Vehicle positioning method, device and equipment at tunnel exit and readable storage medium

Abstract

The application relates to a tunnel exit vehicle positioning method, device and equipment and a readable storage medium, and relates to the technical field of intelligent driving. The application comprises a size relationship between a difference value between a preset length of a tunnel and a real-time displacement of a vehicle in the tunnel and a threshold value determined based on a maximum identification distance of a millimeter wave radar, a target object queue formed by a front road in the tunnel is acquired through the millimeter wave radar; whether the vehicle is at a target position is determined according to a change of a maximum longitudinal distance between the target object and the vehicle, the target position is determined based on a minimum longitudinal distance between the target object and the vehicle that can be detected by the millimeter wave radar; if the vehicle is at the target position, a first displacement with the target position as a starting point is calculated based on a vehicle speed and an acceleration; when the difference value between the minimum longitudinal distance and the first displacement is 0, a positioning system is triggered to update positioning information of the vehicle to preset positioning information corresponding to the tunnel exit, so as to realize accurate positioning when the vehicle is at or is about to reach the tunnel exit.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a vehicle positioning method, device, equipment, and readable storage medium at a tunnel exit. Background Technology

[0002] For autonomous vehicles, tunnels present a unique challenge. GNSS (Global Navigation Satellite System) signals are typically lost upon entering a tunnel, forcing vehicles to rely on visual perception or other sensory systems for degraded driving. However, upon exiting a tunnel, strong sunlight can cause overexposure, making it impossible to recognize road information outside the tunnel. The lack of GNSS signal also means no positioning information, hindering the ability to derive road information from high-precision maps for the tunnel exit. If this is compounded by the absence of exit road information and the tunnel exit is curved, a collision is highly likely. Therefore, accurate vehicle positioning is crucial for the safety of autonomous driving when exiting a tunnel and experiencing visual abnormalities. Thus, accurately locating the vehicle when it is at or nearing a tunnel exit is a pressing issue that needs to be addressed. Summary of the Invention

[0003] This application provides a vehicle positioning method, apparatus, device, and readable storage medium at a tunnel exit to solve the problem in related technologies that it is impossible to locate a vehicle when it is at or about to arrive at the tunnel exit.

[0004] Firstly, a method for locating vehicles at tunnel exits is provided, comprising the following steps:

[0005] Based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold, the target queue formed by the roadside in front of the vehicle in the tunnel is obtained by millimeter-wave radar. The value of the threshold is determined based on the maximum recognition distance of the millimeter-wave radar.

[0006] Whether the vehicle is at the target position is determined by the change in the maximum longitudinal distance between the target object in the target object queue and the vehicle. The target position is determined based on the minimum longitudinal distance between the target object and the vehicle that can be detected by millimeter-wave radar.

[0007] If the vehicle is at the target position, the first displacement is calculated based on the vehicle's speed and acceleration, and the starting point corresponding to the first displacement is the target position;

[0008] When the difference between the minimum longitudinal distance and the first displacement is 0, the positioning system is triggered to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit.

[0009] In some embodiments, the step of acquiring the target object queue formed by the roadside in front of the vehicle in the tunnel using millimeter-wave radar, based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and a preset threshold, includes:

[0010] When the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold satisfies the following first relationship, the target queue formed by the roadside in front of the vehicle in the tunnel is obtained by millimeter-wave radar.

[0011] The first relation is:

[0012] SL < 2N

[0013] In the formula, S represents the preset length of the tunnel, L represents the real-time displacement of the vehicle in the tunnel, 2N represents the threshold, and N represents the maximum identification distance of the millimeter-wave radar.

[0014] In some embodiments, determining whether the vehicle is at the target location based on the change in the maximum longitudinal distance between the target object in the target object queue and the vehicle in the workshop includes:

[0015] When the maximum longitudinal distance between a target in the target queue and the vehicle and the minimum longitudinal distance between a target that can be detected by millimeter-wave radar and the vehicle satisfy the following second relationship, the vehicle is determined to be at the target position.

[0016] The second relation is:

[0017] max(x i )<S limit

[0018] In the formula, max(x) i S represents the maximum longitudinal distance between a target in the target queue and the current workshop. limit This indicates the minimum longitudinal distance between the target object that the millimeter-wave radar can detect and the vehicle.

[0019] In some embodiments, before the step of determining whether the vehicle is at the target location based on the change in the maximum longitudinal distance between the target object in the target object queue and the workshop, the method further includes:

[0020] The first distance between the curb and the lane line is calculated based on the lateral distance between the target object in the target object queue and the vehicle, the lane line width, and the distance between the vehicle and the two lane lines of its own lane obtained by vision technology.

[0021] Based on the first distance, lane width, and field of view of the millimeter-wave radar, the minimum longitudinal distance between the target object that the millimeter-wave radar can detect and the vehicle is calculated.

[0022] In some embodiments, the method further includes:

[0023] The second distance between the vehicle and the center line of its lane is calculated based on the average lateral distance between the target objects in the target object queue and the vehicle, the lane width, and the first distance between the curb and the lane line.

[0024] In some embodiments, after the step of triggering the positioning system to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit, the method further includes:

[0025] Based on the vehicle's location information and the second distance, the road information corresponding to the tunnel exit is output through a high-precision map, so that the vehicle can control its driving actions based on the road information when it exits the tunnel.

[0026] In some embodiments, the first distance is calculated during the N < SL < 2N phase;

[0027] The second distance is calculated during the SL < N phase;

[0028] Where S represents the preset length of the tunnel, L represents the real-time displacement of the vehicle in the tunnel, and N represents the maximum identification distance of the millimeter-wave radar.

[0029] Secondly, a vehicle positioning device at a tunnel exit is provided, comprising:

[0030] The first processing unit is used to acquire the target object queue formed by the roadside in front of the vehicle in the tunnel through millimeter-wave radar based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold. The value of the threshold is determined based on the maximum recognition distance of the millimeter-wave radar.

[0031] The second processing unit is used to determine whether the vehicle is at the target position based on the change in the maximum longitudinal distance between the target object in the target object queue and the vehicle. The target position is determined based on the minimum longitudinal distance between the target object and the vehicle that can be detected by millimeter-wave radar.

[0032] The third processing unit is used to calculate the first displacement based on the vehicle speed and acceleration if the vehicle is at the target position, and the starting point corresponding to the first displacement is the target position.

[0033] The vehicle positioning unit is used to trigger the positioning system to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit when the difference between the minimum longitudinal distance and the first displacement is 0.

[0034] Thirdly, a vehicle positioning device at a tunnel exit is provided, comprising: a memory and a processor, wherein the memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the aforementioned vehicle positioning method at a tunnel exit.

[0035] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned vehicle positioning method at a tunnel exit.

[0036] This application provides a vehicle positioning method, apparatus, device, and readable storage medium at a tunnel exit. The method includes: acquiring a queue of target objects formed by the roadside in front of the vehicle within the tunnel using millimeter-wave radar, based on the relationship between the difference between the tunnel's preset length and the vehicle's real-time displacement within the tunnel and a preset threshold. The threshold is determined based on the maximum detection range of the millimeter-wave radar. The method then determines whether the vehicle is at a target position based on the change in the maximum longitudinal distance between the target objects in the queue and the vehicle. The target position is determined based on the minimum longitudinal distance between the target objects detected by the millimeter-wave radar and the vehicle. If the vehicle is at the target position, a first displacement is calculated based on the vehicle's speed and acceleration, with the starting point corresponding to the first displacement being the target position. When the difference between the minimum longitudinal distance and the first displacement is 0, the positioning system is triggered to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit. This application utilizes the characteristic that millimeter-wave radar reflects off the road within the tunnel and forms a regular queue of target objects, and achieves accurate positioning of the vehicle when it is at or about to reach the tunnel exit based on the changes in the longitudinal and lateral distances between the target objects in the queue and the vehicle. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart illustrating a vehicle positioning method at a tunnel exit, provided as an embodiment of this application;

[0039] Figure 2 A schematic diagram illustrating the changes in the positioning status of the sensing unit corresponding to the tunnel entrance / exit provided in this embodiment of the application;

[0040] Figure 3 This is a schematic diagram of millimeter-wave radar detection at the tunnel exit provided in an embodiment of this application;

[0041] Figure 4 This is a schematic diagram of the structure of a vehicle positioning device at a tunnel exit provided in an embodiment of this application;

[0042] Figure 5 This is a schematic diagram of a vehicle positioning device at a tunnel exit, provided as an embodiment of this application. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] This application provides a vehicle positioning method, apparatus, device, and readable storage medium at a tunnel exit, which can solve the problem in related technologies that it is impossible to locate a vehicle when it is at or about to arrive at the tunnel exit.

[0045] Figure 1 This application provides a vehicle positioning method at a tunnel exit, comprising the following steps:

[0046] Step S10: Based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold, the target queue formed by the roadside in front of the vehicle in the tunnel is obtained by millimeter-wave radar. The value of the threshold is determined based on the maximum recognition distance of the millimeter-wave radar.

[0047] As an example, it should be understood that current GNSS is typically lost during the period from when the device is inside the tunnel until it exits the tunnel, and it can only be restored some time after exiting the tunnel; see also Figure 2 As shown, high-precision maps, wheel speedometers, and radar continuously output corresponding lane line information, pose status information, target object information, and fitted curves within the tunnel. While the vehicle's in-vehicle visual perception system can provide lane line information normally inside the tunnel, it often fails to recognize lane lines due to changes in lighting when exiting the tunnel. It only resumes operation after a period of time following exit. Furthermore, inertial navigation systems can only achieve approximately 2 seconds of positioning estimation, provided GNSS positioning is accurate. This is reliable when entering the tunnel, but completely unreliable when exiting. For these reasons, accurate vehicle positioning will be impossible when the vehicle is at or about to reach the tunnel exit.

[0048] Currently, vehicle positioning within tunnels is often achieved by deploying road markers and other data. Therefore, positioning can also be achieved by placing road markers at the tunnel exit, as positioning at the moment of exiting the tunnel would be difficult to obtain. However, deploying road markers requires significant infrastructure construction and maintenance, as well as marking each marker, resulting in high costs and time. Alternatively, wheel speed sensors combined with positioning can be used to dynamically deduce the vehicle's current location. However, in long tunnels, vehicles frequently accelerate and decelerate, leading to low longitudinal positioning accuracy, which decreases with tunnel length. Therefore, current methods are insufficient to handle situations where vehicles exit tunnels and visual exposure occurs.

[0049] To address the aforementioned issues, this embodiment utilizes the characteristic that the maximum longitudinal distance between the vehicle and low-confidence targets identified by the vehicle's forward-facing millimeter-wave radar within a tunnel continuously changes, enabling the vehicle's location and identification at the tunnel exit. Specifically, within a tunnel, because the curb is higher than the road surface, the millimeter-wave radar detects regular low-confidence targets (i.e., curbs) along the lane lines. The lateral distance of these low-confidence targets relative to the vehicle is typically 0.5-1 times the lane width. Since curbs are usually only present within tunnels on highways, and not outside, once the vehicle exits the tunnel, the forward-facing millimeter-wave radar will be unable to detect the curb, and thus, will be unable to detect low-confidence targets. Consequently, as the vehicle approaches the tunnel exit, the maximum longitudinal distance between the detected target and the vehicle continuously decreases.

[0050] For example, when a vehicle is traveling in the middle of a tunnel, the forward millimeter-wave radar detects a queue of targets including target A and target B. The longitudinal distance between target A and the vehicle is 150m (it should be noted that in this application, the direction of travel of the vehicle is taken as the X-axis, and the direction perpendicular to the direction of travel is taken as the Y-axis, that is, the longitudinal distance is represented by x and the lateral distance is represented by y). The longitudinal distance between target B and the vehicle is 147m. Since 150 is greater than 147, target A is located in front of target B, that is, target A is closer to the tunnel exit. At this time, the maximum longitudinal distance between the target detected by the forward millimeter-wave radar and the vehicle is 150m.

[0051] However, as the vehicle gets closer to the tunnel exit, the number of road edges that can be detected decreases, meaning the maximum longitudinal distance between the detected road edge and the vehicle becomes smaller. For example, when the vehicle is close to the tunnel exit, the target queue detected by the forward millimeter wave includes target C and target D. The longitudinal distance between target C and the vehicle is 15m, and the longitudinal distance between target D and the vehicle is 13m. Since 15 is greater than 13, target C is closer to the tunnel exit. At this point, the maximum longitudinal distance between the target detected by the forward millimeter wave and the vehicle is 15m. Thus, it can be seen that the closer the vehicle is to the tunnel exit, the smaller the maximum longitudinal distance between the target detected by the forward millimeter wave and the vehicle.

[0052] However, since this embodiment only needs to locate and identify the vehicle when it is at or about to reach the tunnel exit, it is not necessary to activate the millimeter-wave radar to detect targets when the vehicle is far from the tunnel exit, thus reducing system computing power. Therefore, in this embodiment, a threshold is determined by the maximum identification distance of the millimeter-wave radar. This threshold is used to characterize whether the forward-facing millimeter-wave radar needs to be activated to detect targets. It should be noted that the specific value of this threshold can also be determined according to actual needs and is not limited here.

[0053] In this embodiment, after the vehicle enters the tunnel, the high-precision positioning system can provide a marker indicating entry into the tunnel and obtain the preset tunnel length S. Simultaneously, the real-time displacement L of the vehicle within the tunnel (i.e., the vehicle's current position) is calculated based on the vehicle's speed and acceleration. Then, based on the relationship between the difference between the preset tunnel length S and the real-time displacement L of the vehicle within the tunnel and a threshold, it is determined whether to drive the millimeter-wave radar to identify targets. If so, the millimeter-wave radar is controlled to detect the roadside in front of the vehicle, i.e., to detect targets, to obtain the corresponding target queue and store the lateral and longitudinal distances between each target and the vehicle. It should be noted that in this embodiment, only the roadside in front of the vehicle needs to be detected. Therefore, the forward-facing millimeter-wave radar installed on the vehicle can be used directly for roadside detection. Of course, if millimeter-wave radars in other directions can also detect the roadside in front of the vehicle, this embodiment can also use millimeter-wave radars in other directions for roadside detection. The specific method can be determined according to the actual situation and is not limited here.

[0054] Furthermore, the step of acquiring the target object queue formed by the roadside in front of the vehicle in the tunnel using millimeter-wave radar, based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and a preset threshold, includes:

[0055] When the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold satisfies the following first relationship, the target queue formed by the roadside in front of the vehicle in the tunnel is obtained by millimeter-wave radar.

[0056] The first relation is:

[0057] SL < 2N

[0058] In the formula, S represents the preset length of the tunnel, L represents the real-time displacement of the vehicle in the tunnel, 2N represents the threshold, and N represents the maximum identification distance of the millimeter-wave radar.

[0059] As an example, in this embodiment, when the preset tunnel length S, the real-time displacement L of the vehicle in the tunnel, and the threshold satisfy SL < 2N, the forward millimeter-wave radar will be activated to identify targets in order to obtain the target queue formed by the roadside in front of the vehicle in the tunnel.

[0060] Specifically, when detecting targets, millimeter-wave radar typically detects target queues along both sides of the roadside inside the tunnel. However, since target queues closer to the current lane are relatively stable, this embodiment first needs to filter the position of the target queues during target detection, i.e., selecting relatively stable targets for detection: assuming that along the vehicle's direction of travel, relative to the midpoint of the vehicle's front axle, the left side is positive and the right side is negative, and the lateral distance of the target relative to the vehicle is y, then the side with the smaller absolute value of y is selected for detection, while the side with the larger absolute value of y is filtered out. For example, if the absolute value of y for a target on the right is smaller than that for a target on the left, then the left side is filtered out, and the right side is retained.

[0061] After identifying the target objects to be detected, a target object queue will be established. Only target objects that meet the following two conditions can enter the target object queue. For example, suppose there are a total of i detected one-sided target objects, and the lane width where the vehicle is located is a:

[0062] (1) Assume the lateral distance between the target object i and this workshop is y. i , then y i Must meet: -0.5m <y i -0.5×a<0.5m. It should be noted that 0.5m is only for the purpose of this example. Other values ​​can also be set, as long as the target objects on the tunnel walls can be excluded.

[0063] (2) Assume the longitudinal distance between the target object i and this workshop is x. i Then x i Must satisfy: Arranged in ascending order, x i -x i-1<4m, meaning the longitudinal distance between adjacent targets must be less than 4m, or the longitudinal distance between adjacent targets in the target sequence must be less than 4m. It should be noted that if the longitudinal distance between adjacent targets in the queue is too large, it indicates the possible presence of non-roadside targets. Therefore, this embodiment limits the longitudinal distance between adjacent targets to exclude non-roadside targets. The 4m limit is merely a representation of this embodiment; the specific value can be determined based on actual circumstances and is not limited here. If this embodiment uses a forward-facing millimeter-wave radar for target detection, then to reduce the influence of external factors, the x-axis can be set... i The condition >0 is used to exclude target data detected by lateral millimeter-wave radar and rearward millimeter-wave radar.

[0064] If all i detected targets satisfy the above two conditions, then the i targets are stored in the target queue, that is, the target queue includes 1 to i targets, and the lateral distance y between each target and the vehicle is stored. i and vertical distance x i .

[0065] Step S20: Determine whether the vehicle is at the target position based on the change in the maximum longitudinal distance between the target object in the target object queue and the vehicle. The target position is determined based on the minimum longitudinal distance between the target object and the vehicle that can be detected by millimeter-wave radar.

[0066] Specifically, determining whether the vehicle is at the target location based on the change in the maximum longitudinal distance between the target object in the target object queue and the vehicle in this workshop includes:

[0067] When the maximum longitudinal distance between a target in the target queue and the vehicle and the minimum longitudinal distance between a target that can be detected by millimeter-wave radar and the vehicle satisfy the following second relationship, the vehicle is determined to be at the target position.

[0068] The second relation is:

[0069] max(x i )<S limit

[0070] In the formula, max(x) i S represents the maximum longitudinal distance between a target in the target queue and the current workshop. limit This indicates the minimum longitudinal distance between the target object that the millimeter-wave radar can detect and the vehicle.

[0071] Exemplary, see Figure 3 As shown, it is understandable that, due to the field of view (FOV) limitation of millimeter-wave radar, there is a minimum longitudinal distance S between the target object that a forward-facing millimeter-wave radar can detect and the vehicle itself. limit(generally within 3m), that is, when the longitudinal distance between the target object and the host vehicle is less than this S limit , the forward millimeter-wave radar cannot detect the corresponding target object. Therefore, when it is detected that the maximum longitudinal distance max(x between the target object and the host vehicle in the target queue i )<S limit , it indicates that the host vehicle is already very close to the tunnel exit at this time, that is, the host vehicle has reached the target position. It should be noted that, in order to prevent the millimeter-wave radar from abnormally losing targets, max(x i )<S limit +1 can also be set as the condition for judging whether the host vehicle has reached the target position. For example, when it is detected that the maximum longitudinal distance max(x between the target object and the host vehicle in the target queue i )<S limit +1, it indicates that the host vehicle is already very close to the tunnel exit at this time, that is, the host vehicle has reached the target position.

[0072] For example, assuming that the target queue detected by the forward millimeter-wave radar includes target objects E and F, the longitudinal distance between target object E and the host vehicle is 2m, and the longitudinal distance between target object F and the host vehicle is 1m, then the maximum longitudinal distance between the target object detected by the forward millimeter-wave radar and the host vehicle is 2m. Since it is less than S limit +1, therefore, it is determined that the host vehicle is at the target position.

[0073] Further, before the step of determining whether the host vehicle is at the target position based on the change of the maximum longitudinal distance between the target object and the host vehicle in the target queue, the method further includes:

[0074] calculating a first distance between the curb and the lane line based on the lateral distance between the target object and the host vehicle in the target queue, the width of the lane line, and the distances between the host vehicle and the two lane lines of the lane where the host vehicle is located obtained through visual technology; wherein the calculation of the first distance is performed during the N<S-L<2N phase;

[0075] calculating the minimum longitudinal distance between the target object detectable by the millimeter-wave radar and the host vehicle based on the first distance, the lane line width and the field of view angle of the millimeter-wave radar.

[0076] Illustratively, in this embodiment, the distance l' between the curb and the lane line (that is, the first distance) is estimated. Since the relative position of the lane line and the curb is a fixed value, l' can be accurately calculated before exiting the tunnel; however, in order to reduce the system computing power, it is not necessary to calculate l' throughout the whole process, and it only needs to be completed during the N<S-L<2N phase. Specifically, when calculating l', visual technology will be introduced to obtain lane line position information, and then calculate the distances c between the host vehicle and the two lane lines of the lane where the host vehicle is located (that is, the left and right lane lines) respectively01 and c 02 Then, the lateral distance y between the target object and this workshop. i Lane widths a and c 01 and c 02 Substituting into the following formula: l′=y i -(c 01 +c 02 The value of l′ can be calculated by ) / 2-a / 2l`.

[0077] Assuming the field of view of the forward-facing millimeter-wave radar is N°, then substituting the first distance l′, lane width a, and field of view N° into the following formula: S limit = (a / 2 + l′) × tan(N°), which can be used to calculate the minimum longitudinal distance S between the target object and the vehicle that can be detected by the forward millimeter-wave radar. limit .

[0078] Step S30: If the vehicle is at the target position, calculate the first displacement based on the vehicle's speed and acceleration, and the starting point corresponding to the first displacement is the target position;

[0079] In this exemplary embodiment, once the vehicle is at the target position, the forward-facing millimeter-wave radar has reached its limited field of view, meaning the vehicle has entered the blind zone of the millimeter-wave radar's corresponding field of view. Therefore, it is not suitable to continue using forward-facing millimeter waves for target detection. Furthermore, since the vehicle is very close to the tunnel exit, meaning the distance from the target position to the tunnel exit is short, even with frequent acceleration and deceleration, the error in estimating displacement using vehicle speed and acceleration can be ignored. Therefore, starting from the target position, the first displacement S′ can be calculated using the vehicle's speed and acceleration. The first displacement S′ is used to help determine whether the vehicle has reached the tunnel exit.

[0080] Step S40: When the difference between the minimum longitudinal distance and the first displacement is 0, the positioning system is triggered to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit.

[0081] As an example, in this embodiment, the minimum longitudinal distance S between the target object detected by the millimeter-wave radar and the vehicle is... limit The first displacement S′ satisfies S limit -S′=0, or S limit When +1-S′=0, it is determined that the vehicle has reached the tunnel exit. At this time, the high-precision positioning system will be triggered to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit. That is, the high-precision positioning system will use the preset positioning corresponding to the tunnel exit as the vehicle's positioning, thereby achieving accurate positioning when the vehicle is at or about to reach the tunnel exit.

[0082] Further, the method further comprises:

[0083] calculating a second distance between the host vehicle and the lane centerline of the lane where the host vehicle is located according to the average value of the lateral distances between the targets in the target queue and the host vehicle, the lane width, and the first distance between the road curb and the lane line. Wherein, the calculation of the second distance is performed in the S-L<N phase.

[0084] Exemplarily, in this embodiment, the calculation of the distance l (i.e., the second distance) between the host vehicle and the lane centerline of the lane where the host vehicle is located is performed, that is, the lateral position estimation of the host vehicle is performed, that is, the position of the host vehicle relative to the lane center. However, to reduce system computing power, it is not necessary to calculate l throughout the entire process, and it only needs to be completed in the S-L<N phase. Specifically, the average value of the lateral distances between the targets in the target queue and the host vehicle average(y i ), the lane width a, and the first distance l' between the road curb and the lane line are substituted into the following formula: l=average(y i )-l'-a / 2, then the second distance l can be calculated. This process essentially replaces visual perception systems such as cameras to complete the estimation of the position relative to the lane line.

[0085] Further, after the step of triggering the positioning system to update the positioning information of the host vehicle to the preset positioning information corresponding to the tunnel exit, the method further comprises:

[0086] based on the positioning information of the host vehicle and the second distance, outputting road information corresponding to the tunnel exit through a high-precision map, so that the host vehicle controls driving actions based on the road information when exiting the tunnel exit.

[0087] Exemplarily, in this embodiment, after accurately positioning that the host vehicle is already at the tunnel exit, when triggering the high-precision positioning system to update the positioning information of the host vehicle to the preset positioning information corresponding to the tunnel exit, the distance l between the host vehicle and the lane centerline of the lane where the host vehicle is located is also sent to the high-precision positioning system; at this time, the high-precision positioning system not only uses the preset positioning corresponding to the tunnel exit as the positioning of the host vehicle, but also combines l and outputs the road information corresponding to the area in front of the tunnel exit through the high-precision map, so that when the host vehicle exits the tunnel exit, the driving action can be controlled according to the road information. For example, if the road information includes that there is a curve in front of the tunnel exit and the specific information of the curve, the host vehicle is controlled to perform corresponding turning driving according to the curve information.

[0088] Therefore, this embodiment first combines the differences between the road features (curb) inside the tunnel and the highway outside the tunnel, and utilizes the characteristic of millimeter-wave radar forming a regular target queue by reflecting the route in the tunnel. When a vehicle is about to exit the tunnel, the maximum longitudinal distance between the target in the queue and the vehicle will shorten. That is, by measuring the change in the maximum longitudinal distance between the target and the vehicle, it is estimated whether the vehicle is about to reach the tunnel exit. When the vehicle is about to reach the tunnel exit, that is, after reaching the blind spot of the corresponding field of view of the millimeter-wave radar, the vehicle displacement is calculated by the vehicle speed and vehicle acceleration, and then it is determined whether the vehicle has reached the tunnel exit. Then, a command is sent to the positioning system to directly update the vehicle's position in the positioning system to the positioning position of the tunnel exit. Combined with a high-precision map, it is possible to obtain road information ahead in a timely and accurate manner when exiting the tunnel and when visual overexposure occurs, so as to support the safe driving of the vehicle.

[0089] In summary, this embodiment not only eliminates the need for LiDAR but also eliminates the need for road signs within the tunnel, enabling accurate vehicle positioning when the vehicle is at or about to reach the tunnel exit. The solution is low-cost and effectively ensures the safety of autonomous driving when exiting the tunnel.

[0090] It should be noted that the step numbers in the embodiments of this application do not limit the order of operations in the technical solution of this application.

[0091] See Figure 4 As shown in the illustration, this application also provides a vehicle positioning device at a tunnel exit, comprising:

[0092] The first processing unit is used to acquire the target object queue formed by the roadside in front of the vehicle in the tunnel through millimeter-wave radar based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold. The value of the threshold is determined based on the maximum recognition distance of the millimeter-wave radar.

[0093] The second processing unit is used to determine whether the vehicle is at the target position based on the change in the maximum longitudinal distance between the target object in the target object queue and the vehicle. The target position is determined based on the minimum longitudinal distance between the target object and the vehicle that can be detected by millimeter-wave radar.

[0094] The third processing unit is used to calculate the first displacement based on the vehicle speed and acceleration if the vehicle is at the target position, and the starting point corresponding to the first displacement is the target position.

[0095] The vehicle positioning unit is used to trigger the positioning system to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit when the difference between the minimum longitudinal distance and the first displacement is 0.

[0096] Furthermore, the first processing unit is specifically used for:

[0097] When the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold satisfies the following first relationship, the target queue formed by the roadside in front of the vehicle in the tunnel is obtained by millimeter-wave radar.

[0098] The first relation is:

[0099] SL < 2N

[0100] In the formula, S represents the preset length of the tunnel, L represents the real-time displacement of the vehicle in the tunnel, 2N represents the threshold, and N represents the maximum identification distance of the millimeter-wave radar.

[0101] Furthermore, the second processing unit is specifically used for:

[0102] When the maximum longitudinal distance between a target in the target queue and the vehicle and the minimum longitudinal distance between a target that can be detected by millimeter-wave radar and the vehicle satisfy the following second relationship, the vehicle is determined to be at the target position.

[0103] The second relation is:

[0104] max(x i )<S limit

[0105] In the formula, max(x) i S represents the maximum longitudinal distance between a target in the target queue and the current workshop. limit This indicates the minimum longitudinal distance between the target object that the millimeter-wave radar can detect and the vehicle.

[0106] Furthermore, the second processing unit is also used for:

[0107] The first distance between the curb and the lane line is calculated based on the lateral distance between the target object in the target object queue and the vehicle, the lane line width, and the distance between the vehicle and the two lane lines of its own lane obtained by vision technology.

[0108] Based on the first distance, lane width, and field of view of the millimeter-wave radar, the minimum longitudinal distance between the target object that the millimeter-wave radar can detect and the vehicle is calculated.

[0109] Furthermore, the third processing unit is also used for:

[0110] The second distance between the vehicle and the center line of its lane is calculated based on the average lateral distance between the target objects in the target object queue and the vehicle, the lane width, and the first distance between the curb and the lane line.

[0111] Furthermore, the device also includes an information output unit, which is used for:

[0112] Based on the vehicle's location information and the second distance, the road information corresponding to the tunnel exit is output through a high-precision map, so that the vehicle can control its driving actions based on the road information when it exits the tunnel.

[0113] Furthermore, the first distance is calculated during the N < SL < 2N stage; the second distance is calculated during the SL < N stage; where S represents the preset tunnel length, L represents the real-time displacement of the vehicle in the tunnel, and N represents the maximum identification distance of the millimeter-wave radar.

[0114] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the device and each unit described above can be referred to the corresponding process in the aforementioned embodiment of the vehicle positioning method at the tunnel exit, and will not be repeated here.

[0115] The vehicle positioning device at the tunnel exit provided in the above embodiments can be implemented as a computer program, which can, for example, Figure 5 The vehicle positioning equipment shown is running at the tunnel exit.

[0116] This application also provides a vehicle positioning device at a tunnel exit, comprising: a memory, a processor, and a network interface connected via a system bus. The memory stores at least one instruction, which is loaded and executed by the processor to implement all or part of the steps of the aforementioned vehicle positioning method at a tunnel exit.

[0117] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0118] A processor can be a CPU, or other general-purpose processors, DSPs (Digital Signal Processors), ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of a computer device, connecting all parts of the computer device through various interfaces and lines.

[0119] Memory can be used to store computer programs and / or modules. The processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, at least one application program required for a function (such as video playback, image playback, etc.), etc.; the data storage area can store data created based on the use of the mobile phone (such as video data, image data, etc.). Furthermore, memory can include high-speed random access memory (RAM), and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, SMC (Smart MediaCard), SD (Secure Digital) cards, flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0120] This application also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements all or part of the steps of the aforementioned vehicle positioning method at the tunnel exit.

[0121] The embodiments of this application can implement all or part of the aforementioned processes, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, ROM (Read-Only memory), RAM (Random Access memory), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0122] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, servers, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0123] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0124] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0125] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for vehicle positioning at a tunnel exit, characterized in that, Includes the following steps: Based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold, the target queue formed by the roadside in front of the vehicle in the tunnel is obtained by millimeter-wave radar. The value of the threshold is determined based on the maximum recognition distance of the millimeter-wave radar. When the maximum longitudinal distance between the target object in the target object queue and this workshop The minimum longitudinal distance between the target object detected by millimeter-wave radar and the vehicle itself. The vehicle is considered to be at the target position when the size of the space satisfies the following relationship: ; If the vehicle is at the target position, the first displacement is calculated based on the vehicle's speed and acceleration, and the starting point corresponding to the first displacement is the target position; When the difference between the minimum longitudinal distance and the first displacement is 0, the positioning system is triggered to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit. Among them, the target objects in the target object queue must meet the following two conditions: the difference between the lateral distance of the target object and the workshop and the half width of the lane is within a preset lateral deviation range, which is used to exclude target objects corresponding to the tunnel wall; after sorting all target objects according to their longitudinal distance from the workshop from smallest to largest, the longitudinal distance between adjacent target objects is less than a preset longitudinal spacing threshold, which is used to exclude non-curb target objects.

2. The vehicle positioning method at the tunnel exit as described in claim 1, characterized in that, The method of acquiring a queue of targets formed by the roadside in front of the vehicle in the tunnel using millimeter-wave radar, based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and a preset threshold, includes: When the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold satisfies the following first relationship, the target queue formed by the roadside in front of the vehicle in the tunnel is obtained by millimeter-wave radar. The first relation is: In the formula, S represents the preset length of the tunnel, L represents the real-time displacement of the vehicle in the tunnel, 2N represents the threshold, and N represents the maximum identification distance of the millimeter-wave radar.

3. The vehicle positioning method at the tunnel exit as described in claim 1, characterized in that, Before the step of determining whether the vehicle is in the target position based on the change in the maximum longitudinal distance between the target object in the target object queue and the vehicle in this workshop, the following steps are also included: The first distance between the curb and the lane line is calculated based on the lateral distance between the target object in the target object queue and the vehicle, the lane line width, and the distance between the vehicle and the two lane lines of its own lane obtained by vision technology. Based on the first distance, lane width, and field of view of the millimeter-wave radar, the minimum longitudinal distance between the target object that the millimeter-wave radar can detect and the vehicle is calculated.

4. The vehicle positioning method at the tunnel exit as described in claim 3, characterized in that, The method further includes: The second distance between the vehicle and the center line of its lane is calculated based on the average lateral distance between the target objects in the target object queue and the vehicle, the lane width, and the first distance between the curb and the lane line.

5. The vehicle positioning method at the tunnel exit as described in claim 4, characterized in that, After the step of triggering the positioning system to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit, the method further includes: Based on the vehicle's location information and the second distance, the road information corresponding to the tunnel exit is output through a high-precision map, so that the vehicle can control its driving actions based on the road information when it exits the tunnel.

6. The vehicle positioning method at the tunnel exit as described in claim 4, characterized in that: exist The first distance is calculated within the phase; exist The second distance is calculated within the phase; Where S represents the preset length of the tunnel, L represents the real-time displacement of the vehicle in the tunnel, 2N represents the threshold, and N represents the maximum recognition distance of the millimeter-wave radar.

7. A vehicle positioning device at a tunnel exit, characterized in that, include: The first processing unit is used to acquire the target object queue formed by the roadside in front of the vehicle in the tunnel through millimeter-wave radar based on the relationship between the difference between the preset tunnel length and the real-time displacement of the vehicle in the tunnel and the preset threshold. The value of the threshold is determined based on the maximum recognition distance of the millimeter-wave radar. The second processing unit is used to handle situations where the target object in the target object queue is at the maximum longitudinal distance from the target object in this workshop. The minimum longitudinal distance between the target object detected by millimeter-wave radar and the vehicle itself. The vehicle is considered to be at the target position when the size of the space satisfies the following relationship: ; The third processing unit is used to calculate the first displacement based on the vehicle speed and acceleration if the vehicle is at the target position, and the starting point corresponding to the first displacement is the target position. The vehicle positioning unit is used to trigger the positioning system to update the vehicle's positioning information to the preset positioning information corresponding to the tunnel exit when the difference between the minimum longitudinal distance and the first displacement is 0. Among them, the target objects in the target object queue must meet the following two conditions: the difference between the lateral distance of the target object and the workshop and the half width of the lane is within a preset lateral deviation range, which is used to exclude target objects corresponding to the tunnel wall; after sorting all target objects according to their longitudinal distance from the workshop from smallest to largest, the longitudinal distance between adjacent target objects is less than a preset longitudinal spacing threshold, which is used to exclude non-curb target objects.

8. A vehicle positioning device at a tunnel exit, characterized in that, include: A memory and a processor, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the vehicle positioning method at the tunnel exit as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed by a processor, implements the vehicle positioning method at the tunnel exit as described in any one of claims 1 to 6.

Images