Path planning method, device, vehicle and storage medium

Abstract

This application discloses a path planning method, device, vehicle, and readable storage medium. The method includes: in response to a vehicle entering a lane change phase, determining a first preview distance based on the vehicle's speed at a first time point; constructing a first lane change guidance path based on path points in a first historical planned path that are between the start and end points of a first lane change guidance path; determining a first lane change transition path at a first time point based on the end point of the first lane change guidance path and a first lane change entry point determined in a target lane reference line; and concatenating the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at the first time point. The method of this application improves the vehicle's autonomous driving experience.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to a path planning method, device, vehicle, and computer-readable storage medium. Background Art

[0002] In the field of autonomous driving, when a vehicle needs to change lanes during autonomous driving, the vehicle plans its own lane change path and then automatically changes lanes based on that path. However, this related technology suffers from low lane change path planning accuracy, resulting in a poor autonomous driving experience. Summary of the Invention

[0003] The present application proposes a path planning method, device, vehicle and computer-readable storage medium to improve the above-mentioned defects.

[0004] In a first aspect, an embodiment of the present application provides a path planning method, the method comprising:

[0005] In response to the vehicle entering a lane change phase, determining a first preview distance based on the vehicle's speed at a first time point; the first time point being no earlier than the time when the vehicle enters the lane change phase;

[0006] Obtaining a path point of the vehicle at a first time point from the first historical planned path as the starting point of a first lane change guidance path at the first time point, and obtaining a point in the first historical planned path that is a distance from the starting point of the first lane change guidance path by a first preview distance along the vehicle's forward direction as the end point of the first lane change guidance path; the first historical planned path is a planned path determined for the vehicle at a time point before the first time point;

[0007] constructing a first lane change guidance path based on path points between a starting point and an end point of the first lane change guidance path in the first historical planned path;

[0008] Determining a first lane change transition path at a first time point based on an endpoint of the first lane change guidance path and a first lane change entry point determined in a target lane reference line; the target lane reference line being a reference line of the target lane in which the vehicle will be located after the lane change;

[0009] The first lane change guidance path and the first lane change transition path are concatenated to obtain a first lane change planning path for the vehicle to change lanes to the target lane at a first time point.

[0010] In a second aspect, an embodiment of the present application further provides a path planning device, the device comprising:

[0011] a response module, configured to determine a first preview distance based on a vehicle speed at a first time point in response to the vehicle entering a lane change phase; the first time point being no earlier than the time when the vehicle enters the lane change phase;

[0012] an acquisition module, configured to acquire, from a first historical planned path, a path point of the vehicle at a first time point as a starting point of a first lane change guidance path at the first time point, and to acquire, from the first historical planned path, a point along a forward direction of the vehicle that is a first preview distance away from the starting point of the first lane change guidance path as an end point of the first lane change guidance path; the first historical planned path being a planned path determined for the vehicle at a time point prior to the first time point;

[0013] a first determining module, configured to construct a first lane change guidance path based on path points in the first historical planned path that are between a starting point and an end point of the first lane change guidance path;

[0014] a second determining module for determining a first lane change transition path at a first time point based on an end point of the first lane change guidance path and a first lane change entry point determined in a target lane reference line; the target lane reference line being a reference line of a target lane in which the vehicle will be located after the lane change;

[0015] The splicing module is used to splice the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at a first time point.

[0016] In a third aspect, an embodiment of the present application also provides a vehicle, comprising: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above method.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a program code executable by a processor, and when the program code is executed by the processor, the processor executes the above method.

[0018] The present application provides a path planning method, device, vehicle and computer-readable storage medium. In the present application, a first lane change guide path is constructed based on a first historical planned path, and a first lane change transition path is determined; the first lane change guide path and the first lane change transition path are spliced ​​to obtain a first lane change planning path for the vehicle to change lanes to a target lane. Since the first lane change guide path is based on the first historical planned path, the first lane change guide path matches the driving state of the vehicle when entering the lane change stage, and the first lane change guide path is more accurate. The first lane change planning path obtained by splicing the first lane change guide path and the first lane change transition path is more accurate. At the same time, the first lane change guide path matches the driving state of the vehicle when entering the lane change stage, so that when the vehicle changes lanes according to the first lane change planning path, the driving state of the vehicle will not suddenly change, thereby improving the vehicle's automatic driving experience.

[0019] Other features and advantages of the embodiments of the present application will be described in the following description and, in part, will become apparent from the description or be understood by practicing the embodiments of the present application. The objectives and other advantages of the embodiments of the present application can be achieved and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown.

[0022] Figure 2 A flow chart of a path planning method proposed according to an embodiment of the present application is shown.

[0023] Figure 3 A schematic diagram of a process for determining a first lane change guidance path in an embodiment of the present application is shown.

[0024] Figure 4 A schematic diagram of a first lane change planning path in an embodiment of the present application is shown.

[0025] Figure 5 A schematic diagram of a process for determining a first lane change planning path in an embodiment of the present application is shown.

[0026] Figure 6 A schematic diagram of a secondary optimization process of a first lane change planning path in an embodiment of the present application is shown.

[0027] Figure 7 Shown Figure 2 The steps after step S105 of the corresponding embodiment are in a flowchart of an embodiment.

[0028] Figure 8 A schematic diagram of a second lane change planning path in an embodiment of the present application is shown.

[0029] Figure 9 Shown Figure 2 The steps after step S105 of the corresponding embodiment are in the flowchart of another embodiment.

[0030] Figure 10 A schematic diagram of a lane changing process in an embodiment of the present application is shown.

[0031] Figure 11 A schematic diagram of a secondary optimization process of returning to a planned path in an embodiment of the present application is shown.

[0032] Figure 12 A structural block diagram of a path planning device proposed in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for which protection is claimed, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0034] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or 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 should not be understood as indicating or implying relative importance.

[0035] Reference Figure 1 , Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown, wherein the vehicle 100 includes an automatic driving system 110. The automatic driving system 110 may have multiple built-in automatic driving functions. The automatic driving system 110 controls the vehicle's automatic driving according to the built-in automatic driving functions. The automatic driving functions may include, for example, automatic lane changing functions and automatic parking functions.

[0036] The autonomous driving system 110 may include an on-board acquisition device 111 , one or more (only one is shown in the figure) processors 112 , and a memory 113 .

[0037] The vehicle-mounted acquisition device 111 is used to collect environmental information during the vehicle's driving process. The environmental information may include information about obstacles and lanes around the vehicle. The vehicle-mounted acquisition device 111 may be, for example, a high-definition camera or radar.

[0038] The processor 112 may be a microcontroller unit (MCU) having a built-in memory 113 . The memory 113 stores a program that can execute the contents of the following embodiments, and the processor 112 can execute the program stored in the memory 113 .

[0039] The processor 112 may include one or more processors. The processor 112 utilizes various interfaces and circuits to connect various components within the vehicle 100 and execute various functions and process data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 113 and accessing data stored in the memory 113.

[0040] The memory 113 may include a random access memory (RAM) or a read-only memory (ROM). The memory 15 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 15 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc.

[0041] See also Figure 2 , Figure 2 A flow chart of a path planning method proposed in one embodiment of the present application is shown, which is used for a vehicle. The method includes:

[0042] S101 : In response to a vehicle entering a lane change phase, determining a first preview distance according to a vehicle speed at a first time point.

[0043] The first time point is no earlier than the moment when the vehicle enters the lane changing phase.

[0044] In this application, the vehicle can be an electric vehicle or a fuel vehicle, or it can be a car, SUV, bus, truck, etc.

[0045] In this application, the vehicle's driving process may include a lane change phase, a following phase, and a lane change return phase. The lane change phase refers to the phase where the vehicle needs to change lanes from its original lane to the target lane. The following phase refers to the phase where the vehicle needs to follow the vehicle ahead in the original lane. The lane change return phase may refer to the phase where the vehicle changes lanes to the target lane and then changes back to the original lane within a short period of time, or returns to the original lane if the lane change to the target lane fails. The lane change failure may be caused by a vehicle entering the target lane, a deceleration of the vehicle ahead in the target lane, etc.

[0046] The vehicle may enter the lane change phase when it receives a lane change instruction or lane change operation from the user. For example, the driver turns on the turn signal to confirm that the vehicle enters the lane change phase. Another example is when the driver says "change lane to the left" or "change lane to the right" by voice to confirm that the vehicle enters the lane change phase.

[0047] In another embodiment, the vehicle may be in an automatic driving state, and the vehicle determines that the vehicle needs to change lanes based on surrounding environmental information. At this time, the vehicle enters the lane changing phase.

[0048] In some embodiments, the vehicle may plan a planned path based on surrounding environmental information, and the vehicle may automatically drive along the planned path. Then, while the vehicle is automatically driving along the planned path, in response to the vehicle entering a lane change phase, S101 is executed. Alternatively, after obtaining the planned path, the driver may drive the vehicle along the planned path and, in response to the vehicle entering a lane change phase, S101 is executed. The planned path generally includes multiple path points, and the curve formed by connecting the multiple path points is the planned path.

[0049] The first time point can be any time point no earlier than the moment the vehicle enters the lane change phase. Generally speaking, during driving, the vehicle determines a planned path based on collected environmental information according to set planned time points (the time intervals between adjacent planned time points can be the same, for example, 0.1 seconds). After the vehicle enters the lane change phase, the first planned time point reached is used as the first time point. Alternatively, the moment the vehicle enters the lane change phase can be used as the first time point.

[0050] It is worth mentioning that after the vehicle enters the lane changing stage, when each planned time point is arrived, the planned time point can be used as the first time point to execute the path planning method of this application, that is, during the vehicle driving process, different first time points determine the corresponding first lane change planning path.

[0051] After the vehicle enters the lane change phase, the vehicle's real-time speed at the first time point is obtained as the vehicle speed in S101. After determining the vehicle speed, the preview distance can be determined based on the vehicle speed. Specifically, the preview distance can be calculated as the product of the vehicle speed and the corresponding preview duration.

[0052] The preview time refers to the time required for the vehicle to control the vehicle to perform the corresponding action according to the control instruction. Generally speaking, the preview time is related to the speed of the vehicle. Therefore, a mapping table can be set up, which includes the preview time corresponding to different vehicle speeds. After determining the speed of the vehicle, the preview time corresponding to the vehicle speed is determined according to the mapping table, and then the seedling raising distance is determined according to the vehicle speed and the corresponding preview time.

[0053] S102. Obtain a path point of the vehicle at the first time point from the first historical planned path as the starting point of the first lane change guidance path at the first time point, and obtain a point in the first historical planned path along the vehicle's forward direction that is a first preview distance away from the starting point of the first lane change guidance path as the end point of the first lane change guidance path.

[0054] The first historical planned path is a planned path determined for the vehicle at a time point before the first time point.

[0055] The moment before the first time point is regarded as a historical moment, and the planned path obtained by the vehicle according to the environmental information around the vehicle at the historical moment is regarded as a first historical planned path.

[0056] As mentioned above, a vehicle typically plans its path at regular intervals during driving, for example, planning a path every 0.1 seconds. Therefore, a planned path obtained at a time point immediately before and adjacent to the first time point can be determined as the first historical planned path. This first historical planned path corresponds to the moment closest to the first time point, has a high degree of consistency with the vehicle's state at the first time point, and therefore has a relatively high accuracy.

[0057] In the first historical planned path, a path point of the vehicle at the first time point is obtained as the starting point of the first lane change guidance path to be constructed. At the same time, a point whose distance from the starting point of the first lane change guidance path is a first preview distance in the forward direction of the vehicle is obtained from the first historical planned path as the end point of the first lane change guidance path.

[0058] S103: Construct a first lane change guidance path according to the path points in the first historical planned path that are between the starting point and the end point of the first lane change guidance path.

[0059] The starting point of the first lane change guidance path, the end point of the first lane change guidance path, and the path points in the first historical planned path located between the starting point and the end point of the first lane change guidance path can be obtained to construct a first point set, and then the path obtained by sequentially connecting the points in the first point set according to the extension direction of the first historical planned path is used as the first lane change guidance path.

[0060] In another embodiment, after obtaining the first point set, points can be inserted between any two adjacent points in the first point set to obtain a second point set, and the distance between any two adjacent points in the second point set is the same. Then, the path obtained by sequentially connecting the points in the second point set according to the extension direction of the first historical planned path is used as the first lane change guidance path.

[0061] Since the path points in the first historical planned path are distributed at equal time intervals, the intervals between path points are different for different vehicle speeds. Therefore, the intervals between any two adjacent points in the first point set are different. Points are inserted between any two adjacent points to obtain a second point set. The points in the second point set are distributed at equal intervals, making the first lane change guidance path constructed based on the points in the second point set more accurate.

[0062] For the convenience of calculation, in this application, any path point (x_global, y_global) on the first historical planned path is transferred to the vehicle coordinate system of the vehicle at the first time point, and the corresponding mapping path point (x_body, y_body) of each path point in the first historical planned path is obtained; then the point on the mapping path point (x_body, y_body) is projected onto the target lane reference line of the target lane through the reference line (equivalent to projecting the first historical planned path onto the SL coordinate system with the target lane reference line as the s-axis, and the origin of the SL coordinate system can be arbitrarily The projected path points (s, l) are obtained. The projected path points (start_s, start_l) at the first time point are determined as the starting point of the first lane change guidance path, and the target projected path point (start_s, extend_s) is determined as the end point of the first lane change guidance path. The projected path points between the projected points s = [start_s, extend_s) are intercepted from the projected path points to form a first point set. These points are interpolated at preset intervals (e.g., every 1 meter) to obtain a second point set. The first lane change guidance path is then constructed based on this second point set. The lane reference line may refer to the centerline of the lane.

[0063] In this embodiment, the process of generating the lane change guidance path is as follows: Figure 3 As shown in the figure. A first preview distance is determined based on vehicle speed, and the first historical planned path is projected onto the target lane reference line to obtain a projected path (the projected path includes the aforementioned projected path points). Projected points are intercepted from the projected path points based on the first preview distance to obtain a first point set. Points are then inserted into the first point set at equal intervals to obtain a second point set. A curve is fitted based on the second point set to obtain the first lane change guidance path.

[0064] S104: Determine a first lane change transition path at a first time point according to the end point of the first lane change guidance path and a first lane change entry point determined in the target lane reference line.

[0065] The target lane reference line is the reference line of the target lane where the vehicle is located after changing lanes.

[0066] In this application, the planned lane change distance can be determined based on the vehicle's speed and standard lane change time at the first time point, and then a point on the target lane reference line whose distance from the current position of the vehicle at the first time point (referring to the distance along the center line of the original lane) is the planned lane change distance is determined as the first lane change entry point.

[0067] In some embodiments, a standard lane change distance can be determined based on the comparison between the planned lane change distance and the minimum lane change distance. A point on the target lane reference line whose distance from the vehicle's current position at the first time point (meaning the distance along the centerline of the original lane) is the standard lane change distance is then determined as the first lane change entry point. The minimum lane change distance can be set as required, for example, to 20 meters. Specifically, the smaller of the planned lane change distance and the minimum lane change distance can be used as the standard lane change distance.

[0068] The lane change process distance can also be determined based on the standard lane change slope and the standard lane width, and the first lane change entry point can be determined on the target lane reference line based on the lane change process distance. The standard lane width can be set based on demand, for example, the standard lane width is 3.75 meters.

[0069] In this application, a method for obtaining a standard lane change slope may include: determining a planned lane change distance based on the vehicle speed and the standard lane change duration; determining a standard lane change distance based on a comparison between the planned lane change distance and the minimum lane change distance; and determining a standard lane change slope based on the standard lane change distance and the standard lane width. Specifically, the ratio of the standard lane width to the standard lane change distance may be determined as the standard lane change slope; and correspondingly, the ratio of the standard lane width to the standard lane change slope may be determined as the lane change process distance.

[0070] Specifically, a point on the target lane reference line whose distance from the current position of the vehicle at the first time point (that is, the distance along the center line of the original lane) is the lane change process distance is determined as the first lane change entry point.

[0071] After determining the first lane change entry point, a curved path can be constructed as the first lane change transition path, with the endpoint of the first lane change guidance path as the starting point and the first lane change entry point as the endpoint of the first lane change transition path. Specifically, a quintic polynomial can be used to fit the starting point and endpoint of the first lane change transition path to obtain the first lane change transition path. The method for fitting the first lane change transition path is not limited to a quintic polynomial.

[0072] In the present application, the first lane change guidance path can be subjected to first-order and second-order derivatives, and the first-order and second-order derivative results can be retained. If the end point of the first lane change transition path is the coordinate in the sl coordinate system constructed with the target lane reference line as the s-axis in the aforementioned process, (the coordinate value of the end point of the first lane change transition path in the first direction, the coordinate value of the end point of the first lane change transition path in the second direction, the first-order derivative result corresponding to the end point of the first lane change transition path, and the second-order derivative result corresponding to the end point of the first lane change transition path) can be determined as the starting point of the quintic polynomial for fitting the first lane change transition path, and (the coordinate value of the end point of the first lane change transition path in the first direction + the lane change process distance value, 0, 0, 0) can be determined as the end point of the quintic polynomial for fitting the first lane change transition path. Then, the quintic polynomial is fitted according to the starting point and end point of the quintic polynomial to obtain the first lane change transition path.

[0073] At this time, the generated first lane change transition path is as follows Figure 4 As shown, 310 is the constructed first lane change guidance path, P1 is the starting point of the first lane change transition path (the end point of the first lane change guide path 310), P2 is the end point of the first lane change transition path, the curve 320 after fitting P1 and P is the first lane change transition path, 330 is the original lane reference line, and 340 is the target lane reference line.

[0074] S105 : Concatenate the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at a first time point.

[0075] Based on the above, it can be known that the end point of the first lane change guidance path is actually the starting point of the first lane change transition path. Therefore, the first lane change guidance path and the first lane change transition path can be directly spliced ​​at the starting point of the first lane change transition path to obtain the first lane change planning path for the vehicle to change lanes to the target lane at the first time point.

[0076] In another embodiment, a first reference line path can be generated, starting from the first lane change entry point, extending along the target lane reference line (extending in the forward direction of the vehicle). The first lane change guidance path, the first lane change transition path, and the first reference line path are then sequentially concatenated to obtain a first lane change planning path for the vehicle to change lanes to the target lane at the first time point. The length of the first reference line path can be set as required, for example, 6 meters.

[0077] like Figure 4 As shown, a first reference line path 350 is constructed with P2 as the starting point, and a path formed by splicing the first lane change guide path 310, the first lane change transition path 320 and the first reference line path 350 is used as the first lane change planning path.

[0078] The process of determining the first lane change planning path is as follows: Figure 5 As shown, a first lane change guide path, a first lane change transition path, and a first reference line path can be determined, and then the first lane change guide path, the first lane change transition path, and the first reference line path are spliced ​​to obtain a path as the first lane change planning path.

[0079] In some embodiments, S105 may include: splicing the first lane change guidance path and the first lane change transition path to obtain an initial lane change planning path for the vehicle to change lanes to the target lane at a first time point; performing secondary convex optimization on the initial lane change planning path; if the secondary convex optimization of the initial lane change planning path is successful, obtaining the initial lane change planning path after the secondary convex optimization as the first lane change planning path.

[0080] The end point of the first lane change guidance path can be directly used as the splicing point to splice the first lane change guidance path and the first lane change transition path to obtain the initial lane change planning path. The initial lane change planning path can be subjected to secondary convex optimization through the OSQP solver. If the secondary convex optimization of the initial lane change planning path is successful, the initial lane change planning path after the secondary convex optimization is obtained as the first lane change planning path.

[0081] If the secondary convex optimization of the initial lane change planning path fails and the first lane change guidance path is not re-optimized within the preset jump range and within the target duration after the start of the secondary convex optimization of the initial lane change planning path, the initial lane change planning path is obtained as the first lane change planning path. The preset jump range and target duration can be set based on actual needs and are not limited in this application. For example, the preset jump range is 0.5m and the target duration is 0.1s.

[0082] After the secondary convex optimization of the initial lane change planning path fails, if it is determined that the first lane change guidance path is outside the preset jump range, secondary planning is performed again. If the secondary convex optimization of the initial lane change planning path is successful, the initial lane change planning path after the secondary convex optimization is obtained as the first lane change planning path; wherein, the restriction range of the restriction parameters of the second secondary convex optimization is greater than the restriction range of the restriction parameters of the first secondary convex optimization; if the secondary convex optimization of the initial lane change planning path fails, the secondary convex optimization function of the initial lane change planning path is stopped, and a prompt message is output to remind the driver that there is a fault in the vehicle and the secondary convex optimization cannot be achieved.

[0083] In this application, the restriction range of the restriction parameters of the second quadratic convex optimization is greater than the restriction range of the restriction parameters of the first quadratic convex optimization, thereby making the success rate of the second quadratic convex optimization higher, increasing the possibility of the initial lane change planning path after the success of the secondary convex optimization as the lane change planning path, improving the accuracy of the lane change planning path, and improving the driving effect.

[0084] After the secondary convex optimization of the initial lane change planning path fails, if the initial lane change planning path is re-secondarily convexly optimized within the target time after the start time of the secondary convex optimization of the initial lane change planning path; determine whether the re-secondarily convex optimization of the initial lane change planning path is successful; if the secondary convex optimization of the initial lane change planning path is successful, obtain the initial lane change planning path after the re-secondarily convex optimization as the first lane change planning path; if the secondary convex optimization of the initial lane change planning path fails, stop the secondary convex optimization function of the initial lane change planning path, and output a prompt message to remind the driver that there is a fault in the vehicle and the secondary convex optimization cannot be achieved.

[0085] The quadratic convex optimization process in this embodiment is as follows Figure 6 As shown, the initial lane change planning path is determined, and then the initial lane change planning path is subjected to secondary convex optimization to determine whether the secondary convex optimization fails. If not, the initial lane change planning path after the secondary convex optimization is output as the first lane change planning path. If it fails, it is determined whether the first lane change guidance path is not re-secondarily convexly optimized within a preset jump range and within a target time length after the start time of the secondary convex optimization of the initial lane change planning path. If so, the initial lane change planning path is obtained as the first lane change planning path. If not, the secondary convex optimization is performed again.

[0086] Afterwards, it is determined whether the re-secondary convex optimization fails. If so, the secondary convex optimization function is exited. If not, the initial lane change planning path after the secondary convex optimization is obtained as the first lane change planning path.

[0087] It is worth mentioning that after the vehicle enters the lane changing stage, each time a planned time point is reached, the planned time point is taken as a first time point, and then the first lane changing planning path for the vehicle to change lanes to the target lane at the first time point is determined according to the aforementioned steps S104-S105, thereby realizing real-time planning of the first lane changing planning path at different times for the vehicle during the real-time lane changing process.

[0088] In this embodiment, based on the first historical planned path, a first lane change guide path is constructed, and a first lane change transition path is determined; the first lane change guide path and the first lane change transition path are spliced ​​to obtain a first lane change planning path for the vehicle to change lanes to the target lane. Since the first lane change guide path is based on the first historical planned path, the first lane change guide path fits the driving state of the vehicle when entering the lane change stage, and the first lane change guide path is more accurate. The first lane change planning path obtained by splicing the first lane change guide path and the first lane change transition path is more accurate. At the same time, the first lane change guide path fits the driving state of the vehicle when entering the lane change stage, so that when the vehicle changes lanes according to the first lane change planning path, the vehicle's driving state will not suddenly change, thereby improving the vehicle's automatic driving experience.

[0089] At the same time, in this embodiment, secondary convex optimization is also performed to further improve the accuracy of the first lane change planning path, so that when the vehicle travels according to the first lane change planning path, the driving performance is higher and the safety is higher.

[0090] In one embodiment, if Figure 7 As shown, after S105, the method may further include:

[0091] S201. During a process of controlling a vehicle to change lanes according to a first lane change planning path, in response to a lane change width of the vehicle reaching a preset lane change width, determining a second preview distance based on a vehicle speed at a second time point.

[0092] The second time point is no earlier than the time when the width of the vehicle's completed lane change reaches the preset lane change width. The preset lane change width can be a width value set according to demand, which is usually no greater than the width of the original lane and the target lane.

[0093] After obtaining the first lane change planning path at each of the aforementioned first time points, the vehicle can be controlled to change lanes according to the first lane change planning path at the first time point when each first time point is reached.

[0094] The width of the lane change completed by the vehicle during the lane change process refers to the distance between the vehicle's current position and the original lane reference line.

[0095] The second time point may be any time point no earlier than the time when the vehicle's lane width reaches the preset lane change width during the lane change process. Generally speaking, the first planned time point reached after the vehicle's lane width reaches the preset lane change width during the lane change process is used as the second time point. Alternatively, the time when the vehicle's lane width reaches the preset lane change width during the lane change process may be used as the second time point.

[0096] It is worth mentioning that after the vehicle has completed the lane change and the width reaches the preset lane change width during the lane change process, when each planned time point is arrived, the planned time point can be used as the second time point to execute the path planning method of this application, that is, during the vehicle driving process, different second time points determine the corresponding second lane change planning path.

[0097] The speed of the vehicle at the second time point may be determined, and then the preview duration corresponding to the speed of the vehicle at the second time point may be determined, and the second preview distance may be determined based on the speed of the vehicle at the second time point and the corresponding preview duration.

[0098] S202. Obtain a path point of the vehicle at the second time point from the second historical planned path as the starting point of the second lane change guidance path at the second time point, and obtain a point from the second historical planned path along the vehicle's forward direction that is a second preview distance away from the starting point of the second lane change guidance path as the end point of the second lane change guidance path.

[0099] The second planned path is a planned path determined for the vehicle at a time point before the second time point.

[0100] As mentioned above, a vehicle typically plans its path at regular intervals during driving, for example, planning a path every 0.1 seconds. Therefore, a planned path obtained at a planned time point immediately before and adjacent to the second time point (typically one of the first time points during the lane change process) can be determined as the second historical planned path. This second historical planned path corresponds to the moment closest to the second time point, has a high degree of consistency with the vehicle's state at the second time point, and therefore has a relatively high accuracy.

[0101] In the second historical planned path, a path point of the vehicle at the second time point is obtained as the starting point of the second lane change guidance path to be constructed. At the same time, a point whose distance from the starting point of the second lane change guidance path is a second preview distance in the vehicle's forward direction is obtained from the second historical planned path as the end point of the second lane change guidance path.

[0102] S203: Construct a second lane change guidance path according to the path points in the second historical planned path that are between the starting point and the end point of the second lane change guidance path.

[0103] The starting point of the second lane change guidance path, the end point of the second lane change guidance path, and the path points in the second historical planned path located between the starting point and the end point of the second lane change guidance path can be obtained to construct a third point set, and then the path obtained by connecting the various points in the third point set in sequence according to the extension direction of the second historical planned path is used as the second lane change guidance path.

[0104] In another embodiment, after obtaining the third point set, points may be interpolated between any two adjacent points in the third point set to obtain a fourth point set, where the spacing between any two adjacent points in the fourth point set is the same. The path obtained by sequentially connecting the points in the fourth point set along the extension direction of the second historical planned path serves as the second lane change guidance path. The method for fitting the second lane change transition path is not limited to a quintic polynomial.

[0105] Since the path points in the second historical planning path are distributed at equal time intervals, the intervals between path points are different for different vehicle speeds. Therefore, the intervals between any two adjacent points in the third point set are different. Points are inserted between any two adjacent points to obtain a fourth point set. The points in the fourth point set are distributed at equal intervals, making the second lane change guidance path constructed based on the points in the third point set more accurate.

[0106] S204: Adjust the standard lane change slope based on a preset slope adjustment rate and the remaining lane change width of the vehicle at the second time point to obtain a target lane change slope at the second time point; and determine the remaining lane change distance at the second time point based on the target lane change slope and the remaining lane change width.

[0107] The target lane change slope is smaller than the standard lane change slope, and the preset slope adjustment rate may also be a value set based on demand, for example, 1 / 3.

[0108] Based on the foregoing, it can be known that the second time point may include multiple second time points, and for each second time point, a target lane change slope at the second time point may be determined.

[0109] Specifically, in this application, the target lane change slope can be calculated according to Formula 1, which is as follows:

[0110]

[0111] Among them, k1 is the target lane change slope, k ratio is the slope adjustment rate, l0 is the remaining lane change width, l t is the standard lane width, and k0 is the standard lane change slope.

[0112] Among them, the remaining lane change width of the vehicle at the second time point is the distance between the position of the vehicle at the second time point and the target lane reference line. At this time, the ratio of the remaining lane change width to the target lane change slope can be calculated as the remaining lane change distance.

[0113] S205: Determine a second lane change entry point on the target lane reference line according to the remaining lane change distance.

[0114] In this application, the point in the target lane reference line whose distance from the current position of the vehicle at the second time point (referring to the distance along the center line of the original lane) is the remaining lane change distance can be determined as the second lane change entry point.

[0115] In some embodiments, S205 may further include: determining an adjusted distance at a second time point based on a preset extended distance, the standard lane width, and the remaining lane change width; determining a corrected remaining lane change distance based on the adjusted distance and the remaining lane change distance; and determining a second lane change entry point on the target lane reference line based on the corrected remaining lane change distance. The extended distance may be a value set based on demand and is not limited in this application. For example, the extended distance may be 1 meter.

[0116] An adjustment distance can be determined based on a preset extension distance, a standard lane width, and a remaining lane change width. The adjustment distance is used to increase the distance traveled during the lane change process. The sum of the adjustment distance and the remaining lane change distance is then calculated as the corrected remaining lane change distance. A point in the target lane reference line whose distance from the current position of the vehicle at the second time point (referring to the distance along the center line of the original lane) is the corrected remaining lane change distance and is then determined as the second lane change entry point.

[0117] Specifically, the adjustment distance may be determined according to Formula 2, which is as follows:

[0118]

[0119] Among them, s t To adjust the distance, s y To extend the distance.

[0120] S206. Determine a second lane change transition path at a second time point based on the endpoint of the second lane change guidance path and the second lane change entry point; and concatenate the second lane change guidance path and the second lane change transition path to obtain a second lane change planning path for the vehicle to change lanes to the target lane at the second time point.

[0121] After determining the second lane change entry point, a curved path can be constructed as the second lane change transition path, with the endpoint of the second lane change guidance path as the starting point and the second lane change entry point as the end point. Specifically, a quintic polynomial can be used to fit the start and end points of the second lane change transition path to obtain the second lane change transition path.

[0122] After obtaining the second lane change transition path, a second reference line path can be generated, starting from the second lane change entry point and extending along the target lane reference line (in the forward direction of the vehicle). The second lane change guidance path, the second lane change transition path, and the second reference line path are then sequentially concatenated to obtain a second lane change planning path for the vehicle to change lanes to the target lane at the second time point. The length of the second reference line path can be set as needed, for example, 6 meters.

[0123] like Figure 8As shown, 501 is a first lane change planning path generated at a first time point according to the aforementioned steps S101-S105, 51 is the original lane reference line, and 52 is the target lane reference line. 5011 is the starting point of the first lane change transition path in the first lane change planning path 501, and 5012 is the end point of the first lane change transition path in the first lane change planning path 501. The slope of the straight line 5013 formed by 5011 and 5012 is the standard lane change slope.

[0124] At the first second time point after the vehicle has completed the lane change and the width reaches the preset lane change width, the current position of the vehicle is 502, and then the second lane change entry point 503 is determined based on the above-mentioned S201-S206 method, wherein 504 refers to the midpoint of the remaining lane change distance whose distance from the current position 502 (the distance along the center line of the lane) is the midpoint. At this time, the slope of the straight line 505 between the midpoint 504 and the current position 502 is the target lane change slope, and the distance between the midpoint 504 and the corrected lane change entry point 503 is also the adjustment distance. At this time, the second lane change planning path 506 fitted according to the current position 502 and the second lane change entry point 503, compared with the original lane change planning path 501, the slope of the straight line 507 between the current position 502 and the second lane change entry point 503 in the second lane change planning path 506 is less than the slope of 505.

[0125] It is worth mentioning that after the width of the vehicle's completed lane change reaches the preset lane change width, each time a planned time point is reached, the planned time point is used as a second time point, and then the second lane change planning path for the vehicle to change lanes to the target lane at the second time point is determined according to the aforementioned steps S201-S206, thereby realizing real-time planning of the second lane change planning path at different times for the vehicle during the real-time lane change process.

[0126] It can be understood that splicing the second lane change guide path and the second lane change transition path to obtain the second lane change planning path for the vehicle to change lanes to the target lane at the second time point may include: splicing the second lane change guide path and the second lane change transition path to obtain the lane change planning path to be optimized for the vehicle to change lanes to the target lane at the second time point; performing secondary convex optimization on the lane change planning path to be optimized; if the secondary convex optimization of the lane change planning path to be optimized is successful, obtaining the lane change planning path to be optimized after the secondary convex optimization as the second lane change planning path.

[0127] If the secondary convex optimization of the lane change planning path to be optimized fails, the second lane change guidance path is within the preset jump range, and the second convex optimization is not performed again within the target time after the start time of the secondary convex optimization of the lane change planning path to be optimized, the initial lane change planning path is obtained as the second lane change planning path;

[0128] After the secondary convex optimization of the lane change planning path to be optimized fails, if it is determined that the second lane change guidance path is outside the preset jump range, re-performing the secondary planning, and if the secondary convex optimization of the lane change planning path to be optimized succeeds, obtaining the lane change planning path to be optimized after the secondary convex optimization as the second lane change planning path; wherein the restriction range of the restriction parameter of the second secondary convex optimization is greater than the restriction range of the restriction parameter of the second secondary convex optimization;

[0129] After the secondary convex optimization of the lane change planning path to be optimized fails, if the lane change planning path to be optimized is re-secondarily convexly optimized within the target time after the start time of the secondary convex optimization of the lane change planning path to be optimized; determine whether the re-secondarily convex optimization of the lane change planning path to be optimized is successful; if the re-secondarily convex optimization of the lane change planning path to be optimized is successful, obtain the lane change planning path to be optimized after the re-secondarily convex optimization as the second lane change planning path.

[0130] In this embodiment, during vehicle driving, after the lane change width reaches the preset lane change width, the standard lane change slope is corrected to reduce the standard lane change slope to obtain a target lane change slope. Then, a corrected lane change entry point is determined based on the target lane change slope. The corrected lane change entry point is further back than the original lane change entry point, so that the obtained corrected lane change transition path is smoother. Therefore, when the vehicle is controlled according to the corrected lane change planning path obtained according to the corrected lane change transition path, the direction of the vehicle changes less, the user experience is better, and the safety is higher.

[0131] At the same time, after correcting the standard lane change slope to the target lane change slope, the adjustment distance is also increased so that the corrected lane change entry point is further back than the original lane change entry point, making the corrected lane change transition path smoother. As a result, when the vehicle is controlled according to the corrected lane change planning path obtained by the corrected lane change transition path, the direction of the vehicle changes less, the user experience is better, and the safety is higher.

[0132] like Figure 9 As shown, after step S105, the method further includes:

[0133] S301. During a process of controlling a vehicle to change lanes according to a first planned lane change path, in response to exiting a lane change phase, determine a third preview distance based on a speed of the vehicle at a third time point.

[0134] The third time point is no earlier than the moment when the vehicle exits the lane change phase;

[0135] After obtaining the first lane change planning path, the first lane change planning path for each of the aforementioned first time points can be obtained, and then the vehicle can be controlled to change lanes according to the first lane change planning path for the first time point when each first time point is reached.

[0136] During the process of the vehicle changing lanes according to the first lane change planning path, if the driver receives a command to return to the original lane or the vehicle itself determines that it needs to return to the original lane based on environmental information, it determines to exit the lane change phase, and the vehicle responds to exit the lane change phase.

[0137] The third time point is any time point no earlier than the moment when the vehicle exits the lane change phase. Generally speaking, the first planned time point reached after the vehicle exits the lane change phase is used as the third time point. Alternatively, the moment when the vehicle exits the lane change phase can be used as the third time point.

[0138] It is worth mentioning that after the vehicle exits the lane change phase, when each planned time point is arrived, the planned time point can be used as the third time point to execute the path planning method of this application, that is, during the vehicle driving process, different third time points determine the corresponding return planned path.

[0139] The speed of the vehicle at the third time point can be determined, and then the preview time corresponding to the speed of the vehicle at the third time point can be determined, and the third preview distance can be determined based on the speed of the vehicle at the third time point and the corresponding preview time.

[0140] S302. Obtain a path point of the vehicle at a third time point from the third historical planned path as the starting point of a third lane change guidance path at the third time point, and obtain a point from the third historical planned path along the vehicle's forward direction that is a third preview distance away from the starting point of the third lane change guidance path as the end point of the third lane change guidance path.

[0141] The third planned path is a planned path determined for the vehicle at a time point before the third time point.

[0142] As mentioned above, a vehicle typically plans its path at regular intervals during driving, for example, planning a path every 0.1 seconds. Therefore, a planned path obtained at a planned time point immediately before and adjacent to the third time point (typically one of the first time points during the lane change process) can be determined as the third historical planned path. This third historical planned path corresponds to the closest time point, closely matches the vehicle's state at the third time point, and therefore has a relatively high accuracy.

[0143] In the third historical planned path, a path point of the vehicle at a third time point is obtained as the starting point of a third lane change guidance path to be constructed. At the same time, a point whose distance from the starting point of the third lane change guidance path is a third preview distance is obtained from the third historical planned path along the vehicle's forward direction as the end point of the third lane change guidance path.

[0144] S303: Construct a third lane change guidance path according to the path points in the third historical planned path that are between the starting point and the end point of the third lane change guidance path.

[0145] The starting point of the third lane change guidance path, the end point of the third lane change guidance path, and the path points in the third historical planned path located between the starting point and the end point of the third lane change guidance path can be obtained to construct a fifth point set, and then the path obtained by connecting the points in the fifth point set in sequence according to the extension direction of the third historical planned path is used as the third lane change guidance path.

[0146] In another embodiment, after obtaining the fifth point set, points may be interpolated between any two adjacent points in the fifth point set to obtain a sixth point set, where the spacing between any two adjacent points in the sixth point set is the same. The path obtained by sequentially connecting the points in the sixth point set along the extension direction of the third historical planned path serves as the third lane change guidance path. The method for fitting the third lane change transition path is not limited to a quintic polynomial.

[0147] Since the path points in the third historical planning path are distributed at equal time intervals, the intervals between path points are different for different vehicle speeds. Therefore, the intervals between any two adjacent points in the fifth point set are different. Points are inserted between any two adjacent points to obtain a sixth point set. The points in the sixth point set are distributed at equal intervals, making the third lane change guidance path constructed based on the points in the fifth point set more accurate.

[0148] S304: Determine a lane change return distance at a third time point based on the lane change width completed by the vehicle during the lane change process.

[0149] The lane change width completed by the vehicle during the lane change process is consistent with the lane change width required for the vehicle to return to the original lane. The ratio of the lane change width completed during the lane change process to the standard lane change slope can be calculated as the lane change return distance.

[0150] It is worth mentioning that the second time point may include multiple ones (as described above), and for each second time point, the lane change return distance at the third time point may be determined. The determined lane change return distances may be different for different second time points.

[0151] S305: Determine a lane-changing return entry point on the original lane reference line of the original lane where the vehicle was before the lane change based on the lane-changing return distance.

[0152] In this application, a point whose distance from the original lane reference line to the current position of the vehicle at the third time point (distance along the lane centerline) is the lane change return distance can be determined as the lane change return entry point.

[0153] In another embodiment, a point whose distance from the end point of the third lane change guidance path (distance along the lane centerline) is the lane change return distance can be determined from the original lane reference line as the lane change return entry point.

[0154] S306. Construct a straight path based on the endpoint of the third lane change guidance path and the lane change return entry point as the third lane change transition path at the third time point; and concatenate the third lane change guidance path and the third lane change transition path to obtain a return planned path for the vehicle to return to the original lane.

[0155] A straight line connecting the end point of the third lane change guidance path and the lane change return entry point can be directly constructed to obtain a straight line path as the third lane change transition path. Then, the end point of the third lane change guidance path is used as the splicing point to splice the third lane change guidance path and the third lane change transition path to obtain the return planned path.

[0156] In one embodiment, a third reference line path can be generated, starting from the lane change return entry point, extending along the original lane reference line (in the forward direction of the vehicle). The third lane change guidance path, the third lane change transition path, and the third reference line path are then sequentially concatenated to obtain a planned return path for the vehicle to return to the original lane. The length of the third reference line path can be set as needed, for example, 6 meters.

[0157] After obtaining the planned return path, the vehicle can be controlled to return to its original lane according to the planned return path. It is worth noting that after the vehicle exits the lane change phase, each planned time point is used as a third time point. The planned return path for the vehicle to return to its original lane at that third time point is then determined according to the aforementioned steps S301-S306. This allows for real-time planning of return paths at different times during the vehicle's real-time lane change process.

[0158] The lane changing process of this embodiment is as follows Figure 10 As shown, a lane change guidance path is determined based on the first historical planned path, a standard lane change slope is determined based on the standard lane width and the standard lane change distance, and a first lane change planning path is constructed based on the standard lane change slope and the first lane change guidance path; and vehicle driving is controlled based on the first lane change planning path.

[0159] If the vehicle state is the vehicle exiting the lane change phase, a third lane change transition path is generated as a straight line, and then a return planned path is obtained by splicing the third lane change transition path.

[0160] If the vehicle status is that the width of the lane change completed by the vehicle reaches the preset lane change width, the target lane change slope and adjustment distance are determined according to the slope adjustment rate and the extension distance, and the second lane change transition path is determined according to the target lane change slope and the adjustment distance. The second lane change planning path is obtained by splicing the second lane change transition paths.

[0161] It is worth mentioning that in this embodiment, after obtaining the return planning path, a secondary convex optimization can also be performed on the return planning path. If the secondary convex optimization of the return planning path is successful, the return planning path after the secondary convex optimization is obtained as the optimized return planning path. This allows the vehicle to return to the original lane according to the optimized return planning path.

[0162] If the quadratic convex optimization of the return planning path fails, the return planning path is re-quadratically convexly optimized; wherein, the restriction range of the restriction parameters of the second quadratic convex optimization here is greater than the restriction range of the restriction parameters of the first quadratic convex optimization; if the re-quadratically convex optimization of the return planning path is successful, the return planning path after the re-quadratically convex optimization is obtained as the optimized return planning path; if the re-quadratically convex optimization of the return planning path fails, the quadratic convex optimization function of the return planning path is stopped, and a prompt message is output to remind the driver that there is a fault in the vehicle and the quadratic convex optimization cannot be achieved.

[0163] The secondary optimization process of returning the planned path is as follows Figure 11 As shown, the return planning path is determined, and then the return planning path is subjected to secondary convex optimization to determine whether the secondary convex optimization fails. If it does not fail, the return planning path after the secondary convex optimization is output as the optimized return planning path; if it fails, the secondary convex optimization is performed again.

[0164] Afterwards, it is determined whether the re-quadratic convex optimization fails. If so, the quadratic convex optimization function is exited. If not, the return planning path after the re-quadratic convex optimization is obtained as the optimized return planning path.

[0165] In this embodiment, when it is necessary to return to the original lane, the lane change return transition path is fitted in a straight line, so that the accuracy of the lane change return transition path is higher, and the accuracy of the return planned path for returning to the original lane is higher. The vehicle is safer when returning to the original lane according to the lane change return transition path.

[0166] See attached Figure 12 , Figure 12 The following is a block diagram of a path planning device according to an embodiment of the present application. The device 1200 includes:

[0167] A response module 1210 is configured to determine a first preview distance based on the vehicle's speed at a first time point in response to the vehicle entering a lane change phase; the first time point being no earlier than the time when the vehicle enters the lane change phase;

[0168] An acquisition module 1220 is configured to acquire, from the first historical planned path, a path point of the vehicle at a first time point as a starting point of a first lane change guidance path at the first time point, and acquire, from the first historical planned path, a point that is a first preview distance away from the starting point of the first lane change guidance path in the vehicle's forward direction as an end point of the first lane change guidance path; the first historical planned path is a planned path determined for the vehicle at a time point prior to the first time point;

[0169] A first determining module 1230 is configured to construct a first lane change guidance path based on path points in the first historical planned path that are between a starting point and an end point of the first lane change guidance path;

[0170] A second determining module 1240 is configured to determine a first lane change transition path at a first time point based on an end point of the first lane change guidance path and a first lane change entry point determined in a target lane reference line; the target lane reference line is a reference line of a target lane in which the vehicle will be located after the lane change;

[0171] The splicing module 1250 is configured to splice the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at a first time point.

[0172] Optionally, the device further includes a re-planning module for determining a second preview distance according to the vehicle's speed at a second time point in response to the width of the vehicle's completed lane change reaching a preset lane change width during the process of controlling the vehicle to change lanes according to the first lane change planning path; the second time point is no earlier than the moment when the width of the vehicle's completed lane change reaches the preset lane change width; obtaining a path point of the vehicle at the second time point from the second historical planning path as the starting point of a second lane change guidance path at the second time point, and obtaining a point from the second historical planning path along the vehicle's forward direction whose distance from the starting point of the second lane change guidance path is the second preview distance as the end point of the second lane change guidance path; the second planned path is a planned path determined for the vehicle at a time point before the second time point; according to the second historical planning path A second lane change guidance path is constructed based on a path point between a starting point and an end point of the second lane change guidance path; the standard lane change slope is adjusted according to a preset slope adjustment rate and a remaining lane change width of the vehicle at the second time point to obtain a target lane change slope at the second time point; the target lane change slope is less than the standard lane change slope; the remaining lane change distance at the second time point is determined according to the target lane change slope and the remaining lane change width; a second lane change entry point is determined in a target lane reference line according to the remaining lane change distance; a second lane change transition path at the second time point is determined according to the end point and the second lane change entry point in the second lane change guidance path; the second lane change guidance path and the second lane change transition path are spliced ​​to obtain a second lane change planning path for the vehicle to change lanes to the target lane at the second time point.

[0173] Optionally, the re-planning module is also used to determine the adjusted distance at a second time point based on a preset extension distance, a standard lane width, and a remaining lane change width; determine a corrected remaining lane change distance based on the adjusted distance and the remaining lane change distance; and determine a second lane change entry point in the target lane reference line based on the corrected remaining lane change distance.

[0174] Optionally, the device also includes a slope acquisition module, which is used to determine the planned lane change distance based on the vehicle speed and the standard lane change time; determine the standard lane change distance based on the comparison result between the planned lane change distance and the minimum lane change distance; and determine the standard lane change slope based on the standard lane change distance and the standard lane width.

[0175] Optionally, the re-planning module is further used to determine a third preview distance according to the speed of the vehicle at a third time point in response to exiting the lane change phase during the process of controlling the vehicle to change lanes according to the first lane change planning path; the third time point is no earlier than the moment when the vehicle exits the lane change phase; obtain the path point of the vehicle at the third time point from the third historical planning path as the starting point of the third lane change guidance path at the third time point, and obtain a point from the third historical planning path along the forward direction of the vehicle with a distance from the starting point of the third lane change guidance path being the third preview distance as the end point of the third lane change guidance path; the third planning path is determined for the vehicle at a time point before the third time point a planned path; constructing a third lane change guidance path based on the path points between the starting point and the end point of the third lane change guidance path in the third historical planned path; determining a lane change return distance at a third time point based on the lane change width that the vehicle has completed during the lane change process; determining a lane change return entry point on the original lane reference line of the original lane in which the vehicle was located before the lane change based on the lane change return distance; constructing a straight path as the third lane change transition path at the third time point based on the end point and the lane change return entry point of the third lane change guidance path; and concatenating the third lane change guide path and the third lane change transition path to obtain a return planned path for the vehicle to return to the original lane.

[0176] Optionally, the splicing module 1250 is further used to splice the first lane change guidance path and the first lane change transition path to obtain an initial lane change planning path for the vehicle to change lanes to the target lane at the first time point; perform secondary convex optimization on the initial lane change planning path; if the secondary convex optimization of the initial lane change planning path is successful, obtain the initial lane change planning path after the secondary convex optimization as the first lane change planning path.

[0177] Optionally, the splicing module 1250 is further used to obtain the initial lane change planning path as the first lane change planning path if the secondary convex optimization of the initial lane change planning path fails, the first lane change guidance path is within a preset jump range, and the initial lane change planning path is not re-secondarily convexly optimized within a target time period after the start time of the secondary convex optimization; after the secondary convex optimization of the initial lane change planning path fails, if it is determined that the first lane change guidance path is outside the preset jump range, re-secondary planning is performed; if the initial lane change planning path is successfully re-secondarily convexly optimized, the initial lane change planning path after the re-secondarily convex optimization is obtained as the first lane change planning path; wherein, the restriction range of the restriction parameter of the second secondary convex optimization is greater than the restriction range of the restriction parameter of the first secondary convex optimization; after the secondary convex optimization of the initial lane change planning path fails, if the initial lane change planning path is re-secondarily convexly optimized within the target time period after the start time of the secondary convex optimization of the initial lane change planning path; determine whether the re-secondarily convex optimization of the initial lane change planning path is successful; if the re-secondarily convex optimization of the initial lane change planning path is successful, obtain the initial lane change planning path after the re-secondarily convex optimization as the first lane change planning path.

[0178] In several embodiments provided in this application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0179] In addition, the functional modules in the various embodiments of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or software functional modules.

[0180] On the other hand, the present application also provides a computer-readable storage medium, which stores program code. The program code can be called by a processor to execute the method described in the above method embodiment.

[0181] The computer-readable storage medium can be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk, or a cluster of ROMs. Alternatively, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program codes for executing any of the method steps of the above-described method. These program codes can be read from or written to one or more computer program products. The program codes can be compressed, for example, in a suitable form.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A path planning method, characterized in that: The method comprises: In response to the vehicle entering a lane change phase, determining a first preview distance based on the vehicle's speed at a first time point; the first time point being no earlier than the time when the vehicle enters the lane change phase; Obtaining a path point of the vehicle at the first time point from a first historical planned path as a starting point of a first lane change guidance path at the first time point, and obtaining a point in the first historical planned path that is a distance from the starting point of the first lane change guidance path along the vehicle's forward direction by the first preview distance as an end point of the first lane change guidance path; the first historical planned path is a planned path determined for the vehicle at a time point before the first time point; constructing the first lane change guidance path according to the path points in the first historical planned path that are between the starting point and the end point of the first lane change guidance path; determining a first lane change transition path at the first time point based on an end point of the first lane change guidance path and a first lane change entry point determined in a target lane reference line, wherein the target lane reference line is a reference line of the target lane in which the vehicle will be located after the lane change; The first lane change guidance path and the first lane change transition path are combined to obtain a first lane change planning path for the vehicle to change lanes to the target lane at the first time point.

2. The method according to claim 1, characterized in that After splicing the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at the first time point, the method further includes: During the process of controlling the vehicle to change lanes according to the first lane change planned path, in response to the width of the vehicle's completed lane change reaching a preset lane change width, determining a second preview distance based on the vehicle's speed at a second time point; the second time point being no earlier than the time when the width of the vehicle's completed lane change reaches the preset lane change width; obtaining, from the second historical planned path, a path point of the vehicle at the second time point as the starting point of a second lane change guidance path at the second time point, and obtaining, from the second historical planned path, a point along the vehicle's forward direction that is a distance from the starting point of the second lane change guidance path by a second preview distance as the end point of the second lane change guidance path; the second historical planned path is a planned path determined for the vehicle at a time point before the second time point; constructing the second lane change guidance path according to the path points between the starting point and the end point of the second lane change guidance path in the second historical planned path; adjusting the standard lane change slope according to a preset slope adjustment rate and a remaining lane change width of the vehicle at the second time point to obtain a target lane change slope at the second time point; the target lane change slope is less than the standard lane change slope; determining a remaining lane change distance at the second time point according to the target lane change slope and the remaining lane change width; determining a second lane change entry point on the target lane reference line according to the remaining lane change distance; determining a second lane change transition path at the second time point according to an end point in the second lane change guidance path and the second lane change entry point; The second lane change guidance path and the second lane change transition path are spliced ​​together to obtain a second lane change planning path for the vehicle to change lanes to the target lane at a second time point.

3. The method according to claim 2, characterized in that Determining a second lane change entry point on the target lane reference line according to the remaining lane change distance includes: determining an adjustment distance at the second time point according to a preset extension distance, a standard lane width, and the remaining lane change width; determining a corrected remaining lane change distance according to the adjusted distance and the remaining lane change distance; A second lane change entry point is determined in the target lane reference line according to the corrected remaining lane change distance.

4. The method according to claim 2, characterized in that The method for obtaining the standard lane change slope includes: Determining a planned lane change distance based on the vehicle's speed and a standard lane change time; determining a standard lane change distance based on a comparison result between the planned lane change distance and the minimum lane change distance; The standard lane change slope is determined according to the standard lane change distance and the standard lane width.

5. The method according to claim 1, wherein After splicing the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at a first time point, the method further includes: During the process of controlling the vehicle to change lanes according to the first lane change planned path, in response to exiting the lane change phase, determining a third preview distance based on the vehicle's speed at a third time point; the third time point is no earlier than the time when the vehicle exits the lane change phase; obtaining, from a third historical planned path, a path point of the vehicle at the third time point as a starting point of a third lane change guidance path at the third time point, and obtaining, from the third historical planned path, a point along the vehicle's forward direction that is a distance from the starting point of the third lane change guidance path by a third preview distance as an end point of the third lane change guidance path; the third historical planned path is a planned path determined for the vehicle at a time point before the third time point; constructing the third lane change guidance path according to the path points in the third historical planned path that are between the starting point and the end point of the third lane change guidance path; determining a lane change return distance at the third time point based on a lane change width completed by the vehicle during the lane change process; Determining a lane-changing return entry point on an original lane reference line of the original lane in which the vehicle was located before the lane change based on the lane-changing return distance; constructing a straight path as a third lane change transition path at the third time point according to the end point of the third lane change guidance path and the lane change return entry point; The third lane change guidance path and the third lane change transition path are spliced ​​together to obtain a return planning path for the vehicle to return to the original lane.

6. The method according to claim 1, wherein The step of combining the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at a first time point includes: splicing the first lane change guidance path and the first lane change transition path to obtain an initial lane change planning path for the vehicle to change lanes to the target lane at a first time point; performing a secondary convex optimization on the initial lane change planning path; If the secondary convex optimization of the initial lane change planning path is successful, the initial lane change planning path after the secondary convex optimization is obtained as the first lane change planning path.

7. The method according to claim 6, characterized in that The method further comprises: If the secondary convex optimization of the initial lane change planning path fails and the first lane change guidance path is within a preset jump range and is not re-secondarily convexly optimized within a target time period after the start time of the secondary convex optimization of the initial lane change planning path, obtaining the initial lane change planning path as the first lane change planning path; After the secondary convex optimization of the initial lane change planning path fails, if it is determined that the first lane change guidance path is outside a preset jump range, re-performing secondary planning; if the secondary convex optimization of the initial lane change planning path succeeds, obtaining the initial lane change planning path after the secondary convex optimization as the first lane change planning path; wherein the restriction range of the restriction parameter of the second secondary convex optimization is greater than the restriction range of the restriction parameter of the first secondary convex optimization; After the secondary convex optimization of the initial lane change planning path fails, if the initial lane change planning path is re-secondarily convexly optimized within a target time length after the start time of the secondary convex optimization of the initial lane change planning path; determine whether the re-secondarily convex optimization of the initial lane change planning path is successful; if the re-secondarily convex optimization of the initial lane change planning path is successful, obtain the initial lane change planning path after the re-secondarily convex optimization as the first lane change planning path.

8. A path planning device, characterized in that: The device comprises: a response module, configured to determine a first preview distance based on a speed of the vehicle at a first time point in response to the vehicle entering a lane change phase; the first time point being no earlier than a time when the vehicle enters the lane change phase; an acquisition module, configured to acquire, from a first historical planned path, a path point of the vehicle at the first time point as a starting point of a first lane change guidance path at the first time point, and to acquire, from the first historical planned path, a point along the vehicle's forward direction that is a distance from the starting point of the first lane change guidance path by a first preview distance as an end point of the first lane change guidance path; the first historical planned path is a planned path determined for the vehicle at a time point prior to the first time point; a first determining module, configured to construct the first lane change guidance path based on path points in the first historical planned path that are between a starting point and an end point of the first lane change guidance path; a second determining module, configured to determine a first lane change transition path at the first time point based on an end point of the first lane change guidance path and a first lane change entry point determined in a target lane reference line, wherein the target lane reference line is a reference line of a target lane in which the vehicle will be located after the lane change; A splicing module is configured to splice the first lane change guidance path and the first lane change transition path to obtain a first lane change planning path for the vehicle to change lanes to the target lane at the first time point.

9. A vehicle, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program codes executable by a processor, and when the program codes are executed by the processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images