Vehicle risk avoiding method, vehicle controller, system and vehicle

Abstract

The invention relates to a vehicle risk avoiding method, a vehicle controller, a vehicle risk avoiding system and a vehicle, and belongs to the technical field of vehicle safety. According to the track information and the attitude information of the surrounding vehicles, track disorder evaluation indexes and attitude sudden change evaluation indexes of the surrounding vehicles are determined respectively; according to the track disorder evaluation index and the posture sudden change evaluation index, the tire burst risk of the surrounding vehicles is determined; and generating a vehicle risk avoiding strategy according to the tire burst risk. The method does not depend on a communication link between vehicles, the applicability is wider, and compared with audio / voiceprint, image and simple track deviation detection, the accuracy is higher.

Description

Technical Field

[0001] This invention relates to the field of vehicle safety technology, and in particular to a vehicle hazard avoidance method, vehicle controller, system, and vehicle. Background Technology

[0002] Currently, the main methods for determining whether other vehicles have had tire blowouts are the following, which have significant limitations in terms of false alarms and false negatives:

[0003] 1. Tire blowout recognition based on audio / voiceprint: Because the environment on the road is noisy, the angle of the noise and the location of the sound source are inaccurate, and the delay is serious.

[0004] 2. Image-based tire deformation recognition: Relying solely on images results in a high rate of false negatives and false negatives.

[0005] 3. Simple trajectory deviation detection: Based solely on simple trajectory prediction, it often fails to distinguish between non-blowout scenarios, resulting in a high false alarm rate.

[0006] 4. Identification based on V2V communication: This method allows for the wireless exchange of information about the speed and location of surrounding vehicles, sharing vehicle information through vehicle-to-vehicle (V2V) communication for collision warnings or avoidance. However, this connectivity is only possible when all vehicles can communicate with each other. If only 2 out of 10 vehicles are equipped with V2V technology, a communication network cannot be established, rendering it meaningless. For most low-end vehicles on the road, achieving standard V2V capability is difficult; therefore, the V2V method is unlikely to be effective in real-world scenarios.

[0007] In summary, current technology for determining whether other vehicles have experienced tire blowouts suffers from significant false alarms, false negatives, and equipment limitations. Summary of the Invention

[0008] In view of this, it is necessary to provide a vehicle avoidance method, vehicle controller, system and vehicle to solve the problems of obvious false alarms and false alarms and equipment limitations in the current technology for judging whether other vehicles have had tire blowouts.

[0009] To address the aforementioned problems, in a first aspect, the present invention provides a vehicle hazard avoidance method, comprising: Obtain trajectory and attitude information of surrounding vehicles; The trajectory disorder evaluation index of the surrounding vehicles is determined based on the trajectory information; The attitude change evaluation index of the surrounding vehicles is determined based on the attitude information; The risk of tire blowout for surrounding vehicles is determined based on the trajectory disorder evaluation index and the attitude change evaluation index. A vehicle risk avoidance strategy is generated based on the described tire blowout risk.

[0010] In one possible implementation, the trajectory information includes a sequence of trajectory points, and the trajectory disorder evaluation index includes information entropy; determining the trajectory disorder evaluation index of the surrounding vehicles based on the trajectory information includes: Calculate the change in steering angle between two adjacent trajectory points in the sequence of trajectory points of surrounding vehicles to obtain the sequence of steering angle changes; The sequence of steering angle changes is discretized into multiple intervals, and the steering mode of each interval is determined based on the steering angle change in each interval. The frequency of each turning mode within each first sliding time window is statistically analyzed, and the information entropy corresponding to the first sliding time window is calculated using the information entropy formula.

[0011] In one possible implementation, the attitude change evaluation index includes an attitude change index; determining the attitude change evaluation index of the surrounding vehicles based on the attitude information includes: Based on the attitude information of surrounding vehicles, construct the covariance matrix of attitude parameters within each second sliding time window; The attitude change index is calculated based on the change in the covariance matrix of the adjacent second sliding time window.

[0012] In one possible implementation, the attitude mutation index includes at least one of: Frobenius norm difference, divergence, and singular value rate of change.

[0013] In one possible implementation, the trajectory disorder evaluation index includes trajectory entropy, and the attitude change evaluation index includes attitude change index; determining the tire blowout risk of surrounding vehicles based on the trajectory disorder evaluation index and the attitude change evaluation index includes: When the trajectory entropy continues to increase within a preset time period and the attitude change index is greater than the change index threshold, it is determined that the surrounding vehicles are at risk of tire blowout.

[0014] In one possible implementation, the trajectory disorder evaluation index further includes the rate of change of trajectory entropy, and the attitude change evaluation index further includes the rate of change of multiple attitude parameters; the step of determining that the surrounding vehicles have a tire blowout risk when the trajectory entropy continuously increases within a preset time period and the attitude change index is greater than the change index threshold includes: When the rate of change of the trajectory entropy is greater than the trajectory entropy change rate threshold, and the trajectory entropy is continuously greater than the trajectory entropy threshold within a preset time period, and the attitude mutation index is greater than the mutation index threshold, and the rate of change of any attitude parameter is greater than the attitude parameter change rate threshold, it is determined that the surrounding vehicles are at risk of tire blowout.

[0015] In one possible implementation, generating a vehicle risk avoidance strategy based on the tire blowout risk includes: Based on the impact of the tire blowout risk, the tire blowout instability manifestations of surrounding vehicles, and the vehicle distribution on the road, a vehicle risk avoidance strategy is generated.

[0016] In a second aspect, the present invention also provides a vehicle controller, including a memory and a processor, wherein the memory is used to store a program; the processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the vehicle avoidance method described in any of the above claims.

[0017] Thirdly, the present invention also provides a vehicle driving assistance system, including a sensing system, the aforementioned vehicle controller, and an execution system; wherein, The sensing system is used to collect trajectory and attitude information of surrounding vehicles; The execution system executes the vehicle risk avoidance strategy.

[0018] Fourthly, the present invention also provides a vehicle including the aforementioned vehicle driving assistance system.

[0019] The beneficial effects of this invention are: In summary, this invention monitors the tire blowout risk of surrounding vehicles and formulates avoidance strategies based on the monitoring results. This can reduce or avoid collisions with the vehicle caused by tire blowouts of surrounding vehicles, thus improving the vehicle's safety. Furthermore, during the monitoring process, this invention determines the presence of tire blowout risk based on trajectory chaos evaluation indicators and attitude change evaluation indicators of surrounding vehicles. It does not rely on communication links between vehicles, making it more widely applicable and more accurate than audio / voiceprint, image, or simple trajectory deviation detection methods. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating an embodiment of the vehicle hazard avoidance method provided by the present invention; Figure 2 A flowchart illustrating an embodiment of the trajectory disorder evaluation index determination steps provided by the present invention; Figure 3 A flowchart of a method for detecting tire blowouts of surrounding vehicles based on information entropy provided by the present invention; Figure 4A flowchart illustrating an embodiment of the posture change evaluation index determination steps provided by the present invention; Figure 5 A flowchart of a method for detecting tire blowouts of surrounding vehicles based on the covariance matrix provided by the present invention; Figure 6 A schematic diagram of a vehicle risk avoidance strategy provided by the present invention; Figure 7 This invention provides a schematic diagram of the overall process for vehicle hazard avoidance. Figure 8 A schematic diagram of a structure of an embodiment of the vehicle controller provided by the present invention; Figure 9 This is a schematic diagram of the structure of an embodiment of the vehicle driving assistance system provided by the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0023] In the description of the embodiments of this invention, unless otherwise stated, "a plurality of" means two or more. The terms "first," "second," etc., used in the embodiments of this invention are used to distinguish similar objects, and are not used to describe a specific order or sequence, nor to indicate or imply their relative importance or implicitly specify the number of indicated technical features. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, and the number of objects is not limited; for example, a first object can be one or more.

[0024] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0025] Reference Figure 1 The diagram illustrates a flowchart of an embodiment of the vehicle hazard avoidance method provided by the present invention, the method comprising: S101, acquire trajectory and attitude information of surrounding vehicles.

[0026] Surrounding vehicles can refer to other vehicles within a certain range around your vehicle.

[0027] Trajectory information can include trajectory parameters such as position, velocity, and acceleration at various points in time.

[0028] Attitude information can include attitude parameters such as roll angle, roll rate, pitch angle, pitch rate, yaw angle, and yaw rate at various time points.

[0029] Trajectory and attitude information can be acquired through the vehicle's sensing system. This sensing system can integrate sensors such as cameras, LiDAR, millimeter-wave radar, and ultrasonic radar.

[0030] S102, determine the trajectory disorder evaluation index of surrounding vehicles based on trajectory information.

[0031] Indicators for evaluating trajectory disorder can include trajectory entropy or the rate of change of trajectory entropy. More specifically, trajectory entropy can include information entropy, sample entropy, or permutation entropy.

[0032] S103, determine the attitude change evaluation index of surrounding vehicles based on attitude information.

[0033] Attitude change evaluation metrics can include the rate of change of each attitude parameter or the overall attitude change resulting from the combined changes of all attitude parameters. The process of determining the overall change can include: constructing a covariance matrix based on each attitude parameter, and obtaining the overall attitude change based on the changes in the covariance matrix.

[0034] It should be noted that steps S102 and S103 can be executed simultaneously or in any order. This embodiment does not specify the execution order of S102 and S103.

[0035] S104, based on the trajectory disorder evaluation index and attitude change evaluation index, determines the tire blowout risk of surrounding vehicles.

[0036] A vehicle traveling normally and under control has a predictable short-term trajectory (low entropy). However, when a serious malfunction occurs, such as a tire blowout, the driver's control decreases sharply, and the vehicle's movement becomes dominated by physical disturbances, resulting in a chaotic, random, and unpredictable trajectory (high entropy). Trajectory entropy assesses the overall disorder of the trajectory from the perspective of "information content," is more robust to noise, and can reveal vehicle instability due to tire blowouts earlier and more fundamentally. Furthermore, when a vehicle transitions from controlled to unstable driving, this transition is also reflected in the rate of change of trajectory entropy.

[0037] In a normally driving vehicle, the changes in its attitude parameters are smooth and interconnected. When one tire blows out, the vehicle instantly loses balance, causing these attitude parameters to undergo drastic and uncoordinated abrupt changes simultaneously.

[0038] Therefore, this embodiment combines trajectory disorder evaluation index and attitude change evaluation index to determine whether there is a risk of tire blowout for surrounding vehicles, and the magnitude of the risk of tire blowout.

[0039] S105 generates vehicle risk avoidance strategies based on the risk of tire blowout.

[0040] The vehicle generates its own risk avoidance strategy based on the risk of a tire blowout. The vehicle risk avoidance strategy may include the direction of avoidance, the selection of braking or acceleration mode, and the degree of braking or acceleration.

[0041] The vehicle risk avoidance method provided in this embodiment can be applied to a vehicle risk avoidance software system, which can run on a terminal device. The terminal device can be an in-vehicle device.

[0042] In summary, this embodiment monitors the tire blowout risk of surrounding vehicles and formulates avoidance strategies based on the monitoring results. This can reduce or avoid collisions with the vehicle caused by tire blowouts of surrounding vehicles, thus improving the vehicle's safety. Furthermore, during the monitoring process, this embodiment determines the presence of tire blowout risk based on trajectory chaos evaluation indicators and attitude change evaluation indicators of surrounding vehicles. This method does not rely on communication links between vehicles, making it more widely applicable and more accurate than audio / voiceprint, image, or simple trajectory deviation detection methods.

[0043] In some embodiments of the present invention, such as Figure 2 As shown, the trajectory information includes a sequence of trajectory points, and the trajectory disorder evaluation index includes information entropy; S102 includes: S201, calculate the change in steering angle between two adjacent trajectory points in the trajectory point sequence of surrounding vehicles to obtain the sequence of steering angle changes.

[0044] S202, the steering angle change sequence is discretized into multiple intervals, and the steering mode of each interval is determined based on the steering angle change of each interval.

[0045] S203, count the frequency of each turning mode within each first sliding time window, and calculate the information entropy corresponding to the first sliding time window using the information entropy formula.

[0046] Specifically, the trajectory points can be sorted by time to obtain a trajectory point sequence. Then, based on the trajectory points at N consecutive time points in the trajectory point sequence, the change in steering angle Δθ between adjacent trajectory points can be calculated, because the change in steering angle Δθ reflects the driver's control intention and vehicle disturbances better than directly using coordinates.

[0047] Then, the continuous multiple Δθ values ​​are discretized into multiple intervals, and the steering mode of the vehicle in each interval is determined based on the Δθ value of each interval. The steering modes include: large left turn, small left turn, straight ahead, small right turn, and large right turn. The frequency of all steering modes is counted within the first sliding time window, and the frequency is normalized to obtain the probability distribution of steering modes within the first sliding time window.

[0048] Next, the probability of the turning mode corresponding to the first sliding time window is substituted into the information entropy formula H=-∑P(i). log2(Pi), where Pi represents the probability of the turning mode, is used to calculate the information entropy corresponding to the first sliding time window.

[0049] If surrounding vehicles consistently travel in a straight line, the probability distribution is concentrated, and the entropy value is low. However, if surrounding vehicles sway erratically from side to side, the probability distribution is uniform, and the entropy value increases sharply. Therefore, in addition to considering the magnitude of the information entropy itself, we can also determine whether surrounding vehicles have experienced tire blowouts or instability by observing how the information entropy changes over a preset time period.

[0050] In summary, information entropy can comprehensively characterize the physical disturbance of surrounding vehicles when they become unstable, as well as the trajectory disturbance caused by the driver's operation. Therefore, this embodiment uses information entropy to determine whether surrounding vehicles have blown out and become unstable, which can avoid the unpredictability of vehicle behavior caused by different driver reactions after a tire blowout.

[0051] Reference Figure 3 This paper illustrates a flowchart of a method for detecting tire blowouts of surrounding vehicles based on information entropy, provided by the present invention. A sequence of steering angle changes is generated based on the trajectory point sequence (X_t, Y_t), where (X_t, Y_t) represents the position of surrounding vehicles at time t. Steering patterns for different intervals are determined based on the steering angle change sequence. A probability distribution P is constructed within a first sliding time window based on the frequency of the steering patterns. The information entropy H of the first sliding time window is calculated using the information entropy formula combined with the probability distribution P. If the rate of change of information entropy H (represented by the slope of the information entropy curve or the difference in information entropy) exceeds a threshold within a short period, and information entropy H remains high, then from the perspective of information entropy, it can be determined that surrounding vehicles are at risk of tire blowout and instability.

[0052] In some embodiments of the present invention, such as Figure 4 As shown, the attitude change evaluation index includes the attitude change index; S103 includes: S401, based on the attitude information of surrounding vehicles, construct the covariance matrix of attitude parameters within each second sliding time window.

[0053] S402, the attitude change index is calculated based on the change in the covariance matrix of the adjacent second sliding time window.

[0054] Specifically, the attitude parameters are chosen as directional vectors; for example, yaw rate is used instead of yaw angle. Because abrupt attitude changes are reflected in the rate of change and are more sensitive to instantaneous shocks, the covariance matrix is ​​constructed using attitude parameters from N consecutive frames within a preset time period.

[0055] The construction process includes: dividing the attitude parameters according to a preset second sliding time window, the length of which can be the same as or different from the length of the first sliding time window. A covariance matrix C_k is calculated based on the attitude parameters of each second sliding time window: the diagonal elements of the matrix are the variances (energy) of each attitude parameter, and the off-diagonal elements are their covariances (linear correlation strength). During a tire blowout, all elements may change drastically.

[0056] Then, the change in the covariance matrix of adjacent second sliding time windows is determined, and the attitude mutation index D_k is calculated based on the change in the covariance matrix. The attitude mutation index includes at least one of the following: Frobenius norm difference, divergence, and singular value rate of change.

[0057] The Frobenius norm is calculated by taking the square root of the sum of the squares of the differences between the matrix elements. This method is direct and has a clear physical meaning.

[0058] The divergence can be LogDet divergence, calculated using the formula: D_k = tr(C_{k-1}^{-1} C_k) - log(det(C_{k-1}^{-1} C_{k-1} - n, where C_{k-1} represents the covariance matrix of the previous second sliding time window, C_k represents the covariance matrix of the current second sliding time window, tr(·) represents the trace of the matrix within the brackets, det(·) represents the determinant of the matrix within the brackets, and n represents the dimension of the covariance matrix. It measures the "distance" between two covariance matrices from an information geometry perspective and is more robust to multidimensional correlation changes.

[0059] The process of calculating the singular value rate of change is as follows: perform singular value decomposition on the covariance matrix of adjacent second sliding time windows respectively, and then calculate the singular value rate of change based on the singular values ​​corresponding to adjacent second sliding time windows.

[0060] The above calculations yield the attitude change index sequence.

[0061] In summary, changes in the covariance matrix of attitude parameters can capture the patterns of abrupt changes in the coupling of various attitude parameters. Compared with the individual judgment of a single attitude parameter, it can more accurately reflect whether surrounding vehicles have experienced tire blowouts and instability, reducing false alarms or missed alarms.

[0062] Reference Figure 5The diagram illustrates a flowchart of a method for detecting tire blowouts of surrounding vehicles based on a covariance matrix, provided by this invention. A covariance matrix C_k is constructed based on the yaw rate, pitch rate, and roll acceleration of surrounding vehicles across N consecutive frames. This second sliding time window is a continuously overlapping time window, for example, 0.5 s with 50% overlap. C_k is a 3×3 symmetric matrix reflecting the relationship between the three attitudes within the window. Then, the attitude change index D_k is calculated based on the covariance matrix C_k, and the D_k sequence is searched and judged. If D_k exceeds a threshold and is a local maximum, it can be determined from the perspective of attitude information that the surrounding vehicles are at risk of tire blowout and instability.

[0063] In some embodiments of the present invention, S104 includes: When the trajectory entropy continues to increase within a preset time period and the attitude change index is greater than the change index threshold, it is determined that there is a risk of tire blowout for surrounding vehicles.

[0064] In some embodiments of the present invention, the step of determining that there is a risk of tire blowout for surrounding vehicles when the trajectory entropy continuously increases within a preset time period and the attitude change index is greater than the change index threshold includes: When the rate of change of trajectory entropy is greater than the trajectory entropy change rate threshold, and the trajectory entropy is continuously greater than the trajectory entropy threshold within a preset time period, and the attitude mutation index is greater than the mutation index threshold, and the rate of change of any attitude parameter is greater than the attitude parameter change rate threshold, it is determined that there is a risk of tire blowout for surrounding vehicles.

[0065] Specifically, the trajectory entropy continuously increases within a preset time period, reflected in the rate of change, which is positive, and the magnitude of the rate of change reflects the rate of increase. This embodiment, based on the previous embodiment, further limits the rate of increase of the trajectory entropy. Simultaneously, it introduces judgment conditions where the trajectory entropy continuously exceeds a trajectory entropy threshold, and the rate of change of any attitude parameter exceeds a threshold for the rate of change of the attitude parameter, further improving the robustness of the judgment and reducing false alarms and false negatives.

[0066] In some embodiments of the present invention, S105 includes: Based on the impact of tire blowout risk, the instability manifestations of tire blowouts in surrounding vehicles, and the distribution of vehicles on the road, a vehicle risk avoidance strategy is generated.

[0067] Specifically, the impact of a tire blowout risk refers to the effect of surrounding vehicles' tire blowouts on the vehicle itself. Blowout instability can manifest as sideslip, serpentine, or rollover. The distribution of vehicles on the road can include the distribution of vehicles around the vehicle.

[0068] Based on a pre-built AI model, vehicle risk avoidance strategies can be generated according to the impact of tire blowout risk, the instability of tire blowouts of surrounding vehicles, and the distribution of vehicles on the road.

[0069] In some embodiments of the present invention, a mapping relationship can be established in advance between vehicle risk avoidance strategies and the impact of tire blowout risk, the manifestation of tire blowout instability of surrounding vehicles, and the distribution of vehicles on the road. In practical applications, vehicle risk avoidance strategies are determined based on this mapping relationship.

[0070] Based on the mapping relationship between instability state and defensive driving strategy, standardized corresponding actions are adopted according to the type of instability to avoid the inherent logic of the current solution and improve the effectiveness of defensive driving.

[0071] Reference Figure 6 In this diagram, white vehicles represent the vehicle itself, red vehicles represent surrounding vehicles at risk of tire blowout and instability, and blue vehicles represent surrounding vehicles without such risk. Vehicle safety strategies include: 1. For example Figure 6 (a) If a vehicle to the side or rear (the red vehicle) is about to collide with your vehicle and there is enough space in front to avoid the collision, control your vehicle to accelerate urgently and drive away from the danger zone and alert the driver.

[0072] 2. For example Figure 6 (b) If a vehicle from the side or rear is about to collide with your vehicle and there is not enough space in front to avoid the collision, but there is enough space in the adjacent lane, steer the vehicle away from the danger zone and alert the driver.

[0073] 3. For example Figure 6 (c) If a vehicle on the side or rear is about to collide with the vehicle and there is not enough space in front to avoid the collision, and there is not enough space in the adjacent lane and no vehicle is following behind the vehicle, control the vehicle to apply sufficient braking to avoid the collision and alert the driver.

[0074] 6. For example Figure 6 (d) If a vehicle on the side or rear is about to collide with the vehicle and there is not enough space in front to avoid the collision, and there is not enough space in the adjacent lane while a vehicle is following behind, control the vehicle to brake appropriately to avoid the collision and alert the driver.

[0075] Reference Figure 7 This diagram illustrates a vehicle risk avoidance process provided by the present invention. Based on collected image data of surrounding vehicles, abnormal conditions of the surrounding vehicle tires are identified. Trajectory entropy and attitude mutation index are calculated based on the trajectory and attitude sequences of the surrounding vehicles. If the trajectory entropy consistently exceeds the trajectory entropy threshold, and the attitude mutation index exceeds the mutation index threshold, it is determined that a sudden instability has occurred in the surrounding vehicles. At this point, based on the mapping relationship between the tire blowout instability manifestations of the surrounding vehicles and the defense strategy, the specific defense actions of the vehicle are determined, and control commands are issued to control the vehicle's execution system to perform the defense actions.

[0076] Reference Figure 8 The diagram illustrates a vehicle controller 800 provided by the present invention. The vehicle controller 800 includes a processor 801 and a memory 802. Figure 8 Only some of the components of the vehicle controller 800 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0077] In some embodiments, processor 801 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 802 or process data, such as the vehicle avoidance method of the present invention.

[0078] In some embodiments, processor 801 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 801 may be local or remote. In some embodiments, processor 801 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0079] In some embodiments, memory 802 may be an internal storage unit of vehicle controller 800, such as a hard disk or memory of vehicle controller 800. In other embodiments, memory 802 may also be an external storage device of vehicle controller 800, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on vehicle controller 800.

[0080] Furthermore, the memory 802 may include both internal storage units of the vehicle controller 800 and external storage devices. The memory 802 is used to store application software and various types of data installed on the vehicle controller 800.

[0081] In one embodiment, when processor 801 executes the vehicle avoidance program in memory 802, the following steps can be implemented: Obtain trajectory and attitude information of surrounding vehicles; Determine the trajectory disorder evaluation index of surrounding vehicles based on trajectory information; Determine the attitude change evaluation index of surrounding vehicles based on attitude information; Based on the trajectory disorder evaluation index and attitude change evaluation index, determine the tire blowout risk of surrounding vehicles; Vehicle risk mitigation strategies are generated based on the risk of tire blowout.

[0082] It should be understood that when the processor 801 executes the vehicle avoidance program in the memory 802, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0083] Current Advanced Driver Assistance Systems (ADAS) primarily aim to avoid collisions between the vehicle and other vehicles or obstacles ahead, such as forward collision warning, automatic emergency braking, driver-assisted steering, and automatic emergency steering. Their rear-end collision prevention function mainly involves issuing a warning to the driver of the vehicle in question or the driver of the vehicle behind when a potential collision from a rear vehicle is detected. ADAS rear-end collision prevention functions mainly include: Rear blind spot monitoring: When a vehicle enters the blind spot from the side or rear, the system alerts the driver; if the driver steers at this time, the system will intervene to prevent a collision with the vehicle behind.

[0084] Rear vehicle alert: When a vehicle following too closely is detected, the following vehicle will be alerted by flashing taillights or other means.

[0085] Mitigation of rear-end collisions involving parked vehicles: By detecting vehicles behind using lidar, if a rear-end collision risk is anticipated, the steering wheel will be turned to a specific angle in advance. Thus, at the moment of a rear-end collision, the impact force will cause the vehicle to steer to the side in the predetermined direction, effectively avoiding running towards obstacles and reducing the damage from secondary accidents.

[0086] In real-world scenarios, accidents caused by tire blowouts are often fatal. Statistics show that approximately 70% of major traffic accidents on Chinese highways are due to tire blowouts, and this percentage is even higher in other countries. Vehicles experiencing tire blowouts typically veer off course, posing a significant safety hazard to surrounding vehicles. Current ADAS (Advanced Driver Assistance Systems) are unable to effectively warn of or prevent collisions caused by tire blowouts from other vehicles.

[0087] In view of this, refer to Figure 9 The present invention also provides a vehicle driving assistance system 900, including a sensing system 901, the aforementioned vehicle controller 800, and an execution system 902; wherein, The sensing system 901 is used to collect trajectory and attitude information of surrounding vehicles; System 902 executes vehicle hazard avoidance strategies.

[0088] Specifically, the sensing system 901 can integrate sensors such as cameras, lidar, millimeter-wave radar, and ultrasonic radar to perceive the movement of vehicles around the vehicle in real time and send the perceived information (such as trajectory and attitude information) to the vehicle controller 800 through the corresponding interface.

[0089] The vehicle controller 800 is used to synchronize the perceived information in time and generate environmental dynamic data sequences (trajectory sequences, attitude sequences, etc.). The instability determination subsystem in the vehicle controller 800 is used to determine whether the surrounding vehicles have blown out and become unstable based on the environmental dynamic data sequences. When it is determined that the surrounding vehicles have blown out and become unstable, the subsystem determines the corresponding vehicle avoidance strategy and generates control commands to send to the execution system 902.

[0090] The execution system 902 may include a braking system, a power system, a steering system, a human-machine interface (HMI), etc., and is used to control the driving of the vehicle in response to control commands.

[0091] This embodiment optimizes the ADAS function so that it can effectively alert or prevent collisions caused by tire blowouts of surrounding vehicles.

[0092] The present invention also provides a vehicle including the above-described vehicle driving assistance system.

[0093] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0094] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A vehicle hazard avoidance method, characterized in that, include: Obtain trajectory and attitude information of surrounding vehicles; The trajectory disorder evaluation index of the surrounding vehicles is determined based on the trajectory information; The attitude change evaluation index of the surrounding vehicles is determined based on the attitude information; The risk of tire blowout for surrounding vehicles is determined based on the trajectory disorder evaluation index and the attitude change evaluation index. A vehicle risk avoidance strategy is generated based on the described tire blowout risk.

2. The vehicle hazard avoidance method according to claim 1, characterized in that, The trajectory information includes a sequence of trajectory points, and the trajectory disorder evaluation index includes information entropy; determining the trajectory disorder evaluation index of the surrounding vehicles based on the trajectory information includes: Calculate the change in steering angle between two adjacent trajectory points in the sequence of trajectory points of surrounding vehicles to obtain the sequence of steering angle changes; The sequence of steering angle changes is discretized into multiple intervals, and the steering mode of each interval is determined based on the steering angle change in each interval. The frequency of each turning mode within each first sliding time window is statistically analyzed, and the information entropy corresponding to the first sliding time window is calculated using the information entropy formula.

3. The vehicle hazard avoidance method according to claim 1, characterized in that, The attitude change evaluation index includes the attitude change index; determining the attitude change evaluation index of the surrounding vehicles based on the attitude information includes: Based on the attitude information of surrounding vehicles, construct the covariance matrix of attitude parameters within each second sliding time window; The attitude change index is calculated based on the change in the covariance matrix of the adjacent second sliding time window.

4. The vehicle hazard avoidance method according to claim 3, characterized in that, The attitude mutation index includes at least one of the following: Frobenius norm difference, divergence, and singular value rate of change.

5. The vehicle hazard avoidance method according to claim 1, characterized in that, The trajectory disorder evaluation index includes trajectory entropy, and the attitude change evaluation index includes attitude change index; determining the tire blowout risk of surrounding vehicles based on the trajectory disorder evaluation index and the attitude change evaluation index includes: When the trajectory entropy continues to increase within a preset time period and the attitude change index is greater than the change index threshold, it is determined that the surrounding vehicles are at risk of tire blowout.

6. The vehicle avoidance method according to claim 5, characterized in that, The trajectory disorder evaluation index also includes the rate of change of trajectory entropy, and the attitude change evaluation index also includes the rate of change of multiple attitude parameters; when the trajectory entropy continues to increase within a preset time period and the attitude change index is greater than the change index threshold, it is determined that the surrounding vehicles have a risk of tire blowout, including: When the rate of change of the trajectory entropy is greater than the trajectory entropy change rate threshold, and the trajectory entropy is continuously greater than the trajectory entropy threshold within a preset time period, and the attitude mutation index is greater than the mutation index threshold, and the rate of change of any attitude parameter is greater than the attitude parameter change rate threshold, it is determined that the surrounding vehicles are at risk of tire blowout.

7. The vehicle avoidance method according to claim 1, characterized in that, The method for generating a vehicle risk avoidance strategy based on the tire blowout risk includes: Based on the impact of the tire blowout risk, the tire blowout instability manifestations of surrounding vehicles, and the vehicle distribution on the road, a vehicle risk avoidance strategy is generated.

8. A vehicle controller, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the vehicle avoidance method according to any one of claims 1 to 7.

9. A vehicle driving assistance system, characterized in that, It includes a sensing system, the vehicle controller as described in claim 8, and an execution system; wherein, The sensing system is used to collect trajectory and attitude information of surrounding vehicles; The execution system executes the vehicle risk avoidance strategy.

10. A vehicle, characterized in that, Includes the vehicle driving assistance system as described in claim 9.

Images