Method and device for identifying stationary obstacle, vehicle and storage medium

Abstract

The application relates to a method and device for identifying a static obstacle, a vehicle and a storage medium, wherein the method comprises: performing clustering processing on radar waves reflected by a radar, and screening at least one moving target and at least one static target in combination with vehicle speed information of a current vehicle; projecting the at least one static target to a preset vehicle coordinate system, fitting a drivable interval, and fitting a predicted driving track of the current vehicle in a current driving state; obtaining a plurality of initial targets based on a drivable interval boundary of the drivable interval, and identifying at least one static obstacle from the plurality of initial targets based on the predicted driving track. According to the application, the static target can be determined based on the data after the clustering processing, the plurality of initial targets can be obtained based on the drivable interval boundary, and at least one static obstacle can be identified based on the predicted driving track, so that the identification accuracy is improved, the misidentification and the missed identification are avoided, the safety and the reliability of the vehicle are improved, and the driving experience is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving assistance technology for automobiles, and in particular to a method, device, vehicle, and storage medium for identifying stationary obstacles. Background Technology

[0002] With the development of the intelligent driving industry, cars equipped with intelligent driving assistance are becoming more and more common. As an important sensing component of the driving assistance system, the ability of sensors to perceive the vehicle's driving environment will directly affect the function and performance of the driving assistance system. Millimeter-wave radar, as an important sensing sensor, is widely used in driving assistance systems due to its good adaptability and strong anti-interference ability.

[0003] In related technologies, during the sensing process of millimeter-wave radar, the radar emits millimeter waves outward. For targets near roadside obstacles, especially targets with similar radar reflection properties to the obstacles, it will reflect millimeter waves with similar properties.

[0004] However, when radar processes targets and obstacles in related technologies, it tends to cluster obstacles and targets into the same target, leading to misidentification or missed identification. This results in the failure or mis-triggering of driver assistance functions, reducing vehicle driving safety, affecting the user's driving experience, and indicating a low level of intelligence, which urgently needs improvement. Summary of the Invention

[0005] This application provides a method, device, vehicle, and storage medium for identifying stationary obstacles, in order to solve the problems in related technologies where radar tends to cluster obstacles and targets into the same target when processing them, leading to misidentification or missed identification, missed or false triggering of driving assistance functions, reduced vehicle driving safety, impact on user driving experience, and low level of intelligence.

[0006] The first aspect of this application provides a method for identifying stationary obstacles, comprising the following steps: clustering radar waves reflected by radar and combining them with the current vehicle speed information to filter out at least one moving target and at least one stationary target; projecting the at least one stationary target onto a preset vehicle coordinate system, fitting a drivable range, and fitting a predicted driving trajectory of the current vehicle under its current driving state; and obtaining multiple initial targets based on the drivable range boundary obtained from the drivable range, and identifying at least one stationary obstacle from the multiple initial targets based on the predicted driving trajectory.

[0007] Based on the above technical means, the embodiments of this application can determine stationary targets based on clustered data and obtain multiple initial targets based on the boundaries of the drivable section, thereby identifying at least one stationary obstacle based on the predicted driving trajectory, improving the accuracy of identification, effectively avoiding misidentification and missed identification, and improving the safety and reliability of the vehicle.

[0008] Optionally, in one embodiment of this application, obtaining multiple initial targets based on the drivable section boundary includes: determining whether the trajectory curvature of the drivable section boundary satisfies a preset abrupt change condition; if the preset abrupt change condition is satisfied, then the target at the abrupt change point is reprocessed to filter the radar waves of roadside obstacles at the abrupt change point.

[0009] Based on the above technical means, the embodiments of this application can determine whether the trajectory curvature of the boundary of the drivable section meets certain abrupt change conditions, and when certain abrupt change conditions are met, the target at the abrupt change point is reprocessed to filter the radar waves of roadside obstacles at the abrupt change point, thereby identifying stationary obstacles in a targeted manner, improving the safety and reliability of the vehicle, and enhancing the user's driving experience.

[0010] Optionally, in one embodiment of this application, identifying at least one stationary obstacle from the plurality of initial targets based on the predicted driving trajectory includes: determining whether the processed target attributes meet preset conditions; if the preset conditions are met and the target is within the predicted driving trajectory, it is considered a stationary obstacle.

[0011] Based on the above technical means, the embodiments of this application can determine whether the processed target attributes meet certain conditions. When the certain conditions are met and the target is within the predicted driving trajectory, the initial target can be used as a stationary obstacle, thereby reminding the driver to pay attention to the stationary obstacle, improving the accuracy of identification, improving the safety of vehicle driving, and enhancing the user's driving experience.

[0012] Optionally, in one embodiment of this application, the preset mutation condition is that the difference between the lateral position of the mutation point and the lateral position before the mutation is greater than a first preset threshold and the radius of curvature of the previous point exceeds a second preset threshold.

[0013] According to the above technical means, the preset mutation condition in this application embodiment is that the difference between the lateral position of the mutation point and the lateral position before the mutation is greater than the first preset threshold and the radius of curvature of the previous point exceeds the second preset threshold. The mutation condition can effectively handle the target of the mutation, thereby assisting the driving system, increasing the user's driving experience, and ensuring the practicality of the vehicle.

[0014] Optionally, in one embodiment of this application, after identifying the at least one stationary obstacle, the method further includes: while alerting the at least one stationary obstacle, generating a deceleration strategy and / or a steering strategy based on the relative speed, longitudinal distance, and / or lateral distance between the current vehicle and the obstacle.

[0015] Based on the above-mentioned technical means, the embodiments of this application can generate different strategies according to the different speeds and distances between the current vehicle and the obstacle while prompting at least one stationary obstacle, thereby effectively avoiding stationary obstacles, improving the vehicle's intelligence level, and enhancing the safety of vehicle driving.

[0016] A second aspect of this application provides a device for identifying stationary obstacles, comprising: a screening module for clustering radar waves reflected by radar and, in conjunction with the current vehicle speed information, screening out at least one moving target and at least one stationary target; a fitting module for projecting the at least one stationary target onto a preset vehicle coordinate system, fitting a drivable range, and fitting a predicted driving trajectory of the current vehicle under its current driving state; and an identification module for obtaining multiple initial targets based on the drivable range boundary obtained from the drivable range, and identifying at least one stationary obstacle from the multiple initial targets based on the predicted driving trajectory.

[0017] Optionally, in one embodiment of this application, the identification module includes: a first judgment unit, used to judge whether the trajectory curvature of the boundary of the drivable section meets a preset abrupt change condition; and a filtering unit, used to reprocess the target at the abrupt change point and filter the radar waves of roadside obstacles at the abrupt change point when the preset abrupt change condition is met.

[0018] Optionally, in one embodiment of this application, the identification module further includes: a second judgment unit, used to judge whether the processed target attribute meets the preset conditions; and an identification unit, used to identify the target as a stationary obstacle when the preset conditions are met and the target is within the predicted driving trajectory.

[0019] Optionally, in one embodiment of this application, the preset mutation condition is that the difference between the lateral position of the mutation point and the lateral position before the mutation is greater than a first preset threshold and the radius of curvature of the previous point exceeds a second preset threshold.

[0020] Optionally, in one embodiment of this application, the identification module further includes: a generation unit, configured to, while prompting the at least one stationary obstacle, generate a deceleration strategy and / or a steering strategy based on the relative speed, longitudinal distance and / or lateral distance between the current vehicle and the obstacle.

[0021] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for identifying stationary obstacles as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for identifying stationary obstacles.

[0023] The beneficial effects of the embodiments of this application are as follows:

[0024] (1) The embodiments of this application can determine stationary targets based on the data after clustering and obtain multiple initial targets based on the boundaries of the drivable section, thereby identifying at least one stationary obstacle based on the predicted driving trajectory, improving the accuracy of identification, effectively avoiding misidentification and missed identification, and improving the safety and reliability of the vehicle.

[0025] (2) The embodiments of this application can determine whether the trajectory curvature of the boundary of the drivable section meets certain mutation conditions, and when certain mutation conditions are met, the target of the mutation point is reprocessed and the radar waves of the roadside obstacles at the mutation point are filtered out, thereby identifying stationary obstacles in a targeted manner, improving the safety and reliability of the vehicle, and enhancing the driving experience.

[0026] (3) The embodiments of this application can determine whether the processed target attributes meet certain conditions. When the certain conditions are met and the target is within the predicted driving trajectory, the initial target can be used as a stationary obstacle, thereby reminding the driver to pay attention to the stationary obstacle, improving the recognition accuracy, improving the safety of vehicle driving, and increasing the user's driving experience.

[0027] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0028] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0029] Figure 1 This is a flowchart of a method for identifying stationary obstacles according to an embodiment of this application;

[0030] Figure 2 This is a flowchart illustrating the identification of stationary obstacles according to an embodiment of this application;

[0031] Figure 3 This is a schematic diagram of the structure of a stationary obstacle identification device according to an embodiment of this application;

[0032] Figure 4 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application.

[0033] Among them, 10-Identification device for stationary obstacles: 100-Screening module, 200-Fitting module, 300-Identification module. Detailed Implementation

[0034] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0035] The following description, with reference to the accompanying drawings, outlines a method, apparatus, vehicle, and storage medium for identifying stationary obstacles according to embodiments of this application. Addressing the issues raised in the background section regarding the tendency of radar to cluster obstacles and targets into the same category when processing them, leading to misidentification or missed identification, missed or false triggering of driver assistance functions, reduced vehicle safety, negatively impacted user experience, and low levels of intelligence, this application provides a method for identifying stationary obstacles. This method determines stationary targets based on clustered data and obtains multiple initial targets based on the boundaries of the drivable section. At least one stationary obstacle is then identified based on a predicted driving trajectory, improving identification accuracy, avoiding misidentification and missed identification, enhancing vehicle safety and reliability, and improving the driving experience. This solves the problems in the related art where radar easily clusters obstacles and targets into the same category, leading to misidentification or missed identification, missed or false triggering of driver assistance functions, reduced vehicle safety, negatively impacted user experience, and low levels of intelligence.

[0036] Specifically, Figure 1 This is a flowchart illustrating a method for identifying stationary obstacles provided in an embodiment of this application.

[0037] like Figure 1 As shown, the method for identifying stationary obstacles includes the following steps:

[0038] In step S101, the radar waves reflected by the radar are clustered and combined with the current vehicle speed information to filter out at least one moving target and at least one stationary target.

[0039] It is understood that, in the embodiments of this application, the radar waves reflected by the radar can illuminate the target and receive its echo. The ECU (Electronic Control Unit) controller can cluster targets with the same attributes as the radar waves, such as RCS (Radar Cross-Section) value, speed, angle, etc., and cluster the reflection points into target points. Combined with the current vehicle speed information, at least one moving target and at least one stationary target can be selected.

[0040] For example, embodiments of this application can measure or calculate the ability of a target to reflect millimeter radar waves in the radar receiving direction using RCS; another example is that embodiments of this application can measure the speed and angle of millimeter radar waves to determine the location of a remote object. The ECU controller can cluster targets with similar attributes of millimeter radar waves, clustering RCS values, speeds, angles, etc., and combining the current vehicle speed with the relevant attributes of the target point to determine whether the target is a stationary or moving target. When the absolute value of the relative speed between the target point and the vehicle is approximately equal to the difference between the vehicle speed and the absolute value of the relative speed between the target point and the vehicle is approximately equal to 0, the target point can be determined to be stationary.

[0041] A target can be identified as a moving target when the absolute value of the relative speed between the target point and the vehicle is greater than the difference between the vehicle's speed and the target point's speed.

[0042] The embodiments of this application can filter out at least one moving target and at least one stationary target by combining clustered radar waves with vehicle speed, thereby improving vehicle driving safety and increasing the vehicle's intelligence and practicality.

[0043] In step S102, at least one stationary target is projected onto a preset vehicle coordinate system, a drivable range is fitted, and a predicted driving trajectory of the current vehicle under its current driving state is fitted.

[0044] It is understood that the embodiments of this application can project clustered static targets onto a vehicle coordinate system, based on...

[0045] Using the position information of a stationary target, a drivable range is fitted. By smoothing the boundary trajectory of the drivable range, the boundary trajectory information of the drivable range can be output. Based on information such as vehicle speed, steering wheel angle, and vehicle yaw rate, the predicted driving trajectory of the vehicle under the current driving state is fitted.

[0046] For example, in this embodiment of the application, stationary targets with the same and continuous positions can be continuously connected into a boundary of a drivable area. If the lateral position of two stationary points exceeds a threshold of 1m, they cannot be continuously connected into a line.

[0047] The line can be smoothed to form a boundary with continuous curvature. By determining the relevant attributes of the boundary, including but not limited to the lateral distance, longitudinal distance, and corresponding curvature, the area within the current boundary can be determined as a drivable region. For example, the ECU controller in this embodiment can determine the drivable area based on the current vehicle speed, steering wheel angle, yaw rate, etc.

[0048] By fitting the current vehicle's trajectory and the relevant information of the aforementioned boundaries, a model of the driving lane can be synthesized, the current vehicle's lane can be determined, and the relative distance between the current vehicle and the boundary can be calculated.

[0049] When the distance between the center of the current vehicle and the boundary of the drivable zone is less than 3.5m, it can be determined that the current vehicle is traveling in the lane close to a stationary obstacle.

[0050] This application embodiment can improve vehicle safety and reliability and enhance the user's driving experience by projecting a stationary target onto a certain vehicle coordinate system, fitting a drivable range, and predicting the driving trajectory.

[0051] 5. In step S103, multiple initial targets are obtained based on the drivable section boundaries, and based on the pre-...

[0052] The vehicle trajectory is measured to identify at least one stationary obstacle from multiple initial targets.

[0053] It is understood that, based on the position information of different stationary targets, the embodiments of this application can fit a drivable range, and continuously connect the same stationary targets with consecutive positions as the boundary of a drivable range. When the absolute value of the relative speed between the target and the vehicle within the drivable range is approximately equal to the difference between the speed of the vehicle and the relative speed of the target is approximately equal to 0, the target is determined to be a stationary obstacle.

[0054] For example, embodiments of this application can determine the lane in which the vehicle is traveling based on relevant information about the driving boundary, and calculate...

[0055] Calculate the relative distance between the current vehicle and the boundary. If the distance between the current vehicle and the boundary of the drivable section is less than 3.5m, it can be determined that the vehicle is traveling in a lane close to a stationary obstacle. When there are multiple initial targets such as streetlights, trees, and pedestrians in front of the vehicle in the lane of a stationary obstacle, the speed difference between the current vehicle and the multiple initial targets can be determined. When the absolute value of the relative speed between the streetlights / trees and the current vehicle in the drivable section is approximately equal to the speed of the current vehicle, the streetlights / trees can be determined to be stationary obstacles. When the absolute value of the relative speed between the pedestrians and the current vehicle in the drivable section is greater than the speed of the current vehicle, the pedestrians can be determined to be not stationary obstacles.

[0056] The embodiments of this application can obtain multiple initial targets based on the boundaries of the drivable section, thereby identifying at least one stationary obstacle based on the predicted driving trajectory, improving the accuracy of identification, effectively avoiding false identification and missed identification, improving vehicle safety and reliability, and enhancing the driving experience.

[0057] Optionally, in one embodiment of this application, obtaining multiple initial targets based on the drivable section boundary includes: determining whether the trajectory curvature of the drivable section boundary satisfies a preset abrupt change condition; if the preset abrupt change condition is satisfied, then the target at the abrupt change point is reprocessed to filter the radar waves of roadside obstacles at the abrupt change point.

[0058] It is understood that the embodiments of this application can determine whether the trajectory curvature of the boundary of the drivable section changes abruptly through the ECU controller. The preset abrupt change condition can be that the difference in position of the abrupt change point exceeds a certain threshold. The ECU controller can filter out the abrupt change point on the boundary of the drivable section and re-establish the boundary with consistent lateral position information. At the same time, the target of the abrupt change point is reprocessed, and the radar waves of roadside obstacles at the abrupt change point are filtered out, and only the radar waves reflected by the target within the boundary of the drivable section are processed.

[0059] As one possible implementation, this application embodiment can determine that the trajectory curvature of the drivable boundary has changed abruptly when the difference in the location of the abrupt change point exceeds a certain threshold. At this time, the target at the abrupt change point can be reprocessed, filtering out the radar waves of roadside obstacles at the abrupt change point, and only processing the radar waves reflected by the target within the boundary of the drivable section. If the RCS attribute of the processed target point meets the target threshold and the location information is within the vehicle's driving trajectory, it will be used as the final target selected by the function, and can remind the driver that there is an obstacle ahead, thereby improving the accuracy of recognition, improving the safety of vehicle driving, and enhancing the user's driving experience.

[0060] It should be noted that the preset mutation conditions can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0061] Optionally, in one embodiment of this application, identifying at least one stationary obstacle from the plurality of initial targets based on the predicted driving trajectory includes: determining whether the processed target attributes meet preset conditions; if the preset conditions are met and the target is within the predicted driving trajectory, it is considered a stationary obstacle.

[0062] It is understood that the preset conditions in this application embodiment can be abrupt changes in the curvature of the boundary curve of the drivable section. It can determine whether the attributes of the target after processing at the abrupt change point meet certain conditions. Combined with the predicted driving trajectory, it can be determined whether the processed target is a stationary obstacle. For example, if the position difference of the abrupt change point in this application embodiment exceeds a certain threshold, the preset conditions are met and the street light is within the predicted driving trajectory, then the street light is a stationary obstacle. By identifying stationary obstacles, collisions can be prevented, thereby assisting the driving system and improving vehicle driving safety.

[0063] It should be noted that the preset conditions can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0064] Optionally, in one embodiment of this application, the preset mutation condition is that the difference between the lateral position of the mutation point and the lateral position before the mutation is greater than a first preset threshold and the radius of curvature of the previous point exceeds a second preset threshold.

[0065] It is understood that the embodiments of this application can determine whether the curvature of the curve of the drivable section boundary trajectory has changed abruptly. When the difference between the lateral position of the change point and the lateral position before the change is greater than a first preset threshold and the radius of curvature of the previous point exceeds a second preset threshold, it is determined that a certain change condition is met. For example, when the difference between the lateral position of the change point and the lateral position before the change is greater than 0.7m and the radius of curvature of the previous point exceeds a certain threshold of 500m, it can be determined that the curvature of the curve has changed abruptly. At this time, it is determined that a certain change condition is met. The embodiments of this application can process the change target when the change condition is met, help identify stationary obstacles, and thus improve the safety of vehicle driving.

[0066] It should be noted that the preset mutation conditions and preset thresholds can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0067] Optionally, in one embodiment of this application, after identifying the at least one stationary obstacle, the method further includes: while alerting the at least one stationary obstacle, generating a deceleration strategy and / or a steering strategy based on the relative speed, longitudinal distance, and / or lateral distance between the current vehicle and the obstacle.

[0068] It is understood that the embodiments of this application can remind the driver that there is a stationary obstacle in front of the vehicle, and the ECU controller can decelerate and / or steer based on the relative speed, longitudinal distance, lateral distance, etc. between the vehicle and the target obstacle.

[0069] For example, in this embodiment, when a stationary obstacle such as a tree is detected in front of the vehicle, the information of the stationary obstacle can be displayed on the in-vehicle screen to remind the driver to slow down. The steering wheel angle can be controlled based on the lateral distance between the vehicle and the stationary obstacle. Alternatively, when a stationary obstacle such as a streetlight is detected in front of the vehicle, the ECU can remind the driver via voice. The ECU can generate deceleration and steering strategies based on the relative speed and distance between the vehicle and the streetlight, allowing the driver to control the vehicle to slow down and control the steering wheel angle to prevent accidents and ensure vehicle safety and reliability.

[0070] Specifically, in combination Figure 2 As shown, an embodiment of the present application will be described in detail to illustrate the identification of stationary obstacles.

[0071] like Figure 2 As shown, the embodiments of this application may include: millimeter-wave radar module 1, vehicle speed module 2, steering wheel angle module 3, yaw rate module 4, ECU control module 5, display module 6, deceleration module 7, and steering module 8.

[0072] This embodiment of the application can output raw target millimeter-wave data through millimeter-wave radar module 1, transmit millimeter waves through radar module 1 mounted on the vehicle, and receive millimeter waves reflected back to the radar by the target. This embodiment of the application can output the current vehicle speed information through vehicle speed module 2. This embodiment of the application can output the steering wheel angle through steering wheel angle module 3. When a stationary obstacle is detected, it can prompt the stationary obstacle and generate or turn a strategy based on the relative speed, longitudinal distance and / or lateral distance between the current vehicle and the obstacle, thereby controlling the steering. This embodiment of the application can output the vehicle yaw rate through yaw rate module 4, fit the driving trajectory in the current state, and fit a model of the driving lane based on the driving trajectory of the vehicle and the relevant information of the above-mentioned boundary, determine the driving lane of the vehicle, and calculate the relative distance between the vehicle and the boundary.

[0073] Furthermore, in this embodiment, the ECU control module 5 can cluster millimeter-wave targets with similar attributes (RCS value, speed, angle, etc.), clustering reflection points into target points, and simultaneously determining the relevant attributes of the target, including RCS value, speed, position information, etc. The ECU controller module 5 can determine whether the target is stationary or moving based on the vehicle speed output by the vehicle speed module 2 and the relevant attributes of the target point. The ECU controller module 5 can also fit a model based on the vehicle speed from the vehicle speed module 2, the steering angle output by the steering wheel angle module 3, and the yaw rate output by the yaw rate module 4.

[0074] The ECU controller module 5 displays the current driving trajectory via the display module 6, alerting the driver that there is an obstacle ahead. The ECU controller module 5 then adjusts its deceleration based on the relative speed, longitudinal distance, and lateral distance between the vehicle and the target.

[0075] Module 7 performs deceleration, and steering control is performed through steering module 8.

[0076] The method for identifying stationary obstacles according to the embodiments of this application can determine stationary targets based on clustered data and obtain multiple initial targets based on the boundaries of drivable sections, thereby identifying at least one target based on the predicted driving trajectory.

[0077] Stationary obstacles are identified more accurately, avoiding false and missed identifications, thus improving vehicle safety and reliability and enhancing the driving experience. This solves the problem in related technologies where radar tends to cluster obstacles with targets.

[0078] The same target can lead to misidentification or missed identification, missed or false triggering of driving assistance functions, reduced vehicle driving safety, impact on user driving experience, and low level of intelligence.

[0079] Next, the identification device for stationary obstacles according to an embodiment of this application is described with reference to the accompanying drawings.

[0080] 0 Figure 3 This is a schematic diagram of the structure of the stationary obstacle identification device according to an embodiment of this application.

[0081] like Figure 3 As shown, the static obstacle identification device 10 includes: a screening module 100, a fitting module 200, and an identification module 300.

[0082] Specifically, the filtering module 100 is used to cluster the radar waves reflected by the radar and, in conjunction with the current vehicle speed information, filter out at least one moving target and at least one stationary target.

[0083] 5. Fitting module 200 is used to project at least one stationary target onto a preset vehicle coordinate system and fit the drivable area.

[0084] In between, the predicted driving trajectory of the current vehicle under its current driving state is fitted.

[0085] The identification module 300 is used to obtain multiple initial targets based on the drivable section boundary obtained from the drivable section, and to identify at least one stationary obstacle from the multiple initial targets based on the predicted driving trajectory.

[0086] Optionally, in one embodiment of this application, the identification module 300 includes: a first judgment unit and a filtering unit. The first judgment unit is used to determine whether the trajectory curvature of the drivable section boundary meets a preset abrupt change condition.

[0087] The filtering unit is used to reprocess the target at the mutation point when the preset mutation conditions are met, and to filter the radar waves of roadside obstacles at the mutation point.

[0088] Optionally, in one embodiment of this application, the identification module 300 further includes a second judgment unit and an identification unit.

[0089] The second judgment unit is used to determine whether the processed target attribute meets the preset conditions.

[0090] The identification unit is used to identify a stationary obstacle when it meets preset conditions and is within the predicted driving trajectory.

[0091] Optionally, in one embodiment of this application, the preset mutation condition is that the difference between the lateral position of the mutation point and the lateral position before the mutation is greater than a first preset threshold and the radius of curvature of the previous point exceeds a second preset threshold.

[0092] Optionally, in one embodiment of this application, the identification module 300 further includes a generation unit.

[0093] The generation unit is used to prompt at least one stationary obstacle while generating a deceleration strategy and / or a steering strategy based on the current relative speed, longitudinal distance and / or lateral distance between the vehicle and the obstacle.

[0094] It should be noted that the explanation of the above-described method for identifying stationary obstacles also applies to the device for identifying stationary obstacles in this embodiment, and will not be repeated here.

[0095] The stationary obstacle identification device proposed in this application can determine stationary targets based on clustered data and obtain multiple initial targets based on the boundaries of the drivable section. This allows for the identification of at least one stationary obstacle based on a predicted driving trajectory, improving identification accuracy, avoiding false and missed identifications, enhancing vehicle safety and reliability, and improving the driving experience. This solves the problems in related technologies where radar processing of target obstacles often clusters obstacles and targets into the same target, leading to false or missed identifications, missed or false triggering of driving assistance functions, reduced vehicle driving safety, negatively impacting the user's driving experience, and exhibiting low levels of intelligence.

[0096] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0097] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0098] When the processor 402 executes the program, it implements the method for identifying stationary obstacles provided in the above embodiments.

[0099] Furthermore, the vehicle also includes:

[0100] Communication interface 403 is used for communication between memory 401 and processor 402.

[0101] The memory 401 is used to store computer programs that can run on the processor 402.

[0102] The memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0103] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0104] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0105] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0106] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for identifying stationary obstacles.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0109] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application 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 should be understood by those skilled in the art to which embodiments of this application pertain.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and...

[0111] Portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium could even be paper or other suitable media on which the programs described above can be printed, since the programs can be obtained electronically by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0112] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments...

[0113] In this embodiment, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0114] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium.

[0115] When executed, the program includes one or a combination of steps from the method embodiments.

[0116] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The integrated module described above...

[0117] It can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored on a computer-readable storage device.

[0118] Take it from the storage medium.

[0119] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for identifying stationary obstacles, characterized in that, Includes the following steps: The radar waves reflected by the radar are clustered and combined with the current vehicle speed information to filter out at least one moving target and at least one stationary target. The at least one stationary target is projected onto a preset vehicle coordinate system, a drivable range is fitted, and a predicted driving trajectory of the current vehicle under its current driving state is fitted. as well as Based on the drivable section boundary obtained from the drivable section, multiple initial targets are obtained, and at least one stationary obstacle is identified from the multiple initial targets based on the predicted driving trajectory; The drivable section boundary obtained based on the drivable section yields multiple initial targets, including: Determine whether the trajectory curvature of the boundary of the drivable section meets the preset abrupt change condition; If the preset mutation conditions are met, the target at the mutation point is reprocessed to filter out radar waves from roadside obstacles at the mutation point. The step of identifying at least one stationary obstacle from the plurality of initial targets based on the predicted driving trajectory includes: Determine whether the processed target attribute meets the preset conditions; If the preset conditions are met and the object is within the predicted driving trajectory, it is considered a stationary obstacle. The preset mutation condition is that the difference between the lateral position of the mutation point and the lateral position before the mutation is greater than a first preset threshold and the radius of curvature of the previous point exceeds a second preset threshold.

2. The method according to claim 1, characterized in that, After identifying the at least one stationary obstacle, the method further includes: While indicating at least one stationary obstacle, a deceleration strategy and / or steering strategy are generated based on the relative speed, longitudinal distance, and / or lateral distance between the current vehicle and the obstacle.

3. A device for identifying stationary obstacles, characterized in that, The identification device is used to implement the identification method as described in any one of claims 1-2, and the identification device includes: The filtering module is used to cluster the radar waves reflected by the radar and, in combination with the current vehicle speed information, filter out at least one moving target and at least one stationary target. A fitting module is used to project the at least one stationary target onto a preset vehicle coordinate system, fit a drivable range, and fit a predicted driving trajectory of the current vehicle under its current driving state; and The identification module is used to obtain multiple initial targets based on the drivable section boundary obtained from the drivable section, and to identify at least one stationary obstacle from the multiple initial targets based on the predicted driving trajectory; The identification module includes: The first judgment unit is used to determine whether the trajectory curvature of the boundary of the drivable section meets the preset abrupt change condition; The filtering unit is used to reprocess the target at the mutation point and filter the radar waves of roadside obstacles at the mutation point when the preset mutation condition is met. The identification module further includes: The second judgment unit is used to determine whether the processed target attribute meets the preset conditions. The identification unit is used to identify a stationary obstacle when the preset conditions are met and the object is within the predicted driving trajectory.

4. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method for identifying stationary obstacles as described in any one of claims 1-2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method for identifying stationary obstacles as described in any one of claims 1-2.

Images