Vehicle risk avoiding method and device and electronic equipment

Abstract

The invention discloses a vehicle risk avoiding method and device and electronic equipment, and the method comprises the steps: obtaining the own vehicle driving information of a current vehicle and the other vehicle driving information of a target vehicle in a preset range in the driving process of the current vehicle, and determining the longitudinal risk time and transverse risk time of the current vehicle; according to the longitudinal risk time and the transverse risk time, current collision risk remaining time between the current vehicle and the target vehicle is determined; screening in a plurality of preset risk avoiding directions according to the current collision risk remaining time, and determining a target risk avoiding direction of the current vehicle; determining the current driving state of the current vehicle according to the vehicle driving information, and determining the target risk avoiding track of the current vehicle according to the target risk avoiding direction and the current driving state; and controlling the current vehicle to run according to the target risk avoiding track. The risk avoiding direction can be determined in advance before the risk avoiding track is planned, computing resources are effectively reduced, and the risk avoiding planning efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle intelligent decision-making and planning technology, and in particular to a vehicle risk avoidance method, device and electronic equipment. Background Technology

[0002] With the continuous improvement of automotive intelligence technology, cars are becoming increasingly intelligent and automated. An intelligent vehicle is a comprehensive system integrating environmental perception, planning and control, and multi-level driver assistance functions. It utilizes technologies such as computers, perception fusion, artificial intelligence, and automatic control, making it a typical high-tech complex. Current research on intelligent vehicles primarily focuses on improving vehicle safety and comfort, as well as providing a fast and smooth human-machine interface.

[0003] Current risk assessment methods have comprehensively considered collision risks in existing scenarios, but they still have shortcomings in analyzing potential collision risks. At the same time, many hazard avoidance trajectory planning methods are mostly limited to optimizing traditional planning methods, but have not fully combined vehicle collision risks, scenarios with obstacles in adjacent lanes, and high computational resource consumption to achieve optimal overall performance.

[0004] Current risk assessment methods have comprehensively considered collision risks in existing scenarios, but they still have shortcomings in analyzing potential collision risks. At the same time, many hazard avoidance trajectory planning methods are mostly limited to optimizing traditional planning methods, but have not fully combined vehicle collision risks, scenarios with obstacles in adjacent lanes, and high computational resource consumption to achieve optimal overall performance. Summary of the Invention

[0005] This application provides a vehicle risk avoidance method, device, and electronic device. This application can determine the risk avoidance direction in advance before planning the risk avoidance trajectory, realize real-time risk avoidance of intelligent driving vehicles, and effectively reduce computing resources.

[0006] On the one hand, this application provides a vehicle hazard avoidance method, the method comprising: During the current vehicle's driving process, the vehicle's own driving information and the driving information of other vehicles within a preset range are obtained, and the longitudinal risk time and lateral risk time of the current vehicle are determined based on the vehicle's own driving information and the driving information of other vehicles. The remaining time of the current collision risk between the current vehicle and the target vehicle is determined based on the longitudinal risk time and the lateral risk time; the target vehicle includes at least two vehicles, and each target vehicle corresponds to one remaining time of the current collision risk. If the remaining time of any of the current collision risks is less than a preset risk time threshold, it is determined that the current vehicle has a collision risk, and the target avoidance direction of the current vehicle is determined by filtering among multiple preset avoidance directions based on the remaining time of the current collision risk. The current driving status of the vehicle is determined based on the vehicle's driving information, and the target avoidance trajectory of the vehicle is determined based on the target avoidance direction and the current driving status. Control the current vehicle to travel along the target avoidance trajectory.

[0007] In one exemplary embodiment, determining the target hazard avoidance trajectory of the current vehicle based on the target hazard avoidance direction and the current driving state includes: The current position of the vehicle is obtained based on the current driving status; Based on the target avoidance direction and the current position, determine multiple target avoidance positions for the current vehicle; By fitting the current position with each of the target avoidance positions, the speed and acceleration of the current vehicle during its journey from the current position to each of the target positions are obtained, and multiple initial avoidance trajectories are determined. Obtain the longitudinal avoidance distance, lateral avoidance distance, and lateral acceleration corresponding to each initial avoidance path, and obtain the avoidance cost corresponding to each initial avoidance trajectory based on the longitudinal avoidance distance, the lateral avoidance distance, and the lateral acceleration; The target hazard avoidance trajectory is obtained by filtering multiple initial hazard avoidance trajectories based on the hazard avoidance cost.

[0008] In one exemplary embodiment, determining multiple target avoidance positions of the current vehicle based on the target avoidance direction and the current position includes: Based on the driving information of other vehicles, obtain the location information of other vehicles of the target vehicle; Based on the current location and the location information of other vehicles, determine the avoidance area for the current vehicle; Based on the target hazard avoidance direction, multiple target hazard avoidance locations are obtained by filtering within the hazard avoidance area.

[0009] In one exemplary embodiment, the initial evacuation locations are obtained by filtering within the evacuation area based on the target evacuation direction, including: Based on the target evacuation direction, an initial screening is performed within the evacuation area to obtain multiple initial evacuation locations; Obtain the lateral offset corresponding to each initial avoidance position, and compare the multiple lateral offsets with a preset offset threshold to obtain the offset comparison result; Based on the offset comparison results, a secondary screening is performed on the multiple initial avoidance positions to obtain multiple target avoidance positions.

[0010] In one exemplary embodiment, the target vehicle includes the vehicle in front and adjacent vehicles, and the other vehicle driving information includes the driving information of the vehicle in front and the driving information of adjacent vehicles. The step of determining the longitudinal risk time and lateral risk time of the current vehicle based on the vehicle's own driving information and the other vehicle driving information includes: Based on the vehicle's own driving information and the vehicle's driving information in front, determine the collision time and time distance between the current vehicle and the vehicle in front; The longitudinal risk time between the current vehicle and the vehicle ahead is determined based on the collision time, the vehicle-to-vehicle time distance, and a preset time threshold. The lane merging time is determined based on the vehicle's driving information and the neighboring vehicle's driving information; the lane merging time represents the time required for the lateral position of the current vehicle to overlap with the lateral position of the neighboring vehicle. The lateral risk time between the current vehicle and the adjacent vehicle is determined based on the longitudinal risk time and the lane merging time.

[0011] In one exemplary embodiment, determining the remaining time of the current collision risk between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time includes: The longitudinal risk time is compared with the horizontal risk time to obtain the risk time comparison result; If the risk time comparison result indicates that the longitudinal risk time is greater than the lateral risk time, the longitudinal risk time shall be taken as the remaining time of the current collision risk. If the risk time comparison result indicates that the longitudinal risk time is less than or equal to the lateral risk time, the remaining time of the current collision risk is obtained based on the longitudinal risk time and the lateral risk time.

[0012] In one exemplary embodiment, determining the collision time and time distance between the current vehicle and the vehicle in front based on the vehicle's own driving information and the preceding vehicle's driving information includes: Based on the vehicle's driving information, the current position and speed of the current vehicle are obtained, and based on the preceding vehicle's driving information, the preceding vehicle's position and speed are obtained. Based on the current position and the position of the vehicle in front, determine the current distance between the current vehicle and the vehicle in front; The collision time and the inter-vehicle time distance are determined based on the current vehicle distance, the current vehicle speed, and the speed of the vehicle in front.

[0013] In one exemplary embodiment, determining the lane-merging time based on the vehicle's driving information and the neighboring vehicle's driving information includes: Obtain the current vehicle width; Based on the neighboring vehicle's driving information, the width, position, and speed of the neighboring vehicle are obtained. The lane merging time is obtained based on the current position, the width of the vehicle, the width of the neighboring vehicle, the position of the neighboring vehicle, and the speed of the neighboring vehicle.

[0014] On the other hand, a vehicle avoidance device is provided, the device comprising: The driving information acquisition module is used to acquire the driving information of the current vehicle and the driving information of other vehicles within a preset range during the driving process of the current vehicle, and to determine the longitudinal risk time and lateral risk time of the current vehicle based on the driving information of the current vehicle and the driving information of other vehicles. The current collision risk remaining time determination module is used to determine the current collision risk remaining time between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time; the target vehicle includes at least two vehicles, and each target vehicle corresponds to one current collision risk remaining time; The target avoidance direction determination module is used to determine that the current vehicle has a collision risk when any of the remaining times of the current collision risk are less than a preset risk time threshold, and to filter among multiple preset avoidance directions based on the remaining time of the current collision risk to determine the target avoidance direction of the current vehicle. The target avoidance trajectory determination module is used to determine the current driving state of the current vehicle based on the vehicle driving information, and to determine the target avoidance trajectory of the current vehicle based on the target avoidance direction and the current driving state; The control module is used to control the current vehicle to travel according to the target avoidance trajectory.

[0015] On the other hand, an electronic device is provided, including a processor and a memory, wherein the processor is configured to store processor-executable instructions in the memory; wherein the processor is configured to execute the instructions to implement the vehicle avoidance method described above.

[0016] On the other hand, a computer-readable storage medium is provided, which contains at least one instruction or at least one program, which is loaded and executed by a processor to implement the above-described vehicle avoidance method.

[0017] The vehicle hazard avoidance method, device, and electronic equipment provided in this application have the following technical effects: This application acquires the current vehicle's own driving information and the driving information of other vehicles within a preset range during the current vehicle's driving process. Based on the own vehicle's driving information and the other vehicle's driving information, it determines the current vehicle's longitudinal risk time and lateral risk time. Based on the longitudinal risk time and lateral risk time, it determines the remaining time of the current collision risk between the current vehicle and the target vehicles. The target vehicles include at least two vehicles, each with a corresponding remaining time of the current collision risk. If the remaining time of any forward collision risk is less than a preset risk time threshold, it determines that the current vehicle has a collision risk. Based on the remaining time of the current collision risk, it filters from multiple preset avoidance directions to determine the target avoidance direction of the current vehicle. Based on the own vehicle's driving information, it determines the current vehicle's current driving state. Based on the target avoidance direction and the current driving state, it determines the target avoidance trajectory of the current vehicle. It then controls the current vehicle to drive according to the target avoidance trajectory. This application, by acquiring the driving information of its own vehicle and other vehicles, can monitor current driving risks, determine in real time whether there is a collision risk, and combine lateral collision risks with longitudinal collision risks to provide an accurate basis for intervention in hazard avoidance planning. By determining the hazard avoidance direction before planning the hazard avoidance trajectory, it can reduce large-scale sampling to improve the computing speed and reduce the consumption of computing resources, quickly lock the target hazard avoidance path, improve the efficiency of hazard avoidance planning, and ensure driving safety.

[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a vehicle hazard avoidance method provided in the embodiments of this specification; Figure 2 This is a schematic diagram of a vehicle driving environment provided in the embodiments of this specification; Figure 3 This is a flowchart illustrating a method for obtaining longitudinal risk time and lateral risk time provided in an embodiment of this specification. Figure 4This is a flowchart illustrating a method for obtaining collision time and workshop time distance provided in an embodiment of this specification; Figure 5 This is a flowchart illustrating a method for obtaining merging time provided in an embodiment of this specification; Figure 6 This is a flowchart illustrating a method for determining the remaining time of a current collision risk, as provided in an embodiment of this specification. Figure 7 This is a flowchart illustrating a method for determining a target trajectory, as provided in an embodiment of this specification. Figure 8 This is a schematic diagram of a risk field provided in the embodiments of this specification; Figure 9 This is a schematic diagram of a vehicle avoidance device provided in the embodiments of this specification; Figure 10 The embodiment of the specification provides a schematic diagram of the structure of a server used for a vehicle avoidance method. Detailed Implementation

[0021] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0023] The following describes a vehicle hazard avoidance method according to this application. Figure 1This is a flowchart illustrating a vehicle avoidance method provided in an embodiment of this specification. This specification provides the operational steps of the method described in the embodiment or flowchart, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiment is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the method can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment) as shown in the embodiment or drawings. Specifically, as... Figure 1 As shown, the method may include: S1: During the current vehicle's driving process, acquire the current vehicle's own driving information and the driving information of other vehicles within a preset range, and determine the current vehicle's longitudinal risk time and lateral risk time based on the own vehicle's driving information and the other vehicle's driving information.

[0024] In this embodiment, vehicles face both longitudinal and lateral collision risks while driving. To avoid these risks, the current vehicle and target vehicles within a preset range are monitored in real time. Based on the vehicle's own driving information and the driving information of other vehicles, the longitudinal and lateral risk time between the current vehicle and other target vehicles is calculated. This monitoring of driving risks allows for real-time determination of whether a collision risk exists, providing a basis for accurate intervention in hazard avoidance planning. Target vehicles include vehicles in the vehicle's lane and vehicles in adjacent lanes.

[0025] S2: Determine the remaining time of the current collision risk between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time; the target vehicle includes at least two vehicles, and each target vehicle corresponds to one remaining time of the current collision risk.

[0026] In this embodiment, the longitudinal risk time and the lateral risk time are combined to obtain the remaining time of the current collision risk between the current vehicle and the target vehicle. The target vehicle may be in motion in both the lane where the vehicle is located and the adjacent lane. Therefore, there may be a collision risk between the current vehicle and the target vehicle in the surrounding area, i.e., within the preset range. Therefore, for each target vehicle within the preset range, it is necessary to obtain the remaining time of the current collision risk with the current vehicle in order to more comprehensively monitor the vehicle risk and perform risk avoidance planning in advance before a collision occurs, so as to avoid potential collision risks.

[0027] S3: If the remaining time of any of the current collision risks is less than a preset risk time threshold, it is determined that the current vehicle has a collision risk, and the target avoidance direction of the current vehicle is determined by filtering among multiple preset avoidance directions based on the remaining time of the current collision risk.

[0028] In this embodiment, if the remaining time of the current collision risk between any target vehicle and the current vehicle within a preset range is less than a preset risk time threshold, it indicates that the current vehicle faces a collision risk and intervention is required for evasive planning to avoid a collision. The evasive direction of the current vehicle is determined by filtering based on the remaining time of the current collision risk between each target vehicle and the current vehicle within the preset range. The preset evasive directions mainly include left, right, and straight. If the current vehicle faces a collision risk with the vehicle ahead, the evasive direction can be left or right. Based on the remaining time of the current collision risk between the current vehicle and the target vehicle in the adjacent lane, the side with the more sufficient remaining time of the current collision risk can be preferentially selected as the target evasive direction.

[0029] S4: Determine the current driving status of the current vehicle based on the vehicle driving information, and determine the target avoidance trajectory of the current vehicle based on the target avoidance direction and the current driving status.

[0030] S5: Control the current vehicle to travel according to the target avoidance trajectory.

[0031] For example, such as Figure 2 As shown, taking a three-lane road as an example, consider two types of vehicles: the driver (the current vehicle) and other vehicles. The driver is the current vehicle, and other vehicles are the target vehicles within a preset range. To reduce planning resource consumption, the avoidance direction (longitudinal braking avoidance, left avoidance, right avoidance) is screened before planning the avoidance trajectory. The preset avoidance direction can be defined as follows: ( To the left, Go straight. (to the right) The determination method is as follows:

[0032] in, These refer to the current vehicle, i.e., the owner's vehicle, and the target vehicle. The current collision risk and remaining time. These are the time thresholds for assessing risk.

[0033] In this embodiment of the application, after determining the target avoidance direction, the target avoidance trajectory of the current vehicle is determined according to the current driving state of the current vehicle, and the current vehicle is controlled to avoid the collision according to the target avoidance trajectory. This method of determining the avoidance direction before planning the avoidance path can reduce sampling in most areas to improve the computing speed and reduce the consumption of computing resources, quickly lock the target avoidance path, and improve the efficiency of avoidance planning.

[0034] This application embodiment combines lateral collision risk with longitudinal collision risk, enabling real-time assessment of the existence of collision risk and providing an accurate basis for intervention in hazard avoidance planning. By determining the hazard avoidance direction before planning the hazard avoidance trajectory, it can reduce large-scale sampling to improve computing speed and reduce computing resource consumption, quickly lock the target hazard avoidance path, improve hazard avoidance planning efficiency, and ensure driving safety.

[0035] In one exemplary embodiment, such as Figure 3 As shown, the target vehicle includes the vehicle in front and adjacent vehicles, and the other vehicle driving information includes the driving information of the vehicle in front and the driving information of adjacent vehicles. The step of determining the longitudinal risk time and lateral risk time of the current vehicle based on the vehicle's own driving information and the other vehicle driving information includes: S11: Based on the vehicle's driving information and the preceding vehicle's driving information, determine the collision time and time distance between the current vehicle and the preceding vehicle; S12: Determine the longitudinal risk time between the current vehicle and the vehicle ahead based on the collision time, the vehicle-to-vehicle time distance, and a preset time threshold; S13: Determine the lane merging time based on the vehicle's driving information and the neighboring vehicle's driving information; the lane merging time represents the time required for the lateral position of the current vehicle to overlap with the lateral position of the neighboring vehicle. S14: Determine the lateral risk time between the current vehicle and the adjacent vehicle based on the longitudinal risk time and the lane merging time.

[0036] In this embodiment, the operating scenario of intelligent driving vehicles is a structured road, mainly covering two driving behaviors: going straight and changing lanes. Taking a three-lane road as an example, the vehicles include two types: the driver's own vehicle (the current vehicle) and other vehicles, such as... Figure 2 As shown in the diagram, the dashed lines represent lane lines. and These represent the longitudinal and lateral positions of the vehicle, respectively. and Representing the first The longitudinal and lateral positions of the target vehicle; and These represent the vehicle's length and width, respectively. and They represent the first The length and width of the target vehicle; and These represent the vehicle's longitudinal and lateral speeds, respectively. and They are the first The longitudinal and lateral velocities of the target vehicle.

[0037] During the driving process of a vehicle, there are longitudinal and lateral collision risks simultaneously. For the longitudinal collision risk, which mainly exists between the host vehicle and the vehicle in front, the Time to Collision (TTC) and the Time Headway (THW) can be used as the longitudinal risk indicators for the risk avoidance decision-making. The longitudinal risk time can be determined based on the collision time, the time headway, and a preset time threshold to make a decision on the collision risk. Exemplarily, the above preset time threshold can include a first preset time threshold and a second preset time threshold, and the Time to Longitudinal Risk (TLR) can be:

[0038] Wherein, is the first preset time threshold, is the second preset time threshold, and the first preset time threshold is less than the second preset time threshold.

[0039] For the lateral collision risk, which mainly exists between the host vehicle and the vehicle in the adjacent lane, the longitudinal risk time TLR and the Time to Merge (TTM) can be used as the lateral risk indicators for the risk avoidance decision-making. TTM represents the time required for the lateral positions of the two vehicles to overlap when the vehicle in the adjacent lane merges into the host vehicle's lane. When the target vehicle in the adjacent lane merges into the host vehicle's lane, the longitudinal risk time TLR and the time to merge TTM can be obtained. If TLR > TTM, that is, the vehicle in the adjacent lane has basically completed the lane change before the longitudinal positions of the two vehicles overlap, only the longitudinal risk needs to be considered at this time; if TLR < TTM, that is, the vehicle in the adjacent lane has not completed the lane change before the longitudinal positions of the two vehicles overlap, the collision risk is relatively high at this time. Therefore, a new indicator, the Time to Risk (TTR), is defined by combining the above risk indicators, and it can be specifically as follows:

[0040] The embodiment of the present application adopts a risk measurement method combining the time domain and the space domain as the evaluation standard for the lateral and longitudinal collision risks, which can monitor the driving risks, determine in real time whether there is a collision risk for the vehicle, and provide a basis for the accurate intervention of the risk avoidance plan.

[0041] In an exemplary embodiment, as Figure 4 shown, determining the collision time and the time headway between the current vehicle and the vehicle in front according to the driving information of the host vehicle and the driving information of the vehicle in front includes: S111: Based on the driving information of the host vehicle, obtain the current position and the current vehicle speed of the current vehicle, and based on the driving information of the vehicle in front, obtain the corresponding position and the vehicle speed of the vehicle in front; S112: Determine the current distance between the current vehicle and the vehicle in front based on the current position and the position of the vehicle in front; S113: Determine the collision time and the inter-vehicle time distance based on the current vehicle distance, the current vehicle speed, and the speed of the vehicle in front.

[0042] In this embodiment, to determine the longitudinal risk time of the current vehicle, calculations can be performed based on the current position and speed of the vehicle itself (from its own driving information) and the position and speed of the vehicle in front (from the driving information of the vehicle in front). First, the current distance between the current vehicle and the vehicle in front is obtained based on the current position of the vehicle itself and the position of the vehicle in front. Specifically, the collision time and the time between the two vehicles are mainly calculated using the longitudinal speeds of the vehicle and the target vehicle. The formula for calculating the collision time is as follows:

[0043] In the formula, TTC is the collision time. This represents the current distance between the current vehicle and the vehicle in front. Let the longitudinal speed of the vehicle be denoted as . For the first The longitudinal speed of the target vehicle.

[0044] When the current speed of the vehicle is less than the speed of the target vehicle, the TTC indicator is not applicable to this scenario. Therefore, the vehicle-to-vehicle headway (THW) is introduced as a supplement to the longitudinal risk assessment. The formula for calculating the vehicle-to-vehicle headway is as follows:

[0045] In the formula, THW represents the workshop time interval. This represents the current distance between the current vehicle and the vehicle in front. This represents the longitudinal speed of the vehicle.

[0046] The embodiments of this application use both collision time and inter-vehicle distance to assess the longitudinal collision risk of a vehicle, which enables more accurate, timely and comprehensive monitoring and judgment of collision risk.

[0047] In one exemplary embodiment, such as Figure 5 As shown, determining the lane-merging time based on the vehicle's driving information and the neighboring vehicle's driving information includes: S131: Obtain the current vehicle width; S132: Based on the neighboring vehicle driving information, obtain the neighboring vehicle width, neighboring vehicle position and neighboring vehicle speed of the adjacent vehicle; S133: The lane merging time is obtained based on the current position, the width of the vehicle, the width of the neighboring vehicle, the position of the neighboring vehicle, and the speed of the neighboring vehicle.

[0048] In this embodiment of the application, the lane merging time is the time required for the lateral position of the adjacent vehicle to overlap with the lateral position of the current vehicle. Therefore, the lane merging time can be calculated by the current position of the vehicle, the width of the vehicle, the width, position, and speed of the adjacent vehicle. The specific calculation formula is shown in the following formula.

[0049] In the formula, TTM is the lane merging time. The lateral position of the vehicle. For the width of the vehicle, The lateral position of the adjacent vehicle. For the width of the adjacent car, The lateral speed of the vehicle. The lateral speed of the adjacent vehicle.

[0050] This application's embodiments calculate the time required for the lateral positions of two vehicles to overlap by using information such as the position, width, and speed of the vehicle and the adjacent vehicle. This provides a reliable basis for judging collision risks, enabling precise early intervention and risk avoidance.

[0051] In one exemplary embodiment, such as Figure 6 As shown, determining the remaining time of the current collision risk between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time includes: S21: Compare the longitudinal risk time with the lateral risk time to obtain a risk time comparison result; S22: If the risk time comparison result indicates that the longitudinal risk time is greater than the lateral risk time, the longitudinal risk time shall be taken as the remaining time of the current collision risk; S23: If the risk time comparison result indicates that the longitudinal risk time is less than or equal to the lateral risk time, the remaining time of the current collision risk is obtained based on the longitudinal risk time and the lateral risk time.

[0052] In this embodiment, after obtaining the longitudinal risk time and the lateral risk time, to more accurately determine whether there is a collision risk for the current vehicle, the longitudinal risk time and the lateral risk time can be compared to obtain the remaining time of the current collision risk. If the longitudinal risk time is greater than the lateral risk time, that is, the adjacent vehicle has basically completed its lane change before the longitudinal positions of the two vehicles overlap, only the longitudinal risk needs to be considered. Therefore, the remaining time of the current collision risk is the longitudinal risk time. If the longitudinal risk time is less than or equal to the lateral risk time, that is, the adjacent vehicle has not yet completed its lane change before the longitudinal positions of the two vehicles overlap, the collision risk is relatively high. In this case, it is necessary to comprehensively consider the lateral risk time and the longitudinal risk time to calculate the remaining time of the current collision risk. The calculation formula is shown in the following formula:

[0053] In the formula, TTR is the remaining time of the current collision risk, TTM is the lane change time, and TLR is the longitudinal risk time.

[0054] This application combines lateral collision risk with longitudinal collision risk, enabling monitoring of driving risks and real-time determination of whether a vehicle is at risk of collision. This provides a basis for accurate intervention in risk avoidance planning and improves the accuracy of risk avoidance decisions.

[0055] In one exemplary embodiment, such as Figure 7 As shown, determining the target avoidance trajectory of the current vehicle based on the target avoidance direction and the current driving state includes: S41: Obtain the current position of the vehicle based on the current driving state; S42: Determine multiple target avoidance positions for the current vehicle based on the target avoidance direction and the current position; S43: Fit the current position to each of the target avoidance positions to obtain the speed and acceleration of the current vehicle from the current position to each of the target positions, and determine multiple initial avoidance trajectories; S44: Obtain the longitudinal avoidance distance, lateral avoidance distance, and lateral acceleration corresponding to each initial avoidance path, and obtain the avoidance cost corresponding to each initial avoidance trajectory based on the longitudinal avoidance distance, the lateral avoidance distance, and the lateral acceleration; S45: Based on the risk avoidance cost, filter the multiple initial risk avoidance trajectories to obtain the target risk avoidance trajectory.

[0056] In this embodiment, the target avoidance position of the vehicle can be determined based on its current driving state and the target avoidance direction. Then, a polynomial fitting is performed based on the vehicle's current position and the target avoidance position to obtain the vehicle's velocity and acceleration from its current position to the target avoidance position, thus generating multiple candidate avoidance trajectories, i.e., multiple initial avoidance trajectories. Furthermore, to ensure the safety of the avoidance process, the avoidance trajectory with the lowest possible collision risk should be selected from the multiple initial avoidance trajectories as the target avoidance trajectory.

[0057] In this embodiment, the hazard avoidance trajectory planning needs to plan a safe emergency braking or steering trajectory within a short period of time to avoid or mitigate accident damage as much as possible. The vehicle state can be defined as follows:

[0058] in, Vertical position and x is relative to time. The first and second derivatives, The horizontal position and They are respectively Relative to time The first and second derivatives.

[0059] In this embodiment, terminal sampling based on a baseline is performed in the hazard avoidance direction to determine the vehicle's initial state. and terminal status The initial state of the vehicle can be obtained by fitting the driving trajectory using a fifth-order polynomial, as shown below.

[0060] The vehicle's terminal status can be as follows;

[0061] in, , , , , , , , , , , , The coefficients are those of a fifth-degree polynomial.

[0062] In this embodiment of the application, a target cost function can be set to filter multiple initial avoidance trajectories. The target cost function may include longitudinal distance cost, lateral offset cost, lateral acceleration cost, and velocity cost, etc. The longitudinal avoidance distance, lateral avoidance distance, lateral acceleration, etc. of each initial avoidance trajectory are obtained to obtain the avoidance cost corresponding to each initial avoidance trajectory, and the initial avoidance trajectory with the smallest avoidance cost is taken as the target avoidance trajectory.

[0063] For example, the objective cost function may include a velocity cost function. Vertical distance cost function Lateral offset cost function Lateral acceleration cost function Therefore, the objective cost function can be expressed as follows:

[0064] in, For the first The total cost function of the candidate trajectories. , , , These are the weighting coefficients for each cost function.

[0065] In this embodiment, if the vehicle maintains a high speed during the avoidance process, the required braking distance will be larger, increasing the risk of collision. Therefore, a speed-related cost function is designed; if the difference between the reference speed and the vehicle's speed is large, and the reference speed is reached quickly, then... Relatively low, as defined below:

[0066] in, For the first The first candidate trajectory The velocity at each trajectory point; This represents the desired vehicle speed at the terminal. For the longitudinal distance cost function The longitudinal avoidance distance, as the distance increases, allows for the avoidance of more risks. Its definition is as follows:

[0067] in, This refers to the longitudinal hazard avoidance distance. This represents the longitudinal distance between the vehicle and the obstacle.

[0068] For the lateral offset cost function The larger the lateral offset, the higher the cost, as defined below:

[0069] in, This represents the lateral offset.

[0070] For the cost function of lateral acceleration The greater the lateral acceleration, the higher the cost, as defined below:

[0071] in, Indicates the first Lateral acceleration on the candidate trajectory.

[0072] This application embodiment combines longitudinal avoidance distance, lateral avoidance distance, and lateral acceleration as the criteria for screening avoidance trajectories. Under the premise of ensuring safety, it can select feasible trajectories with shorter longitudinal avoidance distances and smaller lateral offsets and accelerations from the candidate trajectories.

[0073] In an exemplary embodiment, determining multiple target avoidance positions of the current vehicle based on the target avoidance direction and the current position includes: Based on the driving information of other vehicles, obtain the location information of other vehicles of the target vehicle; Based on the current location and the location information of other vehicles, determine the avoidance area for the current vehicle; Based on the target hazard avoidance direction, multiple target hazard avoidance locations are obtained by filtering within the hazard avoidance area.

[0074] In this embodiment of the application, in order to determine the target avoidance location, an avoidance area can be determined first based on the current location of the vehicle and the location information of other vehicles. Then, the target avoidance direction can be filtered within this avoidance area to obtain multiple target avoidance locations.

[0075] For example, if the target avoidance direction is to the right, avoidance positions in other directions can be removed, and only the avoidance positions on the right side can be considered, thus avoiding large-scale sampling.

[0076] In one exemplary embodiment, the step of filtering within the avoidance area based on the target avoidance direction to obtain a plurality of initial avoidance locations includes: Based on the target evacuation direction, an initial screening is performed within the evacuation area to obtain multiple initial evacuation locations; Obtain the lateral offset corresponding to each initial avoidance position, and compare the multiple lateral offsets with a preset offset threshold to obtain the offset comparison result; Based on the offset comparison results, a secondary screening is performed on the multiple initial avoidance positions to obtain multiple target avoidance positions.

[0077] In this embodiment, based on the vehicle's target avoidance direction, avoidance positions outside the avoidance area that are not in the target avoidance direction can be removed first. Then, considering the magnitude of the lateral offset during the vehicle's avoidance process, avoidance positions with excessive lateral offset can be removed, thereby obtaining multiple target avoidance positions, narrowing the range, reducing the computational load of avoidance trajectory planning, and thus improving the efficiency of avoidance trajectory planning.

[0078] The embodiments of this application reduce the amount of computation during the planning of avoidance trajectories by screening avoidance locations before planning the avoidance trajectories, effectively improve the computing speed, reduce the consumption of computing resources, and improve the planning efficiency of avoidance trajectories.

[0079] In this embodiment, a reasonable driving potential field can quantify the impact of obstacles on the vehicle, forming a specific potential force. A risk field can be constructed for five target vehicles adjacent to the vehicle, and through the aforementioned risk avoidance planning and risk avoidance direction decision-making, the trajectory planning problem in complex environments with multiple vehicles traveling in parallel can be solved. Target point potential field As shown in the following formula;

[0080] in, This is the proportional gain coefficient. It is a vector representing the vehicle's position. relative to the target point location The Euclidean distance between them.

[0081] Corresponding gravity The negative gradient of the potential field at the target point is given by the following equation:

[0082] The factor determining the obstacle risk potential field is the distance between the vehicle and the obstacle. When the vehicle is outside the obstacle's influence range, its potential energy is 0. After the vehicle enters the obstacle's influence range, the greater the distance between the two, the smaller the potential energy the vehicle experiences; conversely, the smaller the distance, the greater the potential energy. The potential field function of the risk potential field is shown below:

[0083] in, This is the proportional gain coefficient. is a constant, representing the maximum distance at which an obstacle affects the vehicle.

[0084] Corresponding repulsive force As shown below;

[0085] To avoid the collision risk of the avoidance trajectory, a constructed risk field needs to be introduced when sampling the vehicle's terminal state, as shown in the diagram below. Figure 8 As shown. During the sampling process, it is necessary to consider the time corresponding to the terminal state and the magnitude of the risk field after the lateral offset, thus changing the uniform sampling method to non-uniform sampling based on the vehicle risk field, i.e., the lateral offset is a vehicle risk correlation function. The relationship between the lateral offset and the avoidance direction can be shown below;

[0086] in, This is the lateral offset. The number in the above formula represents the offset of the state sampling, such as 1 m, 2 m, and 3 m, depending on the current lateral position of the vehicle.

[0087] This application embodiment can monitor current driving risks by acquiring the driving information of its own vehicle and other vehicles, and determine in real time whether there is a collision risk. By combining lateral collision risks and longitudinal collision risks, it can provide an accurate basis for intervention in risk avoidance planning. By determining the risk avoidance direction before planning the risk avoidance trajectory, it can reduce large-scale sampling to improve the computing speed and reduce the consumption of computing resources, quickly lock the target risk avoidance path, improve the efficiency of risk avoidance planning, and ensure driving safety.

[0088] This specification also provides a vehicle risk avoidance method, which includes: during vehicle operation, real-time monitoring of the current vehicle and target vehicles within a preset range; calculating the longitudinal and lateral risk times between the current vehicle and other target vehicles based on the vehicle's own driving information and the driving information of other vehicles; combining the longitudinal and lateral risk times to obtain the remaining time of the current collision risk between the current vehicle and the target vehicles; monitoring driving risks; and determining in real time whether a collision risk exists. If a collision risk is determined, the current vehicle's avoidance direction is determined by filtering based on the remaining times of each current collision risk between the current vehicle and each target vehicle within the preset range. The preset avoidance directions mainly include left, right, and straight. Terminal sampling based on the baseline is performed in the avoidance direction. The vehicle's initial state (current state) and terminal state are fitted with a fifth-order polynomial to obtain the avoidance trajectory. Multiple initial avoidance trajectories are then screened using a target cost function. Under the premise of ensuring safety, the feasible trajectory with the shortest longitudinal avoidance, the smallest lateral offset, and the smallest acceleration should be selected from the candidate trajectories. Therefore, the avoidance cost of each initial avoidance trajectory is calculated, and the initial avoidance trajectory with the smallest avoidance cost is selected as the target avoidance trajectory so that the current vehicle can avoid danger according to the target avoidance trajectory, intervene in danger in advance, and prevent the vehicle from colliding.

[0089] This specification also provides a vehicle avoidance device, such as... Figure 9 As shown, the device may include: The driving information acquisition module 910 is used to acquire the driving information of the current vehicle and the driving information of other vehicles within a preset range during the driving process of the current vehicle, and to determine the longitudinal risk time and lateral risk time of the current vehicle based on the driving information of the current vehicle and the driving information of other vehicles. The current collision risk remaining time determination module 920 is used to determine the current collision risk remaining time between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time; the target vehicle includes at least two vehicles, and each target vehicle corresponds to one current collision risk remaining time; The target avoidance direction determination module 930 is used to determine that the current vehicle has a collision risk when any of the remaining times of the current collision risk are less than a preset risk time threshold, and to filter among multiple preset avoidance directions based on the remaining time of the current collision risk to determine the target avoidance direction of the current vehicle. The target avoidance trajectory determination module 940 is used to determine the current driving state of the current vehicle based on the vehicle driving information, and to determine the target avoidance trajectory of the current vehicle based on the target avoidance direction and the current driving state. The control module 950 is used to control the current vehicle to travel according to the target avoidance trajectory.

[0090] In an exemplary embodiment, the target vehicle includes the vehicle in front and the adjacent vehicle, the other vehicle driving information includes the driving information of the vehicle in front and the driving information of the adjacent vehicle, and the driving information acquisition module 910 may include: The driving information acquisition submodule is used to determine the collision time and time distance between the current vehicle and the vehicle in front based on the vehicle's driving information and the vehicle's driving information in front. The longitudinal risk time determination submodule is used to determine the longitudinal risk time between the current vehicle and the vehicle in front based on the collision time, the vehicle-to-vehicle time distance and a preset time threshold. The lane merging time determination submodule is used to determine the lane merging time based on the vehicle's driving information and the neighboring vehicle's driving information; the lane merging time represents the time required for the lateral position of the current vehicle to overlap with the lateral position of the neighboring vehicle. The lateral risk time determination submodule is used to determine the lateral risk time between the current vehicle and the adjacent vehicle based on the longitudinal risk time and the lane merging time.

[0091] In an exemplary embodiment, the driving information acquisition submodule may include: The driving information acquisition unit is used to acquire the current position and current speed of the current vehicle based on the vehicle's driving information, and to acquire the position and speed of the vehicle in front based on the vehicle in front's driving information. The current vehicle distance determination unit is used to determine the current vehicle distance between the current vehicle and the vehicle in front based on the current position and the position of the vehicle in front; The collision time and vehicle distance determination unit is used to determine the collision time and vehicle distance based on the current vehicle distance, the current vehicle speed, and the speed of the vehicle in front.

[0092] In an exemplary embodiment, the lane merging time determination submodule may include: The vehicle width acquisition unit is used to acquire the vehicle width of the current vehicle. The neighbor vehicle information acquisition unit is used to acquire the width, position, and speed of the neighbor vehicle based on the neighbor vehicle driving information. The lane merging time determination unit is used to determine the lane merging time based on the current position, the width of the vehicle, the width of the adjacent vehicle, the position of the adjacent vehicle, and the speed of the adjacent vehicle.

[0093] In an exemplary embodiment, the current collision risk remaining time determination module 920 may include: The risk time comparison result acquisition submodule is used to compare the longitudinal risk time with the horizontal risk time to obtain the risk time comparison result. The first determining submodule is used to determine the longitudinal risk time as the remaining time of the current collision risk when the risk time comparison result indicates that the longitudinal risk time is greater than the lateral risk time. The second determining submodule is used to determine the remaining time of the current collision risk based on the longitudinal risk time and the lateral risk time when the risk time comparison result indicates that the longitudinal risk time is less than or equal to the lateral risk time.

[0094] In an exemplary embodiment, the target avoidance trajectory determination module 940 may include: The current location acquisition submodule is used to acquire the current location of the vehicle based on the current driving state; The target avoidance location determination submodule is used to determine multiple target avoidance locations of the current vehicle based on the target avoidance direction and the current location; The initial avoidance trajectory determination submodule is used to fit the current position with each of the target avoidance positions to obtain the speed and acceleration of the current vehicle from the current position to each of the target positions, and to determine multiple initial avoidance trajectories; The risk avoidance cost acquisition submodule is used to acquire the longitudinal risk avoidance distance, lateral risk avoidance distance, and lateral acceleration corresponding to each initial risk avoidance path, and to obtain the risk avoidance cost corresponding to each initial risk avoidance trajectory based on the longitudinal risk avoidance distance, the lateral risk avoidance distance, and the lateral acceleration. The target avoidance trajectory determination submodule is used to filter multiple initial avoidance trajectories based on the avoidance cost to obtain the target avoidance trajectory.

[0095] In an exemplary embodiment, the initial hazard avoidance trajectory determination submodule may include: The other vehicle location information acquisition unit is used to acquire the other vehicle location information of the target vehicle based on the other vehicle driving information; The avoidance area determination unit is used to determine the avoidance area of ​​the current vehicle based on the current location and the location information of other vehicles; The target evacuation location determination unit is used to filter within the evacuation area based on the target evacuation direction to obtain multiple target evacuation locations.

[0096] In an exemplary embodiment, the target avoidance location determination unit may include: The initial evacuation location acquisition subunit is used to perform an initial screening within the evacuation area based on the target evacuation direction to obtain multiple initial evacuation locations. The offset comparison result acquisition subunit is used to acquire the lateral offset corresponding to each of the initial avoidance positions, and compare the multiple lateral offsets with a preset offset threshold to obtain the offset comparison result; The target avoidance position determination subunit is used to perform secondary filtering on multiple initial avoidance positions based on the offset comparison results to obtain multiple target avoidance positions.

[0097] The apparatus and method embodiments described above are based on the same inventive concept.

[0098] This specification provides an electronic device including a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the vehicle avoidance method provided in the above method embodiments.

[0099] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in a terminal to store at least one instruction or at least one program related to implementing the vehicle avoidance method in the method embodiments. The at least one instruction or at least one program is loaded and executed by the processor to implement the vehicle avoidance method provided in the above method embodiments.

[0100] Embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle avoidance method provided in the above-described method embodiments.

[0101] Optionally, in the embodiments of this specification, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0102] The memory described in the embodiments of this specification can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for the functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0103] The vehicle avoidance methods described in this specification can be executed on mobile terminals, computer terminals, servers, or similar computing devices. Taking a server as an example... Figure 10 This is a hardware structure block diagram of a server for a vehicle risk avoidance method provided in the embodiments of this specification. For example... Figure 10As shown, the server 1000 can vary significantly due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1010 (CPUs 1010 may include, but are not limited to, microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 1030 for storing data, and one or more storage media 1020 (e.g., one or more mass storage devices) for storing application programs 1023 or data 1022. The memory 1030 and storage media 1020 may be temporary or persistent storage. The program stored in the storage media 1020 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the CPU 1010 may be configured to communicate with the storage media 1020 and execute the series of instruction operations in the storage media 1020 on the server 1000. Server 1000 may also include one or more power supplies 1060, one or more wired or wireless network interfaces 1050, one or more input / output interfaces 1040, and / or one or more operating systems 1021, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0104] The input / output interface 1040 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 1000. In one example, the input / output interface 1040 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 1040 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0105] Those skilled in the art will understand that Figure 10 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 1000 may also include... Figure 10 The more or fewer components shown, or having the same Figure 10 The different configurations shown.

[0106] As can be seen from the embodiments of the vehicle avoidance method, device, and electronic device provided in this application, during the driving process of the current vehicle, this application acquires the driving information of the current vehicle and the driving information of other vehicles within a preset range, and determines the longitudinal risk time and lateral risk time of the current vehicle based on the driving information of the current vehicle and the driving information of other vehicles; determines the remaining time of the current collision risk between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time; the target vehicles include at least two vehicles, each target vehicle corresponding to a remaining time of the current collision risk; if the remaining time of any forward collision risk is less than a preset risk time threshold, it is determined that the current vehicle has a collision risk, and the target avoidance direction of the current vehicle is determined by filtering from multiple preset avoidance directions based on the remaining time of the current collision risk; the current driving state of the current vehicle is determined based on the driving information of the current vehicle, and the target avoidance trajectory of the current vehicle is determined based on the target avoidance direction and the current driving state; and the current vehicle is controlled to drive according to the target avoidance trajectory. This application, by acquiring the driving information of its own vehicle and other vehicles, can monitor current driving risks, determine in real time whether there is a collision risk, and combine lateral collision risks with longitudinal collision risks to provide an accurate basis for intervention in hazard avoidance planning. By determining the hazard avoidance direction before planning the hazard avoidance trajectory, it can reduce large-scale sampling to improve the computing speed and reduce the consumption of computing resources, quickly lock the target hazard avoidance path, improve the efficiency of hazard avoidance planning, and ensure driving safety.

[0107] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0108] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0109] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer storage medium, such as a read-only memory, a disk, or an optical disk.

[0110] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A vehicle hazard avoidance method, characterized in that, The method includes; During the current vehicle's driving process, the vehicle's own driving information and the driving information of other vehicles within a preset range are obtained, and the longitudinal risk time and lateral risk time of the current vehicle are determined based on the vehicle's own driving information and the driving information of other vehicles. The remaining time of the current collision risk between the current vehicle and the target vehicle is determined based on the longitudinal risk time and the lateral risk time; the target vehicle includes at least two vehicles, and each target vehicle corresponds to one remaining time of the current collision risk. If the remaining time of any of the current collision risks is less than a preset risk time threshold, it is determined that the current vehicle has a collision risk, and the target avoidance direction of the current vehicle is determined by filtering among multiple preset avoidance directions based on the remaining time of the current collision risk. The current driving status of the vehicle is determined based on the vehicle's driving information, and the target avoidance trajectory of the vehicle is determined based on the target avoidance direction and the current driving status. Control the current vehicle to travel along the target avoidance trajectory.

2. The method according to claim 1, characterized in that, Determining the target hazard avoidance trajectory of the current vehicle based on the target hazard avoidance direction and the current driving state includes: The current position of the vehicle is obtained based on the current driving status; Based on the target avoidance direction and the current position, determine multiple target avoidance positions for the current vehicle; By fitting the current position with each of the target avoidance positions, the speed and acceleration of the current vehicle during its journey from the current position to each of the target positions are obtained, and multiple initial avoidance trajectories are determined. Obtain the longitudinal avoidance distance, lateral avoidance distance, and lateral acceleration corresponding to each initial avoidance path, and obtain the avoidance cost corresponding to each initial avoidance trajectory based on the longitudinal avoidance distance, the lateral avoidance distance, and the lateral acceleration; The target hazard avoidance trajectory is obtained by filtering multiple initial hazard avoidance trajectories based on the hazard avoidance cost.

3. The method according to claim 2, characterized in that, The step of determining multiple target avoidance positions for the current vehicle based on the target avoidance direction and the current position includes: Based on the driving information of other vehicles, obtain the location information of other vehicles of the target vehicle; Based on the current location and the location information of other vehicles, determine the avoidance area for the current vehicle; Based on the target hazard avoidance direction, multiple target hazard avoidance locations are obtained by filtering within the hazard avoidance area.

4. The method according to claim 3, characterized in that, The process of filtering within the evacuation area based on the target evacuation direction yields multiple initial evacuation locations, including: Based on the target evacuation direction, an initial screening is performed within the evacuation area to obtain multiple initial evacuation locations; Obtain the lateral offset corresponding to each initial avoidance position, and compare the multiple lateral offsets with a preset offset threshold to obtain the offset comparison result; Based on the offset comparison results, a secondary screening is performed on the multiple initial avoidance positions to obtain multiple target avoidance positions.

5. The method according to claim 1, characterized in that, The target vehicle includes the vehicle in front and adjacent vehicles. The other vehicle driving information includes the driving information of the vehicle in front and the driving information of adjacent vehicles. Determining the longitudinal risk time and lateral risk time of the current vehicle based on the vehicle's own driving information and the other vehicle driving information includes: Based on the vehicle's own driving information and the vehicle's driving information in front, determine the collision time and time distance between the current vehicle and the vehicle in front; The longitudinal risk time between the current vehicle and the vehicle ahead is determined based on the collision time, the vehicle-to-vehicle time distance, and a preset time threshold. The lane merging time is determined based on the vehicle's driving information and the neighboring vehicle's driving information; the lane merging time represents the time required for the lateral position of the current vehicle to overlap with the lateral position of the neighboring vehicle. The lateral risk time between the current vehicle and the adjacent vehicle is determined based on the longitudinal risk time and the lane merging time.

6. The method according to claim 5, characterized in that, Determining the remaining time of the current collision risk between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time includes: The longitudinal risk time is compared with the horizontal risk time to obtain the risk time comparison result; If the risk time comparison result indicates that the longitudinal risk time is greater than the lateral risk time, the longitudinal risk time shall be taken as the remaining time of the current collision risk. If the risk time comparison result indicates that the longitudinal risk time is less than or equal to the lateral risk time, the remaining time of the current collision risk is obtained based on the longitudinal risk time and the lateral risk time.

7. The method according to claim 6, characterized in that, Determining the collision time and time distance between the current vehicle and the vehicle in front based on the vehicle's own driving information and the preceding vehicle's driving information includes: Based on the vehicle's driving information, the current position and speed of the current vehicle are obtained, and based on the preceding vehicle's driving information, the preceding vehicle's position and speed are obtained. Based on the current position and the position of the vehicle in front, determine the current distance between the current vehicle and the vehicle in front; The collision time and the inter-vehicle time distance are determined based on the current vehicle distance, the current vehicle speed, and the speed of the vehicle in front.

8. The method according to claim 7, characterized in that, Determining the lane-merging time based on the vehicle's driving information and the neighboring vehicle's driving information includes: Obtain the current vehicle width; Based on the neighboring vehicle's driving information, the width, position, and speed of the neighboring vehicle are obtained. The lane merging time is obtained based on the current position, the width of the vehicle, the width of the neighboring vehicle, the position of the neighboring vehicle, and the speed of the neighboring vehicle.

9. A vehicle safety avoidance device, characterized in that, The device includes: The driving information acquisition module is used to acquire the driving information of the current vehicle and the driving information of other vehicles within a preset range during the driving process of the current vehicle, and to determine the longitudinal risk time and lateral risk time of the current vehicle based on the driving information of the current vehicle and the driving information of other vehicles. The current collision risk remaining time determination module is used to determine the current collision risk remaining time between the current vehicle and the target vehicle based on the longitudinal risk time and the lateral risk time; the target vehicle includes at least two vehicles, and each target vehicle corresponds to one current collision risk remaining time; The target avoidance direction determination module is used to determine that the current vehicle has a collision risk when any of the remaining times of the current collision risk are less than a preset risk time threshold, and to filter among multiple preset avoidance directions based on the remaining time of the current collision risk to determine the target avoidance direction of the current vehicle. The target avoidance trajectory determination module is used to determine the current driving state of the current vehicle based on the vehicle driving information, and to determine the target avoidance trajectory of the current vehicle based on the target avoidance direction and the current driving state; The control module is used to control the current vehicle to travel according to the target avoidance trajectory.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the vehicle avoidance method as described in any one of claims 1-8.

Images