Vehicle cruise tracking target determination method and device
By creating virtual safety channels in the vehicle's surrounding environment perception system and filtering forward targets, the misidentification problem caused by fuzzy lane lines in complex traffic environments is solved, and the accuracy of cruise tracking targets and driving safety is improved.
Patent Information
- Application Number
- CN202411138456.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-08
AI Technical Summary
Existing autonomous driving and advanced driving assistance systems are difficult to accurately identify lane lines in complex traffic environments, resulting in misidentification or misidentification of other vehicles, affecting driving safety.
Obtain information through the vehicle's surrounding environment perception system, create virtual safety channels, filter forward targets, and ensure accurate target selection under various road conditions.
It improves the accuracy and driving safety of cruise tracking targets, reduces the probability of manslaughter or missed killing, and can identify lane-changing targets in advance to avoid abnormal deceleration or acceleration.
Smart Images

Figure CN118907112A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent driving technology, and more specifically, to a method and device for determining a vehicle cruise tracking target. Background Art
[0002] At present, in the field of autonomous driving and advanced driver assistance systems, the existing cruise target screening scheme mainly uses the lane line of the lane as a safety boundary to determine whether other vehicles have invaded the lane to select the front tracking target. However, in practice, it is found that this technology overly relies on clear and regular lane line information. In complex and changeable traffic environments, such as rural roads, construction areas, or rainy and snowy weather where lane lines are blurred, this technology often has difficulty accurately identifying lane lines, which leads to misidentification or missed identification of other vehicles, seriously threatening driving safety. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a method and device for determining a vehicle cruise tracking target, which can ensure that the vehicle can achieve better target selection on various roads based on a virtual safety channel, improve the accuracy of determining the cruise tracking target, and increase the safety of cruise driving.
[0004] The first aspect of the present application provides a method for determining a vehicle cruise tracking target, comprising:
[0005] Obtaining vehicle surrounding environment information and vehicle chassis information through the vehicle-mounted environment perception system of the current vehicle;
[0006] Creating a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information;
[0007] Acquire the original target in front of the current vehicle;
[0008] Screening the original front target based on the forward virtual safety channel to obtain the front target closest to the current vehicle;
[0009] The front target is determined as a vehicle cruise tracking target.
[0010] In the above implementation process, the method can ensure that the vehicle can achieve better target selection on various roads based on the virtual safety channel, improve the accuracy of determining the cruise tracking target, and increase the safety of cruise driving.
[0011] Furthermore, the creating a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information includes:
[0012] Acquiring lane line information according to the vehicle surrounding environment information;
[0013] Establishing left and right lane line equations according to the lane line information;
[0014] Determining whether the current vehicle has a lane change intention according to the vehicle chassis information and the left and right lane line equations;
[0015] If yes, the forward channel is established using the preset ego-vehicle curvature model;
[0016] The forward channel is encapsulated to obtain a forward virtual security channel.
[0017] Furthermore, the method further comprises:
[0018] When it is determined that the current vehicle has no lane change intention, obtaining a vehicle speed according to the vehicle surrounding environment information;
[0019] determining a confidence threshold value according to the vehicle speed;
[0020] Determining the availability of left and right lane lines according to the left and right lane line equations and the confidence threshold value;
[0021] When the left and right lane line availability is that both the left lane line and the right lane line are unavailable, the forward channel is established using the preset ego-vehicle curvature model.
[0022] Furthermore, the method further comprises:
[0023] When the left and right lane line availability is that the left lane line or the right lane line is available, determining the available lane line according to the left and right lane line availability;
[0024] Constructing a first virtual lane line on the other side according to a preset fixed vehicle width and the available lane line;
[0025] A forward channel is established according to the available lane line and the first virtual lane line, and the forward channel is encapsulated to obtain a forward virtual safety channel.
[0026] Furthermore, the method further comprises:
[0027] When the left and right lane line availability means that both the left lane line and the right lane line are available, judging whether there is an intersection or a distant separation point between the left lane line and the right lane line according to the left and right lane line equations;
[0028] If not, constructing a lane line model according to the left and right lane line equations;
[0029] The lane line model is encapsulated to obtain a forward virtual safety channel.
[0030] Furthermore, the method further comprises:
[0031] When it is determined that the left lane line and the right lane line have the intersection point or the distant separation point, determining whether the distance between the intersection point or the distant separation point and the current vehicle is greater than a preset distance threshold;
[0032] If yes, execute the step of constructing a lane line model according to the left and right lane line equations.
[0033] Furthermore, the method further comprises:
[0034] When it is determined that the distance between the intersection point or the distant separation point and the current vehicle is not greater than the preset distance threshold, determining the longest lane line between the left lane line and the right lane line;
[0035] Determining whether the longest lane line is greater than a preset length threshold;
[0036] If yes, construct a second virtual lane line on the other side according to the longest lane line and a preset fixed vehicle width;
[0037] A lane line model is constructed according to the longest lane line and the second virtual lane line, and the lane line model is encapsulated to obtain a forward virtual safety channel.
[0038] Furthermore, the method further comprises:
[0039] When it is determined that the longest lane line is not greater than the preset length threshold, the forward channel is established using the preset vehicle curvature model.
[0040] Furthermore, the screening of the front original target based on the forward virtual safety channel to obtain the front target closest to the current vehicle includes:
[0041] Filtering the original target according to the target attribute to obtain candidate targets;
[0042] Determining the intrusion status of each candidate target into the virtual security channel within a preset time period;
[0043] Performing horizontal screening on the candidate targets according to the intrusion status to obtain all candidate targets in the forward channel;
[0044] Bubble sorting of the longitudinal distances of all the candidate targets is performed to obtain a sorted sequence;
[0045] A front target closest to the current vehicle is determined according to the sorted sequence.
[0046] A second aspect of the present application provides a vehicle cruise tracking target determination device, the vehicle cruise tracking target determination device comprising:
[0047] The vehicle cruise tracking target determination device comprises:
[0048] A first acquisition unit, used to acquire vehicle surrounding environment information and vehicle chassis information through a vehicle-mounted environment perception system of the current vehicle;
[0049] A creating unit, used for creating a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information;
[0050] A second acquisition unit, used to acquire an original target in front of the current vehicle;
[0051] A target screening unit, configured to screen the original front target based on the forward virtual safety channel to obtain the front target closest to the current vehicle;
[0052] The target determination unit is used to determine the front target as a vehicle cruise tracking target.
[0053] Furthermore, the creation unit includes:
[0054] A first acquisition subunit, configured to acquire lane line information according to the vehicle surrounding environment information;
[0055] A first establishing subunit, used to establish left and right lane line equations according to the lane line information;
[0056] A first judgment subunit is used to judge whether the current vehicle has a lane change intention according to the vehicle chassis information and the left and right lane line equations;
[0057] A second establishing subunit is used to establish a forward channel using a preset vehicle curvature model when the current vehicle has an intention to change lanes;
[0058] The encapsulation subunit is used to encapsulate the forward channel to obtain a forward virtual security channel.
[0059] Furthermore, the creation unit further includes:
[0060] A second acquisition subunit is used to acquire the vehicle speed according to the vehicle surrounding environment information when the current vehicle has no lane change intention;
[0061] a first determining subunit, configured to determine a confidence threshold value according to the vehicle speed;
[0062] The first determination subunit is further used to determine the availability of the left and right lane lines according to the left and right lane line equations and the confidence threshold value;
[0063] The second establishing subunit is further used to establish a forward channel using a preset ego-vehicle curvature model when the left and right lane line availability is that both the left lane line and the right lane line are unavailable.
[0064] Furthermore, the creation unit further includes:
[0065] The first determining subunit is further configured to determine an available lane line according to the left and right lane line availability when the left and right lane line availability is that the left lane line or the right lane line is available;
[0066] A first construction subunit, configured to construct a first virtual lane line on the other side according to a preset fixed vehicle width and the available lane line;
[0067] The third establishing subunit is used to establish a forward channel according to the available lane line and the first virtual lane line, and trigger the encapsulation subunit to perform the operation of encapsulating the forward channel to obtain a forward virtual safety channel.
[0068] Furthermore, the creation unit further includes:
[0069] A second judgment subunit is used for judging whether there is an intersection or a distant separation point between the left lane line and the right lane line according to the left and right lane line equations when the left and right lane line availability is that both the left lane line and the right lane line are available;
[0070] A second construction subunit is used to construct a lane line model according to the left and right lane line equations when the left lane line and the right lane line do not have the intersection point or the distant separation point;
[0071] The encapsulation subunit is further used to encapsulate the lane line model to obtain a forward virtual safety channel.
[0072] Furthermore, the creation unit further includes:
[0073] A third judgment subunit is used to judge whether the distance between the intersection point or the distant separation point and the current vehicle is greater than a preset distance threshold when it is judged that the left lane line and the right lane line have the intersection point or the distant separation point;
[0074] The second construction subunit is further configured to construct a lane line model according to the left and right lane line equations when the distance between the intersection or the distant separation point and the current vehicle is greater than the preset distance threshold.
[0075] Furthermore, the creation unit further includes:
[0076] A second determination subunit is used to determine the longest lane line between the left lane line and the right lane line when it is determined that the distance between the intersection point or the distant separation point and the current vehicle is not greater than the preset distance threshold;
[0077] A fourth judgment subunit is used to judge whether the longest lane line is greater than a preset length threshold;
[0078] A third construction subunit, configured to construct a second virtual lane line on the other side according to the longest lane line and a preset fixed vehicle width when the longest lane line is greater than the preset length threshold;
[0079] The third construction subunit is used to construct a lane line model according to the longest lane line and the second virtual lane line, and trigger the encapsulation subunit to perform the operation of encapsulating the lane line model to obtain a forward virtual safety channel.
[0080] Furthermore, the second establishing subunit is further configured to establish a forward channel using a preset vehicle curvature model when the longest lane line is not greater than the preset length threshold.
[0081] Furthermore, the target screening unit comprises:
[0082] A filtering subunit, used to filter the original target according to the target attribute to obtain candidate targets;
[0083] A third determination subunit is used to determine the intrusion status of each candidate target into the virtual security channel within a preset time period;
[0084] A screening subunit, used for horizontally screening the candidate targets according to the intrusion status to obtain all candidate targets in the forward channel;
[0085] A sorting subunit, used for performing a bubble sort of the longitudinal distance on all the candidate targets to obtain a sorting sequence;
[0086] The fourth determining subunit is used to determine the front target closest to the current vehicle according to the sorting sequence.
[0087] A third aspect of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the vehicle cruise tracking target determination method described in any one of the first aspects of the present application.
[0088] A fourth aspect of the present application provides a computer-readable storage medium storing computer program instructions, which, when read and executed by a processor, executes the vehicle cruise tracking target determination method described in any one of the first aspect of the present application.
[0089] The beneficial effects of the present application are: it can realize the effect of early recognition of the target in the active lane change scenario of the vehicle, so that the target in the own lane can be released earlier or the target in the target lane can be used as the cruise tracking target, thereby avoiding the abnormal deceleration or acceleration caused by late release of the target in the own lane or late recognition of the target in the target lane when changing lanes;
[0090] At the same time, the virtual safety channel that takes into account various scenarios such as no lane line, single-side line, lane line crossing, lane line separation, etc. can ensure that the vehicle can achieve better target selection on various roads, thereby reducing the probability of false kills or missed kills during cruising;
[0091] Finally, horizontal and vertical screening methods are introduced in target recognition, and a certain prediction time is considered in the horizontal screening process, so that the cutting-in condition of the leading vehicle can be identified earlier, thereby increasing the safety of cruising. BRIEF DESCRIPTION OF THE DRAWINGS
[0092] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0093] Figure 1 A flow chart of a method for determining a vehicle cruise tracking target provided in an embodiment of the present application;
[0094] Figure 2 A flowchart of another method for determining a vehicle cruise tracking target provided in an embodiment of the present application;
[0095] Figure 3 A forward channel establishment effect diagram in a single-sideline scenario provided in an embodiment of the present application;
[0096] Figure 4 A diagram showing the effect of establishing a virtual security channel provided in an embodiment of the present application;
[0097] Figure 5 A schematic diagram of the effect of constructing a lane line model provided in an embodiment of the present application;
[0098] Figure 6 A schematic diagram of establishing a forward channel provided in an embodiment of the present application;
[0099] Figure 7 A schematic diagram of an example process of creating a virtual security channel provided in an embodiment of the present application;
[0100] Figure 8 A schematic diagram of a screening process of a forward tracking target (vehicle cruise tracking target) provided in an embodiment of the present application;
[0101] Fig. 9 A flow chart of a vehicle cruise tracking target determination method provided in an embodiment of the present application;
[0102] Fig.10 A schematic diagram of the structure of a vehicle cruise tracking target determination device provided in an embodiment of the present application;
[0103] Fig.11 A schematic diagram of the structure of another vehicle cruise tracking target determination device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0104] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0105] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0106] Example 1
[0107] Please see Figure 1 , Figure 1 A flow chart of a vehicle cruise tracking target determination method provided in this embodiment. The vehicle cruise tracking target determination method includes:
[0108] S101. Acquire vehicle surrounding environment information and vehicle chassis information through the vehicle-mounted environment perception system of the current vehicle.
[0109] S102: Create a forward virtual safety channel based on the vehicle's surrounding environment information and vehicle chassis information.
[0110] In this embodiment, the method can create a forward virtual safety channel based on lane lines and vehicle chassis information.
[0111] S103: Acquire the original target in front of the current vehicle.
[0112] S104: Screen the original targets ahead based on the forward virtual safety channel to obtain the target ahead that is closest to the current vehicle.
[0113] S105: Determine the target ahead as the vehicle cruise tracking target.
[0114] In this embodiment, the method can filter the original targets, perform horizontal screening, and then sort them vertically, so as to select the nearest tracking target in front of the lane.
[0115] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and no limitation is made in this embodiment.
[0116] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.
[0117] It can be seen that the implementation of the vehicle cruise tracking target determination method described in this embodiment can ensure that the vehicle can achieve better target selection on various roads based on the virtual safety channel, improve the accuracy of determining the cruise tracking target, and increase the safety of cruise driving.
[0118] Example 2
[0119] Please see Figure 2 , Figure 2 A flow chart of a vehicle cruise tracking target determination method provided in this embodiment. The vehicle cruise tracking target determination method includes:
[0120] S201. Acquire vehicle surrounding environment information and vehicle chassis information through the vehicle-mounted environment perception system of the current vehicle.
[0121] In this embodiment, the environment perception system includes two parts: one is to obtain the vehicle's surrounding environment information (surrounding vehicles and lane lines, etc.), and the other is to obtain the vehicle chassis information (vehicle speed and yaw rate, etc.). Among them, the left and right lane lines are generally represented by cubic polynomials:
[0122] Y=c0+c1*X+c2*X^2+c3*X^3
[0123] Among them, c0 is the lateral offset distance of the lane line, c1 is the lane line angle, c2 is the lane line curvature / 2, and c3 is the lane line curvature change rate / 6.
[0124] S202: Acquire lane line information according to the vehicle surrounding environment information.
[0125] S203: Establish left and right lane line equations according to the lane line information.
[0126] In this embodiment, the method includes at least the following four parts: vehicle lane change determination, lane line availability determination, irregular lane line processing, and virtual safety channel output.
[0127] S204. Determine whether the current vehicle has the intention to change lanes based on the vehicle chassis information and the left and right lane line equations. If so, execute step S209; if not, execute step S205.
[0128] In this embodiment, for the lane change determination of the vehicle:
[0129] The situation where the left or right corner point in front of the vehicle crosses the line after the predicted time t_pre (t_pre = 300ms) is considered as the vehicle's intention to change lanes.
[0130] S205: Obtain vehicle speed according to vehicle surrounding environment information.
[0131] S206: Determine a confidence threshold value according to the vehicle speed.
[0132] S207: Determine the availability of the left and right lane lines according to the left and right lane line equations and the confidence threshold value.
[0133] In this embodiment, when the left and right lane lines are respectively determined to be available, when the lane line confidence is high and the effective length is greater than the threshold value L_line, the current lane line is considered available, otherwise it is considered unavailable. Here, the threshold value L_line = max(V*1.5, 10), and V is the vehicle speed.
[0134] S208. When the left and right lane markings are unavailable, execute step S209.
[0135] In this embodiment, irregular lane line processing refers to special processing for non-standard lane lines and abnormal lane lines to provide a reasonable forward channel for subsequent target screening, including: no lane line scenario, single side line scenario and cross separation scenario.
[0136] As an optional implementation, after step S207, the method further includes:
[0137] S301. When the left lane line or the right lane line availability is that the left lane line or the right lane line is available, determine the available lane line according to the left lane line availability.
[0138] S302: Construct a first virtual lane line on the other side according to a preset fixed vehicle width and available lane lines.
[0139] S303: Establish a forward channel according to the available lane line and the first virtual lane line, and execute step S210.
[0140] In this embodiment, one of the situations of irregular lane line processing is the single-side line scenario: only one lane line is available. At this time, the other lane line is virtualized according to the fixed vehicle width of 3.6m, and then the left and right lane lines are used to establish the forward channel. Figure 3 , Figure 3 The figure shows the effect of establishing a forward channel in a single-side line scenario, wherein the dotted line on the far left is the single-side line.
[0141] As an optional implementation, after step S207, the method further includes:
[0142] S401. When the left and right lane line availability means that both the left lane line and the right lane line are available, determine whether there is an intersection or a distant separation point between the left lane line and the right lane line according to the left and right lane line equations. If not, execute step S408; if yes, execute step S402.
[0143] S403, determining whether the distance between the intersection point or the distant separation point and the current vehicle is greater than a preset distance threshold, if so, executing step S408; if not, executing step S404.
[0144] S404: Determine the longest lane line between the left lane line and the right lane line.
[0145] S405. Determine whether the longest lane line is greater than a preset length threshold. If so, execute steps S406 to S407; if not, execute step S209.
[0146] In this embodiment, one of the situations regarding the processing of irregular lane lines is the no-lane-line scenario: the lane lines on both sides of the lane are unavailable. In this case, the lane line model is no longer used, and the vehicle curvature model is used to establish the forward channel. Figure 4 , Figure 4 A diagram showing the effect of establishing a virtual safety channel is shown.
[0147] S406: Construct a second virtual lane line on the other side according to the longest lane line and a preset fixed vehicle width.
[0148] S407. Construct a lane line model according to the longest lane line and the second virtual lane line, and execute step S409.
[0149] S408. Construct a lane line model according to the left and right lane line equations, and execute step S409.
[0150] In this embodiment, one of the situations regarding the processing of irregular lane lines is the intersection and separation scenario: the lane lines on the left and right sides are available, but there is an intersection or they are separated in the distance. At this time, first check whether the intersection and separation point is far away. If it is far enough, the lane line model is still used; otherwise, check whether the lane lines on both sides are long enough, select the longer one as the reference, and then offset to generate the lane line on the other side, and use these two lane lines to establish the lane line model; if the two lane lines are very short, downgrade to use the vehicle curvature model. Please refer to Figure 5 , Figure 5 A schematic diagram of the lane line model construction effect is shown, where the inner dotted line in the left figure is a virtual safety channel and the outer dotted line is the lane line.
[0151] S409: Encapsulate the lane line model to obtain a forward virtual safety channel, and execute step S211.
[0152] S209: Use the preset vehicle curvature model to establish a forward channel, and execute step S210.
[0153] In this embodiment, when the ego vehicle intends to change lanes, the ego vehicle curvature model is used to establish a forward channel to select targets in the vehicle's driving direction in advance. The left and right lane line equations can be approximated by a quadratic polynomial as follows:
[0154] Left side: Y=0.5*R*X^2-0.5*LaneWidth;
[0155] Right side: Y=0.5*R*X^2+0.5*LaneWidth;
[0156] Among them, R represents the curvature of the vehicle, and LaneWidth represents the lane width.
[0157] Please see Figure 6 , Figure 6 A schematic diagram of establishing a forward channel is shown. When the right corner point in front of the vehicle crosses the right lane line, the virtual channel is shown by the dotted line on the right.
[0158] S210: Encapsulate the forward channel to obtain a forward virtual security channel.
[0159] In this embodiment, the method may select the previously created lane line model or the vehicle curvature model and encapsulate it as a virtual safety channel output for subsequent horizontal and vertical screening.
[0160] Please see Figure 7 , Figure 7 An example flowchart of creating a virtual secure channel is shown.
[0161] S211. Obtain the original target in front of the current vehicle.
[0162] S212: Filter the original target according to the target attribute to obtain candidate targets.
[0163] S213: Determine the intrusion status of each candidate target on the virtual security channel within a preset time period.
[0164] S214. Perform horizontal screening on the candidate targets according to the intrusion status to obtain all the candidate targets in the forward channel.
[0165] S215. Bubble sort the vertical distances of all candidate targets to obtain a sorted sequence.
[0166] S216. Determine the front target closest to the current vehicle according to the sorting sequence.
[0167] S217: Determine the target ahead as the vehicle cruise tracking target.
[0168] In this embodiment, horizontal and vertical screening includes three parts: target filtering, horizontal screening, and vertical sorting.
[0169] Target filtering: filter original targets according to their attributes such as age, class, oncoming, etc. to obtain candidate targets;
[0170] Horizontal screening: decide whether to keep the target to the next stage according to whether the target invades the virtual security channel within the prediction time t_pre (t_pre = 300ms), and obtain all candidate targets in the forward channel;
[0171] Vertical sorting: This step performs vertical distance bubble sorting on all candidate targets to obtain the target in front that is closest to the vehicle as the tracking target.
[0172] Please see Figure 8 , Figure 8 A schematic diagram of a screening process for a forward tracking target (vehicle cruise tracking target) is shown.
[0173] Please see Fig. 9 , Fig. 9 A flow chart of a vehicle cruise tracking target determination method is shown.
[0174] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and no limitation is made in this embodiment.
[0175] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.
[0176] It can be seen that the implementation of the vehicle cruise tracking target determination method described in this embodiment can ensure that the vehicle can achieve better target selection on various roads based on the virtual safety channel, improve the accuracy of determining the cruise tracking target, and increase the safety of cruise driving.
[0177] Example 3
[0178] Please see Fig.10 , Fig.10 The schematic diagram of the structure of a vehicle cruise tracking target determination device provided in this embodiment. Fig.10 As shown, the vehicle cruise tracking target determination device includes:
[0179] The first acquisition unit 510 is used to acquire vehicle surrounding environment information and vehicle chassis information through the vehicle-mounted environment perception system of the current vehicle;
[0180] A creation unit 520, configured to create a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information;
[0181] The second acquisition unit 530 is used to acquire the original target in front of the current vehicle;
[0182] The target screening unit 540 is used to screen the original targets ahead based on the forward virtual safety channel to obtain the target ahead that is closest to the current vehicle;
[0183] The target determination unit 550 is used to determine the front target as the vehicle cruise tracking target.
[0184] In this embodiment, the explanation of the vehicle cruise tracking target determination device can refer to the description in embodiment 1 or embodiment 2, and will not be further described in this embodiment.
[0185] It can be seen that the vehicle cruise tracking target determination device described in this embodiment can ensure that the vehicle can achieve better target selection on various roads based on the virtual safety channel, improve the accuracy of determining the cruise tracking target, and increase the safety of cruise driving.
[0186] Example 4
[0187] Please see Fig.11 , Fig.11 The schematic diagram of the structure of a vehicle cruise tracking target determination device provided in this embodiment. Fig.11 As shown, the vehicle cruise tracking target determination device includes:
[0188] The first acquisition unit 510 is used to acquire vehicle surrounding environment information and vehicle chassis information through the vehicle-mounted environment perception system of the current vehicle;
[0189] A creation unit 520, configured to create a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information;
[0190] The second acquisition unit 530 is used to acquire the original target in front of the current vehicle;
[0191] The target screening unit 540 is used to screen the original targets ahead based on the forward virtual safety channel to obtain the target ahead that is closest to the current vehicle;
[0192] The target determination unit 550 is used to determine the front target as the vehicle cruise tracking target.
[0193] As an optional implementation, the creating unit 520 includes:
[0194] The first acquisition subunit 521 is used to acquire lane line information according to the vehicle surrounding environment information;
[0195] A first establishing subunit 522 is used to establish left and right lane line equations according to lane line information;
[0196] The first judgment subunit 523 is used to judge whether the current vehicle has a lane change intention according to the vehicle chassis information and the left and right lane line equations;
[0197] The second establishing subunit 524 is used to establish a forward channel using a preset ego-vehicle curvature model when the current vehicle has an intention to change lanes;
[0198] The encapsulation subunit 525 is used to encapsulate the forward channel to obtain a forward virtual security channel.
[0199] As an optional implementation, the creating unit 520 further includes:
[0200] The second acquisition subunit 526 is used to acquire the vehicle speed according to the vehicle surrounding environment information when the current vehicle has no lane change intention;
[0201] A first determining subunit 527, configured to determine a confidence threshold value according to a vehicle speed;
[0202] The first determination subunit 527 is further used to determine the availability of the left and right lane lines according to the left and right lane line equations and the confidence threshold value;
[0203] The second establishing subunit 524 is further configured to establish a forward channel using a preset ego-vehicle curvature model when the left and right lane line availability is that both the left lane line and the right lane line are unavailable.
[0204] As an optional implementation, the creating unit 520 further includes:
[0205] The first determining subunit 527 is further configured to determine the available lane line according to the availability of the left and right lane lines when the availability of the left and right lane lines is that the left lane line or the right lane line is available;
[0206] A first constructing subunit 528, configured to construct a first virtual lane line on the other side according to a preset fixed vehicle width and available lane lines;
[0207] The third establishing subunit 529 is used to establish a forward channel according to the available lane line and the first virtual lane line, and trigger the encapsulation subunit 525 to perform encapsulation on the forward channel to obtain a forward virtual safety channel.
[0208] As an optional implementation, the creating unit 520 further includes:
[0209] The second judgment subunit 52a is used to judge whether there is an intersection or a distant separation point between the left lane line and the right lane line according to the left and right lane line equations when the left and right lane line availability is that both the left lane line and the right lane line are available;
[0210] The second construction subunit 52b is used to construct a lane line model according to the left and right lane line equations when there is no intersection point or distant separation point between the left lane line and the right lane line;
[0211] The encapsulation subunit 525 is further used to encapsulate the lane line model to obtain a forward virtual safety channel.
[0212] As an optional implementation, the creating unit 520 further includes:
[0213] The third judgment subunit 52c is used to judge whether the distance between the intersection point or the distant separation point and the current vehicle is greater than a preset distance threshold when it is determined that there is an intersection point or a distant separation point between the left lane line and the right lane line;
[0214] The second constructing subunit 52b is further used to construct a lane line model according to left and right lane line equations when the distance between the intersection or the distant separation point and the current vehicle is greater than a preset distance threshold.
[0215] As an optional implementation, the creating unit 520 further includes:
[0216] A second determination subunit 52d is used to determine the longest lane line between the left lane line and the right lane line when it is determined that the distance between the intersection point or the distant separation point and the current vehicle is not greater than a preset distance threshold;
[0217] The fourth judgment subunit 52e is used to judge whether the longest lane line is greater than a preset length threshold;
[0218] The third constructing subunit 52f is used to construct a second virtual lane line on the other side according to the longest lane line and a preset fixed vehicle width when the longest lane line is greater than a preset length threshold;
[0219] The third construction subunit 52f is used to construct a lane line model according to the longest lane line and the second virtual lane line, and trigger the encapsulation subunit 525 to perform the operation of encapsulating the lane line model to obtain a forward virtual safety channel.
[0220] As an optional implementation, the second establishing subunit 524 is further used to establish a forward channel using a preset vehicle curvature model when the longest lane line is not greater than a preset length threshold.
[0221] As an optional implementation, the target screening unit 540 includes:
[0222] A filtering subunit 541 is used to filter the original target according to the target attribute to obtain a candidate target;
[0223] The third determining subunit 542 is used to determine the intrusion status of each candidate target on the virtual security channel within a preset time period;
[0224] The screening subunit 543 is used to screen the candidate targets horizontally according to the intrusion status to obtain all the candidate targets in the forward channel;
[0225] The sorting subunit 544 is used to perform a bubble sort of the longitudinal distance on all candidate targets to obtain a sorting sequence;
[0226] The fourth determining subunit 545 is used to determine the front target closest to the current vehicle according to the sorting sequence.
[0227] In this embodiment, the explanation of the vehicle cruise tracking target determination device can refer to the description in embodiment 1 or embodiment 2, and will not be further described in this embodiment.
[0228] It can be seen that the vehicle cruise tracking target determination device described in this embodiment can ensure that the vehicle can achieve better target selection on various roads based on the virtual safety channel, improve the accuracy of determining the cruise tracking target, and increase the safety of cruise driving.
[0229] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the vehicle cruise tracking target determination method in embodiment 1 or embodiment 2 of the present application.
[0230] An embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the vehicle cruise tracking target determination method in embodiment 1 or embodiment 2 of the present application is executed.
[0231] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0232] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0233] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0234] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0235] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0236] It should be noted that, in this article, relational terms such as first and second, etc. 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 existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A vehicle cruise tracking target determination method, characterized in that: include: Obtaining vehicle surrounding environment information and vehicle chassis information through the vehicle-mounted environment perception system of the current vehicle; Creating a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information; Acquire the original target in front of the current vehicle; Screening the original front target based on the forward virtual safety channel to obtain the front target closest to the current vehicle; The front target is determined as a vehicle cruise tracking target.
2. The vehicle cruise tracking target determination method according to claim 1, characterized in that: The step of creating a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information includes: Acquiring lane line information according to the vehicle surrounding environment information; Establishing left and right lane line equations according to the lane line information; Determining whether the current vehicle has a lane change intention according to the vehicle chassis information and the left and right lane line equations; If yes, the forward channel is established using the preset ego-vehicle curvature model; The forward channel is encapsulated to obtain a forward virtual security channel.
3. The vehicle cruise tracking target determination method according to claim 2, characterized in that: The method further comprises: When it is determined that the current vehicle has no lane change intention, obtaining a vehicle speed according to the vehicle surrounding environment information; determining a confidence threshold value according to the vehicle speed; Determining the availability of left and right lane lines according to the left and right lane line equations and the confidence threshold value; When the left and right lane line availability is that both the left lane line and the right lane line are unavailable, the forward channel is established using the preset ego-vehicle curvature model.
4. The vehicle cruise tracking target determination method according to claim 3, characterized in that: The method further comprises: When the left and right lane line availability is that the left lane line or the right lane line is available, determining the available lane line according to the left and right lane line availability; Constructing a first virtual lane line on the other side according to a preset fixed vehicle width and the available lane line; A forward channel is established according to the available lane line and the first virtual lane line, and the forward channel is encapsulated to obtain a forward virtual safety channel.
5. The vehicle cruise tracking target determination method according to claim 3, characterized in that: The method further comprises: When the left and right lane line availability means that both the left lane line and the right lane line are available, judging whether there is an intersection or a distant separation point between the left lane line and the right lane line according to the left and right lane line equations; If not, constructing a lane line model according to the left and right lane line equations; The lane line model is encapsulated to obtain a forward virtual safety channel.
6. The vehicle cruise tracking target determination method according to claim 5, characterized in that: The method further comprises: When it is determined that the left lane line and the right lane line have the intersection point or the distant separation point, determining whether the distance between the intersection point or the distant separation point and the current vehicle is greater than a preset distance threshold; If yes, execute the step of constructing a lane line model according to the left and right lane line equations.
7. The vehicle cruise tracking target determination method according to claim 6, characterized in that: The method further comprises: When it is determined that the distance between the intersection point or the distant separation point and the current vehicle is not greater than the preset distance threshold, determining the longest lane line between the left lane line and the right lane line; Determining whether the longest lane line is greater than a preset length threshold; If yes, construct a second virtual lane line on the other side according to the longest lane line and a preset fixed vehicle width; A lane line model is constructed according to the longest lane line and the second virtual lane line, and the lane line model is encapsulated to obtain a forward virtual safety channel.
8. The vehicle cruise tracking target determination method according to claim 7, characterized in that: The method further comprises: When it is determined that the longest lane line is not greater than the preset length threshold, the forward channel is established using the preset vehicle curvature model.
9. The vehicle cruise tracking target determination method according to claim 1, characterized in that: The screening of the front original target based on the forward virtual safety channel to obtain the front target closest to the current vehicle includes: Filtering the original target according to the target attribute to obtain candidate targets; Determining the intrusion status of each candidate target into the virtual security channel within a preset time period; Performing horizontal screening on the candidate targets according to the intrusion status to obtain all candidate targets in the forward channel; Bubble sorting of the longitudinal distances of all the candidate targets is performed to obtain a sorted sequence; A front target closest to the current vehicle is determined according to the sorted sequence.
10. A vehicle cruise tracking target determination device, characterized in that: The vehicle cruise tracking target determination device comprises: A first acquisition unit, used to acquire vehicle surrounding environment information and vehicle chassis information through a vehicle-mounted environment perception system of the current vehicle; A creating unit, used for creating a forward virtual safety channel according to the vehicle surrounding environment information and the vehicle chassis information; A second acquisition unit, used to acquire an original target in front of the current vehicle; A target screening unit, configured to screen the original front target based on the forward virtual safety channel to obtain the front target closest to the current vehicle; The target determination unit is used to determine the front target as a vehicle cruise tracking target.
