Path planning method, device, electronic device and medium for autonomous driving

By screening and smoothing the control points of autonomous driving vehicles, the comfort and safety issues of path planning in complex traffic scenarios are solved, a more optimized driving path is achieved, and the vehicle's operating stability and safety are improved.

CN115993120BActive Publication Date: 2024-11-08吉咖智能机器人有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310077829.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-01-31
Publication Date
2024-11-08
Estimated Expiration
2043-01-31

AI Technical Summary

Technical Problem

In the existing autonomous driving technology, map-based global reference paths are difficult to ensure the comfort and safety of vehicle paths in complex traffic scenarios, especially the smoothness problems caused by the density or sparseness of control points and deviation.

Method used

By obtaining multiple control points associated with the vehicle's target driving path, filtering and smoothing based on conditions such as distance and angle changes, lateral changes, conventional radius constraints, abnormal control points are deleted, and first-order filtering and equal-spacing interpolation are used to use methods such as first-order filtering and equal-spacing interpolation. , optimize the distribution of control points to form a smooth target driving path.

Benefits of technology

It improves the driving comfort and safety of the vehicle in complex traffic scenarios, ensures the smoothness and executability of the path, and reduces the resource consumption of the electronic controller.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115993120B_ABST
    Figure CN115993120B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a path planning method, device, electronic device and medium for autonomous driving. The method includes: obtaining multiple control points associated with a target driving path of a vehicle; screening a first type of control point from the multiple control points based on the distance from the multiple control points to the vehicle; smoothing the first type of control points to obtain a second type of control point, wherein the smoothing is associated with one or more of the following: an angle change, a lateral change, a conventional radius constraint and an S-type path radius constraint of one or more points in the first type of control points; and determining the target driving path for the vehicle based on the second type of control points. In this way, a relatively good path smoothing effect can be achieved with a relatively small amount of calculation, the resource consumption of the electronic controller can be reduced, and smooth vehicle control can be performed according to the control points of the high-precision map.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure generally relates to the field of autonomous driving technology, and in particular to a path planning method, device, electronic device, and computer-readable storage medium for autonomous driving. Background Art

[0002] As high-speed pilot assisted driving functions begin to be applied in smart vehicles, it is difficult to give the vehicle's guidance trajectory based on visual solutions for complex traffic scenarios, such as irregular or unclear lane lines, the need to change ramps, and large curves blocked by concrete guardrails. At this time, the application of global reference paths based on maps (such as high-precision maps) plays an irreplaceable role in smart driving vehicles.

[0003] The reference paths (such as global reference paths or local reference paths) provided by many map manufacturers are a series of lateral and longitudinal control points based on the vehicle coordinate system. Since these control points are densely or sparsely distributed and some points are deviated, if these control points are directly used for vehicle path following, comfort cannot be guaranteed. Worse still, it may affect the normal driving of the vehicle and cause traffic safety accidents. Summary of the invention

[0004] According to an example embodiment of the present disclosure, a solution for path planning for autonomous driving is provided to at least partially solve the problems existing in the prior art.

[0005] In a first aspect of the present disclosure, a method for path planning for autonomous driving is provided. The method comprises: obtaining a plurality of control points associated with a target driving path of a vehicle; screening a first type of control point from the plurality of control points based on the distances from the plurality of control points to the vehicle; smoothing the first type of control points to obtain a second type of control point, wherein the smoothing is associated with one or more of the following: an angle change, a lateral change, a conventional radius constraint, and an S-type path radius constraint of one or more points in the first type of control points; and determining the target driving path for the vehicle based on the second type of control points.

[0006] In some embodiments, smoothing the first type of control points to obtain the second type of control points includes: determining the vector angle between two consecutive points from one point in the first type of control points to the one point; and in response to determining that the vector angle is greater than a threshold, deleting the middle point among the three points in the first type of control points.

[0007] In some embodiments, smoothing the first type of control points to obtain the second type of control points includes: traversing from the first point of the first type of control points to determine the lateral distance difference between two adjacent control points of the first type of control points; in response to determining that the lateral distance difference is greater than a predetermined threshold, connecting two adjacent control points to obtain a reference line; and deleting one or more control points located on the opposite side of the reference line.

[0008] In some embodiments, smoothing the first type of control points to obtain the second type of control points includes: performing equidistant interpolation on the first type of control points; performing conventional radius constraints on three adjacent points of the first type of control points that have been equidistantly interpolated; and in response to determining that the radius is less than a threshold, adjusting the middle point of the three points to be the midpoint of the first point and the third point.

[0009] In some embodiments, smoothing the first type of control points to obtain the second type of control points includes: determining whether an S-shaped path exists based on the lateral position difference of multiple consecutive points in the first type of control points; and in response to determining that the S-shaped path exists, straightening the corresponding points in the first type of control points to obtain the second type of control points.

[0010] In some embodiments, screening the first type of control points from the plurality of control points includes: deleting control points with a trend of approaching from the plurality of control points based on the control points being far away from the vehicle; and performing first-order filtering on the remaining control points after deletion to obtain the first type of control points.

[0011] In some embodiments, obtaining multiple control points associated with the target driving path of the vehicle includes: obtaining the global path of the vehicle based on a high-precision map; and taking the vehicle as the starting point, determining the control points within a preset distance on the global path along the forward direction of the vehicle as the multiple control points.

[0012] In a second aspect of the present disclosure, a path planning device for autonomous driving is provided. The device includes: a control point acquisition module configured to acquire a plurality of control points associated with a target driving path of a vehicle; a first type of control point screening module configured to screen a first type of control point from a plurality of control points based on the distances of the plurality of control points to the vehicle; a smoothing processing module configured to smooth the first type of control points to obtain a second type of control point, wherein the smoothing processing is associated with one or more of the following: an angle change, a lateral change, a conventional radius constraint, and an S-type path radius constraint of one or more points of the first type of control points; and a path determination module configured to determine the target driving path for the vehicle based on the second type of control points.

[0013] In some embodiments, the smoothing processing module can also be configured to: determine the vector angle between one point in the first type of control point and two consecutive points after the one point; and in response to determining that the vector angle is greater than a threshold, delete the middle point among the three points in the first type of control point.

[0014] In some embodiments, the smoothing processing module can also be configured to: traverse from the first point of the first type of control point to determine the lateral distance difference between two adjacent control points in the first type of control point; in response to determining that the lateral distance difference is greater than a predetermined threshold, connect the two adjacent control points to obtain a reference line; and delete one or more control points located on the opposite side of the reference line.

[0015] In some embodiments, the smoothing processing module can also be configured to: perform equidistant interpolation on the first type of control points; perform conventional radius constraints on three adjacent points of the first type of control points that have been equidistant interpolated; and in response to determining that the radius is less than a threshold, adjust the middle point of the three points to be the midpoint of the first point and the third point.

[0016] In some embodiments, the smoothing processing module can also be configured to: determine whether there is an S-shaped path based on the lateral position difference of multiple consecutive points in the first type of control point; and in response to determining that the S-shaped path exists, straighten the corresponding points in the first type of control point to obtain the second type of control point.

[0017] In some embodiments, the first type control point screening module can also be configured to: based on the characteristics of the control points being far away from the vehicle, delete control points with a trend of approaching from the multiple control points; and perform first-order filtering on the remaining control points after deletion to obtain the first type control points.

[0018] In some embodiments, the control point acquisition module can also be configured to: acquire the global path of the vehicle based on a high-precision map; and take the vehicle as the starting point and determine the control points within a preset distance on the global path along the vehicle's forward direction as multiple control points.

[0019] In a third aspect of the present disclosure, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to the first aspect of the present disclosure.

[0020] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0021] In a fifth aspect of the present disclosure, a computer program product is provided, which includes a computer program / instructions, and when the computer program / instructions are executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0022] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure, wherein:

[0024] Figure 1 A schematic diagram illustrating an example environment in which various embodiments of the present disclosure can be implemented;

[0025] Figure 2 A flow chart of a path planning method for autonomous driving according to some embodiments of the present disclosure is shown;

[0026] Figure 3 A schematic diagram showing deleting control points with a close trend according to some embodiments of the present disclosure is shown;

[0027] Figure 4 A schematic diagram showing deleting a control point with an excessively large control angle change according to some embodiments of the present disclosure;

[0028] Figure 5 A schematic diagram showing deleting control points with excessive lateral changes according to some embodiments of the present disclosure;

[0029] Figure 6 A schematic diagram showing a conventional radius constraint on a control point according to some embodiments of the present disclosure is shown;

[0030] Figure 7 A schematic diagram of performing S-shaped path constraints on control points according to some embodiments of the present disclosure is shown;

[0031] Figure 8 A flow chart of a path planning method for autonomous driving according to a specific embodiment of the present disclosure is shown;

[0032] Fig. 9 A schematic diagram of optimized path control points obtained by using a path planning method for autonomous driving according to a specific embodiment of the present disclosure is shown;

[0033] Fig.10 A schematic block diagram showing a path planning device for autonomous driving according to some embodiments of the present disclosure; and

[0034] Fig.11 A block diagram of a computing device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0035] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0036] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0037] As mentioned above, in response to the phenomenon that the control points on the reference path provided by the map manufacturer are dense or sparse, and some points are deviated, the common smoothing method is to smooth the trajectory of discrete sampling points under constraints, such as using quadratic programming to add position constraints and curvature constraints to smooth the global path. However, in the application process, due to the complexity of the algorithm, the solution process will take a long time and the points solved will have sudden changes, which has high computing power requirements for the operating platform and cannot be achieved by engineering.

[0038] In response to the above problems, the present invention proposes a path planning solution, which deletes problematic control points in the path according to the characteristic that the distance between the control points and the vehicle increases monotonically, and eliminates control points with excessive angles and lateral changes between adjacent points, smoothes all available control points at equal intervals in the longitudinal direction, and converts the original path reference points into control points that can be executed by the vehicle's lateral control module, thereby achieving optimization of the driving path on the path in the map coverage area and ensuring driving comfort and safety.

[0039] The following will be combined Figures 1 to 11 Exemplary embodiments of the present disclosure are introduced.

[0040] Figure 1A schematic diagram of an example environment 100 in which multiple embodiments of the present disclosure can be implemented is shown. A vehicle 110 is schematically shown in the environment 100, and the vehicle 110 may be traveling on a road. For example, the vehicle 110 may be traveling on a high-speed elevated road or the like.

[0041] In some embodiments, the vehicle 110 may be any type of vehicle that can carry people and / or objects and move through a power system such as an engine, including but not limited to cars, trucks, buses, electric vehicles, motorcycles, RVs, trains, etc. In some embodiments, one or more vehicles 110 in the environment 100 may be vehicles with certain autonomous driving capabilities, which are also referred to as unmanned vehicles. In some embodiments, the vehicle 110 may also be a vehicle without autonomous driving capabilities.

[0042] In some embodiments, continue to refer to Figure 1 , the vehicle 110 can be communicatively coupled to the computing device 103. Although shown as a separate entity, the computing device 103 can be embedded in the vehicle 110. The computing device 103 can also be an entity external to the vehicle 110 and can communicate with the vehicle 110 via a wireless network. The computing device 103 can be any device with computing capabilities. As a non-limiting example, the computing device 103 can be any type of fixed computing device, mobile computing device, or portable computing device, including but not limited to a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a multimedia computer, a mobile phone, etc.; all or part of the components of the computing device 103 can be distributed in the cloud. The computing device 103 includes at least a processor, a memory, and other components that are typically present in a general-purpose computer to implement computing, storage, communication, control, and the like. The computing device 103 can perform all or part of the operations according to the various embodiments of the present disclosure, which will be described in detail below.

[0043] Reference Figure 1 . The computing device 103 can receive map data 101. The map data 101 can be a global path or a local path transmitted by high-precision map information, or it can be just basic data of the global path or the local path. The computing device 103 further processes the basic data to obtain the global path or the local path. The map data 101 can be obtained in any suitable manner, and the present disclosure does not impose any restrictions on this. The computing device 103 can then further process the path information to obtain a re-planned target driving path 105. In this way, the global path or the local path is optimized to improve driving comfort and safety.

[0044] It should be understood that Figure 1Only one example environment in which the vehicle may travel is shown. In addition to traveling on outdoor roads, the vehicle 110 may also travel in various environments such as tunnels, outdoor parking lots, inside buildings (e.g., indoor parking lots), residential areas, and parks. Depending on actual conditions, objects that may appear in different traffic environments will be changed or omitted. Figure 1 To describe the embodiments of the present disclosure.

[0045] Figure 2 FIG. 2 is a flow chart of a path planning process 200 for autonomous driving according to some embodiments of the present disclosure. The process 200 may be performed by Figure 1 The computing device 103 can be embedded in the vehicle 110 or as a standalone device outside the vehicle 110. Figure 1 The process 200 is described below.

[0046] In box 210, the computing device 103 obtains a plurality of control points associated with the target driving path 105 of the vehicle 110. The plurality of control points may be control points corresponding to an initial global path or a local path provided by the map data 101, or may be control points corresponding to a global path or a local path obtained by the computing device 101 after processing the map data 101. In one embodiment, the global path of the vehicle 110 may be obtained based on a high-precision map, and the control points within a preset distance on the global path may be determined as a plurality of control points along the forward direction of the vehicle 110, starting from the vehicle 110. The embodiments below will be described in detail with the global path as an exemplary embodiment.

[0047] In one embodiment, the preset distance may be, for example, 100 meters. Specifically, according to the vehicle control requirements, the control points sent by the high-precision map may be represented by length vectors such as RefPosX and RefPosY, and points with longitudinal positions within 0 to 100 meters in the forward direction of the vehicle 110 may be selected, that is, numbers within the range of 0 to 100 meters are selected from the RefPosX vector, and numbers of the RefPoxY vectors corresponding to the indexes are selected at the same time, to form a new control point vector as the control points to be initially screened.

[0048] It should be understood that the preset distance can also be set according to actual needs, and the present disclosure does not limit this.

[0049] In one embodiment, the computing device 103 may include a signal receiving module to receive a high-precision map global reference path or high-precision map global reference path basic data. It should be understood that the signal receiving module may also be provided on other devices that are communicatively coupled to the computing device 103, and the present disclosure does not limit this.

[0050] In box 220, based on the distances from the multiple control points to the vehicle 110, the first type of control points are screened from the multiple control points. In one embodiment, the first-order filtering module in the computing device 130 can be used to delete the problematic control points in the path and perform preliminary smoothing of the path according to the monotonically increasing characteristic of the control points from the vehicle 110. The monotonically increasing characteristic of the multiple control points from the vehicle 110 can mean that the distance from the next control point in the multiple control points to the vehicle 110 is farther than the current control point. In this way, the control points with an obvious approaching trend can be deleted to achieve preliminary screening of the control points.

[0051] Figure 3 FIG. 4 is a schematic diagram showing deleting control points with a close trend according to some embodiments of the present disclosure. In such an embodiment, Figure 3 As shown, RefNum defaults to 0, and the RefPosX and RefPosY vectors are indexed from 0. If the distance of the control point of the next index value is greater than that of the control point of the current index value, RefNum is increased by 1. If the distance is small, RefNum remains unchanged, and the next control point is moved to obtain the valid control point number RefNum and the global reference path control point horizontal position vector RefPosX and the global reference path control point vertical position vector RefPosY. Figure 3 As shown in the figure, the gray points are valid points, and the black points (RefPosX(i), RefPosY(i)) are not useful control points because they tend to approach the vehicle at the current index, so they are deleted. Subsequently, the useful control points are updated to the RefPosX and RefPosY vectors to obtain the first type of control points.

[0052] In one embodiment, first-order filtering can also be performed on the RefPosX and RefPosY of RefNum number. Figure 3 The first type of control points in are initially smoothed. Specifically, the following equation can be used to implement Figure 3 The first type of control points obtained after screening are initially smoothed:

[0053] RefPosX(i)=FltFac×RefPosX(i)+(1-FltFac)×RefPosX(i-1)

[0054] RefPosY(i)=FltFac×RefPosY(i)+(1-FltFac)×RefPosY(i-1)

[0055] Among them, i represents the index of the control point, and its value ranges from 2 to RefNum. FltFac is the first-order filter coefficient. The larger its value is, the less obvious the smoothing effect is. It can be set according to the discreteness of the high-precision map control points. Generally, it should not be too small. For example, the value can be 0.8 to achieve a better initial smoothing effect.

[0056] It should be noted that the above control point screening and preliminary smoothing methods are only exemplary, and other suitable methods may be used to obtain the first type of control points, which is not limited in the present disclosure.

[0057] At block 230 , the first type of control points are smoothed to obtain second type of control points, the smoothing being associated with one or more of: angular variation, lateral variation, conventional radius constraints, and S-path radius constraints of one or more of the first type of control points.

[0058] Figure 4 A schematic diagram of deleting control points with excessively large control angle changes according to some embodiments of the present disclosure is shown. Figure 4 As shown, the vector angle between two consecutive points after one point in the first type of control points is determined, and in response to determining that the vector angle is greater than a threshold, the middle point among the three points in the first type of control points is deleted.

[0059] Since the direction of the vehicle cannot be changed significantly, the angle at the control point cannot change too much. If the angle is too large, it means that the steering wheel will turn too much at a certain moment, the comfort of the passengers will be reduced, and in serious cases, the vehicle will be out of control. Figure 4 As shown, from the first point to RefNum, the angle of the vector is calculated for each three adjacent points to ensure that the angle α does not exceed AngLmt. If the angle is too large, the middle point is discarded. AngLmt can be set according to actual needs, for example, set to 45 degrees, so that when the control points are close to each other, 90 turns can be avoided. Figure 4 , the angle α can be obtained by the following equation:

[0060]

[0061] Therefore, when the angle α does not exceed AngLmt, steep turns can be avoided and driving comfort can be improved.

[0062] Figure 5 FIG. 4 is a schematic diagram showing the deletion of control points with excessive lateral variation according to some embodiments of the present disclosure. Figure 5As shown, traversal can be performed from the first point of the first type of control points to determine the lateral distance difference between two adjacent control points in the first type of control points, and then in response to determining that the lateral distance difference is greater than a predetermined threshold, the two adjacent control points are connected to obtain a reference line, and one or more control points located on the opposite side of the reference line are deleted.

[0063] In one embodiment, referring to Figure 5 , you can start traversing from the first point, compare the difference between adjacent points of RefPosY, if the lateral distance difference of consecutive FshNum points is less than the allowable error DstTor, then update the index value RefId used to judge the farther control point. When it is found that the lateral distance difference between the i+1th control point and the i-th control point is greater than DstErr, the point with the largest lateral distance difference between the control points i and i+1 and the RefID control point is defined as FarId, then the control points indexed as RefId and FarId are connected to form a straight line L, i+1 is FarId. According to the i-th control point and the reference line L, delete the point on the opposite side of L to the i-th point (such as Figure 5 Central control points (RefPosX(m), RefPosY(m)) and FarId points (such as Figure 5 Middle control point (RefPosX(i+1), RefPosY(i+1)). Among them, FshNum = 3, DstTor = 0.8m, DstErr = 3.0m, DstTor and DstErr can be adjusted according to the distance between adjacent control points in the high-precision map, and FshNum is not less than 3.

[0064] In this way, control points with too large lateral distance differences are deleted, and such abnormal points are excluded for subsequent radius constraints on each control point. It should be noted that the above thresholds can be set according to the actual path and driving conditions, and the present disclosure does not limit this.

[0065] In some embodiments, the first type of control points may be interpolated at equal intervals. In an example embodiment, specifically, the points processed in the above steps may be updated to the global reference path control point transverse position vector RefPosX and the global reference path control point longitudinal position vector RefPosY, and at the same time, if the control points are deleted, RefNum is also updated synchronously. Since the control point spacing is uneven at this time, the RefPosX of the first point and the RefNum point may be interpolated at equal intervals to obtain uniform CtrlNum points.

[0066] In this embodiment, further, the two index values ​​of RefPosY corresponding to the lateral position can be found within the two index values ​​of the control point vector RefPosX, and CtrlNum lateral control points with uniform longitudinal spacing can be obtained by linear interpolation, and the CtrlNum points are updated to the RefPosX and RefPosY vectors, and RefNum is CtrlNum at this time. CtrlNum = 30, so that 30 uniform points can be obtained by interpolating the control points within 0 to 100 meters. It should be noted that the number of control points can be set according to actual needs, but it should not be too many or too few. Too many requires high control accuracy and computing power, and too few results in insufficient calculation accuracy.

[0067] Figure 6 FIG. 4 is a schematic diagram showing a conventional radius constraint on a control point according to some embodiments of the present disclosure. Figure 6 As shown, a conventional radius constraint can be applied to three adjacent points of the first type of control points interpolated with equal spacing, and in response to determining that the radius is less than a threshold, the middle point of the three points is adjusted to be the midpoint of the first point and the third point, wherein the midpoint is equidistant from the first point and the third point.

[0068] In this embodiment, refer to Figure 6 , you can constrain the radius of CtrlNum control points. From RefNum to 1, if you calculate the radius for every three points, if the radius is less than RLmt, adjust the middle point to the midpoint of the first and third points. Iterate FixAllTms times in total, such as Figure 6 The FixPnt shown is the adjusted middle point, where RLmt = 60m, FixAllTms = 30, and FixAllTms is not less than CtrlNum, thereby ensuring that each point that does not meet the radius constraint can be adjusted at least once.

[0069] It should be noted that the values ​​of the above parameters are only illustrative, and other parameter values ​​may be selected according to specific driving environments and requirements, and the present disclosure does not impose any limitation on this.

[0070] Figure 7 FIG. 4 is a schematic diagram showing an S-shaped path constraint for a control point according to some embodiments of the present disclosure. Figure 7 As shown, whether there is an S-shaped path can be determined based on the lateral position difference of multiple consecutive points in the first type of control points, and in response to determining that there is an S-shaped path, the corresponding points in the first type of control points are straightened to obtain second type control points.

[0071] In one embodiment, referring to Figure 7, within the first CtrlNum / 2 control points, determine the cumulative sum of the lateral position difference with the first control point. If the cumulative sum is less than DstSCurLmt, it is determined that there is a relatively urgent S control path and adjustment is required. The adjustment method can be the same as the conventional radius constraint, mainly to constrain the radius SrLmt of the first CtrlNum / 2 control points, and the number of iterations is SFixTms. Where DstSCurLmt = 0.8m, SrLmt = 100m, SFixTms = 50. Figure 7 As shown by the arrow in , SrLmt must be greater than Rlmt in the general radius constraint to ensure that the S-bend can be straightened.

[0072] It should be noted that the values ​​of the above parameters are only illustrative, and other parameter values ​​may be selected according to specific driving environments and requirements, and the present disclosure does not impose any limitation on this.

[0073] return Figure 2 In block 240, a target driving path 105 for the vehicle is determined based on the second type of control points. After the second type of control points are obtained, the target driving path 105 of the vehicle can be planned according to the distribution of the control points. During the driving process of the vehicle, the driving of the autonomous driving vehicle can be controlled according to the target driving path 105.

[0074] The following will combine Figure 8 and Fig. 9 A specific embodiment of performing control point selection and path planning using the scheme according to the present disclosure is introduced.

[0075] Figure 8 A flow chart of a path planning method for autonomous driving according to a specific embodiment of the present disclosure is shown. Figure 8 In the process of determining whether the control point is monotonically away from the vehicle, it is possible to first determine whether the control point is within 0-100 meters. If so, it is possible to directly determine whether the control point is monotonically away from the vehicle. If not, it is possible to obtain all the control points within the range and then determine whether the control point is monotonically away from the vehicle. In the process of determining whether the control point is monotonically away from the vehicle, if yes, a first-order filtering process is performed. If not, a first-order filtering process is performed after deleting the control point with a close tendency.

[0076] Next, for the processed control points, first delete the control points with too large control angle changes, then delete the control points with too large lateral changes, then perform conventional radius constraints on the control points, and finally perform S-shaped path radius constraints as needed to finally obtain the target planned driving path.

[0077] Need to explain, Figure 8 The flowchart shown is a relatively complete processing flow according to an embodiment of the present disclosure, wherein each processing step may be omitted or adjusted according to actual needs.

[0078] Fig. 9 FIG. 4 shows a schematic diagram of optimized path control points obtained by using a path planning method for autonomous driving according to a specific embodiment of the present disclosure. Figure 8 After the processing flow shown is completed, at the right lane line, the planned path can be controlled from the global reference path of the high-precision map to the path where the smoothed control points are located. It can be seen that compared with the lane line and the original global reference path, the smoothed path not only has no sharp bends, but also has a more even and reasonable distribution of control points. With a smaller amount of calculation, it has a better path smoothing effect, can reduce the resource consumption of the electronic controller, and can perform smooth vehicle control according to the control points of the high-precision map, improving driving comfort and safety.

[0079] Fig.10 FIG. 1 is a schematic block diagram of a path planning device 1000 for autonomous driving according to some embodiments of the present disclosure. The device 1000 may be included in Figure 1 in or as computing device 103 .

[0080] like Fig.10 As shown, the device 1000 includes a control point acquisition module 1010, which is configured to acquire multiple control points associated with the target driving path of the vehicle. The device 1000 also includes a first type control point screening module 1020, which is configured to screen the first type control points from the multiple control points based on the distances from the multiple control points to the vehicle. The device 1000 also includes a smoothing processing module 1030, which is configured to smooth the first type control points to obtain the second type control points, and the smoothing is associated with one or more of the following: angle changes, lateral changes, conventional radius constraints, and S-type path radius constraints of one or more points in the first type control points. The device 1000 further includes a path determination module 1040, which is configured to determine the target driving path for the vehicle based on the second type control points.

[0081] In some embodiments, the smoothing processing module 1030 can also be configured to: determine the vector angle between two consecutive points after a point in the first type of control points is connected to a point; and in response to determining that the vector angle is greater than a threshold, delete the middle point among the three points in the first type of control points.

[0082] In some embodiments, the smoothing processing module 1030 can also be configured to: traverse from the first point of the first type of control point to determine the lateral distance difference between two adjacent control points in the first type of control point; in response to determining that the lateral distance difference is greater than a predetermined threshold, connect the two adjacent control points to obtain a reference line; and delete one or more control points located on the opposite side of the reference line.

[0083] In some embodiments, the smoothing module 1030 can also be configured to: perform equidistant interpolation on the first type of control points; perform conventional radius constraints on three adjacent points among the equidistant interpolated first type control points; and in response to determining that the radius is less than a threshold, adjust the middle point of the three points to be the midpoint of the first point and the third point.

[0084] In some embodiments, the smoothing module 1030 can also be configured to: determine whether there is an S-shaped path based on the lateral position difference of multiple consecutive points in the first type of control points; and in response to determining that there is an S-shaped path, straighten the corresponding points in the first type of control points to obtain second type control points.

[0085] In some embodiments, the first type control point screening module 1020 can also be configured to: based on the characteristics of the control points being far away from the vehicle, delete the control points with a trend of approaching from multiple control points; and perform first-order filtering on the remaining control points after deletion to obtain the first type control points.

[0086] In some embodiments, the control point acquisition module 1010 can also be configured to: acquire the global path of the vehicle based on the high-precision map; and determine the control points within a preset distance on the global path as multiple control points along the vehicle's forward direction, taking the vehicle as the starting point.

[0087] Fig.11 1 is a schematic block diagram of an example electronic device 1100 that can be used to implement an embodiment of the present disclosure. The electronic device 1100 can be used to implement Figure 2 The operations in process 200 shown may be used to at least partially implement Figure 1 103 shown in . Electronic device 1100 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0088] like Fig.11As shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0089] A number of components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0090] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1101 performs the various methods and processes described above, such as process 200. For example, in some embodiments, process 200 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of process 200 described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the process 200 in any other appropriate manner (eg, by means of firmware).

[0091] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0093] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0094] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0095] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0096] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0097] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0098] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A path planning method for autonomous driving, characterized in that: include: Acquire a plurality of control points associated with a target driving path of the vehicle; Based on the distances from the plurality of control points to the vehicle, selecting a first type of control point from the plurality of control points; smoothing the first type of control points to obtain a second type of control points, the smoothing being associated with one or more of: an angular variation, a lateral variation, a conventional radius constraint, and an S-path radius constraint of one or more of the first type of control points; and Determining the target driving path for the vehicle based on the second type of control points; The step of smoothing the first type of control points to obtain the second type of control points includes: Traversing from a first point of the first type of control points, determining a lateral distance difference between two adjacent control points of the first type of control points; In response to determining that the lateral distance difference is greater than a predetermined threshold, connecting two adjacent control points to obtain a reference line; and Deleting one or more control points located on the opposite side of the reference line; The step of smoothing the first type of control points to obtain the second type of control points includes: Performing equidistant interpolation on the first type of control points; Performing conventional radius constraints on three adjacent points among the first type of control points interpolated with equal spacing; and In response to determining that the radius is less than a threshold, adjusting a middle point among the three points to be a midpoint between the first point and the third point; And wherein, smoothing the first type of control points to obtain the second type of control points comprises: Determining whether there is an S-shaped path based on the lateral position difference of a plurality of consecutive points among the first type of control points; and In response to determining that the S-shaped path exists, corresponding points in the first type of control points are straightened to obtain the second type of control points.

2. The method according to claim 1, characterized in that Smoothing the first type of control points to obtain second type of control points includes: Determine the vector angles between one point of the first type of control points and two consecutive points after the one point; and In response to determining that the vector angle is greater than a threshold, a middle point among the three points of the first type of control points is deleted.

3. The method according to claim 1, characterized in that Screening the first type of control points from the plurality of control points comprises: Based on the characteristic that the control point is far away from the vehicle, deleting the control point with a trend of approaching from the plurality of control points; and Perform first-order filtering on the remaining control points after deletion to obtain the first type of control points.

4. The method according to claim 1, characterized in that Acquiring a plurality of control points associated with a target driving path of a vehicle includes: Acquiring a global path of the vehicle based on a high-precision map; and Taking the vehicle as a starting point, control points within a preset distance on the global path along the vehicle's forward direction are determined as a plurality of control points.

5. A path planning device for autonomous driving, characterized in that: include: A control point acquisition module is configured to acquire a plurality of control points associated with a target driving path of the vehicle; A first type control point screening module is configured to screen first type control points from the plurality of control points based on distances from the plurality of control points to the vehicle; a smoothing module configured to perform smoothing on the first type of control points to obtain second type of control points, wherein the smoothing is associated with one or more of: an angular variation, a lateral variation, a conventional radius constraint, and an S-path radius constraint of one or more of the first type of control points; and a path determination module, configured to determine the target driving path for the vehicle based on the second type of control points; The step of smoothing the first type of control points to obtain the second type of control points includes: Traversing from a first point of the first type of control points, determining a lateral distance difference between two adjacent control points of the first type of control points; In response to determining that the lateral distance difference is greater than a predetermined threshold, connecting two adjacent control points to obtain a reference line; and Deleting one or more control points located on the opposite side of the reference line; The step of smoothing the first type of control points to obtain the second type of control points includes: Performing equidistant interpolation on the first type of control points; Performing conventional radius constraints on three adjacent points among the first type of control points interpolated with equal spacing; and In response to determining that the radius is less than a threshold, adjusting a middle point among the three points to be a midpoint between the first point and the third point; And wherein, smoothing the first type of control points to obtain the second type of control points comprises: Determining whether there is an S-shaped path based on the lateral position difference of a plurality of consecutive points among the first type of control points; and In response to determining that the S-shaped path exists, corresponding points in the first type of control points are straightened to obtain the second type of control points.

6. An electronic device, comprising: one or more processors; as well as A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method according to any one of claims 1 to 4.