A method for calculating vehicle driving trajectory area and identifying stationary obstacles

Abstract

The present application relates to a method for calculating a vehicle driving trajectory area and identifying a stationary obstacle, which comprises: when the real-time vehicle speed is less than a first speed value, obtaining a trajectory curvature based on a steering parameter; the steering parameter comprises a steering wheel angle, a steering gear ratio and a wheelbase; when the real-time vehicle speed is between the first speed value and the second speed value, obtaining a trajectory curvature based on the steering parameter, the yaw angular velocity, the real-time vehicle speed, the first speed value and the second speed value; when the real-time vehicle speed is greater than the second speed value, obtaining a trajectory curvature according to the yaw angular velocity and the real-time vehicle speed; selecting a corresponding trajectory curvature according to the real-time vehicle speed to obtain a driving trajectory area; selecting factors of a steering wheel angle and a yaw angular velocity that affect the trajectory curvature according to different vehicle speeds to calculate an accurate trajectory curvature, so as to solve the problem of incorrect identification of stationary obstacles caused by inaccurate trajectory at low vehicle speeds.

Description

Technical Field

[0001] The present application relates to the technical field of radar obstacle detection, and in particular to a method for calculating a vehicle driving trajectory area and identifying stationary obstacles. Background Art

[0002] Obstacles in the planned path of intelligent vehicles will affect the driving safety of the vehicles, so obstacles in the planned area are effective targets that need to be identified. The millimeter wave radar can obtain the position and speed of the target in front, but it cannot identify the type and shape of the obstacle. It is precisely because of this characteristic of radar that when identifying stationary targets on the road, it will be interfered by stationary objects such as tunnel walls, guardrails on both sides of the road, trees, road piers, signboards, and viaducts high above the road. It is easy to mistakenly regard these interfering stationary objects as effective targets. This causes the system to make wrong judgments and trigger wrong responses.

[0003] To accurately identify effective stationary obstacle targets, it is necessary to first accurately calculate the vehicle's planned trajectory, and then identify the effective obstacles within the trajectory range and eliminate interfering obstacles. For trajectory planning, the current vehicle trajectory calculation is mainly based on yaw rate, but for commercial vehicles, trajectory calculation based on yaw rate is more effective at high speeds.

[0004] However, at low speeds, the vehicle is subject to greater interference due to factors such as vibration, which leads to large errors in trajectory calculation, resulting in inaccurate trajectory calculation and the inability to determine the effective obstacle recognition range. Summary of the invention

[0005] The embodiment of the present application provides a method for calculating a vehicle driving trajectory area and identifying stationary obstacles to solve the problem that trajectory calculation based on yaw angular velocity in the related art works better at high speeds; but at low speeds, the vehicle is subject to greater interference from factors such as vibration of the vehicle itself, resulting in large trajectory calculation errors and an inability to determine the identification range of effective obstacles.

[0006] In a first aspect, a method for calculating a vehicle driving trajectory area is provided, comprising:

[0007] When the real-time vehicle speed is less than the first speed value, the trajectory curvature is obtained based on the steering parameters; the steering parameters include the steering wheel angle, the steering transmission ratio and the wheelbase;

[0008] When the real-time vehicle speed is between the first speed value and the second speed value, the trajectory curvature is obtained based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value;

[0009] When the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw rate and the real-time vehicle speed;

[0010] The corresponding track curvature is selected according to the real-time vehicle speed to obtain the driving track area.

[0011] In some embodiments, when the real-time vehicle speed is less than the first speed value, the trajectory curvature is obtained based on the steering parameters; the steering parameters include the steering wheel angle, the steering gear ratio and the wheelbase, including the following steps:

[0012] The trajectory curvature is calculated according to the following mapping relationship:

[0013] Track curvature = steering wheel angle steering ratio × wheelbase.

[0014] In some embodiments, when the real-time vehicle speed is between the first speed value and the second speed value, obtaining the trajectory curvature based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value comprises the following steps:

[0015] The yaw rate is low-pass filtered using a cutoff frequency;

[0016] Calculate a first steering wheel angle based on the real-time vehicle speed, wheelbase and steering ratio, and the filtered yaw rate;

[0017] Then, the angle is adjusted based on the first steering wheel angle and the steering wheel clearance to obtain a calibration range;

[0018] Compare the measured steering wheel angle with the calibration range;

[0019] If the measured steering wheel angle is not within the calibration range, the trajectory curvature calculation will not be performed;

[0020] If the measured steering wheel angle is within the calibration range, the trajectory curvature is calculated based on the real-time vehicle speed, the first speed value, the second speed value, the wheelbase, the steering ratio and the filtered yaw rate.

[0021] In some embodiments, when the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw rate and the real-time vehicle speed, including the following steps:

[0022] The trajectory curvature is calculated according to the following mapping relationship:

[0023] Track curvature = yaw rate x real-time vehicle speed.

[0024] In a second aspect, a method for identifying a stationary obstacle is provided, comprising:

[0025] Determining the driving trajectory area according to the stationary obstacle recognition method as claimed in claim 1;

[0026] After the driving trajectory area is obtained, the radar is used to screen out effective stationary obstacles in the driving trajectory area.

[0027] In some embodiments, using radar to screen out effective stationary obstacles in the driving trajectory area includes the following steps:

[0028] In the radar detection phase, multiple stationary obstacles are obtained based on the driving trajectory area, real-time vehicle speed, and the relative speed of the object in front of the vehicle;

[0029] In the radar tracking stage, multiple stationary obstacles are screened out as stationary obstacles to be selected based on the continuous tracking time;

[0030] In the radar confirmation stage, based on the effective area lateral distance determination rule and the effective area maximum longitudinal distance determination rule, the effective stationary obstacles are obtained from the candidate stationary obstacles.

[0031] In some embodiments, obtaining a plurality of stationary obstacles based on the driving trajectory area, the real-time vehicle speed, and the relative speed of the object in front of the vehicle includes the following steps:

[0032] Subtract the real-time vehicle speed from the relative speed of the object in front of the vehicle to obtain the absolute difference;

[0033] The absolute difference is compared with the stationary effective speed value;

[0034] If the absolute difference is less than the static effective speed value, the object in front of the vehicle is considered a static obstacle;

[0035] Otherwise, the object in front of the vehicle is not a stationary obstacle.

[0036] In some embodiments, screening out a plurality of stationary obstacles to be selected based on the continuous tracking time includes the following steps:

[0037] If the continuous tracking time of a stationary obstacle located in the driving trajectory area is greater than the first time threshold, it is marked as a stationary obstacle to be selected;

[0038] If the continuous tracking time of a stationary obstacle located in the driving trajectory area is less than a first time threshold, the stationary obstacle is screened out;

[0039] If the continuous tracking time of a stationary obstacle outside the driving track area is greater than a second time threshold, it is marked as a stationary obstacle to be selected;

[0040] If the continuous tracking time of the stationary obstacle outside the driving track area is less than the second time threshold, the stationary obstacle is screened out.

[0041] In some embodiments, based on a valid area lateral distance determination rule and a valid area maximum longitudinal distance determination rule, obtaining a valid stationary obstacle from the stationary obstacles to be selected includes the following steps:

[0042] Determine the maximum lateral distance of the radar effective area according to the width of the vehicle and the longitudinal distance of the stationary obstacle to be selected;

[0043] Determine the maximum longitudinal distance of the radar's effective detection area based on the height limit of the road and the vertical field of view angle of the radar;

[0044] Based on the maximum lateral distance and the maximum longitudinal distance, the effective area actually detected by the radar is determined, and the stationary obstacles to be selected within the effective area actually detected by the radar are taken as effective stationary obstacles.

[0045] In a third aspect, a stationary obstacle recognition system is provided, comprising:

[0046] A first module is used for obtaining a trajectory curvature based on steering parameters when the real-time vehicle speed is less than a first speed value; the steering parameters include a steering wheel angle, a steering gear ratio and a wheelbase;

[0047] A second module is used for obtaining the trajectory curvature based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value when the real-time vehicle speed is between the first speed value and the second speed value;

[0048] A third module is used for obtaining the trajectory curvature according to the yaw rate and the real-time vehicle speed when the real-time vehicle speed is greater than the second speed value;

[0049] The fourth module is used to select the corresponding track curvature according to the real-time vehicle speed to obtain the driving track area.

[0050] The beneficial effects of the technical solution provided by this application include:

[0051] The embodiment of the present application provides a method for calculating a vehicle driving trajectory area and identifying stationary obstacles. For the yaw angular velocity, the yaw angular velocity is greatly affected at low speeds and contains a large clutter signal. The main reason is that on the one hand, when the speed of the commercial vehicle is low, its own vibration is large, and the frequency is above 12Hz after analysis; on the other hand, in order to maintain stable driving at low speeds, the steering wheel will also perform low-frequency fine-tuning, and the frequency is above 1Hz after analysis; in addition, there is often an adjustment gap in the steering wheel angle. After analysis, it is found that the effect is not significant when the vehicle speed is very low, but as the vehicle speed increases, the impact of the error will gradually appear. Therefore, with the technical solution of the present application, when the real-time vehicle speed is small, the steering wheel will be adjusted. When the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw angular velocity and the real-time vehicle speed; thus, the corresponding trajectory curvature is selected according to different vehicle speeds to calculate the driving trajectory area, that is, the factors of the steering wheel angle and yaw angular velocity that affect the trajectory curvature are selected according to different vehicle speeds to calculate the accurate trajectory curvature, thereby avoiding the influence of the vehicle vibration itself on the detection at low speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 A general flow chart of the vehicle driving trajectory area calculation method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0055] For the identification of effective stationary obstacles, for example, Chinese application 202110893540.7 uses clustering and fitting to extract the edges of stationary targets such as curbs and fences to eliminate interfering targets. The problem is that the density of the millimeter-wave radar point cloud is low, the lateral distance error is large and there is a probability of loss, making it difficult to accurately and stably identify its edges. As a result, the radar will misidentify other interfering obstacles. In addition, in combination with the description in the above background technology, the present application solves the problem that the radar has a large lateral distance error and a probabilistic loss; and the related art uses yaw angular velocity to calculate the trajectory, which works better at high speeds; but at low speeds, the vehicle is subject to greater interference due to factors such as vibration of the vehicle itself, resulting in a large error in trajectory calculation and an inability to determine the identification range of effective obstacles.

[0056] In addition, the clear production tool attributes of automobiles make them more sensitive to costs, which hinders the large-scale deployment of ADAS. The vehicle yaw rate is an important information for ADAS technology. For example, AEB, FCW and LDW use yaw rate to predict the vehicle trajectory at high speed. The measurement of the existing vehicle yaw rate mainly relies on inertial touch sensor gyroscopes. Such sensor measurement systems are complex and costly. In order to reduce vehicle costs, the existing vehicle dynamics sensor wheel speed sensor and a suitable vehicle dynamics model are used to estimate the yaw rate.

[0057] The present invention provides a method for identifying a stationary obstacle, which includes the following steps:

[0058] When the real-time vehicle speed is less than the first speed value, the trajectory curvature is obtained based on the steering parameters; the steering parameters include the steering wheel angle, the steering transmission ratio and the wheelbase;

[0059] When the real-time vehicle speed is between the first speed value and the second speed value, the trajectory curvature is obtained based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value;

[0060] When the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw rate and the real-time vehicle speed;

[0061] The corresponding track curvature is selected according to the real-time vehicle speed to obtain the driving track area.

[0062] As for the yaw rate, it is greatly affected at low speeds and contains large clutter signals. The main reason is that on the one hand, when the speed of a commercial vehicle is low, its own vibration is large, and the frequency is above 12Hz after analysis; on the other hand, in order to maintain stable driving at low speeds, the steering wheel will also be fine-tuned at a low frequency, and the frequency is above 1Hz after analysis. On the other hand, the present invention analyzes the trajectory calculation based on the steering wheel angle. There is often an adjustment gap in the steering wheel angle. After analysis, it has little effect when the vehicle speed is very low, but as the vehicle speed increases, the impact of the error will gradually appear. Therefore, the above technical solution is adopted to calculate the driving trajectory area according to the corresponding trajectory curvature selected according to different vehicle speeds, that is, the factors of the steering wheel angle and yaw rate that affect the trajectory curvature are selected according to different vehicle speeds to calculate the accurate trajectory curvature, thereby avoiding the influence of the vehicle's own vibration on the detection at low speeds.

[0063] In some preferred embodiments, the following specific explanations are provided to improve the accurate detection of the driving trajectory area:

[0064] Case 1

[0065] When the real-time vehicle speed is less than the first speed value, the trajectory curvature is obtained based on the steering parameters; the steering parameters include the steering wheel angle, the steering transmission ratio and the wheelbase, including the following steps:

[0066] The trajectory curvature is calculated according to the following mapping relationship:

[0067] Track curvature = steering wheel angle steering ratio × wheelbase.

[0068] When the vehicle speed V is lower than V1 (ultra-low speed), the trajectory is calculated using the steering wheel angle. Kv = δ / (isg*L). δ is the steering wheel angle, isg is the steering gear ratio, L is the wheelbase, and Kv is the trajectory curvature.

[0069] Case 2

[0070] When the real-time vehicle speed is between the first speed value and the second speed value, the trajectory curvature is obtained based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value, including the following steps:

[0071] The yaw rate is low-pass filtered using a cutoff frequency;

[0072] Calculate a first steering wheel angle based on the real-time vehicle speed, wheelbase and steering ratio, and the filtered yaw rate;

[0073] Then, the angle is adjusted based on the first steering wheel angle and the steering wheel clearance to obtain a calibration range;

[0074] Compare the measured steering wheel angle with the calibration range;

[0075] If the measured steering wheel angle is not within the calibration range, the trajectory curvature calculation will not be performed;

[0076] If the measured steering wheel angle is within the calibration range, the trajectory curvature is calculated based on the real-time vehicle speed, the first speed value, the second speed value, the wheelbase, the steering ratio and the filtered yaw rate.

[0077] Specifically, it can be understood as follows: when the vehicle speed V is greater than V1 and less than V2 (low speed), the error influence of the steering wheel angle adjustment gap continues to increase, and the error influence of the yaw rate continues to decrease. First, the yaw rate ωr is processed by a low-pass filter with a cutoff frequency of 1Hz to eliminate the interference signal caused by vehicle vibration and steering wheel fine-tuning at low speed. Secondly, the yaw rate is redundantly judged to confirm whether the yaw rate value is available. Redundancy judgment formula: δ0=ωr*isg*L / V, δ0 is calculated based on the filtered ωr. The calibration can only be successful when the measured steering wheel angle δ is within the range of [δ0-△δ,δ0+△δ], otherwise ωr cannot be used for curvature calculation. Among them, △δ is the steering wheel gap adjustment angle. Finally, if the calibration is successful, the steering wheel angle and yaw rate are fused and calculated. The curvature of the fused trajectory Kv = δ / (isg*L)*K1+ωr / V*K2, where K1 and K2 are proportional coefficients, K1 = (V2-V) / (V2-V1), K2 = (V-V1) / (V2-V1).

[0078] Case 3

[0079] When the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw rate and the real-time vehicle speed, including the following steps:

[0080] The trajectory curvature is calculated according to the following mapping relationship:

[0081] Track curvature = yaw rate x real-time vehicle speed.

[0082] Among them, c) when the vehicle speed V is greater than V2 (high speed), the yaw rate error is not large, and the trajectory curvature Kv = ωr / V. When the trajectory curvature Kv is determined, the driving trajectory area of ​​the vehicle can be determined.

[0083] In some preferred embodiments, the radar lateral distance error model is designed according to the dynamic recognition characteristics and recognition accuracy of the radar for stationary obstacles, and the effective recognition area is selected accordingly. The specific method of effectively eliminating the interfering stationary objects such as tunnel walls, road piers, guardrails on both sides of the road, trees, signboards, and viaducts high above the road through the tracking and confirmation mechanism is described as follows:

[0084] Among them, the driving trajectory area is the screening range of candidate stationary obstacles, and then the screening is carried out according to the characteristics of radar detection obstacles.

[0085] Using radar to screen out effective stationary obstacles in the driving trajectory area includes the following steps:

[0086] I. In the radar detection stage, multiple stationary obstacles are obtained based on the driving track area, the real-time vehicle speed and the relative speed of the object in front of the vehicle; the specific steps are as follows:

[0087] Subtract the real-time vehicle speed from the relative speed of the object in front of the vehicle to obtain an absolute difference; compare the absolute difference with the static effective speed value;

[0088] If the absolute difference is less than the static effective speed value, the object in front of the vehicle is considered a static obstacle;

[0089] Otherwise, the object in front of the vehicle is not a stationary obstacle.

[0090] II. In the radar tracking stage, multiple stationary obstacles are screened out based on the continuous tracking time; the specific steps are as follows:

[0091] If the continuous tracking time of a stationary obstacle located in the driving trajectory area is greater than the first time threshold, it is marked as a stationary obstacle to be selected;

[0092] If the continuous tracking time of a stationary obstacle located in the driving trajectory area is less than a first time threshold, the stationary obstacle is screened out;

[0093] If the continuous tracking time of a stationary obstacle outside the driving track area is greater than a second time threshold, it is marked as a stationary obstacle to be selected;

[0094] If the continuous tracking time of the stationary obstacle outside the driving track area is less than the second time threshold, the stationary obstacle is screened out.

[0095] III. In the radar confirmation stage, based on the effective area lateral distance determination rule and the effective area maximum longitudinal distance determination rule, the effective stationary obstacles are selected from the stationary obstacles. The specific steps are:

[0096] Determine the maximum lateral distance of the radar effective area according to the width of the vehicle and the longitudinal distance of the stationary obstacle to be selected;

[0097] Determine the maximum longitudinal distance of the radar's effective detection area based on the height limit of the road and the vertical field of view angle of the radar;

[0098] Based on the maximum lateral distance and the maximum longitudinal distance, the effective area actually detected by the radar is determined, and the stationary obstacles to be selected within the effective area actually detected by the radar are taken as effective stationary obstacles.

[0099] A specific embodiment is given below:

[0100] This application divides the identification of stationary obstacles into the detection stage, the tracking stage, and the confirmation stage. The following processing methods will be adopted in different stages to filter out interfering obstacles:

[0101] a. In the detection phase, static obstacles are detected by the formula ︱V-Vrel︱<=Vstatic, including effective static obstacles and interfering obstacles, where Vrel is the relative speed between the vehicle and the vehicle in front, or the relative speed between the vehicle and the object in front; Vstatic is the effective speed range for judging static obstacles. Since the relative speed obtained by the radar has a certain error, the threshold of Vstatic is selected as 2m / s when judging whether it is a static obstacle.

[0102] b. In the tracking phase, the same stationary object identified by the radar is tracked. Since the relative lateral position between the vehicle and roadside objects is constantly changing during lane changes and cornering, most stationary objects will disappear within 2 seconds. Most roadside interference targets can be removed through the tracking phase. For targets detected in the driving trajectory area, the continuous tracking time threshold is T1, and for targets detected in the non-trajectory area, the tracking time threshold is T2. Only obstacles that meet the tracking time can be used as candidate valid stationary targets. The threshold for tracking time T1 is 2s, and the threshold for T2 is 3s. In other words, targets that do not meet the tracking time are interference targets, and most roadside interference targets and overtaken vehicles during overtaking can be removed.

[0103] c. In the confirmation stage, due to the inaccurate lateral distance of the millimeter-wave radar, the effective area is selected according to the lateral distance error model, and interference objects such as viaducts, road signs near the middle of the road, and trees are removed to ensure that all interference objects are filtered. The rules for determining the effective area are as follows:

[0104] ① Rules for determining the lateral distance of the effective area. The lateral error model adopted is that the lateral error of the radar increases with the longitudinal distance. That is, the lateral detection accuracy of the radar is that for every increase of Xm in the longitudinal distance, the lateral distance accuracy will decrease by 0.1m. Based on the above model, the width of the commercial vehicle is W. It can be obtained that when the longitudinal distance of the obstacle is D, the lateral threshold is max(W / 2-D / X*0.1). 0.7m is the minimum lateral threshold value for judging an effective stationary obstacle. That is, the effective lateral distance is between this minimum and maximum value.

[0105] ② Rules for determining the maximum longitudinal distance of the effective area. Considering the characteristics of interfering objects such as viaducts, this method limits the maximum longitudinal distance. If the vertical FOV of the radar is θ, according to the height limit of the highway is 5m, the longitudinal threshold is min(5 / tan(θ / 2),50). Among them, 50m is the maximum longitudinal distance for judging as an effective stationary obstacle.

[0106] The lateral distance error model is the software and setting method for implementing the above determination rules.

[0107] The above method comprehensively considers the dynamic recognition characteristics of radar for stationary obstacles, recognition accuracy, and the width of the vehicle, and effectively eliminates roadside interference objects such as guardrails, trees, and road piers on both sides of the road, as well as high-altitude interference objects such as signboards and viaducts above the road. It does not affect the accurate recognition of effective stationary obstacles (vehicles, pedestrians, etc.) on the road.

[0108] A method for calculating a vehicle driving trajectory area, comprising:

[0109] When the real-time vehicle speed is less than the first speed value, the trajectory curvature is obtained based on the steering parameters; the steering parameters include the steering wheel angle, the steering transmission ratio and the wheelbase;

[0110] When the real-time vehicle speed is between the first speed value and the second speed value, the trajectory curvature is obtained based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value;

[0111] When the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw rate and the real-time vehicle speed;

[0112] The corresponding track curvature is selected according to the real-time vehicle speed to obtain the driving track area.

[0113] A stationary obstacle recognition system, characterized in that it comprises:

[0114] A first module is used for obtaining a trajectory curvature based on steering parameters when the real-time vehicle speed is less than a first speed value; the steering parameters include a steering wheel angle, a steering gear ratio and a wheelbase;

[0115] A second module is used for obtaining the trajectory curvature based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value when the real-time vehicle speed is between the first speed value and the second speed value;

[0116] A third module is used for obtaining the trajectory curvature according to the yaw rate and the real-time vehicle speed when the real-time vehicle speed is greater than the second speed value;

[0117] The fourth module is used to select the corresponding track curvature according to the real-time vehicle speed to obtain the driving track area.

[0118] A computer device includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the above-mentioned stationary obstacle identification method.

[0119] A storage medium of computer-readable instructions, when the computer-readable instructions are executed by one or more processors, enables the one or more processors to perform the steps of the above-mentioned stationary obstacle recognition method.

[0120] A vehicle includes a stationary obstacle recognition system. The vehicle may be a fuel vehicle or a new energy vehicle, such as an electric vehicle. The various processes of the stationary obstacle recognition method described in any of the above embodiments can be implemented, and the same technical effect can be achieved. To avoid repetition, they will not be described here.

[0121] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps of the functions specified in the box or multiple boxes. In a typical configuration, the computing device includes one or more processors (CPU), input / output interfaces, network interfaces and memory. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0124] In the description of the present application, it should be noted that the terms "upper", "lower", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. Unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0125] It should be noted that, in this application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0126] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A method for calculating a vehicle driving trajectory area, characterized in that: It includes: When the real-time vehicle speed is less than the first speed value, the trajectory curvature is obtained based on the steering parameter; Steering parameters include steering wheel angle, steering ratio, and wheelbase; When the real-time vehicle speed is between the first speed value and the second speed value, the trajectory curvature is obtained based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value; When the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw rate and the real-time vehicle speed; The corresponding track curvature is selected according to the real-time vehicle speed to obtain the driving track area.

2. The vehicle driving trajectory area calculation method according to claim 1, characterized in that: When the real-time vehicle speed is less than the first speed value, the trajectory curvature is obtained based on the steering parameters; the steering parameters include the steering wheel angle, the steering transmission ratio and the wheelbase, including the following steps: The trajectory curvature is calculated according to the following mapping relationship: Track curvature = steering wheel angle / steering ratio × wheelbase.

3. The vehicle driving track area calculation method according to claim 1, characterized in that: When the real-time vehicle speed is between the first speed value and the second speed value, the trajectory curvature is obtained based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value, including the following steps: The yaw rate is low-pass filtered using a cutoff frequency; Calculate a first steering wheel angle based on the real-time vehicle speed, wheelbase and steering ratio, and the filtered yaw rate; Then, the angle is adjusted based on the first steering wheel angle and the steering wheel clearance to obtain a calibration range; Compare the measured steering wheel angle with the calibration range; If the measured steering wheel angle is not within the calibration range, the trajectory curvature calculation will not be performed; If the measured steering wheel angle is within the calibration range, the trajectory curvature is calculated based on the real-time vehicle speed, the first speed value, the second speed value, the wheelbase, the steering ratio and the filtered yaw rate.

4. The vehicle driving track area calculation method according to claim 1, characterized in that: When the real-time vehicle speed is greater than the second speed value, the trajectory curvature is obtained according to the yaw rate and the real-time vehicle speed, including the following steps: The trajectory curvature is calculated according to the following mapping relationship: Track curvature = yaw rate / real-time vehicle speed.

5. A method for identifying a stationary obstacle, characterized in that: It includes: Determining the driving trajectory area according to the stationary obstacle recognition method as claimed in claim 1; After the driving trajectory area is obtained, the radar is used to screen out effective stationary obstacles in the driving trajectory area.

6. The method for identifying a stationary obstacle according to claim 5, wherein: Using radar to screen out effective stationary obstacles in the driving trajectory area includes the following steps: In the radar detection phase, multiple stationary obstacles are obtained based on the driving trajectory area, real-time vehicle speed, and the relative speed of the object in front of the vehicle; In the radar tracking stage, multiple stationary obstacles are screened out as stationary obstacles to be selected based on the continuous tracking time; In the radar confirmation stage, based on the effective area lateral distance determination rule and the effective area maximum longitudinal distance determination rule, the effective stationary obstacles are obtained from the candidate stationary obstacles.

7. The method for identifying a stationary obstacle according to claim 6, wherein: Based on the driving track area, the real-time vehicle speed and the relative speed of the object in front of the vehicle, a plurality of stationary obstacles are obtained, including the following steps: Subtract the real-time vehicle speed from the relative speed of the object in front of the vehicle to obtain the absolute difference; The absolute difference is compared with the stationary effective speed value; If the absolute difference is less than the static effective speed value, the object in front of the vehicle is considered a static obstacle; Otherwise, the object in front of the vehicle is not a stationary obstacle.

8. The method for identifying a stationary obstacle according to claim 6, wherein: Screening out the stationary obstacles to be selected from the multiple stationary obstacles based on the continuous tracking time includes the following steps: If the continuous tracking time of a stationary obstacle located in the driving trajectory area is greater than the first time threshold, it is marked as a stationary obstacle to be selected; If the continuous tracking time of a stationary obstacle located in the driving trajectory area is less than a first time threshold, the stationary obstacle is screened out; If the continuous tracking time of a stationary obstacle outside the driving track area is greater than a second time threshold, it is marked as a stationary obstacle to be selected; If the continuous tracking time of the stationary obstacle outside the driving track area is less than the second time threshold, the stationary obstacle is screened out.

9. The method for identifying a stationary obstacle according to claim 6, wherein: Based on the effective area lateral distance determination rule and the effective area maximum longitudinal distance determination rule, obtaining effective stationary obstacles from the stationary obstacles to be selected includes the following steps: Determine the maximum lateral distance of the radar effective area according to the width of the vehicle and the longitudinal distance of the stationary obstacle to be selected; Determine the maximum longitudinal distance of the radar's effective detection area based on the height limit of the road and the vertical field of view angle of the radar; Based on the maximum lateral distance and the maximum longitudinal distance, the effective area actually detected by the radar is determined, and the stationary obstacles to be selected within the effective area actually detected by the radar are taken as effective stationary obstacles.

10. A stationary obstacle recognition system, characterized in that: It includes: A first module, which is used to obtain a trajectory curvature based on a steering parameter when the real-time vehicle speed is less than a first speed value; Steering parameters include steering wheel angle, steering ratio, and wheelbase; A second module is used for obtaining the trajectory curvature based on the steering parameter, the yaw rate, the real-time vehicle speed, the first speed value and the second speed value when the real-time vehicle speed is between the first speed value and the second speed value; A third module is used for obtaining the trajectory curvature according to the yaw rate and the real-time vehicle speed when the real-time vehicle speed is greater than the second speed value; The fourth module is used to select the corresponding track curvature according to the real-time vehicle speed to obtain the driving track area.

Images