Target avoidance prediction method and device and vehicle
By detecting target objects in the vehicle and combining multiple factors to select a reasonable prediction strategy, the problem of low accuracy in target avoidance prediction technology is solved, thereby improving the reliability of vehicle active safety functions and driving safety.
Patent Information
- Application Number
- CN202511756117.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-26
- Publication Date
- 2026-02-27
AI Technical Summary
Existing target avoidance prediction technologies have low prediction accuracy, resulting in low reliability of vehicle active safety functions and affecting driving safety and driving experience.
By detecting the target object and obtaining the vehicle's real-time speed corresponding to the limit braking distance and relative distance, and combining factors such as the vehicle's steering wheel angle, yaw angle, accelerator pedal and deceleration pedal opening, an avoidance prediction strategy or a non-avoidance prediction strategy is adopted, and a reasonable prediction method is selected to improve prediction accuracy.
It improves the reliability of vehicle active safety functions, enhancing driving safety and the driving experience.
Smart Images
Figure CN121572973A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of vehicle control technology, and in particular to a target avoidance prediction method, device and vehicle. Background Technology
[0002] Vehicle active safety features typically employ target avoidance prediction technology. This technology predicts whether an external target is within the vehicle's path. If the predicted target is within the path, an avoidance strategy is executed to achieve the vehicle's active safety function. Therefore, the prediction accuracy of target avoidance prediction technology is closely related to the reliability of the vehicle's active safety features. Currently, the prediction accuracy of target avoidance prediction technology is relatively low, resulting in lower reliability of the vehicle's active safety features and impacting driving safety and the driving experience. Summary of the Invention
[0003] This application provides a target avoidance prediction method, device, and vehicle that can improve the reliability of the vehicle's active safety functions, thereby improving vehicle ride safety and driving experience.
[0004] Firstly, embodiments of this application provide a target avoidance prediction method applied to a vehicle. The method includes: detecting a target object; obtaining the vehicle's real-time speed corresponding to the maximum braking distance, and obtaining the relative distance between the target object and the vehicle; when the relative distance is less than or equal to the maximum braking distance, employing an avoidance prediction strategy to predict whether the target object is on the vehicle's travel path; and when the relative distance is greater than the maximum braking distance, employing a non-avoidance prediction strategy to predict whether the target object is on the vehicle's travel path. Thus, when the vehicle detects a target object, it can proactively employ a reasonable prediction strategy to predict whether the target object is on the vehicle's travel path, thereby improving the reliability of the vehicle's active safety functions and ultimately enhancing vehicle safety and driving experience.
[0005] In one possible implementation, when the relative distance is less than or equal to the ultimate braking distance, an avoidance prediction strategy is employed to predict whether the target object is on the vehicle's path. This includes: when the relative distance is less than or equal to the ultimate braking distance and at least one of the following first conditions is met, the avoidance prediction strategy is employed to predict whether the target object is on the vehicle's path. The first conditions include: the vehicle's steering wheel angle is greater than a first threshold, and the vehicle's yaw angle is greater than a second threshold. This further incorporates the vehicle's steering wheel angle and yaw angle factors, allowing the vehicle to employ a more reasonable prediction strategy to predict whether the target object is on the vehicle's path, thereby improving the reliability of the vehicle's active safety functions and ultimately enhancing vehicle safety and driving experience.
[0006] One possible implementation further includes: when the relative distance is less than or equal to the ultimate braking distance, the vehicle's steering wheel angle is less than or equal to a first threshold, and the vehicle's yaw angle is less than or equal to a second threshold, employing a non-avoidance prediction strategy to predict whether the target object is on the vehicle's path. This further combines the vehicle's steering wheel angle and yaw angle factors, allowing the vehicle to use a more reasonable prediction strategy to predict whether the target object is on the vehicle's path, thereby improving the reliability of the vehicle's active safety functions and ultimately enhancing vehicle safety and driving experience.
[0007] In one possible implementation, an obstacle avoidance prediction strategy is used to predict whether a target object is on the vehicle's path. This includes: when at least one of the following second conditions is met, a nonlinear prediction method is used to predict whether the target object is on the vehicle's path; otherwise, a linear prediction method is used. The second conditions include: the accelerator pedal opening is greater than a third threshold, the decelerator pedal opening is greater than a fourth threshold, the steering wheel angle is greater than a fifth threshold, and the yaw angle is greater than a sixth threshold. This further combines factors such as the vehicle's steering wheel angle, yaw angle, accelerator pedal opening, and decelerator pedal opening, allowing the vehicle to more rationally employ linear or nonlinear prediction methods to predict whether a target object is on the vehicle's path in the obstacle avoidance prediction strategy. This improves the reliability of the vehicle's active safety functions, thereby enhancing driving safety and the driving experience.
[0008] In one possible implementation, the method further includes: when the relative distance is less than or equal to the limit braking distance and at least one of the following third conditions is met, discarding the prediction result of the avoidance prediction strategy and using a non-avoidance prediction strategy to predict whether the target object is on the vehicle's travel path; the third conditions include: the vehicle's accelerator pedal opening is greater than a seventh threshold, the vehicle's deceleration pedal opening is greater than an eighth threshold, the vehicle's steering wheel angle is greater than a ninth threshold, the vehicle's yaw angle is greater than a tenth threshold, the seventh threshold is greater than the third threshold, the eighth threshold is greater than the fourth threshold, the ninth threshold is greater than the fifth threshold, and the tenth threshold is greater than the sixth threshold. This further combines factors such as the vehicle's steering wheel angle, yaw angle, accelerator pedal opening, and deceleration pedal opening, allowing the vehicle to arbitrate the result of the avoidance prediction strategy, thereby improving the reliability of the vehicle's active safety functions and ultimately enhancing vehicle safety and driving experience.
[0009] In one possible implementation, a non-avoidance prediction strategy is used to predict whether the target object is on the vehicle's travel path, including: determining whether the collision time between the vehicle and the target object can be calculated based on a preset first linear prediction model; the first linear prediction model is a linear prediction model established based on the non-avoidance of the target object; if the collision time can be calculated, the target object is determined to be on the vehicle's travel path; if the collision time cannot be calculated, the target object is determined not to be on the vehicle's travel path.
[0010] In one possible implementation, a linear prediction method is used to predict whether the target object is on the vehicle's travel path, including: determining whether the collision time between the vehicle and the target object can be calculated based on a preset second linear prediction model; the second linear prediction model is a linear prediction model established based on target object avoidance; if the collision time can be calculated, the target object is determined to be on the vehicle's travel path; if the collision time cannot be calculated, the target object is determined not to be on the vehicle's travel path.
[0011] In one possible implementation, a nonlinear prediction method is used to predict whether a target object is on the vehicle's travel path, including: calculating a first and second travel curve of the vehicle based on the real-time angle of the vehicle's steering wheel; determining whether the target object is located between the first and second travel curves; and / or, calculating a third and fourth travel curve of the vehicle based on the vehicle's yaw angle; determining whether the target object is located between the third and fourth travel curves.
[0012] Secondly, embodiments of this application provide a target avoidance prediction device, the device comprising: The detection module is used to detect the target object; The module is used to obtain the maximum braking distance corresponding to the vehicle's real-time speed, and to obtain the relative distance between the target object and the vehicle. The prediction module is used to predict whether the target object is on the vehicle's path when the relative distance is less than or equal to the limit braking distance, using an avoidance prediction strategy; and to predict whether the target object is on the vehicle's path when the relative distance is greater than the limit braking distance, using a non-avoidance prediction strategy.
[0013] Thirdly, embodiments of this application provide a vehicle including the target avoidance prediction device of the second aspect.
[0014] Fourthly, embodiments of this application provide a vehicle, including: a processor and a memory; wherein one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the processor, cause the vehicle to perform the method of any of the first aspects.
[0015] Fifthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when moved on a computer, causes the computer to execute the method of any one of the first aspects.
[0016] In a sixth aspect, embodiments of this application provide a computer program product, which includes a computer program that, when run on a computer, causes the computer to perform the method of any one of the first aspects. Attached Figure Description
[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments 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.
[0018] Figure 1 A schematic diagram of the structure of a vehicle provided in an embodiment of this application; Figure 2 A schematic flowchart of the target avoidance prediction method provided in the embodiments of this application; Figure 3 This is a second flowchart illustrating the target avoidance prediction method provided in an embodiment of this application. Figure 4 A schematic diagram of a third type of target avoidance prediction method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the fourth process of the target avoidance prediction method provided in the embodiments of this application; Figure 6 A fifth flowchart illustrating the target avoidance prediction method provided in this application embodiment; Figure 7 A sixth flowchart illustrating the target avoidance prediction method provided in this application embodiment; Figure 8 A schematic diagram illustrating the positional relationship between the first running curve, the second running curve, and the target object provided in an embodiment of this application; Figure 9 A seventh flowchart illustrating the target avoidance prediction method provided in this application embodiment; Figure 10 This is an eighth flowchart illustrating the target avoidance prediction method provided in the embodiments of this application. Figure 11 This is a schematic diagram of a target avoidance prediction device provided in an embodiment of this application. Detailed Implementation
[0019] The terminology used in the implementation section of this application is for the purpose of explaining specific embodiments of this application only, and is not intended to limit this application.
[0020] Target avoidance prediction is a crucial process in vehicle active safety functions, enabling more accurate target prediction as if the target were within the path. It reduces the possibility of false triggering of active safety functions to some extent. The target inpath state (including inpath and notinpath states) characterizes whether a target object in front of the vehicle is present on the vehicle's path. It represents a possible collision and influences the vehicle's decision on whether to activate active braking for that target object. When the vehicle and target object are in a dangerous state of impending collision, common target avoidance prediction schemes assume the target object will attempt to avoid the vehicle using predefined avoidance maneuvers. They select possible avoidance maneuvers from these maneuvers to generate the target object's inpath state, indicating whether a collision is imminent and providing a basis for subsequent vehicle decisions. To handle complex target motion states and ensure safe braking before a collision, common target avoidance prediction algorithms optimize the prediction results using specific parameter settings. However, in actual testing, relying solely on adjusting prediction parameters to influence prediction results has limitations. For target objects with motion changes, there is a possibility that the target object may be identified late in the vehicle's driving path due to inaccurate prediction results in the early stages, ultimately resulting in insufficient braking distance and the vehicle's inability to brake safely, affecting driving safety and driving experience.
[0021] Therefore, embodiments of this application provide a target avoidance prediction method, device, and vehicle, which can improve the reliability of the vehicle's active safety functions, thereby improving vehicle driving safety and driving experience.
[0022] The target avoidance prediction method of this application embodiment can be applied to vehicles, including but not limited to: cars, trucks, motorcycles, buses, ships, airplanes, helicopters, lawnmowers, recreational vehicles, amusement park vehicles, construction equipment, trams, golf carts, trains, or handcarts, etc., and this application embodiment does not impose any special limitations.
[0023] Figure 1 This is a schematic diagram of a vehicle structure provided in the embodiments of this application, such as... Figure 1 As shown, the vehicle 100 may include: a processor 110, a memory 120, a steering wheel 130, an accelerator pedal 140, and a deceleration pedal 150.
[0024] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on vehicle 100. In other embodiments of this application, vehicle 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
[0025] The processor 110, memory 120, steering wheel 130, accelerator pedal 140, and deceleration pedal 150 can communicate with each other through internal connection channels to transmit control and / or data signals. The memory 120 is used to store computer programs, and the processor 110 is used to call and run the computer programs from the memory 120.
[0026] The aforementioned memory 120 may be a read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), or other types of dynamic storage devices capable of storing information and instructions. It may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices. Alternatively, it may be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer.
[0027] The processor 110 and memory 120 can be combined into a single processing device, or more commonly, they are independent components. The processor 110 executes the program code stored in the memory 120 to achieve the aforementioned functions. In specific implementations, the memory 120 can be integrated into the processor 110, or it can be independent of the processor 110.
[0028] The steering wheel 130 is used to adjust the forward direction of the vehicle 100.
[0029] Accelerator pedal 140 is used to control the speed of vehicle 100.
[0030] The deceleration pedal 150 is used to control the vehicle to decelerate from 100.
[0031] The following will combine Figure 1 The vehicle structure shown illustrates the target avoidance prediction method of this application embodiment.
[0032] Figure 2 This is a flowchart illustrating a target avoidance prediction method provided in an embodiment of this application. The method can be executed by a vehicle, specifically by a processor within the vehicle. In some embodiments, Figure 2 The method shown can be executed when the vehicle's autonomous driving function is already activated. For example... Figure 2 As shown, the method may include: Step 201: Target object detected.
[0033] The vehicle can detect target objects in front of it based on images captured by cameras and signals detected by vehicle radar while driving. The implementation of this step can refer to related technologies, and the embodiments of this application are not limited thereto.
[0034] Step 202: Obtain the maximum braking distance corresponding to the vehicle's real-time speed, and obtain the relative distance between the target object and the vehicle.
[0035] In some embodiments, the vehicle in this application may be pre-set with a vehicle braking performance distance table to record the maximum braking distance corresponding to different speeds of the vehicle. The maximum braking distance corresponding to each speed is the minimum braking distance of the vehicle at that speed.
[0036] The vehicle braking performance distance table is shown in Table 1 below, which records the limit braking distance for each speed within the vehicle's function activation speed range. The vehicle function activation speed range refers to the interval between the minimum and maximum speeds at which a specific function is activated or effective during vehicle operation. The specific functions mentioned above may include, but are not limited to, adaptive cruise control (ACC) and automatic driver assistance systems.
[0037] Table 1 It is understood that the braking performance of vehicles of different models and configurations may be different. Consequently, the maximum braking distance of different vehicles at the same speed may be different. Therefore, the embodiments of this application do not limit the specific value of the maximum braking distance corresponding to different speeds in the braking performance distance table of vehicles.
[0038] It is understood that the speed step size in the vehicle braking performance distance table shown in Table 1 is 1 km / h. In other embodiments, this step size can be extended to a larger or smaller value. This application embodiment does not impose any restrictions.
[0039] When a vehicle is equipped with a braking performance distance table as shown in Table 1, the vehicle can look up the braking performance distance table based on its real-time speed to obtain the maximum braking distance corresponding to that real-time speed. For example, assuming the vehicle's real-time speed is 3 km / h, the maximum braking distance corresponding to a real-time speed of 3 km / h can be found in Table 1 as a3 meters.
[0040] The process of obtaining the vehicle's real-time speed in this step can refer to relevant technologies, and this application embodiment does not impose any limitations.
[0041] The process of obtaining the relative distance between the vehicle and the target object in this step can refer to relevant technologies, and this application embodiment does not impose any limitations.
[0042] Step 203: When the relative distance is less than or equal to the limit braking distance, use an avoidance prediction strategy to predict whether the target object is on the vehicle's travel path; when the relative distance is greater than the limit braking distance, use a non-avoidance prediction strategy to predict whether the target object is on the vehicle's travel path.
[0043] The vehicle can record prediction results using target parameters. Specifically, the first target parameter value indicates that the target object is on the vehicle's travel path, and the second target parameter value indicates that the target object is not on the vehicle's travel path. For example, the target parameter can be the aforementioned target Inpath state parameter, where the first parameter value can be Inpath, and the second parameter value can be NotInpath.
[0044] The collision avoidance prediction strategy in this embodiment is based on the target object avoiding the vehicle (self-vehicle), while the non-collision prediction strategy is based on the target object not avoiding the vehicle (self-vehicle). Target object avoiding the vehicle means the target object takes a collision avoidance action; target object not avoiding the vehicle means the target object does not take a collision avoidance action. For the specific implementation of the collision avoidance prediction strategy and the non-collision prediction strategy, please refer to the subsequent embodiments; they will not be elaborated here.
[0045] It should be noted that in this embodiment of the application, step 203 is executed only when the vehicle's autonomous driving function is already activated and no driver control behavior is detected. If the vehicle detects driver control behavior before step 203, causing the vehicle's autonomous driving function to be deactivated, then step 203 will not be executed.
[0046] Figure 2In the method shown, based on the vehicle's maximum braking distance and the relative distance between the vehicle and the target object, when the relative distance is less than or equal to the maximum braking distance, an avoidance prediction strategy is used to predict whether the target object is on the vehicle's path. When the relative distance is greater than the maximum braking distance, a non-avoidance prediction strategy is used to predict whether the target object is on the vehicle's path. This enables the vehicle to actively use a reasonable prediction strategy to predict whether the target object is on the vehicle's path, thereby improving the reliability of the vehicle's active safety functions and thus improving the vehicle's driving safety and driving experience.
[0047] In some embodiments, a preset vehicle braking performance distance table can be obtained through a pre-calibrated test method. The following is an example.
[0048] Step S1: Test and record the vehicle's braking performance.
[0049] The ultimate braking distance of a vehicle at several speeds is measured. Specifically, within the vehicle's functional activation speed range, the ultimate braking distance of the vehicle at each speed point from the lowest activation speed to the highest activation speed is measured and recorded at certain speed step intervals.
[0050] For example, assuming the vehicle's functional start-up speed range is (0, 120 km / h) and the speed step is 5 km / h, then the vehicle's limit braking distance at speeds of 5 km / h, 10 km / h, 15 km / h, ..., 120 km / h can be measured and recorded.
[0051] For safety reasons, when measuring the ultimate braking distance at each speed point, the testing equipment can automatically issue a braking command to the vehicle at the speed point.
[0052] In some embodiments, in order to make the limit braking distance of each speed obtained by the test more accurate, each speed point is repeated a preset number of times, such as 3 times, and the average value of the predicted array data is taken as the recorded value of that speed point, so as to improve the accuracy and reliability of the test results.
[0053] Step S2: Construct a distance table for vehicle braking performance.
[0054] In this step, a vehicle braking performance distance table can be constructed based on the test results in step S1, that is, the extreme braking distances corresponding to the multiple speed points recorded.
[0055] In some embodiments, a Simulink model can be used to build a table of the vehicle's maximum braking distances. The test results (speed points, maximum braking distances) from step S1 are converted into table content. The maximum braking distances corresponding to other speeds within the vehicle's functional activation speed range, excluding the speed points, can be generated based on the test results using linear interpolation. Specific implementation details can be found in related technologies, and will not be elaborated upon in this application. For example, speeds such as 1 km / h, 2 km / h, and 3 km / h, which were not tested, can be generated based on the test results from step S1 using linear interpolation.
[0056] By generating the limit braking distance for each speed using linear interpolation, it can be ensured that the vehicle (self-vehicle) can find the limit braking distance from the self-vehicle braking performance distance table at any legal speed, thereby improving the applicability of the target avoidance prediction method in the embodiments of this application.
[0057] In other embodiments provided in this application, based on the relationship between relative distance and ultimate braking distance, the vehicle's steering wheel angle and yaw angle can be further combined to determine the prediction strategy for the target object. For example... Figure 3 As shown, the method may include: Figure 3 This is another flowchart illustrating the target avoidance prediction method provided in an embodiment of this application. Figure 3 As shown, the method may include: Step 301: Target object detected.
[0058] Step 302: Obtain the vehicle's real-time speed and find the limit braking distance corresponding to the vehicle's real-time speed based on the vehicle braking performance distance table.
[0059] Step 303: Obtain the relative distance between the target object and the vehicle.
[0060] The execution order between steps 302 and 303 is not limited in this embodiment.
[0061] Step 304: Determine if the relative distance is greater than the limit braking distance. If not, proceed to step 305; if yes, proceed to step 306.
[0062] Step 305: Determine whether the vehicle's steering wheel angle is greater than the first threshold and whether the vehicle's yaw angle is greater than the second threshold. If both determinations are negative, proceed to step 306. If at least one determination is positive, proceed to step 307.
[0063] The steering wheel angle is a core parameter of the vehicle's steering system, referring to the angle at which the steering wheel is rotated left or right from the center position.
[0064] The yaw angle of a vehicle is the angle at which the vehicle rotates around its vertical axis, reflecting the degree of deviation of the vehicle's direction from its original driving path. It is a key parameter in vehicle dynamics.
[0065] The specific values of the first and second thresholds are not limited in this embodiment. This embodiment employs a non-avoidance prediction strategy when the vehicle's steering wheel angle and yaw angle are relatively small, meaning subsequent avoidance maneuvers are more feasible; and employs an avoidance prediction strategy when the vehicle's steering wheel angle or yaw angle is relatively large, meaning subsequent avoidance maneuvers are less feasible. This allows the vehicle to proactively adopt a more reasonable prediction strategy to predict whether the target object is on the vehicle's path.
[0066] Step 306: Use a non-avoidance prediction strategy to predict whether the target object is on the vehicle's travel path.
[0067] The implementation of this step can be found in the following sections. Figure 4 The illustrated embodiment will not be described in detail here.
[0068] Step 307: Use an avoidance prediction strategy to predict whether the target object is on the vehicle's travel path.
[0069] The implementation of this step can be found in the following sections. Figure 5 The illustrated embodiment will not be described in detail here.
[0070] Figure 3 In the method shown, based on the relationship between relative distance and limit braking distance, the vehicle's steering wheel angle and yaw angle can be further combined to determine the prediction strategy for the target object. This allows the vehicle to actively adopt a more reasonable prediction strategy to predict whether the target object is on the vehicle's travel path, thereby improving the reliability of the vehicle's active safety functions and thus improving the vehicle's driving safety and driving experience.
[0071] The implementation of step 306 is illustrated below.
[0072] In some embodiments, step 306 can determine whether the target object is on the vehicle's travel path by judging whether the collision time between the vehicle and the target object can be calculated based on a preset first linear prediction model. If the collision time can be calculated, the target object is determined to be on the vehicle's travel path; otherwise, the target object is not on the vehicle's travel path.
[0073] The first linear prediction mode is a linear prediction model based on the target object not avoiding the vehicle (self-vehicle). The specific method for establishing the linear prediction model can be referred to relevant technologies, and the embodiments of this application are not limited.
[0074] Specifically, such as Figure 4As shown, step 306 may include: Step 401: Calculate the collision time between the vehicle and the target object based on the preset first linear prediction model.
[0075] Step 402: Determine whether an effective collision time can be calculated based on the preset first linear prediction model. If yes, proceed to step 403; otherwise, proceed to step 404.
[0076] Here, a valid collision time refers to a collision time that meets the collision time requirements. For example, if the collision time between the vehicle and the target object calculated based on the preset first linear prediction model is greater than a certain preset threshold, it means that there is a problem with this collision time, and it is an invalid collision time. The corresponding judgment result of this step is no.
[0077] Step 403: Determine if the target object is on the vehicle's travel route.
[0078] Step 404: Determine that the target object is not on the vehicle's travel route.
[0079] The implementation of step 307 is illustrated below.
[0080] like Figure 5 As shown, step 307 may include: Step 501: Determine whether the opening of the vehicle's accelerator pedal is greater than the third threshold, the opening of the vehicle's deceleration pedal is greater than the fourth threshold, the steering wheel angle of the vehicle is greater than the fifth threshold, and the yaw angle of the vehicle is greater than the sixth threshold. If all of the above are negative, proceed to step 502. If at least one of the above is positive, proceed to step 503.
[0081] In step 501, the decision to execute step 502 or step 503 is based on four judgment conditions. In other embodiments, step 501 may also be based on some of the judgment conditions to determine whether to execute step 502 or step 503. This application does not impose any restrictions.
[0082] In some embodiments, the fifth threshold may be greater than the first threshold mentioned above, and the sixth threshold may be greater than the second threshold mentioned above.
[0083] Step 502: Use the linear obstacle avoidance prediction method to predict whether the target object is on the vehicle's travel path.
[0084] Step 503: Use a nonlinear obstacle avoidance prediction method to predict whether the target object is on the vehicle's travel path.
[0085] In some embodiments, step 502 can determine whether the target object is on the vehicle's travel path by judging whether the collision time between the vehicle and the target object can be calculated based on a preset second linear prediction model. If the collision time can be calculated, the target object is determined to be on the vehicle's travel path; otherwise, the target object is not on the vehicle's travel path.
[0086] The second linear prediction mode is a linear prediction model based on target object avoidance. The specific method for establishing the linear prediction model can be implemented with reference to relevant technologies, and the embodiments of this application are not limited thereto.
[0087] Specifically, such as Figure 6 As shown, step 502 may include: Step 601: Calculate the collision time between the vehicle and the target object based on the preset second linear prediction model.
[0088] Step 602: Determine whether an effective collision time can be calculated based on the preset second linear prediction model. If yes, proceed to step 603; otherwise, proceed to step 604.
[0089] Step 603: Determine if the target object is on the vehicle's travel route.
[0090] Step 604: Determine that the target object is not on the vehicle's travel route.
[0091] In some embodiments, such as Figure 7 As shown, step 503 may include: Step 701: Calculate the first and second running curves of the vehicle based on the steering wheel angle.
[0092] See Figure 8 The first operating curve can be the operating curve of the leftmost edge of the vehicle when the vehicle is traveling at the current steering wheel angle; the second operating curve can be the operating curve of the rightmost edge of the vehicle when the vehicle is traveling at the current steering wheel angle. It can be understood that left and right are relative concepts here; when the driver is sitting in the driver's seat, the driver's left side is the left side of the vehicle, and the driver's right side is the right side of the vehicle. In some embodiments, the leftmost edge of the vehicle can refer to the outermost point of the left side of the vehicle body, and the rightmost edge of the vehicle can refer to the outermost point of the right side of the vehicle body.
[0093] In this step, how the vehicle calculates the first and second running curves based on the steering wheel angle can be referred to relevant technologies, and this application embodiment does not impose any limitations.
[0094] Step 702: Determine whether the corner point of the target object is located between the first running curve and the second running curve. If at least one corner point is located between the first running curve and the second running curve, proceed to step 703; otherwise, proceed to step 704.
[0095] The target object detected by the vehicle can be recorded as a rectangle, and the four vertices of the rectangle can be called the corner points of the target object. For example... Figure 8 As shown, the vehicle can be represented by a rectangle ABCD, with the four vertices of ABCD being the corner points of the target object.
[0096] like Figure 8 Figure (a) shows a scenario where all four corner points of the target object are between the first and second operating curves; figure (b) shows a scenario where some corner points (points A and D) are located between the first and second operating curves; and figure (c) shows a scenario where no corner points are located between the first and second operating curves. It is understood that as long as the target object has any corner points between the first and second operating curves, the vehicle traveling along the aforementioned first and second operating curves will collide with the target object. Therefore, in this embodiment of the application, if at least one corner point of the target object is located between the first and second operating curves, the target object is determined to be on the vehicle's travel path; otherwise, the target object is determined not to be on the vehicle's travel path.
[0097] In this step, how the vehicle determines whether the corner point of the target object is located between the first running curve and the second running curve can be referred to relevant technologies, and will not be elaborated in the embodiments of this application.
[0098] Step 703: Determine if the target object is on the vehicle's travel route.
[0099] Step 704: Determine that the target object is not on the vehicle's travel route.
[0100] In some embodiments, such as Figure 9 As shown, step 503 may include: Step 901: Calculate the vehicle's third and fourth running curves based on the vehicle's yaw angle.
[0101] The third running curve can be the running curve of the vehicle's leftmost edge when the vehicle is traveling at the current yaw angle; the fourth running curve can be the running curve of the vehicle's rightmost edge when the vehicle is traveling at the current yaw angle. For specific implementation details, please refer to [reference needed]. Figure 8 The difference between the first and second running curves shown is that the third and fourth running curves are calculated based on the vehicle's current yaw angle.
[0102] Step 902: Determine whether the corner point of the target object is located between the third running curve and the fourth running curve. If at least one corner point is located between the first running curve and the second running curve, proceed to step 903; otherwise, proceed to step 904.
[0103] In this step, how the vehicle specifically determines whether the corner point of the target object is located between the third and fourth running curves can be referred to relevant technologies, which will not be elaborated in the embodiments of this application.
[0104] Step 903: Determine if the target object is on the vehicle's travel route.
[0105] Step 904: Determine that the target object is not on the vehicle's travel route.
[0106] In other embodiments, step 503 may include Figure 6 and Figure 7 The embodiment shown predicts whether the target object is on the vehicle's travel path based on both the real-time angle of the vehicle's steering wheel and the yaw angle of the vehicle. For the two prediction results, if at least one prediction result indicates that the target object is on the vehicle's travel path, the prediction result in step 503 is that the target object is on the vehicle's travel path. If both prediction results indicate that the target object is not on the vehicle's travel path, the prediction result in step 503 is that the target object is not on the vehicle's travel path.
[0107] In other embodiments provided in this application, such as Figure 10 As shown, after step 307, the embodiments of this application may further include the following steps: Step 308: Determine whether the opening of the vehicle's accelerator pedal is greater than the seventh threshold, whether the opening of the vehicle's deceleration pedal is greater than the eighth threshold, whether the vehicle's steering wheel angle is greater than the ninth threshold, and whether the vehicle's yaw angle is greater than the tenth threshold. If all of these conditions are not met, proceed to step 309. If at least one condition is met, proceed to step 310.
[0108] In some embodiments, the seventh threshold may be greater than the third threshold, the eighth threshold may be greater than the fourth threshold, the ninth threshold may be greater than the fifth threshold, and the tenth threshold may be greater than the sixth threshold.
[0109] Step 309: Determine if the prediction result obtained in step 307 is valid.
[0110] Step 310: Determine that the prediction result obtained in step 307 is invalid, and proceed to step 306.
[0111] If at least one of the judgments in step 308 is true, the prediction result obtained in step 307 can be determined to be invalid, and the prediction result of step 307 can be discarded and step 306 can be re-executed.
[0112] This method further incorporates factors such as the vehicle's steering wheel angle, yaw angle, accelerator pedal opening, and deceleration pedal opening, enabling the vehicle to arbitrate the effectiveness of the avoidance prediction strategy's prediction results. This improves the reliability of the vehicle's active safety functions, thereby enhancing the vehicle's driving safety and experience.
[0113] The target avoidance prediction method provided in this application constructs a vehicle braking performance distance table through measurement and calibration, ensuring basic active safety braking performance. Based on ensuring basic active safety braking performance, it determines whether to use an avoidance prediction strategy or a non-avoidance prediction strategy for prediction depending on whether it is a scenario requiring extreme braking. This reduces the possibility of braking collisions caused by relying solely on avoidance prediction, adds consideration to the safe braking distance dimension, enhances the sense of security for drivers and passengers, and also takes into account a certain degree of anti-false triggering performance, improving the user experience.
[0114] Figure 11 A target avoidance prediction device provided in the embodiments of this application, such as Figure 11 As shown, the device 1100 includes: Detection module 1110 is used to detect the target object; The module 1120 is used to obtain the limit braking distance corresponding to the real-time speed of the vehicle, and to obtain the relative distance between the target object and the vehicle. The prediction module 1130 is used to predict whether the target object is on the vehicle's travel path when the relative distance is less than or equal to the limit braking distance, using an avoidance prediction strategy; and to predict whether the target object is on the vehicle's travel path when the relative distance is greater than the limit braking distance, using a non-avoidance prediction strategy.
[0115] Figure 11 The apparatus provided in the illustrated embodiments can be used to execute the technical solutions of the method embodiments shown in this application, and its implementation principles and technical effects can be further referred to the relevant descriptions in the method embodiments.
[0116] The above should be understood Figure 11The division of the various modules in the illustrated device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. These modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented in software via processing element calls, while others are implemented in hardware. For example, the detection module can be a separate processing element or integrated into a chip in the terminal device. The implementation of other units is similar. Furthermore, these units can be fully or partially integrated together, or they can be implemented independently. For example, the aforementioned uplink synchronization device can be a chip or a chip module, or it can be part of a chip or a chip module. During implementation, each step of the above method or each of the above units can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.
[0117] This application also provides a vehicle including the target avoidance prediction device provided in this application embodiment.
[0118] This application also provides a vehicle, including a processor and a memory, wherein the processor is used to execute the method provided in this application.
[0119] This application also provides a chip module for executing the method provided in this application.
[0120] This application also provides a vehicle that includes the chip module provided in this application.
[0121] This application also provides a computer-readable storage medium storing a computer program that, when moved on a computer, causes the computer to execute the method provided in this application.
[0122] This application also provides a computer program product, which includes a computer program that, when run on a computer, causes the computer to execute the method provided in this application.
[0123] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.
[0124] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0125] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0126] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0127] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.
Claims
1. A target avoidance prediction method characterized by, The method is applied to a vehicle and comprises: detecting a target object; obtaining a limit stopping distance corresponding to a real-time speed of the vehicle, and obtaining a relative distance between the target object and the vehicle; when the relative distance is less than or equal to the limit stopping distance, adopting an avoidance prediction strategy to predict whether the target object is on a travel route of the vehicle; and when the relative distance is greater than the limit stopping distance, adopting a non-avoidance prediction strategy to predict whether the target object is on the travel route of the vehicle.
2. The method of claim 1, wherein, The method further comprises: when the relative distance is less than or equal to the limit stopping distance and at least one first condition is met, adopting the avoidance prediction strategy to predict whether the target object is on the travel route of the vehicle; and the first condition comprises that an angle of a steering wheel of the vehicle is greater than a first threshold value and a yaw angle of the vehicle is greater than a second threshold value.
3. The method of claim 2, wherein, The method further comprises: when the relative distance is less than or equal to the limit stopping distance, the angle of the steering wheel of the vehicle is less than or equal to the first threshold value, and the yaw angle of the vehicle is less than or equal to the second threshold value, adopting the non-avoidance prediction strategy to predict whether the target object is on the travel route of the vehicle.
4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: when at least one second condition is met, adopting a non-linear prediction method to predict whether the target object is on the travel route of the vehicle, otherwise, adopting a linear prediction method to predict whether the target object is on the travel route of the vehicle; and the second condition comprises that an opening degree of an accelerator pedal of the vehicle is greater than a third threshold value, an opening degree of a brake pedal of the vehicle is greater than a fourth threshold value, the angle of the steering wheel of the vehicle is greater than a fifth threshold value, and the yaw angle of the vehicle is greater than a sixth threshold value.
5. The method of claim 4, wherein, The method further comprises: when at least one third condition is met, discarding a prediction result of the avoidance prediction strategy and adopting the non-avoidance prediction strategy to predict whether the target object is on the travel route of the vehicle; and the third condition comprises that the opening degree of the accelerator pedal of the vehicle is greater than a seventh threshold value, the opening degree of the brake pedal of the vehicle is greater than an eighth threshold value, the angle of the steering wheel of the vehicle is greater than a ninth threshold value, and the yaw angle of the vehicle is greater than a tenth threshold value, the seventh threshold value is greater than the third threshold value, the eighth threshold value is greater than the fourth threshold value, the ninth threshold value is greater than the fifth threshold value, and the tenth threshold value is greater than the sixth threshold value.
6. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: judging whether a collision time of the vehicle and the target object can be calculated based on a preset first linear prediction model; the first linear prediction model is a linear prediction model established based on non-avoidance of the target object; if the collision time can be calculated, determining that the target object is on the travel route of the vehicle; and if the collision time cannot be calculated, determining that the target object is not on the travel route of the vehicle. If the collision time cannot be calculated, it is determined that the target object is not on the travel path of the vehicle.
7. The method of claim 4, wherein, The method of predicting whether the target object is on the travel path of the vehicle using a linear prediction method comprises: determining whether the collision time of the vehicle and the target object can be calculated based on a preset second linear prediction model; the second linear prediction model is a linear prediction model established based on the target object avoidance; If the collision time can be calculated, it is determined that the target object is on the travel path of the vehicle. If the collision time cannot be calculated, it is determined that the target object is not on the travel path of the vehicle.
8. The method of claim 4, wherein, The method of predicting whether the target object is on the travel path of the vehicle using a nonlinear prediction method comprises: calculating a first running curve and a second running curve of the vehicle based on the real-time angle of the steering wheel of the vehicle; determining whether the target object is located between the first running curve and the second running curve; and / or, calculating a third running curve and a fourth running curve of the vehicle based on the yaw angle of the vehicle; determining whether the target object is located between the third running curve and the fourth running curve.
9. An object avoidance prediction device characterized by comprising: The device comprises: a detection module for detecting a target object; an obtaining module for obtaining a limit stop distance corresponding to a real-time speed of a vehicle, and obtaining a relative distance between the target object and the vehicle; a prediction module for predicting whether the target object is on the travel path of the vehicle using an avoidance prediction strategy when the relative distance is less than or equal to the limit stop distance, and predicting whether the target object is on the travel path of the vehicle using a non-avoidance prediction strategy when the relative distance is greater than the limit stop distance.
10. A vehicle characterized by comprising: comprise: a processor, a memory; one or more computer programs are stored in the memory, the one or more computer programs comprise instructions, when the instructions are executed by the processor, the vehicle executes the method of any one of claims 1 to 8.