A vehicle collision warning method, system, electronic device and storage medium

Abstract

A vehicle collision warning method, system, electronic device and storage medium, comprising S1, preprocessing the forward observation data set, the backward observation data set and the ego observation data set; S3, performing fusion processing on the backward observation data set to obtain the rear vehicle fusion state data; S4, calculating the backward collision time and the backward risk according to the rear vehicle fusion state data and the ego observation data set; calculating the forward collision time, the forward risk and the braking margin according to the forward observation data set and the ego observation data set; determining the collision risk level according to T, T, T, T and T. Compared with the prior art, the collision risk of the ego vehicle with the front and rear vehicles can be evaluated, thereby avoiding rear-end collision caused by only focusing on the front target. Secondly, the influence of various influencing factors on the control action is considered, so that the backward risk can be more accurately evaluated.

Description

Technical Field

[0001] This invention relates to the field of vehicle collision avoidance system technology, specifically to a vehicle collision warning method, system, electronic device, and storage medium. Background Technology

[0002] Commercial vehicles are characterized by their large overall weight, long braking distance, delayed response of air brakes, significant load variations, and complex trailer configurations. In scenarios such as high-speed cruising, congested traffic, long downhill slopes, or sudden stops by vehicles ahead, if the vehicle's AEB (Autonomous Emergency Braking) only focuses on the target ahead and applies a large deceleration, it can easily lead to rear-end collisions or chain-reaction collisions as following vehicles approach at high speed. Therefore, vehicle driver assistance systems, especially those designed for commercial vehicles, need to not only identify forward collision risks but also simultaneously assess the collision risks of vehicles behind. Summary of the Invention

[0003] This invention provides a vehicle collision warning method, system, electronic device, and storage medium to address the problem that existing vehicle AEB systems only focus on the target in front and directly apply a large deceleration, which can easily lead to rear-end collisions or chain collisions caused by following vehicles approaching at high speeds.

[0004] To achieve the above objectives, the present invention adopts the following technical solution.

[0005] On the one hand, a vehicle collision warning method is provided, including the following steps: S1. Preprocess the forward observation dataset, backward observation dataset, and vehicle observation dataset. The preprocessing includes coordinate normalization and time synchronization. The backward observation dataset is a dataset composed of multi-source observation data. S3. Perform fusion processing on the backward observation dataset to obtain the fused status data of the rear vehicle; S4. Calculate the rear collision time based on the rear vehicle fusion state data and the self-vehicle observation dataset. and backward risk ;Calculate the forward collision time based on the forward observation dataset and the vehicle's own observation dataset. Forward risk and braking margin ; S5, if The collision risk level is set to Level 1. like or The collision risk level is set at level two. like The collision risk level is set at level three. like or or The collision risk level is set at level four. in, , , This is the threshold for backward risk grading. , The threshold for grading backward collision time. This is the threshold for forward risk classification.

[0006] Therefore, this invention combines forward observation datasets, backward observation datasets, and the vehicle's own observation datasets to simultaneously assess the collision risk between the vehicle and vehicles in front and behind, thereby avoiding rear-end collisions caused by focusing only on the target in front. Secondly, it assesses the collision risk level based on the degree of collision risk, providing a basis for response strategies under different collision risk levels.

[0007] In some embodiments, the rear vehicle fusion state data includes the fused longitudinal distance of the rear vehicle, the speed of the rear vehicle, the relative speed between the rear vehicle and the vehicle, the acceleration of the rear vehicle, the estimated available deceleration of the rear vehicle, the probability of being in the same lane, and the braking status of the rear vehicle; the vehicle observation dataset includes the vehicle speed and the vehicle deceleration. The rear collision time is calculated based on the rear vehicle fusion state data and the self-vehicle observation dataset. and backward risk include: The rearward collision time is calculated based on the merged longitudinal distance of the rear vehicle and the relative speed between the rear vehicle and the vehicle itself. ; The rearward safety distance is calculated based on the fused following vehicle speed, the estimated available deceleration of the following vehicle, the vehicle's speed, the reaction time of the following vehicle's driver or control system, the vehicle's deceleration, distance compensation, and static safety margin; the distance compensation is calculated based on the vehicle network message age and positioning error. Calculate the rearward safety distance gap based on the rear vehicle's safety distance and longitudinal distance; The probability of dangerous intent is calculated based on the relative speed between the following vehicle and the vehicle itself, the acceleration of the following vehicle, the braking status of the following vehicle, and the probability of being in the same lane. Based on the time of the rear collision Calculate the backward risk based on the backward safety distance gap, the probability of dangerous intent, and the load / trailer risk item. .

[0008] Existing technologies rely solely on fixed thresholds to determine the risk of rear-end collisions, as illustrated in Chinese invention patent CN115320556A, which describes a method, device, electronic device, and storage medium for preventing rear-end collisions based on AEB (Autonomous Emergency Braking). However, the available deceleration and braking margin of commercial vehicles vary significantly under different operating conditions. Using only fixed thresholds for collision risk assessment fails to reflect the impact of factors such as load / trailer risk on control actions, leading to inaccurate results. This invention calculates rearward risk by comprehensively considering multiple influencing factors, fully taking into account their impact on control actions, thus enabling a more accurate assessment of rearward risk. Furthermore, this invention incorporates calculation biases caused by vehicle-to-everything (V2X) communication delays and positioning errors, using these as distance compensation to calculate the rearward safety distance, further improving the accuracy of rearward risk assessment results.

[0009] In some embodiments, the forward collision time is calculated based on the forward observation dataset and the vehicle observation dataset. Forward risk and backward risk and braking margin include: Calculate the forward collision time based on the distance to the vehicle in front, the speed of the vehicle in front, and the speed of your own vehicle. And the minimum deceleration required to avoid a forward collision; Calculate the braking margin based on the vehicle's maximum available deceleration and the minimum deceleration required to avoid a forward collision. ; Based on forward collision time Calculate forward risk using the minimum deceleration required to avoid a forward collision and the vehicle's maximum available deceleration. .

[0010] Therefore, this invention can not only identify whether a target is approaching, but also determine whether the current braking capacity is sufficient to avoid a forward collision by combining the vehicle's maximum available deceleration. When the braking margin is small, the system can increase the risk level in advance and constrain the braking control amount, thereby avoiding misjudgments caused by triggering braking solely based on forward distance or collision time, and improving the reliability and adaptability of forward collision avoidance control for commercial vehicles.

[0011] In some embodiments, when the collision risk level exceeds level two, the optimal braking deceleration is calculated based on forward risk, rearward risk, vehicle yaw rate, and yaw stability indices; the yaw stability index is equal to the vehicle's yaw rate divided by the upper limit of the permissible yaw rate. Thus, collisions can be avoided or their severity reduced while ensuring the vehicle's yaw stability.

[0012] In some embodiments, the time synchronization process includes: aligning the coordinate-standardized forward observation dataset, backward observation dataset, and vehicle observation dataset to the same time, using the fusion time as a unified time standard; wherein, the backward observation dataset uses a constant acceleration model for time synchronization; and the distance to the preceding vehicle in the forward observation dataset is compensated based on the relative speed between the vehicle and the preceding vehicle during time synchronization.

[0013] Through the above technical solution, this invention solves the problem of inconsistent sampling times among forward observation data, backward observation data, V2X messages, and the vehicle's own observation data. Without time synchronization, the distance to the following vehicle, the distance to the preceding vehicle, and the vehicle's status will correspond to different time points, leading to deviations in subsequent calculations of TTC, safe distance, and risk level. Therefore, this invention can improve the accuracy of calculating rear-end collision time, forward collision time, and safe distance gaps, and reduce false alarms or missed alarms caused by inconsistent sampling times from multiple sensors.

[0014] In some embodiments, no intervention is performed when the collision risk level is Level 1; An alarm will be issued when the collision risk level is level two. When the collision risk level is level three, the electronic braking system will apply the brakes. When the collision risk level is level four, the electronic braking system and the automatic emergency braking system work together to apply the brakes.

[0015] Therefore, this invention reduces the risk of false triggering and rear-end collisions by implementing different response strategies according to different collision risk levels.

[0016] In another aspect, a vehicle collision warning system is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0017] In another aspect, a computer-readable storage medium is provided that stores a computer program or instructions thereon, which, when executed by a processor, implement the steps of the above-described method.

[0018] In another aspect, a computer program product is provided, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0019] This invention has at least the following technical effects or advantages: 1. This invention combines forward observation datasets, backward observation datasets, and vehicle observation datasets to simultaneously assess the collision risk between the vehicle and vehicles in front and behind, thereby avoiding rear-end collisions caused by focusing only on the target in front.

[0020] 2. This invention calculates backward risk by comprehensively considering multiple influencing factors, fully taking into account the impact of these factors on control actions, thereby enabling a more accurate assessment of backward risk.

[0021] 3. This invention also incorporates the calculation deviation caused by vehicle network message communication delay and positioning error, and uses it as distance compensation to calculate the backward safety distance, further improving the accuracy of the backward risk assessment results.

[0022] 4. It can avoid collisions or reduce the severity of collisions while ensuring the vehicle's lateral stability.

[0023] 5. This invention reduces the risk of false triggering and rear-end collisions by implementing different response strategies based on different collision risk levels. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating a vehicle collision warning method according to an embodiment of the present invention. Detailed Implementation

[0025] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0026] Example 1 See Figure 1 A vehicle collision warning method, characterized by comprising the following steps: S1. Preprocess the forward observation dataset, backward observation dataset, and vehicle observation dataset. The preprocessing includes coordinate normalization and time synchronization. The backward observation dataset is a dataset composed of multi-source observation data. S3. Perform fusion processing on the backward observation dataset to obtain the fused status data of the rear vehicle; S4. Calculate the rear collision time based on the rear vehicle fusion state data and the self-vehicle observation dataset. and backward risk ;Calculate the forward collision time based on the forward observation dataset and the vehicle's own observation dataset. Forward risk and braking margin ; S5, if The collision risk level is set to Level 1. like or The collision risk level is set at level two. like The collision risk level is set at level three. like or or The collision risk level is set at level four. in, , , This is the threshold for backward risk grading. , The threshold for grading backward collision time. This is the threshold for forward risk classification.

[0027] Specifically, coordinate standardization includes the following steps: (1) Standardize the raw data from multiple backward sources. For each type of backward sensor, the raw observations are transformed to a unified vehicle coordinate system, and the sampling time, confidence level and observation noise covariance are added.

[0028] ; In the formula, z i s (t s Let be the type s backward sensor at sampling time t. s Standard observations formed for target i; z i s,raw (t s The original observations were taken before standardization. s (·) is a standardized function consisting of coordinate transformation, out-of-bounds rejection, confidence level filtering, and covariance assignment; Cal s Here are the extrinsic parameters, intrinsic parameters, and error calibration parameters for the s-th type of sensor; S R This is a set of rearward sensors, where rad, cam, and us represent rear millimeter-wave radar, rear-view vision, and ultrasonic / side-rearward sensor, respectively.

[0029] (2) Standardize the forward observation dataset (sensed by forward AEB) and the vehicle observation dataset (vehicle chassis status) to form a forward observation and vehicle status that can be entered into a unified coordinate system.

[0030] ; ; In the formula, z f (t f ) represents the forward AEB module at sampling time t f Standard observations formed; z f,raw (t f (This refers to the forward primitive observation;) f (·) represents the forward observation normalization function; Cal f Forward sensing calibration parameters; x E (tE () represents the sampling time t E Standard chassis configuration; x E raw (t E This provides the raw state for the chassis CAN, EBS, ESC, and VCU. E (·) is the unified function for chassis state.

[0031] Time synchronization processing includes the following steps: (1) Calculate the time difference between different sources relative to the fusion time, and synchronize the backward target, forward target and chassis status. The backward target adopts a constant acceleration model; the forward distance is compensated according to the forward relative velocity.

[0032] ; ; ; ; In the formula, This is the current moment of integration; , and These represent the time differences between the backward observation, the forward observation, and the relative fusion of chassis status, respectively. For the backward standard observation after synchronization, p i s (t s ), v i s (t s ) and a i s (t s Let be the position, velocity, and acceleration of target i, respectively. and To compensate for the position and velocity after t0; c i s For observation confidence level; This represents the observation noise covariance after time synchronization.

[0033] ; ; ; ; In the formula, For the synchronized forward standard observation parameter set, This refers to the distance to the vehicle ahead after synchronization; The speed of the preceding vehicle after synchronization; The relative speed between the preceding vehicle and the following vehicle after synchronization; Forward observation confidence; x E (t0) represents the synchronized state of the vehicle chassis; For the vehicle's speed; This refers to the longitudinal acceleration / deceleration of the vehicle. This refers to the yaw rate; Steering wheel angle; This refers to the brake air pressure or brake line pressure. The brake air circuit is in a pressurized state. To estimate the overall vehicle weight; The road surface adhesion coefficient; The road slope angle; For brake temperature; This is a correction factor for load or trailer configuration.

[0034] As a preferred embodiment, the fused rear vehicle status data includes the fused longitudinal distance of the rear vehicle, the speed of the rear vehicle, the relative speed between the rear vehicle and the vehicle, the acceleration of the rear vehicle, the estimated available deceleration of the rear vehicle, the probability of being in the same lane, and the braking status of the rear vehicle; the vehicle observation dataset includes the vehicle speed and the vehicle deceleration. The rear collision time is calculated based on the rear vehicle fusion state data and the self-vehicle observation dataset. and backward risk include: The rearward collision time is calculated based on the merged longitudinal distance of the rear vehicle and the relative speed between the rear vehicle and the vehicle itself. ; The rearward safety distance is calculated based on the fused following vehicle speed, the estimated available deceleration of the following vehicle, the vehicle's speed, the reaction time of the following vehicle's driver or control system, the vehicle's deceleration, distance compensation, and static safety margin; the distance compensation is calculated based on the vehicle network message age and positioning error. Calculate the rearward safety distance gap based on the rear vehicle's safety distance and longitudinal distance; The probability of dangerous intent is calculated based on the relative speed between the following vehicle and the vehicle itself, the acceleration of the following vehicle, the braking status of the following vehicle, and the probability of being in the same lane. Based on the time of the rear collision Calculate the backward risk based on the backward safety distance gap, the probability of dangerous intent, and the load / trailer risk item. .

[0035] Specifically, it includes the following steps: (1) The current state is predicted by the fusion state of the previous cycle and the vehicle motion input. Then the residual, residual covariance and Mahalanobis distance between the synchronous observation and the predicted state are calculated and compared with the gating threshold to eliminate unreliable associations.

[0036] ; ; ; ; ; ; In the formula, u E (t0) is the vehicle motion input vector, where v E (t0), a E (t0), r E δ(t0) and δ(t0) represent the vehicle's velocity, acceleration, yaw rate, and turning angle, respectively; X i - (t0) represents the predicted state of target i; X i,fuse (t0 - ) represents the fusion state of the previous cycle; F i and B i These are the state transition matrix and the vehicle motion input matrix, respectively; r ij s (t0) is the residual between the predicted trajectory i and the candidate observation j of the s-th type of sensor; For the s-th type of sensor at the fusion time The j-th candidate observation output; H s P is the observation matrix; i - (t0) To predict the covariance, it can be obtained from P i,fuse (t0 - The posterior covariance of the previous period is obtained; S ij s (t0) represents the residual covariance; j s (t0) represents the observed covariance after synchronization; d M,ij s,2 (t0) is the squared Mahalanobis distance, used to filter out values ​​exceeding the gate threshold. erroneous associations; gating thresholds It can be calibrated by combining sensor false alarm rate, false detection rate, and real vehicle data; C i s (t0) represents candidate observations that meet the conditions.

[0037] (2) Perform JPDA association and Kalman update on candidate observations that meet the conditions, and obtain the same lane probability and the braking state of the following vehicle by combining the visual lane line constraint.

[0038] ; ; ; In the formula, β ij s The association probability calculated for JPDA; β ij s The larger the value, the more likely the j-th observation of the s-th sensor belongs to target i, and the higher the weight of its residual in the update; weighted updating by multiple candidate observations can reduce erroneous associations caused by occlusion, false detection, or targets in adjacent lanes; P D s Let λ be the detection probability of the s-th type of sensor; N(·) be the Gaussian likelihood function; λ FA s is the false alarm density; l is the candidate trajectory index; K i s (t0) represents the Kalman gain; X i,fuse (t0) represents the updated fusion state. The d in this vector... r,i y R,i v R,i v rel,r,i a R,i P lane,E,i C i and I brake,i These represent the following vehicle's longitudinal distance, lateral position, speed, relative speed to the following vehicle, acceleration, probability of being in the same lane, fusion confidence, and braking status, respectively. The braking status indicates whether the following vehicle has applied brakes or is braking; for example, 1 can be set to braking and 0 to not braking.

[0039] (3) Calculate the rearward TTC, rearward safety distance and its gap based on the fusion distance, closing speed, estimated braking capacity of the rear vehicle, estimated deceleration of the vehicle and distance compensation.

[0040] ; ; ; In the formula, TTC r,i (t0) represents the backward collision time of target i; d r,i (t0) represents the longitudinal distance of the following vehicle; v rel,r,i(t0) is the relative speed of the following vehicle relative to the following vehicle; ε is a small positive number set to prevent the denominator from being zero; D safe,r,i (t0) represents the rearward safety distance; v R,i (t0) and v E (t0) represents the speed of the following vehicle and the speed of the vehicle itself, respectively; t react,R For the reaction time of the driver or control system of the following vehicle; a R,avl The available deceleration estimate for the following vehicle; a E (t0) represents the deceleration after the vehicle synchronizes; Δd v2x For distance compensation; d 0,r This is the static safety margin; ΔD r,i (t0) represents the backward safety distance gap.

[0041] (4) Calculate the probability of dangerous intent based on the closing speed, acceleration, braking status and the probability of being in the same lane of the following vehicle, and then weight the TTC risk, distance gap, dangerous intent and load / trailer risk items into a backward risk.

[0042] ; ; In the formula, P intent,i (t0) represents the probability of the following vehicle's dangerous intent; θ0 is the bias term, and θ1 to θ4 are the logistic regression coefficients; v rel,r,i a R,i I brake,i and P lane,E,i These are the closing velocity, following vehicle acceleration, following vehicle braking state, and probability of being in the same lane, respectively; R r,i (t0) represents backward risk; f T (·) and f D (·) represent the TTC risk mapping function and the distance gap mapping function, respectively; w T w D w I and w L For the corresponding risk item weights; L load (t0) is an additional risk item introduced for load, trailer configuration and operating conditions.

[0043] Regarding the calculation of distance compensation: Delay and positioning error compensation are performed on C-V2X / DSRC messages. This compensation is not used to replace target fusion, but rather as an additional safety margin for backward safe distance.

[0044] ; ; In the formula, τ msgThe age or communication delay of the V2X message is determined by the reception time t. rx Subtract the sending time t tx Δd is obtained. v2x Distance compensation introduced to address communication delays and positioning errors; v rel,r v2x and a rel,r v2x These are the relative speed and relative acceleration of the vehicle and the following vehicle in the V2X message, respectively; σ pos k represents the standard deviation of the positioning error. σ The confidence coefficient can be set to 2 to 3 in engineering practice and calibrated using actual vehicles.

[0045] As a preferred embodiment, the forward collision time is calculated based on the forward observation dataset and the vehicle's own observation dataset. Forward risk and backward risk and braking margin include: Calculate the forward collision time based on the distance to the vehicle in front, the speed of the vehicle in front, and the speed of your own vehicle. And the minimum deceleration required to avoid a forward collision; Calculate the braking margin based on the vehicle's maximum available deceleration and the minimum deceleration required to avoid a forward collision. ; Based on forward collision time Calculate forward risk using the minimum deceleration required to avoid a forward collision and the vehicle's maximum available deceleration. .

[0046] Specifically, (1) Calculate the forward TTC and the minimum deceleration required to avoid a forward collision based on the distance to the preceding vehicle, the speed of the preceding vehicle and the speed of the vehicle after synchronization.

[0047] ; ; In the formula, TTC f (t0) represents the forward collision time; f (t0) represents the distance to the preceding vehicle after synchronization; v E (t0) and F (t0) represents the speed of the vehicle itself and the speed of the vehicle ahead after synchronization, respectively; ε is a small positive number set to prevent the denominator from being zero; a req,f (t0) Minimum deceleration required to avoid a forward collision; d 0,f This is a forward static safety margin. (TTC) f (t0) and a req,f (t0) is used as the input for step 2.

[0048] (2) Estimate the available deceleration and braking margin based on chassis air pressure response, vehicle mass, adhesion, slope, regulatory boundaries, comfort boundaries, load, temperature and trailer status, and calculate forward risk.

[0049] ; ; ; ; In the formula, a EBS (t0) represents the deceleration currently available from the EBS; k p p is the conversion factor from brake air pressure to braking force. brk (t0) represents the braking air pressure; m E (t0) represents the vehicle's mass; a avl (t0) represents the maximum available deceleration under the current operating conditions; μ is the road adhesion coefficient; g is the gravitational acceleration; θ is the road slope angle; a legal and a comfort These are the regulatory boundaries and the comfort boundaries, respectively; η m η temp and η trailer These are the correction factors for load, braking temperature, and trailer configuration, respectively; M b (t0) represents the braking margin; R f (t0) represents the forward continuous risk quantity; w Tf and w af For weights; f Tf (·) and f af (·) represents the TTC risk mapping function and the deceleration demand mapping function.

[0050] As a preferred option, no intervention is required when the collision risk level is Level 1. An alarm will be issued when the collision risk level is level two. When the collision risk level is level three, the electronic braking system will apply the brakes. When the collision risk level is level four, the electronic braking system and the automatic emergency braking system work together to brake, as shown in Table 1.

[0051] Table 1 Risk Level Description

[0052] As a preferred embodiment, when the collision risk level exceeds level two, the optimal braking deceleration is calculated based on forward risk, rearward risk, vehicle yaw rate, and yaw stability index; the yaw stability index is equal to the vehicle yaw rate divided by the upper limit of the allowable yaw rate.

[0053] Specifically, first calculate the vehicle's yaw stability index S. yaw,k Calculate the optimal braking deceleration 'a' under the constraints of available deceleration, jerk, and stability. cmd * instruction.

[0054] ; ; ; In the formula, r e,k Let r be the yaw rate of the vehicle at the k-th prediction time. max The upper limit of permissible yaw rate (obtained from commercial vehicle stability testing calibration); a cmd * The optimal deceleration command is obtained through constraint optimization; a and ρ are the candidate deceleration and sag, respectively; k is the discrete time index in the prediction time domain; N is the prediction time domain length; q f q r q ρ and q s These are the weights for forward risk, backward risk, judder, and yaw stability costs (which need to be calibrated); R f,k R r,k ρ k and S yaw,k For the forward risk, backward risk, quirk, and yaw stability indices at the k-th prediction time; a avl,k The upper limit of available deceleration (calibrated according to risk level); ρ max The upper limit of the jump (calibrated according to the risk level) is determined by the principle that the higher the risk, the stronger the braking capacity allowed, but it is still subject to the constraints of the commercial vehicle's physical braking capacity, adhesion, load, gradient, braking temperature, regulatory boundaries, comfort and stability.

[0055] This invention solves the following technical problems: (1) When the vehicle in front stops suddenly, the traditional AEB ignores the problem of the vehicle being rear-ended due to the high speed of the following vehicle approaching; (2) Fixed threshold backward warning cannot adapt to the problems of commercial vehicle load, slope, adhesion and brake heat fade; (3) The problem of false alarms / missed alarms in complex environments using a single vision, single radar, or single V2X information; (4) The lack of unified arbitration for in-vehicle warning, external warning lights, EBS braking, and AEB / ESC coordination; (5) V2X message delay and positioning error are not included in the safe distance model, resulting in insufficient control reliability.

[0056] The beneficial effects of this invention include: (1) Rearward multi-source perception fusion: Fusion of millimeter-wave radar long-range speed and distance measurement, rear-view visual target category / lane / brake light recognition, ultrasonic radar near-range blind spot compensation and C-V2X / DSRC non-line-of-sight status information; (2) Backward risk calculation model: Backward TTC, safety distance gap, probability of following vehicle intention, load / trailer risk and V2X error compensation are unified into a continuous risk quantity; (3) Front and rear risk constraint AEB: When the vehicle stops suddenly in front, it does not directly execute a single forward AEB, but combines the rear risk calculation with the braking capacity of the commercial vehicle to perform braking control; (4) Estimation of braking capacity of commercial vehicles: taking into account load, gradient, adhesion, EBS capacity, brake heat fade and trailer status, to improve adaptability under different loading conditions; (5) Hierarchical execution link: Reduce the risk of false triggering and rear-end collision through R1 warning, R2 pre-charge / light braking, and R3 AEB / ESC coordination.

[0057] Table 2 Definitions of English Abbreviations

[0058] Example 2 A vehicle collision warning system includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.

[0059] Example 3 A computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0060] Example 4 A computer program product includes a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0061] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0062] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0063] Those skilled in the art will understand that the modules, units, or groups of devices in the examples disclosed herein can be arranged in the device as described in this embodiment, or alternatively, can be located in one or more devices different from the device in this example. The modules in the foregoing examples can be combined into a single module or further divided into multiple sub-modules.

[0064] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or groups in the embodiments can be combined into a single module, unit, or group, and further, they can be divided into multiple sub-modules, sub-units, or sub-groups. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0065] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention and form different embodiments.

[0066] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0067] The various techniques described herein can be implemented in combination with hardware or software, or a combination thereof. Thus, the methods and apparatus of the present invention, or certain aspects or portions thereof, can take the form of program code (i.e., instructions) embedded in a tangible medium, such as a floppy disk, CD-ROM, hard disk, or any other machine-readable storage medium, wherein when the program is loaded into and executed by a machine such as a computer, the machine becomes an apparatus for practicing the present invention.

[0068] When the program code is executed on a programmable computer, the computing device generally includes a processor, a processor-readable storage medium (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. The memory is configured to store program code; the processor is configured to execute the method of the present invention according to instructions in the program code stored in the memory.

[0069] By way of example, and not limitation, computer-readable media include computer storage media and communication media. Computer storage media stores information such as computer-readable instructions, data structures, program modules, or other data. Communication media generally embodies computer-readable instructions, data structures, program modules, or other data in the form of modulated data signals such as carrier waves or other transmission mechanisms, and includes any information delivery medium. Any combination of the above is also included within the scope of computer-readable media.

[0070] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0071] Although the invention has been described with reference to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and instructional purposes, and not for the purpose of interpreting or limiting the subject matter of the invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the invention is illustrative and not restrictive, and the scope of the invention is defined by the appended claims.

[0072] Finally, it should be noted that this invention does not explain in detail the common knowledge recognized by those skilled in the art. The above description is only a specific embodiment of this invention and is not intended to limit this invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the protection scope of this invention.

Claims

1. A vehicle collision warning method, characterized in that, Includes the following steps: S1. Preprocess the forward observation dataset, backward observation dataset, and vehicle observation dataset. The preprocessing includes coordinate standardization and time synchronization. The backward observation dataset is a dataset composed of multi-source observation data; S3. Perform fusion processing on the backward observation dataset to obtain the fused status data of the rear vehicle; S4. Calculate the rear collision time based on the rear vehicle fusion state data and the self-vehicle observation dataset. and backward risk ;Calculate the forward collision time based on the forward observation dataset and the vehicle's own observation dataset. Forward risk and braking margin ; S5, if The collision risk level is set to Level 1. like or The collision risk level is set at level two. like The collision risk level is set at level three. like or or The collision risk level is set at level four. in, , , This is the threshold for backward risk grading. , The threshold for grading backward collision time. This is the threshold for forward risk classification.

2. The vehicle collision warning method according to claim 1, characterized in that: The fused rear vehicle status data includes the fused longitudinal distance of the rear vehicle, the speed of the rear vehicle, the relative speed between the rear vehicle and the vehicle, the acceleration of the rear vehicle, the estimated available deceleration of the rear vehicle, the probability of being in the same lane, and the braking status of the rear vehicle; the vehicle observation dataset includes the vehicle speed and the vehicle deceleration. The rear collision time is calculated based on the rear vehicle fusion state data and the self-vehicle observation dataset. and backward risk include: The rearward collision time is calculated based on the merged longitudinal distance of the rear vehicle and the relative speed between the rear vehicle and the vehicle itself. ; The rearward safety distance is calculated based on the fused following vehicle speed, the estimated available deceleration of the following vehicle, the vehicle's speed, the reaction time of the following vehicle's driver or control system, the vehicle's deceleration, distance compensation, and static safety margin; the distance compensation is calculated based on the vehicle network message age and positioning error. Calculate the rearward safety distance gap based on the rear vehicle's safety distance and longitudinal distance; The probability of dangerous intent is calculated based on the relative speed between the following vehicle and the vehicle itself, the acceleration of the following vehicle, the braking status of the following vehicle, and the probability of being in the same lane. Based on the time of the rear collision Calculate the backward risk based on the backward safety distance gap, the probability of dangerous intent, and the load / trailer risk item. .

3. The vehicle collision warning method according to claim 1 or 2, characterized in that, The forward collision time is calculated based on the forward observation dataset and the vehicle's own observation dataset. Forward risk and backward risk and braking margin include: Calculate the forward collision time based on the distance to the vehicle in front, the speed of the vehicle in front, and the speed of your own vehicle. And the minimum deceleration required to avoid a forward collision; Calculate the braking margin based on the vehicle's maximum available deceleration and the minimum deceleration required to avoid a forward collision. ; Based on forward collision time Calculate forward risk using the minimum deceleration required to avoid a forward collision and the vehicle's maximum available deceleration. .

4. The vehicle collision warning method according to claim 1 or 2, characterized in that: When the collision risk level exceeds level two, the optimal braking deceleration is calculated based on the forward risk, rearward risk, vehicle yaw rate, and yaw stability index; the yaw stability index is equal to the vehicle's yaw rate divided by the upper limit of the allowable yaw rate.

5. The vehicle collision warning method according to claim 1 or 2, characterized in that, The time synchronization process includes: aligning the forward observation dataset, backward observation dataset, and vehicle observation dataset after coordinate standardization to the same time, using the fusion time as a unified time standard; wherein, the backward observation dataset uses a constant acceleration model for time synchronization; and the distance to the preceding vehicle in the forward observation dataset is progressively compensated based on the relative speed between the vehicle and the preceding vehicle during time synchronization.

6. The vehicle collision warning method according to claim 1 or 2, characterized in that: No intervention is required when the collision risk level is Level 1. An alarm will be issued when the collision risk level is level two. When the collision risk level is level three, the electronic braking system will apply the brakes. When the collision risk level is level four, the electronic braking system and the automatic emergency braking system work together to apply the brakes.

7. A vehicle collision warning system, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-6.

8. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-6.

9. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-6.

Images