A method and apparatus for determining the stationary state of a target vehicle.

Abstract

This application proposes a method and apparatus for determining the stationary state of a target vehicle. The method includes obtaining a first stationary probability based on the relative speed between the vehicle and the target vehicle; obtaining a second stationary probability based on the relative distance between the vehicle and the target vehicle; obtaining a third stationary probability based on the collision time between the vehicle and the target vehicle; processing the first, second, and third stationary probabilities to generate an optimal stationary probability; and determining the stationary state of the target vehicle based on the optimal stationary probability if the optimal stationary probability is greater than a preset probability. This application can improve the accuracy of determining the stationary state of a target vehicle and improves the efficiency of multivariate verification of stationary states based on different factors such as speed, distance, and collision time by calculating the three stationary probabilities of the target vehicle.

Description

Technical Field

[0001] This application belongs to the field of intelligent vehicles, and in particular relates to a method and device for determining the stationary state of a target vehicle. Background Technology

[0002] With the rapid development of intelligent vehicles, the requirements for intelligent driving functions are becoming increasingly stringent, as are the requirements for the vehicle's status and functions in intelligent driving scenarios. When a vehicle is in intelligent driving mode, it needs to determine the stationary or moving state of itself and its target vehicles or other objects to obtain more accurate intelligent driving scenario parameters. This information is used to assist the vehicle in performing operations such as lane changing and acceleration, or to upload data to the cloud to provide better data support for other vehicles.

[0003] However, in the existing technology, taking the determination of the stationary state of the target vehicle as an example, there are still problems such as a single method for determining the stationary state of the target vehicle and a large error in the determination result.

[0004] Therefore, the existing technology still needs further development. Summary of the Invention

[0005] To address the issues of a single judgment method and large errors in the judgment results, this application proposes a method and apparatus for judging the stationary state of a target vehicle. This method can improve the accuracy of judging the stationary state of a target vehicle. By calculating the static probability of a target vehicle using three different methods, it improves the efficiency of multivariate verification of the stationary state in different aspects such as speed, distance, and collision time.

[0006] like Figure 1 As shown, in its first aspect, this application provides a method for determining the stationary state of a target vehicle, comprising:

[0007] The first probability of being stationary is obtained based on the relative speed between the vehicle and the target vehicle;

[0008] The second stationary probability is obtained based on the relative distance between the vehicle and the target vehicle;

[0009] The third stationary probability is obtained based on the collision time between the vehicle and the target vehicle;

[0010] The first stationary probability, the second stationary probability, and the third stationary probability are processed to generate an optimal stationary probability. If the optimal stationary probability is greater than a preset probability, the stationary state of the target vehicle is determined based on the optimal stationary probability.

[0011] Optionally, if the optimal probability of remaining still is greater than a preset probability, the method further includes:

[0012] Determine whether the optimal static probability satisfies a preset sampling step size, wherein the preset sampling step size includes multiple consecutive single sampling steps, and the single sampling step size is 20ms-100ms;

[0013] If the optimal stationary probability is greater than the preset probability and satisfies the preset sampling step size, then the optimal stationary probability is output as the target vehicle stationary probability.

[0014] If the optimal stationary probability is greater than the preset probability but does not meet the preset sampling step size, then the output target vehicle stationary probability is 0.

[0015] Optionally, if the optimal stationary probability is less than the preset probability, the output target vehicle stationary probability is 0.

[0016] The process of obtaining the first stationary probability based on the relative speed between the vehicle and the target vehicle includes:

[0017] Step S11: Obtain the absolute value of the relative speed between the vehicle and the target vehicle;

[0018] Step S12: Filter the absolute value of the relative speed between the vehicle and the target vehicle to generate a filtered absolute value;

[0019] Step S13: Calculate the difference diff between the vehicle speed and the absolute value of the filter;

[0020] Step S14: Filter the difference diff and take the absolute value of the difference diff, |diff|, and let |diff| be the first static probability input value;

[0021] The first static probability is obtained by inputting the first static probability value into the normal distribution density function.

[0022] Optionally, the filtering method is low-pass filtering.

[0023] Optionally, the step of inputting the first rest probability input value into the normal distribution density function to obtain the first rest probability includes:

[0024] Let diff = x - μ, the normal distribution density function

[0025] When diff0 = 0, the first rest probability prob10 = 1, yielding the coefficients of the normal distribution density function for the first rest probability, i.e.:

[0026]

[0027] Therefore, the first static probability

[0028] The second stationary probability is obtained based on the relative distance between the vehicle and the target vehicle, including:

[0029] Obtain the relative distance Dx between the vehicle and the target vehicle at the first moment. pre ;

[0030] Obtain the relative distance Dx between the vehicle and the target vehicle at the second moment;

[0031] Obtain the time interval Δt between the first time point and the second time point;

[0032] Based on the relative distance between the vehicle and the target vehicle at the first moment, the relative distance between the vehicle and the target vehicle at the second moment, and the time interval, the relative speed RelV between the vehicle and the target vehicle is obtained, and RelV = x2 - μ2 is set as the input value of the second stationary probability.

[0033] The second rest probability is obtained by inputting the second rest probability into the normal distribution density function.

[0034] Optionally, the step of inputting the second rest probability input value into the normal distribution density function to obtain the second rest probability further includes:

[0035] Let RelV = x - μ, the normal distribution density function

[0036] When RelV0 = 0, the second rest probability prob20 = 1, yielding the coefficients of the normal distribution density function for the second rest probability, i.e.:

[0037]

[0038] Therefore, the second static probability

[0039] Optionally, a third stationary probability is obtained based on the collision time between the vehicle and the target vehicle, including:

[0040] Obtain the first relative distance, Dyor, between the vehicle and the target vehicle;

[0041] The collision time of the target vehicle is processed to obtain the absolute value of the collision time;

[0042] Multiplying the absolute value of the collision time by the vehicle speed yields the second relative distance Dy between the vehicle and the target vehicle;

[0043] The difference between the first relative distance Dyor between the vehicle and the target vehicle and the relative distance Dy between the vehicle and the target vehicle is taken as the absolute value to obtain |Dyor-Dy|=Ddiff. Let Ddiff be the input value of the third stationary probability.

[0044] The third static probability is obtained by inputting the third static probability into the normal distribution density function.

[0045] Optionally, the step of inputting the third rest probability input value into the normal distribution density function to obtain the third rest probability further includes:

[0046] Let Ddiff = x - μ, the normal distribution density function

[0047] When Ddiff0 = 0, the first rest probability prob30 = 1, yielding the coefficients of the normal distribution density function for the first rest probability, i.e.:

[0048]

[0049] Therefore, the third static probability

[0050] Optionally, obtaining the third stationary probability based on the collision time between the self-vehicle and the target vehicle also includes:

[0051] Before obtaining the absolute value of the collision time, the collision time of the target vehicle is subjected to low-pass filtering and / or

[0052] After multiplying the absolute value of the collision time by the vehicle speed to obtain the second relative distance Dy between the vehicle and the target vehicle, the second relative distance Dy between the vehicle and the target vehicle is subjected to low-pass filtering.

[0053] Optionally, the step of processing the first stationary probability, the second stationary probability, and the third stationary probability to generate an optimal stationary probability, and outputting the optimal stationary probability as the target vehicle stationary probability if the optimal stationary probability is greater than a preset probability, includes:

[0054] The maximum probability among the first static probability, the second static probability, and the third static probability is selected and filtered to obtain the maximum filtered probability. If the maximum filtered probability meets the maximum filtering threshold, then the maximum filtered probability is the optimal static probability.

[0055] A second aspect of this application provides a device for determining the stationary state of a target vehicle, comprising:

[0056] The first acquisition module is used at least to acquire a first stationary probability based on the relative speed between the vehicle and the target vehicle;

[0057] The second acquisition module is used at least to acquire a second stationary probability based on the relative distance between the vehicle and the target vehicle;

[0058] The third acquisition module is used at least to acquire the third stationary probability based on the collision time between the vehicle and the target vehicle;

[0059] The judgment module is at least used to process the first stationary probability, the second stationary probability, and the third stationary probability to generate an optimal stationary probability. If the optimal stationary probability is greater than a preset probability, the stationary state of the target vehicle is judged based on the optimal stationary probability.

[0060] A third aspect of this application provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the judgment method described in the first aspect of this application.

[0061] This application improves the requirements for judging the stationary state of a target vehicle in intelligent driving vehicles and intelligent driving functions, and also provides a method for calculating and processing the probability of the target vehicle being stationary, thereby improving the accuracy of the calculation of the target vehicle being stationary state. This provides a good reference for subsequent research, decision-making, planning and pre-judgment of autonomous vehicles and overall intelligent driving functions. Attached Figure Description

[0062] Figure 1 A flowchart illustrating a method for determining the stationary state of a target vehicle according to an embodiment of this application is shown.

[0063] Figure 2 A flowchart illustrating a method for determining the stationary state of a target vehicle in one embodiment of this application is shown.

[0064] Figure 3 A flowchart illustrating a method for determining the stationary state of a target vehicle in one embodiment of this application is shown.

[0065] Figure 4 A flowchart illustrating a method for determining the stationary state of a target vehicle in one embodiment of this application is shown.

[0066] Figure 5 This diagram illustrates the structural composition of a device for determining the stationary state of a target vehicle according to an embodiment of this application. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0068] Determining the stationary state of a target vehicle plays a crucial and positive role in intelligent driving systems and autonomous vehicle systems. It can help autonomous vehicles with path planning and motion modeling, and also assist autonomous vehicles or other vehicles in completing other intelligent decision-making behaviors and obstacle avoidance planning.

[0069] With the development of automotive technology, sensor technology, control technology and artificial intelligence technology, the methods for detecting target vehicles have become increasingly diverse.

[0070] like Figure 1 As shown, the first aspect of this application provides a method for determining the stationary state of a target vehicle, comprising:

[0071] Step S1: Obtain the first stationary probability based on the relative speed between the vehicle and the target vehicle;

[0072] Step S2: Obtain the second stationary probability based on the relative distance between the vehicle and the target vehicle;

[0073] Step S3: Obtain the third stationary probability based on the collision time between the vehicle and the target vehicle.

[0074] Specifically, the relative speed between the vehicle and the target vehicle can be obtained through adaptive cruise control, which is a relatively easy parameter to acquire.

[0075] The relative distance between the vehicle and the target vehicle can be obtained through millimeter-wave radar, lidar, cameras, ultrasonic sensors, infrared sensors, multi-sensor fusion algorithms, etc.

[0076] One method for calculating the Time To Collision (TTC) between the autonomous vehicle and the target vehicle involves estimating the size changes of the target vehicle through key points, establishing a motion model of the target vehicle, using Kalman filtering to track the parameters of the target vehicle motion model, and employing a strategy to fuse the calculation results of multiple motion models to obtain the result.

[0077] It should be understood that the relative speed between the vehicle and the target vehicle, the relative distance between the vehicle and the target vehicle, and the collision time between the vehicle and the target vehicle are all obtainable with existing technology, and will not be elaborated further.

[0078] Step S4: Process the first stationary probability, the second stationary probability, and the third stationary probability to generate the optimal stationary probability. If the optimal stationary probability is greater than the preset probability, then determine the stationary state of the target vehicle based on the optimal stationary probability.

[0079] Since the first, second, and third stationary probabilities represent three possible outcomes of the target vehicle's stationary state, to improve the accuracy of determining the target vehicle's stationary state, it is necessary to generate the optimal stationary probability by referring to the first, second, and third stationary probabilities. This can be achieved using existing technologies, such as calculating the average, median, maximum, and minimum values ​​of the first, second, and third stationary probabilities and then filtering them, or by using parameter tuning to incorporate the first, second, and third stationary probabilities into the parameter model to generate the optimal stationary probability.

[0080] One way to generate the optimal stationary probability is to select the maximum probability among the first stationary probability, the second stationary probability, and the third stationary probability and filter it to obtain the maximum filtered probability. If the maximum filtered probability satisfies the maximum filtering threshold, then the maximum filtered probability is the optimal stationary probability.

[0081] Here, by using the relatively accurate relative speed between the self-vehicle and the target vehicle, the relative distance between the self-vehicle and the target vehicle, and the collision time of the self-vehicle with the target vehicle obtained in the prior art as the starting values ​​for calculation, the calculation accuracy of the first stationary probability, the second stationary probability, and the third stationary probability is improved respectively. Furthermore, by processing the generated optimal stationary probability, the accuracy of judging the stationary state of the target vehicle is further improved.

[0082] In addition, in order to determine the actual stationary state of the target vehicle, a preset probability is set as a reference for the optimal stationary probability. The preset probability can be adjusted according to the actual driving conditions and the parameters of the vehicle and the target vehicle. For example, the preset probability can be set to 30%, 40%, 60%, etc., to improve the accuracy of determining the stationary state of the target vehicle.

[0083] In one embodiment of this application, the step of "if the optimal static probability is greater than the preset probability" further includes:

[0084] Determine whether the optimal static probability satisfies a preset sampling step size, wherein the preset sampling step size includes multiple consecutive single sampling steps, and the single sampling step size is 20ms-100ms;

[0085] If the optimal stationary probability is greater than the preset probability and satisfies the preset sampling step size, then the optimal stationary probability is output as the target vehicle stationary probability.

[0086] Specifically, the sampling step size is a way to determine the stability of the target vehicle's stationary state. For example, the optimal stationary probability can be set to be greater than the preset probability, and three sampling steps must be satisfied. With a preset probability of 40% and each sampling step size of 150ms, the optimal stationary probability must be approximately 40% within 450ms.

[0087] In one embodiment of this application, if the optimal stationary probability is greater than the preset probability but does not meet the preset sampling step size, then the output target vehicle stationary probability is 0.

[0088] If the optimal stationary probability is less than the preset probability, then the output target vehicle stationary probability is 0.

[0089] This method allows for the quantitative analysis of the optimal stationary probability. If the optimal stationary probability is lower than the preset probability, it is determined that the target vehicle is not stationary.

[0090] Preferably, before judging the optimal stationary probability and the preset probability, low-pass filtering can be performed to eliminate interference from irrelevant signals and improve the accuracy of judging the stationary state of the target vehicle.

[0091] like Figure 2 As shown in one embodiment of this application, obtaining the first stationary probability based on the relative speed between the vehicle and the target vehicle includes:

[0092] Step S11: Obtain the absolute value of the relative speed between the vehicle and the target vehicle. The relative speed between the vehicle and the target vehicle can be obtained through adaptive cruise control, which is a relatively easy parameter to acquire. Obtaining the absolute value of the relative speed between the vehicle and the target vehicle is used to unify the relative deceleration or acceleration of the vehicle relative to the target vehicle.

[0093] Step S12: Filter the absolute value of the relative speed between the vehicle and the target vehicle to generate a filtered absolute value. Here, a low-pass filter can be used to improve the accuracy of the absolute value of the relative speed between the vehicle and the target vehicle. The filtered value is called the filtered absolute value.

[0094] Step S13: Calculate the difference diff between the vehicle speed and the absolute value of the filter;

[0095] Step S14: Filter the difference diff and take the absolute value of the difference diff, |diff|, and let |diff| be the first static probability input value;

[0096] Specifically, the difference value (diff) is used to represent the difference between the vehicle speed and the relative speed. Here, filtering the difference value (diff) and taking its absolute value (|diff|) is only the first way to obtain |diff|, and the filtering method is low-pass filtering. In addition, the second way is to take the absolute value of the difference value and then filter it, and the filtering method can also be low-pass filtering.

[0097] The first static probability is obtained by inputting the first static probability value into the normal distribution density function.

[0098] Specifically, the normal distribution density function can meet the requirements for judging the stationary state of the target vehicle in this application. The normal distribution function is also a relatively conventional way to calculate probability. However, the normal distribution probability density function is only one tool for calculating probability density in this application. If other density distribution functions, such as the Poisson distribution, can also meet the requirements for judging the stationary state of the target vehicle in this application, they also fall within the scope of protection of this application.

[0099] Specifically, the step of inputting the first rest probability input value into the normal distribution density function to obtain the first rest probability includes:

[0100] Let diff = x - μ, the normal distribution density function

[0101] When diff0 = 0, the first rest probability prob10 = 1, yielding the coefficients of the normal distribution density function for the first rest probability, i.e.:

[0102]

[0103] Therefore, the first static probability

[0104] This method allows us to calculate the first probability of the vehicle coming to a standstill, given the relative speeds of the vehicle and the target vehicle.

[0105] like Figure 3 As shown, in one embodiment of this application, obtaining a second stationary probability based on the relative distance between the vehicle and the target vehicle includes:

[0106] Step S21: Obtain the relative distance Dx between the vehicle and the target vehicle at the first moment. pre ;

[0107] Step S22: Obtain the relative distance Dx between the vehicle and the target vehicle at the second moment;

[0108] Step S23: Obtain the time interval Δt between the first time point and the second time point;

[0109] Specifically, the relative distance Dx between the vehicle and the target vehicle at the first moment.pre The relative distance Dx between the vehicle and the target vehicle at the second moment, as well as the time interval Δt between the first moment and the second moment, can be obtained through the adaptive cruise control system or through millimeter-wave radar, lidar, camera, ultrasonic sensor, infrared sensor, multi-sensor fusion algorithm, etc.

[0110] Step S24: Based on the relative distance between the vehicle and the target vehicle at the first moment, the relative distance between the vehicle and the target vehicle at the second moment, and the time interval, obtain the relative speed RelV between the vehicle and the target vehicle.

[0111] RelV=(Dx-Dx pre ) / Δt;

[0112] Let RelV = x² - μ² be the input value of the second rest probability;

[0113] Step S25: Input the second rest probability input value into the normal distribution density function to obtain the second rest probability.

[0114] Specifically, the step of inputting the second rest probability input value into the normal distribution density function to obtain the second rest probability further includes: letting RelV = x - μ, and the normal distribution density function...

[0115] When RelV0 = 0, the second rest probability prob20 = 1, yielding the coefficients of the normal distribution density function for the second rest probability, i.e.:

[0116]

[0117] Therefore, the second static probability

[0118] In this way, the second probability of being stationary can be calculated when the relative speeds of the vehicle and the target vehicle are equal.

[0119] like Figure 4 As shown, in one embodiment of this application, obtaining a third stationary probability based on the collision time between the vehicle and the target vehicle includes:

[0120] Step S31: Obtain the first relative distance Dyor between the vehicle and the target vehicle. It should be understood that the first relative distance Dyor between the vehicle and the target vehicle is different from the relative distance Dx between the vehicle and the target vehicle at the first moment in this application. pre Alternatively, the method for obtaining the relative distance Dx between the vehicle and the target vehicle at the second moment is the same, so we will not repeat it again.

[0121] Step S32: Process the collision time of the target vehicle to obtain the absolute value of the collision time. In one method for calculating the TTC (Time To Collision) between the vehicle and the target vehicle, the size change of the target vehicle is estimated by key points, a motion model of the target vehicle is established, the parameters of the motion model of the target vehicle are tracked by Kalman filtering, and the calculation results of multiple motion models are fused by a strategy to obtain the absolute value.

[0122] Step S33: Multiply the absolute value of the collision time by the vehicle speed to obtain the second relative distance Dy between the vehicle and the target vehicle; Step S34: Subtract the first relative distance Dyor between the vehicle and the target vehicle from the relative distance Dy between the vehicle and the target vehicle and take the absolute value to obtain |Dyor-Dy|=Ddiff, and let Ddiff be the input value of the third stationary probability;

[0123] Step S35: Input the third rest probability input value into the normal distribution density function to obtain the third rest probability.

[0124] Specifically, the step of inputting the third rest probability input value into the normal distribution density function to obtain the third rest probability further includes:

[0125] Let Ddiff = x - μ, the normal distribution density function

[0126] When Ddiff0 = 0, the first rest probability prob30 = 1, yielding the coefficients of the normal distribution density function for the first rest probability, i.e.:

[0127]

[0128] Therefore, the third static probability

[0129] This method allows us to calculate the third probability of the vehicle remaining stationary, given the relative speeds of the vehicle and the target vehicle.

[0130] Furthermore, obtaining the third stationary probability based on the collision time between the self-vehicle and the target vehicle also includes:

[0131] Before obtaining the absolute value of the collision time, the collision time of the target vehicle is subjected to low-pass filtering and / or

[0132] After multiplying the absolute value of the collision time by the vehicle speed to obtain the second relative distance Dy between the vehicle and the target vehicle, the second relative distance Dy between the vehicle and the target vehicle is subjected to low-pass filtering.

[0133] Here, low-pass filtering is used to improve the accuracy of determining the stationary state of the target vehicle.

[0134] like Figure 5 As shown, a second aspect of this application provides a device for determining the stationary state of a target vehicle, comprising:

[0135] The first acquisition module 41 is used at least to acquire a first stationary probability based on the relative speed between the vehicle and the target vehicle;

[0136] The second acquisition module 42 is used at least to acquire a second stationary probability based on the relative distance between the vehicle and the target vehicle;

[0137] The third acquisition module 43 is used at least to acquire a third stationary probability based on the collision time between the vehicle and the target vehicle;

[0138] The judgment module 44 is at least used to process the first stationary probability, the second stationary probability and the third stationary probability to generate an optimal stationary probability. If the optimal stationary probability is greater than a preset probability, the stationary state of the target vehicle is judged based on the optimal stationary probability.

[0139] Optionally, if the optimal probability of remaining still is greater than a preset probability, the method further includes:

[0140] Determine whether the optimal static probability satisfies a preset sampling step size, wherein the preset sampling step size includes multiple consecutive single sampling steps, and the single sampling step size is 20ms-100ms;

[0141] If the optimal stationary probability is greater than the preset probability and satisfies the preset sampling step size, then the optimal stationary probability is output as the target vehicle stationary probability.

[0142] If the optimal stationary probability is greater than the preset probability but does not meet the preset sampling step size, then the output target vehicle stationary probability is 0.

[0143] Optionally, if the optimal stationary probability is less than the preset probability, the output target vehicle stationary probability is 0.

[0144] Optionally, obtaining the first stationary probability based on the relative speed between the vehicle and the target vehicle includes:

[0145] Obtain the absolute value of the relative speed between the vehicle and the target vehicle;

[0146] The absolute value of the relative speed between the vehicle and the target vehicle is filtered to generate a filtered absolute value;

[0147] Calculate the difference between the vehicle speed and the absolute value of the filter, diff.

[0148] The difference diff is filtered and the absolute value of the difference diff, |diff|, is taken. Let |diff| be the first static probability input value.

[0149] The first static probability is obtained by inputting the first static probability value into the normal distribution density function.

[0150] Optionally, the filtering method is low-pass filtering.

[0151] Optionally, the step of inputting the first rest probability input value into the normal distribution density function to obtain the first rest probability includes:

[0152] Let diff = x - μ, the normal distribution density function

[0153] When diff0 = 0, the first rest probability prob10 = 1, yielding the coefficients of the normal distribution density function for the first rest probability, i.e.:

[0154]

[0155] Therefore, the first static probability

[0156] Optionally, obtaining a second stationary probability based on the relative distance between the vehicle and the target vehicle includes:

[0157] Obtain the relative distance Dx between the vehicle and the target vehicle at the first moment. pre ;

[0158] Obtain the relative distance Dx between the vehicle and the target vehicle at the second moment;

[0159] Obtain the time interval Δt between the first time point and the second time point;

[0160] Based on the relative distance between the vehicle and the target vehicle at the first moment, the relative distance between the vehicle and the target vehicle at the second moment, and the time interval, the relative speed RelV between the vehicle and the target vehicle is obtained, and RelV = x2 - μ2 is set as the input value of the second stationary probability.

[0161] The second rest probability is obtained by inputting the second rest probability into the normal distribution density function.

[0162] Optionally, the step of inputting the second rest probability input value into the normal distribution density function to obtain the second rest probability further includes:

[0163] Let RelV = x - μ, the normal distribution density function

[0164] When RelV0 = 0, the second rest probability prob20 = 1, yielding the coefficients of the normal distribution density function for the second rest probability, i.e.:

[0165]

[0166] Therefore, the second static probability

[0167] Optionally, a third stationary probability is obtained based on the collision time between the vehicle and the target vehicle, including:

[0168] Obtain the first relative distance, Dyor, between the vehicle and the target vehicle;

[0169] The collision time of the target vehicle is processed to obtain the absolute value of the collision time;

[0170] Multiplying the absolute value of the collision time by the vehicle speed yields the second relative distance Dy between the vehicle and the target vehicle;

[0171] The difference between the first relative distance Dyor between the vehicle and the target vehicle and the relative distance Dy between the vehicle and the target vehicle is taken as the absolute value to obtain |Dyor-Dy|=Ddiff. Let Ddiff be the input value of the third stationary probability.

[0172] The third static probability is obtained by inputting the third static probability into the normal distribution density function.

[0173] Optionally, the step of inputting the third rest probability input value into the normal distribution density function to obtain the third rest probability further includes:

[0174] Let Ddiff = x - μ, the normal distribution density function

[0175] When Ddiff0 = 0, the first rest probability prob30 = 1, yielding the coefficients of the normal distribution density function for the first rest probability, i.e.:

[0176]

[0177] Therefore, the third static probability

[0178] Optionally, obtaining the third stationary probability based on the collision time between the self-vehicle and the target vehicle also includes:

[0179] Before obtaining the absolute value of the collision time, the collision time of the target vehicle is subjected to low-pass filtering and / or

[0180] After multiplying the absolute value of the collision time by the vehicle speed to obtain the second relative distance Dy between the vehicle and the target vehicle, the second relative distance Dy between the vehicle and the target vehicle is subjected to low-pass filtering.

[0181] Optionally, the step of processing the first stationary probability, the second stationary probability, and the third stationary probability to generate an optimal stationary probability, and outputting the optimal stationary probability as the target vehicle stationary probability if the optimal stationary probability is greater than a preset probability, includes:

[0182] The maximum probability among the first, second, and third stationary probabilities is selected and filtered to obtain the maximum filtered probability. If the maximum filtered probability satisfies a maximum filtering threshold, then the maximum filtered probability is the optimal stationary probability. The maximum filtering threshold is an empirical threshold that can be obtained through calibration. For example, if the maximum filtering threshold is 0.4, meaning the maximum filtered probability is greater than 0.4, then the maximum filtered probability is the optimal stationary probability.

[0183] A third aspect of this application provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the determination method as described in any embodiment of this application.

[0184] A fourth aspect of this application provides an electronic device comprising:

[0185] At least one processor; and at least one memory communicatively connected to the processor, wherein the memory stores program instructions executable by the processor, and the processor invokes the program instructions to execute the determination method as described in any embodiment of this application.

[0186] It is understood that computer-readable storage media can include: any entity or device capable of carrying computer programs, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc. Computer programs include computer program code. Computer program code can be in the form of source code, object code, executable files, or certain intermediate forms, etc. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0187] In some embodiments of the present invention, the device may include a controller, which is a microcontroller chip integrating a processor, memory, communication module, etc. The processor may refer to the processor included in the controller. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0188] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0189] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. 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 implementations should not be considered beyond the scope of this invention.

[0190] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the stationary state of a target vehicle, characterized in that, include: The first probability of being stationary is obtained based on the relative speed between the vehicle and the target vehicle; The second stationary probability is obtained based on the relative distance between the vehicle and the target vehicle; The third stationary probability is obtained based on the collision time between the vehicle and the target vehicle; The first stationary probability, the second stationary probability, and the third stationary probability are processed to generate an optimal stationary probability. If the optimal stationary probability is greater than a preset probability, the stationary state of the target vehicle is determined based on the optimal stationary probability; wherein: The steps for obtaining the first static probability, the second static probability, and the third static probability include: Obtain the absolute value of the relative speed between the vehicle and the target vehicle; The absolute value of the relative speed between the vehicle and the target vehicle is filtered to generate a filtered absolute value; Calculate the difference between the vehicle speed and the absolute value of the filter, diff. The difference diff is filtered and the absolute value of the difference diff, |diff|, is taken. Let |diff| be the first static probability input value. Obtain the relative distance between the vehicle and the target vehicle at the first instant. ; Obtain the relative distance between the vehicle and the target vehicle at the second moment. ; Obtain the time interval between the first time point and the second time point. ; The relative speed between the vehicle and the target vehicle is obtained based on the relative distance between the vehicle and the target vehicle at the first moment, the relative distance between the vehicle and the target vehicle at the second moment, and the time interval. ,make This is the input value for the second static probability; Obtain the first relative distance between the vehicle and the target vehicle. ; The collision time of the target vehicle is processed to obtain the absolute value of the collision time; The second relative distance between the vehicle and the target vehicle is obtained by multiplying the absolute value of the collision time by the vehicle speed. ; The first relative distance between the vehicle and the target vehicle The second relative distance between the vehicle and the target vehicle Difference and take the absolute value = ,make The input value for the third static probability; The first static probability input value, the second static probability input value, and the third static probability input value are respectively input into the normal distribution density function to obtain the first static probability, the second static probability, and the third static probability.

2. The determination method as described in claim 1, characterized in that, The step of "if the optimal static probability is greater than the preset probability" further includes: Determine whether the optimal static probability satisfies the preset sampling step size; If the optimal stationary probability is greater than the preset probability and satisfies the preset sampling step size, then the optimal stationary probability is output as the target vehicle stationary probability. If the optimal stationary probability is greater than the preset probability but does not meet the preset sampling step size, then the output target vehicle stationary probability is 0.

3. The determination method as described in claim 1, characterized in that, If the optimal stationary probability is less than the preset probability, then the output target vehicle stationary probability is 0.

4. The determination method as described in claim 1, characterized in that, The filtering method is low-pass filtering.

5. The determination method as described in claim 1, characterized in that, The first rest probability is obtained by inputting the first rest probability input value into the normal distribution density function, including: make Normal distribution density function ; when At that time, the first probability of being stationary We obtain the coefficients of the normal distribution density function for the first rest probability, i.e.: Therefore, the first static probability .

6. The determination method as described in claim 1, characterized in that, The process of inputting the second rest probability input value into the normal distribution density function to obtain the second rest probability also includes: make Normal distribution density function ; when At that time, the second static probability =1, thus obtaining the coefficients of the normal distribution density function for the second rest probability, i.e.: Therefore, the second static probability .

7. The determination method as described in claim 1, characterized in that, The process of obtaining the third rest probability by inputting the third rest probability input value into the normal distribution density function further includes: make Normal distribution density function ; when At that time, the first probability of being stationary We obtain the coefficients of the normal distribution density function for the first rest probability, i.e.: Therefore, the third static probability .

8. The determination method as described in claim 1, characterized in that, Obtaining the third static probability also includes: Before obtaining the absolute value of the collision time, the collision time of the target vehicle is subjected to low-pass filtering and / or The second relative distance between the vehicle and the target vehicle is obtained by multiplying the absolute value of the collision time by the vehicle speed. Then, the second relative distance between the vehicle and the target vehicle is calculated. Perform low-pass filtering.

9. The determination method as described in claim 1, characterized in that, The step of processing the first stationary probability, the second stationary probability, and the third stationary probability to generate the optimal stationary probability includes: The maximum probability among the first static probability, the second static probability, and the third static probability is selected and filtered to obtain the maximum filtered probability. If the maximum filtered probability satisfies the maximum filtering threshold, then the maximum filtered probability is the optimal static probability.

10. A device for determining the stationary state of a target vehicle, characterized in that, include: The first acquisition module is used at least to acquire a first stationary probability based on the relative speed between the vehicle and the target vehicle; The second acquisition module is used at least to acquire a second stationary probability based on the relative distance between the vehicle and the target vehicle; The third acquisition module is used at least to acquire the third stationary probability based on the collision time between the vehicle and the target vehicle; The judgment module is at least configured to process the first stationary probability, the second stationary probability, and the third stationary probability to generate an optimal stationary probability; if the optimal stationary probability is greater than a preset probability, then the stationary state of the target vehicle is determined based on the optimal stationary probability; wherein: The steps for obtaining the first static probability, the second static probability, and the third static probability include: Obtain the absolute value of the relative speed between the vehicle and the target vehicle; The absolute value of the relative speed between the vehicle and the target vehicle is filtered to generate a filtered absolute value; Calculate the difference between the vehicle speed and the absolute value of the filter, diff. The difference diff is filtered and the absolute value of the difference diff, |diff|, is taken. Let |diff| be the first static probability input value. Obtain the relative distance between the vehicle and the target vehicle at the first instant. ; Obtain the relative distance between the vehicle and the target vehicle at the second moment. ; Obtain the time interval between the first time point and the second time point. ; The relative speed between the vehicle and the target vehicle is obtained based on the relative distance between the vehicle and the target vehicle at the first moment, the relative distance between the vehicle and the target vehicle at the second moment, and the time interval. ,make This is the input value for the second static probability; Obtain the first relative distance between the vehicle and the target vehicle. ; The collision time of the target vehicle is processed to obtain the absolute value of the collision time; The second relative distance between the vehicle and the target vehicle is obtained by multiplying the absolute value of the collision time by the vehicle speed. ; The first relative distance between the vehicle and the target vehicle The second relative distance between the vehicle and the target vehicle Difference and take the absolute value = ,make The input value for the third static probability; The first static probability input value, the second static probability input value, and the third static probability input value are respectively input into the normal distribution density function to obtain the first static probability, the second static probability, and the third static probability.

11. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the judgment method as described in any one of claims 1 to 9.

Images