between the vehicle and the vehicle behind, k 52 =0.9, in other cases, k 52 =1.0;

[0052] k 53 This represents the vehicle's trajectory coefficient. When cameras and radar detect that surrounding vehicles are significantly deviating from their trajectory, there is a possibility of abnormal driving behavior. (k) 53 =0.7, in other cases, k 53 =1.0;

[0053] k 54 k represents the vehicle attitude coefficient, which is the coefficient used when cameras and radar detect tilting and tire slippage of surrounding vehicles. 54 =0.8, in other cases, k 54= 1.0;

[0054] S3. Calculate the total driving force evaluation parameter K according to the following formula

[0055]

[0056] where, α1, α2, α3, α4, α5 are the weighted values calculated for individual indicators;

[0057] The driving force adjustment module is used to select the driving force adjustment mode of the vehicle according to the total driving force evaluation parameter K;

[0058] The adjustment efficiency determination module includes a performance index calculation module and an adjustment effect judgment module.

[0059] The driving force adjustment module describes the selection of the driving force adjustment mode by introducing the first judgment parameter ζ1, the second judgment parameter ζ2 and the third judgment parameter ζ3, and the judgment parameters satisfy the following conditions:

[0060]

[0061] The driving force adjustment module includes a conservative adjustment mode, a moderate adjustment mode, an active adjustment mode and an emergency adjustment mode. Among them, the conservative adjustment mode has the smallest degree of adjustment to the original driving force, the moderate adjustment mode has a relatively small degree of adjustment to the original driving force, the active adjustment mode has a larger adjustment to the original driving force, and the emergency adjustment mode has the largest adjustment to the original driving force.

[0062] When the total driving force evaluation parameter K satisfies 0 < K ≤ ζ1, the driving force adjustment module will execute the conservative adjustment mode, and the driving force F of the vehicle t satisfies the formula:

[0063]

[0064] where, F f represents the rolling resistance of the vehicle, F w represents the air resistance of the vehicle, F i represents the ramp resistance of the vehicle, δ represents the conversion coefficient of the rotating mass of the vehicle, m represents the total mass of the vehicle, v represents the speed of the vehicle, and t represents the time;

[0065] When the total driving force evaluation parameter K satisfies ζ1 < K ≤ ζ2, the driving force adjustment module will execute the moderate adjustment mode, and the driving force F of the vehicle t satisfies the formula:

[0066]

[0067] where, F f represents the rolling resistance of the vehicle, F wDenotes the air resistance of the vehicle, F i Denotes the ramp resistance of the vehicle, δ denotes the conversion coefficient of the rotating mass of the vehicle, m denotes the total mass of the vehicle, v denotes the speed of the vehicle, and t denotes time;

[0068] When the total driving force evaluation parameter K satisfies ζ2 < K ≤ ζ3, the driving force adjustment module will execute the active adjustment mode, and the driving force F of the vehicle t Satisfies the formula:

[0069]

[0070] Among them, F f Denotes the rolling resistance of the vehicle, F w Denotes the air resistance of the vehicle, F i Denotes the ramp resistance of the vehicle, δ denotes the conversion coefficient of the rotating mass of the vehicle, m denotes the total mass of the vehicle, v denotes the speed of the vehicle, and t denotes time;

[0071] When the total driving force evaluation parameter K satisfies ζ3 < K < 1, the driving force adjustment module will execute the emergency adjustment mode, and the driving force F of the vehicle t Satisfies the formula:

[0072]

[0073] Among them, F f Denotes the rolling resistance of the vehicle, F w Denotes the air resistance of the vehicle, F i Denotes the ramp resistance of the vehicle, δ denotes the conversion coefficient of the rotating mass of the vehicle, m denotes the total mass of the vehicle, v denotes the speed of the vehicle, and t denotes time.

[0074] The performance index calculation module is used to calculate the adjustment performance index Res, and the calculation formula of the adjustment performance index Res is as follows:

[0075]

[0076] Among them, β1, β2, and β3 denote weighting coefficients, and β1 + β2 + β3 = 1;

[0077] V represents the actual driving speed of the vehicle using the intelligent driving system based on camera and radar preview information;

[0078] V0 represents the best driving speed that the vehicle can reach under the same driving conditions for measuring V when the vehicle does not use the intelligent driving system based on camera and radar preview information;

[0079] T represents the actual driving torque of the vehicle using the intelligent driving system based on camera and radar preview information;

[0080] T0 represents the optimal driving torque that the vehicle can achieve under the same driving conditions measured T when the vehicle is not using the intelligent drive system based on camera and radar pre-aiming information.

[0081] S represents the driver's rating of driving comfort on a 100-point scale when the vehicle uses the aforementioned intelligent drive system based on camera and radar pre-aiming information;

[0082] S0 represents the highest percentage score of driving comfort that the vehicle can achieve under the same driving conditions measured by S when the vehicle is not using the aforementioned intelligent drive system based on camera and radar pre-aiming information.

[0083] The adjustment effect judgment module is used to judge the working state of the intelligent drive system based on camera and radar pre-aiming information according to the adjustment performance index Res, which is described by introducing a first threshold χ1 and a second threshold χ2, where 0<χ1<χ2<1;

[0084] When Res < χ1, the intelligent drive system based on camera and radar pre-aiming information is working well, and the driver can selectively exit the intelligent drive system based on camera and radar pre-aiming information.

[0085] When χ1≤Res<χ2, the intelligent drive system based on camera and radar pre-aiming information is in normal working condition, and the driver can selectively exit the intelligent drive system based on camera and radar pre-aiming information.

[0086] When Res>χ2, the intelligent drive system based on camera and radar pre-aiming information malfunctions, and the vehicle will be forcibly disengaged from the intelligent drive system based on camera and radar pre-aiming information.

[0087] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0088] 1. An intelligent drive system based on camera and radar pre-aiming information includes a driving data acquisition module, a pre-aiming information analysis module, a drive force adjustment module, and an adjustment efficiency determination module;

[0089] 2. The driving force adjustment module of the present invention describes the selection of driving force adjustment mode by introducing a first judgment parameter ζ1, a second judgment parameter ζ2 and a third judgment parameter ζ3. The driving force adjustment module includes a conservative adjustment mode, a moderate adjustment mode, an active adjustment mode and an emergency adjustment mode. Among them, the conservative adjustment mode has the smallest adjustment degree to the original driving force, the moderate adjustment mode has a relatively small adjustment degree to the original driving force, the active adjustment mode has a relatively large adjustment to the original driving force, and the emergency adjustment mode has the largest adjustment to the original driving force.

[0090] 3. The performance index calculation module of the present invention is used to calculate the adjustment performance index Res, and to describe the adjustment effect in conjunction with the first threshold χ1 and the second threshold χ2. Attached Figure Description

[0091] The present invention will be further described below with reference to the accompanying drawings:

[0092] Figure 1 This is a framework diagram of an intelligent driving system based on camera and radar pre-aiming information proposed in this invention. Detailed Implementation

[0093] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0094] like Figure 1 As shown, the present invention is an intelligent driving system based on camera and radar pre-aiming information, including a driving data acquisition module, a pre-aiming information analysis module, a driving force adjustment module, and an adjustment efficiency determination module;

[0095] The driving data acquisition module is used to collect data of the vehicle during driving, including the total mass of the vehicle m, the speed of the vehicle v, the width of the road B, and the wheelbase of the vehicle L.

[0096] The pre-aiming information analysis module analyzes and calculates various parameters related to vehicle driving based on information collected by cameras and radar installed on the vehicle, including:

[0097] S1. Establish a driving force model for the vehicle during driving, where the vehicle's driving force F is... t Satisfying the formula:

[0098]

[0099] Among them, F f F represents the rolling resistance of a vehicle. w F represents the air resistance of a vehicle. i The vehicle's slope resistance is represented by δ, the vehicle's rotational mass conversion factor is represented by m, the vehicle's total mass is represented by v, the vehicle's speed is represented by t, and time is represented by m.

[0100] S2. Calculate the evaluation parameters for each influencing driving force according to the following formulas, including:

[0101] S2.1 Calculate the road sign sub-parameter K1 according to the following formula,

[0102]

[0103] Where w1, w2, and w3 represent weighting coefficients;

[0104] k 11This represents the speed limit sign coefficient. When the camera and radar detect a speed limit sign ahead and the vehicle's speed exceeds the limit, k... 11 =0.8, when the camera detects a speed limit sign ahead and the vehicle speed does not exceed the limit, k 11 =1.0, when the camera does not detect a speed limit sign ahead, k 11 =1.2;

[0105] k 12 This indicates the speed limit cancellation factor. When a vehicle is traveling in a speed-limited section and the camera and radar detect a speed limit cancellation sign ahead, k... 12 =1.2, in other cases, k 12 =1.0;

[0106] k 13 k represents the highway exit coefficient. When a vehicle is traveling on a highway and a camera or radar detects a highway exit sign, k... 13 =0.9, in other cases, k 13 =1.0;

[0107] k 14 k represents the highway entrance coefficient, which is the coefficient used when cameras and radar detect a highway entrance sign. 14 =1.1, other cases,

[0108] k 14 =1.0;

[0109] k 15 k represents the special area sign coefficient, which is used when cameras and radar detect construction zone signs, school zone signs, and pedestrian crossing signs ahead. 15 =0.8, in other cases, k 15 =1.0;

[0110] k 16 k represents the curve coefficient, which is used when cameras and radar detect a level curve in the road. 16 =0.9, when the camera and radar detect that the road is a perpendicular curve, k 16 =0.8, in other cases, k 16 =1.0;

[0111] k 17 k represents the gradient coefficient, which is used when cameras and radar detect that the road has a longitudinal slope. 17 =0.9, when the camera and radar detect that the road is a transverse slope, k 17 =0.8, in other cases, k 17 =1.0;

[0112] S2.2 Calculate the camera blind spot detection sub-parameter K2 according to the following formula.

[0113]

[0114] Where w4 and w5 represent weighting coefficients;

[0115] k 21 k represents the automatic white balance coefficient, and its value depends on the camera's automatic white balance capability. When the camera can provide accurate white balance under different lighting conditions, k... 21 =1.2, in other cases, k 21 =1.0;

[0116] k 22 This represents the vertical field of view spread factor, the value of which depends on the vertical field of view extension factor of the camera. Where Angv0 represents the driver's vertical field of view, Angv represents the sum of the vertical field of view angles of all cameras, and when φ1 < 100%, k 22 =0.5, when 100%≤φ1<150%, k 22 =1.1, when φ1≥150%, k 22 =1.2;

[0117] k 23 This represents the horizontal field-of-view spread factor, the value of which depends on the horizontal field-of-view extension factor of the camera. Where Angh0 represents the driver's horizontal field of view, Angh represents the sum of the horizontal field of view angles of all cameras, and when φ2 < 100%, k 23 =0.5, when 100%≤φ2<150%, k 23 =1.1, when φ2≥150%, k 23 =1.2;

[0118] k 24 This represents the field of view expansion factor, the value of which depends on the percentage of blind spot coverage captured by the camera. Where Area0 represents the driver's blind spot area, and Area represents the blind spot area captured by all cameras. When ψ1 < 60%, k 24 =1.2, when ψ1≥60%, k 24 =1.3;

[0119] k 25 This represents the field of view expansion accuracy coefficient, the value of which depends on the percentage of blind spot accuracy captured by the camera. Where Area represents the blind spot area captured by all cameras, Area1 represents the blind spot area correctly identified by all cameras, and when ψ2 < 85%, k 25 =0.8, when ψ2≥85%, k 25 =1.2;

[0120] S2.3 Calculate the traffic environment monitoring sub-parameter K3 according to the following formula.

[0121]

[0122] Where w6 and w7 represent weighting coefficients;

[0123] k 31 k represents the pedestrian visibility coefficient, which is the coefficient used when cameras and radar detect pedestrians engaging in behaviors that affect vehicle movement or exhibiting a tendency to do so. 31 =0.7, in other cases, k 31 =1.0;

[0124] k 32 k represents the coefficient of surrounding traffic violations. It is calculated when cameras and radar detect traffic violations or trends of violations by surrounding drivers. 32 =0.8, in other cases, k 32 =1.0;

[0125] k 33 This represents the roadside emergency coefficient, indicating when cameras and radar detect an emergency event in the surrounding area. Emergency events include, but are not limited to, road collapses, traffic accidents, and sudden braking of the vehicle in front. k 33 =0.5, otherwise, k 33 =1.0;

[0126] k 34 This represents the road width coefficient, the value of which depends on the relationship between the road width B detected by cameras and radar and the vehicle wheelbase L. At that time, k 34 =0.7, when At that time, k 34 =1.0, when At that time, k 34 =1.3;

[0127] k 35 k represents the road slipperiness coefficient, which is the coefficient of slipperiness detected by cameras and radar when there is water, snow, or oil on the road. 35 =0.8, in other cases, k 35 =1.0;

[0128] S2.4 Calculate the driver state component parameter K4 according to the following formula.

[0129]

[0130] Where w8 and w9 represent weighting coefficients;

[0131] k 41 This represents the driver's head movement coefficient, the value of which depends on the frequency Δf of the driver's head tilting as captured by the in-vehicle camera. Where, N act T represents the number of times the driver looks down within a certain period of time. act f represents the observation duration. ave This indicates a reference value for the frequency of a driver looking down while driving in a safe manner. At that time, there is a potential for driver inattention and fatigue. 41 =0.8, when At that time, k 41 =1.0;

[0132] k 42 This represents the driver's hand movement coefficient. When the in-vehicle camera captures frequent hand movements, hands leaving the steering wheel, or excessive gripping of the steering wheel, it indicates a potential for driver inattention, mental stress, or fatigue. (k) 42 =0.8, in other cases, k 42 =1.0;

[0133] k 43 This represents the driver's eye movement coefficient. When the in-vehicle camera captures excessively long eye closure, significantly increased blinking frequency, and bloodshot eyes, the driver may be experiencing inattention or fatigue. 43 =0.8, in other cases, k 43 =1.0;

[0134] k 44 This represents the impact coefficient of road traffic volume. When cameras and radar detect high road traffic volume, it may cause drivers to feel nervous and anxious. 44 =0.9, in other cases, k 44 =1.0;

[0135] k 45 k represents the coefficient of change in driving behavior. When cameras and radar detect frequent lane changes, fluctuations in vehicle speed, and unstable lane keeping, it indicates a potential for driver inattention and fatigue. 45 =0.8, in other cases, k 45 =1.0;

[0136] k 46This represents the driver's facial expression coefficient. When the in-vehicle camera captures the driver with their mouth tightly closed, brows furrowed, and forehead sweating for a period of time, it indicates a potential for the driver to drive under stress. 46 =0.9, in other cases, k 46 =1.0;

[0137] S2.5 Calculate the surrounding vehicle state sub-parameter K5 according to the following formula.

[0138]

[0139] Among them, w 10 w 11 Indicates the weighting coefficient;

[0140] k 51 This represents the headlight status coefficient of the vehicle ahead. When the camera and radar detect that the turn signal of the vehicle ahead is on, k... 51 =0.8, when the brake lights of the vehicle in front are detected to be on, k 51 =0.6, in other cases, k 51 =1.0;

[0141] k 52 This represents the following vehicle status coefficient, k, which is calculated when the camera and radar detect that the following vehicle has activated its left turn signal, indicating an intention to overtake. 52 =0.8, when the camera and radar detect a decrease in the relative distance between the vehicle and the vehicle behind, k 52 =0.9, in other cases, k 52 =1.0;

[0142] k 53 This represents the vehicle's trajectory coefficient. When cameras and radar detect that surrounding vehicles are significantly deviating from their trajectory, there is a possibility of abnormal driving behavior. (k) 53 =0.7, in other cases, k 53 =1.0;

[0143] k 54 k represents the vehicle attitude coefficient, which is the coefficient used when cameras and radar detect tilting and tire slippage of surrounding vehicles. 54 =0.8, in other cases, k 54 =1.0;

[0144] S3. Calculate the total driving force evaluation parameter K according to the following formula.

[0145]

[0146] Among them, α1, α2, α3, α4, and α5 are the weighted values ​​for individual indicators;

[0147] The driving force adjustment module is used to select the driving force adjustment mode of the vehicle according to the total driving force evaluation parameter K;

[0148] The adjustment effectiveness determination module includes a performance index calculation module and an adjustment effect judgment module.

[0149] The driving force adjustment module describes the selection of the driving force adjustment mode by introducing the first judgment parameter ζ1, the second judgment parameter ζ2, and the third judgment parameter ζ3, and the judgment parameters satisfy the following conditions:

[0150]

[0151] The driving force adjustment module includes a conservative adjustment mode, a moderate adjustment mode, an active adjustment mode, and an emergency adjustment mode. Among them, the conservative adjustment mode has the smallest adjustment degree for the original driving force, the moderate adjustment mode has a smaller adjustment degree for the original driving force, the active adjustment mode has a larger adjustment for the original driving force, and the emergency adjustment mode has the largest adjustment for the original driving force.

[0152] When the total driving force evaluation parameter K satisfies 0 < K ≤ ζ1, the driving force adjustment module will execute the conservative adjustment mode, and the driving force F of the vehicle t satisfies the formula:

[0153]

[0154] where F f represents the rolling resistance of the vehicle, F w represents the air resistance of the vehicle, F i represents the ramp resistance of the vehicle, δ represents the conversion coefficient of the rotating mass of the vehicle, m represents the total mass of the vehicle, v represents the speed of the vehicle, and t represents time;

[0155] When the total driving force evaluation parameter K satisfies ζ1 < K ≤ ζ2, the driving force adjustment module will execute the moderate adjustment mode, and the driving force F of the vehicle t satisfies the formula:

[0156]

[0157] where F f represents the rolling resistance of the vehicle, F w represents the air resistance of the vehicle, F i represents the ramp resistance of the vehicle, δ represents the conversion coefficient of the rotating mass of the vehicle, m represents the total mass of the vehicle, v represents the speed of the vehicle, and t represents time;

[0158] When the total driving force evaluation parameter K satisfies ζ2 < K ≤ ζ3, the driving force adjustment module will execute the active adjustment mode, and the driving force F of the vehicle t satisfies the formula:

[0159]

[0160] Among them, F f represents the rolling resistance of the vehicle, F w represents the aerodynamic drag of the vehicle, F i represents the grade resistance of the vehicle, δ represents the conversion coefficient of the rotating mass of the vehicle, m represents the total mass of the vehicle, v represents the speed of the vehicle, and t represents time;

[0161] When the total driving force evaluation parameter K satisfies ζ3 < K < 1, the driving force adjustment module will execute the emergency adjustment mode, and the driving force F of the vehicle t satisfies the formula:

[0162]

[0163] Among them, F f represents the rolling resistance of the vehicle, F w represents the aerodynamic drag of the vehicle, F i represents the grade resistance of the vehicle, δ represents the conversion coefficient of the rotating mass of the vehicle, m represents the total mass of the vehicle, v represents the speed of the vehicle, and t represents time.

[0164] The performance index calculation module is used to calculate the adjustment performance index Res, and the calculation formula of the adjustment performance index Res is as follows:

[0165]

[0166] Among them, β1, β2, and β3 represent weighting coefficients, and β1 + β2 + β3 = 1;

[0167] V represents the actual driving speed of the vehicle using the intelligent driving system based on camera and radar preview information;

[0168] V0 represents the best driving speed that the vehicle can reach under the same driving conditions for measuring V when the vehicle does not use the intelligent driving system based on camera and radar preview information;

[0169] T represents the actual driving torque of the vehicle using the intelligent driving system based on camera and radar preview information;

[0170] T0 represents the best driving torque that the vehicle can reach under the same driving conditions for measuring T when the vehicle does not use the intelligent driving system based on camera and radar preview information;

[0171] S represents the driver's percentile score based on driving comfort when the vehicle uses the intelligent driving system based on camera and radar preview information;

[0172] S0 represents the highest percentage score of driving comfort that the vehicle can achieve under the same driving conditions measured by S when the vehicle is not using the aforementioned intelligent drive system based on camera and radar pre-aiming information.

[0173] The adjustment effect judgment module is used to judge the working state of the intelligent drive system based on camera and radar pre-aiming information according to the adjustment performance index Res, which is described by introducing a first threshold χ1 and a second threshold χ2, where 0<χ1<χ2<1;

[0174] When Res < χ1, the intelligent drive system based on camera and radar pre-aiming information is working well, and the driver can selectively exit the intelligent drive system based on camera and radar pre-aiming information.

[0175] When χ1≤Res<χ2, the intelligent drive system based on camera and radar pre-aiming information is in normal working condition, and the driver can selectively exit the intelligent drive system based on camera and radar pre-aiming information.

[0176] When Res>χ2, the intelligent drive system based on camera and radar pre-aiming information malfunctions, and the vehicle will be forcibly disengaged from the intelligent drive system based on camera and radar pre-aiming information.

Claims

1. An intelligent driving system based on camera and radar pre-aiming information, characterized in that, Includes the following: Driving data acquisition module, anti-aiming information analysis module, driving force adjustment module, and adjustment efficiency judgment module; The driving data acquisition module is used to collect data on the vehicle during its operation, including the vehicle's total mass m and speed. Road width Vehicle wheelbase ; The pre-aiming information analysis module analyzes and calculates various parameters related to vehicle driving based on information collected by cameras and radar installed on the vehicle, including: S1. Establish a driving force model for the vehicle during driving, including the vehicle's driving force. Satisfying the formula: in, This indicates the rolling resistance of the vehicle. Indicates the vehicle's air resistance. This indicates the vehicle's gradient resistance. This represents the vehicle rotational mass conversion factor, where m represents the vehicle's total mass. Indicates the speed of the vehicle. Indicates time; S2. Calculate the evaluation parameters for each influencing driving force according to the following formulas, including: S2.1 Calculate the road sign sub-parameters according to the following formula. , in, , and Indicates the weighting coefficient; This indicates the speed limit sign coefficient; when the camera and radar detect a speed limit sign ahead and the vehicle's speed exceeds the limit... When the camera detects a speed limit sign ahead and the vehicle's speed does not exceed the limit, When the camera does not detect a speed limit sign ahead, ; This indicates the speed limit cancellation factor. When a vehicle is traveling in a speed-limited section, and the camera and radar detect a speed limit cancellation sign ahead, it indicates that the speed limit has been lifted. In other cases, ; This indicates the highway exit coefficient. When a vehicle is traveling on a highway, and cameras and radar detect a highway exit sign, In other cases, ; This indicates the highway entrance coefficient, which is used when cameras and radar detect highway entrance signs. In other cases, ; This indicates the special area sign coefficient, which is used when cameras and radar detect construction zone signs, school zone signs, and pedestrian crossing signs ahead. In other cases, ; This indicates the curvature coefficient, which is used when cameras and radar detect a level curve in the road. When cameras and radar detect that the road has a perpendicular curve, In other cases, ; This indicates the gradient coefficient, which is used when cameras and radar detect that the road has a longitudinal slope. When cameras and radar detect that the road is a transverse ramp, In other cases, ; S2.2 Calculate the camera blind spot detection sub-parameters according to the following formula. , in, , Indicates the weighting coefficient; This represents the automatic white balance factor, the value of which depends on the camera's automatic white balance capability. When the camera can provide accurate white balance under different lighting conditions, [the white balance factor is considered optimal]. In other cases, ; This represents the vertical field of view spread factor, the value of which depends on the vertical field of view extension factor of the camera. ,in, This indicates the driver's vertical field of view angle. This represents the sum of the vertical field of view angles of all cameras. hour, ,when hour, ,when hour, ; This represents the horizontal field-of-view spread factor, the value of which depends on the horizontal field-of-view extension factor of the camera. ,in, This indicates the driver's horizontal field of view angle. This represents the sum of the horizontal field of view angles of all cameras. hour, ,when hour, ,when hour, ; This represents the field of view expansion factor, the value of which depends on the percentage of blind spot coverage captured by the camera. ,in, Indicates the driver's blind spot area. This represents the blind spot area captured by all cameras. hour, ,when hour, ; This represents the field of view expansion accuracy coefficient, the value of which depends on the percentage of blind spot accuracy captured by the camera. ,in, This indicates the blind spot area captured by all cameras. 1 indicates that all cameras correctly identified the blind spot area. hour, ,when hour, ; S2.3 Calculate the traffic environment monitoring sub-parameters according to the following formulas. , in, , Indicates the weighting coefficient; This represents the pedestrian visibility coefficient, indicating when cameras and radar detect pedestrians engaging in behaviors that affect vehicle movement or exhibiting a tendency to do so. In other cases, ; This indicates the coefficient of surrounding traffic violations. When cameras and radar detect that surrounding drivers are engaging in or exhibiting traffic violations or a tendency to do so, In other cases, ; This indicates the roadside emergency coefficient, which is triggered when cameras and radar detect an emergency event in the surrounding area. Emergency events include, but are not limited to, road collapses, traffic accidents, and sudden braking of the vehicle in front. In other cases, ; This represents the road width coefficient, the value of which depends on the width of the road detected by cameras and radar. With vehicle wheelbase The relationship between them, when hour, ,when hour, ,when hour, ; This indicates the road slipperiness coefficient, which is the level at which cameras and radar detect water, snow, or oil on the road. In other cases, ; S2.4 Calculate the driver state sub-parameters according to the following formula. , in, , Indicates the weighting coefficient; This represents the driver's head movement coefficient, the value of which depends on the frequency of the driver's head tilting down as captured by the in-vehicle camera. , ,in, This indicates the number of times the driver looks down within a certain period of time. Indicates the observation duration. This indicates a reference value for the frequency of a driver looking down while driving in a safe manner. At that time, there is a potential for drivers to be inattentive and drive while fatigued. ,when hour, ; This indicates the driver's hand movement coefficient. When the in-vehicle camera captures frequent hand movements, hands leaving the steering wheel, or excessive gripping of the steering wheel, it suggests that the driver may be inattentive, nervous, or driving while fatigued. In other cases, ; This indicates the driver's eye movement coefficient. When the in-vehicle camera captures that the driver's eyes are closed for too long, blinking frequency is significantly increased, and bloodshot eyes appear, it indicates that the driver may be inattentive or driving while fatigued. In other cases, ; This indicates the impact of road traffic volume. When cameras and radar detect high road traffic volume, it may cause drivers to feel nervous and anxious. In other cases, ; This represents the coefficient of variation in driving behavior. When cameras and radar detect frequent lane changes, fluctuations in vehicle speed, and unstable lane keeping, it indicates a potential for driver inattention and fatigue. In other cases, ; This indicates the driver's facial expression index. When the in-car camera captures the driver with their mouth tightly closed, brows furrowed, and forehead sweating for a period of time, it suggests a potential for the driver to be driving under stress. In other cases, ; S2.5 Calculate the surrounding vehicle state sub-parameters according to the following formula. , in, , Indicates the weighting coefficient; This indicates the status coefficient of the headlights of the vehicle in front. When the camera and radar detect that the turn signal of the vehicle in front is on, When the brake lights of the vehicle in front are detected to be on, In other cases, ; This indicates the following vehicle's status coefficient; it is used when the camera and radar detect that the following vehicle has activated its left turn signal, indicating an intention to overtake. When cameras and radar detect a decrease in the relative distance between a vehicle and the vehicle behind it, In other cases, ; This represents the vehicle's trajectory coefficient. When cameras and radar detect that surrounding vehicles are significantly deviating from their trajectory, there is a possibility of abnormal driving behavior. In other cases, ; This represents the vehicle's attitude coefficient, which is determined when cameras and radar detect tilting and tire slippage of surrounding vehicles. In other cases, ; S3. Calculate the total parameters for driving force evaluation according to the following formula. , in, Calculate the weighted value for each individual indicator; The driving force adjustment module is used to evaluate the total parameters of the driving force. To select the vehicle's drive force adjustment mode; The regulation effectiveness determination module includes a performance index calculation module and a regulation effect judgment module.

2. The intelligent drive system based on camera and radar pre-aiming information according to claim 1, characterized in that: The driving force adjustment module introduces a first judgment parameter. Second judgment parameter and the third judgment parameter To describe the selection of the driving force adjustment mode, the parameters are determined to meet the following conditions: The driving force adjustment module includes a conservative adjustment mode, a moderate adjustment mode, an active adjustment mode, and an emergency adjustment mode. Among them, the conservative adjustment mode has the smallest adjustment to the original driving force, the moderate adjustment mode has a relatively small adjustment to the original driving force, the active adjustment mode has a large adjustment to the original driving force, and the emergency adjustment mode has the largest adjustment to the original driving force.

3. The intelligent drive system based on camera and radar pre-aiming information according to claim 1, characterized in that: When the driving force is evaluated as a total parameter satisfy At this time, the drive force adjustment module will execute a conservative adjustment mode, and the vehicle's drive force will be adjusted accordingly. Satisfying the formula: in, This indicates the rolling resistance of the vehicle. Indicates the vehicle's air resistance. This indicates the vehicle's gradient resistance. This represents the vehicle rotational mass conversion factor, where m represents the vehicle's total mass. Indicates the speed of the vehicle. Indicates time; When the driving force is evaluated as a total parameter satisfy At this time, the drive force adjustment module will execute the medium adjustment mode, and the vehicle's drive force will be adjusted accordingly. Satisfying the formula: in, This indicates the rolling resistance of the vehicle. Indicates the vehicle's air resistance. This indicates the vehicle's gradient resistance. This represents the vehicle rotational mass conversion factor, where m represents the vehicle's total mass. Indicates the speed of the vehicle. Indicates time; When the driving force is evaluated as a total parameter satisfy At this time, the drive force adjustment module will execute an active adjustment mode, and the vehicle's drive force will be adjusted accordingly. Satisfying the formula: in, This indicates the rolling resistance of the vehicle. Indicates the vehicle's air resistance. This indicates the vehicle's gradient resistance. This represents the vehicle rotational mass conversion factor, where m represents the vehicle's total mass. Indicates the speed of the vehicle. Indicates time; When the driving force is evaluated as a total parameter satisfy At this time, the drive force adjustment module will execute the emergency adjustment mode, and the vehicle's drive force will be adjusted. Satisfying the formula: in, This indicates the rolling resistance of the vehicle. Indicates the vehicle's air resistance. This indicates the vehicle's gradient resistance. This represents the vehicle rotational mass conversion factor, where m represents the vehicle's total mass. Indicates the speed of the vehicle. Indicates time.

4. The intelligent drive system based on camera and radar pre-aiming information according to claim 1, characterized in that: The performance index calculation module is used to calculate the adjustment performance index. Adjusting performance indicators The calculation formula is as follows: in, , and Indicates the weighting coefficient. ; This indicates the actual driving speed of the vehicle using the intelligent drive system based on camera and radar pre-aiming information; This indicates that when the vehicle is not using the aforementioned intelligent drive system based on camera and radar pre-aiming information, the vehicle is measuring... The optimal driving speed that can be achieved under the same driving conditions; This indicates the actual driving torque of the vehicle using the aforementioned intelligent drive system based on camera and radar pre-aiming information; This indicates that when the vehicle is not using the aforementioned intelligent drive system based on camera and radar pre-aiming information, the vehicle is measuring... The optimal driving torque that can be achieved under the same driving conditions; This indicates that when the vehicle uses the aforementioned intelligent drive system based on camera and radar pre-aiming information, the driver rates the driving comfort on a 100-point scale. This indicates that when the vehicle is not using the aforementioned intelligent drive system based on camera and radar pre-aiming information, the vehicle is measuring... The highest percentage score for driving comfort that can be achieved under the same driving conditions.

5. The intelligent drive system based on camera and radar pre-aiming information according to claim 1, characterized in that: The adjustment effect judgment module is used to judge the adjustment performance index. The operating status of the intelligent driving system based on camera and radar pre-aiming information is determined by introducing a first threshold. Second threshold Describe, in which ; when At that time, the intelligent drive system based on camera and radar pre-aiming information is in good working order, and the driver can selectively exit the intelligent drive system based on camera and radar pre-aiming information. when At this time, the intelligent drive system based on camera and radar pre-aiming information is in normal working state, and the driver can selectively exit the intelligent drive system based on camera and radar pre-aiming information. when If the intelligent drive system based on camera and radar pre-aiming information malfunctions, the vehicle will be forcibly disengaged from the intelligent drive system.

Images