Intersection turning track planning method and device, vehicle and storage medium

Abstract

The invention discloses an intersection turning track planning method and device, a vehicle and a storage medium, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining navigation map information, vehicle positioning information and vehicle sensing information which is used for representing environment information of a target intersection where the vehicle is located, the target intersection is the intersection of the current road of the vehicle; based on navigation map information, generating a first turning track corresponding to a target intersection, the navigation map information at least comprising information of a plurality of key points within a preset range of the target intersection; and adjusting the first turning track based on the navigation map information, the vehicle positioning information and the vehicle sensing information to obtain a second turning track. According to the method and the device, the vehicle can generate the first turning track at various turning intersections according to the navigation map information, and the proper second turning track is adjusted and obtained in combination with the vehicle sensing information, so that automatic turning passing of the vehicle at the intersections is realized, and the robustness of turning passing is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and more specifically, to a method, device, vehicle and computer-readable storage medium for planning a turning trajectory at an intersection. Background Art

[0002] With the development and application of intelligent driving systems in urban scenarios, autonomous driving technology also needs to adapt to various complex urban driving conditions, and turning at urban intersections is one of them. The working principle of turning at urban intersections is that the vehicle selects a turning lane before the intersection, and determines whether to turn based on the lane type and traffic light status information. During the turning process, the vehicle is controlled to complete the intersection turn and enter the corresponding lane based on the turning curvature information and lane line, curb boundary and other information provided by the navigation.

[0003] At present, most of the turning solutions used in autonomous driving systems still rely on high-precision maps to provide the information needed for turning behavior. Since the update of high-precision maps has a certain timeliness, it is easy to obtain erroneous data. Under the influence of erroneous data, it is difficult to complete the turn, which seriously affects the driving experience and safety. Summary of the invention

[0004] The present application proposes a method, device, vehicle and storage medium for intersection turning trajectory planning to improve the above-mentioned defects.

[0005] In a first aspect, an embodiment of the present application provides a method for planning a turning trajectory at an intersection, which is applied to a vehicle, and includes: obtaining navigation map information, vehicle positioning information, and vehicle perception information, wherein the vehicle perception information is used to characterize environmental information of a target intersection at which the vehicle is located, and the target intersection is an intersection to be turned on a road at which the vehicle is currently located; based on the navigation map information, generating a first turning trajectory corresponding to the target intersection, the navigation map information at least includes information on multiple key points within a preset range of the target intersection; based on the navigation map information, the vehicle positioning information, and the vehicle perception information, adjusting the first turning trajectory to obtain a second turning trajectory.

[0006] In the second aspect, an embodiment of the present application also provides a device for planning an intersection turning trajectory, which is applied to a vehicle and includes: an information acquisition module, used to acquire navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize environmental information of a target intersection where the vehicle is located, and the target intersection is a turning intersection on the road where the vehicle is currently located; a trajectory generation module, used to generate a first turning trajectory corresponding to the target intersection based on the navigation map information, wherein the navigation map information at least includes information on multiple key points within a preset range of the target intersection; a trajectory adjustment module, used to adjust the first turning trajectory based on the navigation map information, the vehicle positioning information and the vehicle perception information to obtain a second turning trajectory.

[0007] In a third aspect, an embodiment of the present application also provides a vehicle, comprising: a perception sensor, the perception sensor being used to obtain vehicle perception information; 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 applications are configured to execute the method as described above.

[0008] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program code executable by a processor, and when the program code is executed by the processor, the processor executes the above-mentioned method.

[0009] Therefore, the present application provides a method, device, vehicle and storage medium for planning a turning trajectory at an intersection. The method is applied to a vehicle, including: obtaining navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize the environmental information of the target intersection where the vehicle is located, and the target intersection is the intersection of the road where the vehicle is currently located; based on the navigation map information, generating a first turning trajectory corresponding to the target intersection, wherein the navigation map information at least includes information of multiple key points within a preset range of the target intersection; based on the navigation map information, the vehicle positioning information and the vehicle perception information, adjusting the first turning trajectory to obtain a second turning trajectory. Therefore, the present application generates a first turning trajectory for passing through the target intersection through the navigation map information, and, based on the first turning trajectory, adjusts the first turning trajectory using the navigation map information, the vehicle positioning information and the vehicle perception information to obtain a second turning trajectory that is more accurate and more in line with the actual traffic conditions of the road. Therefore, the method provided by the present application can generate a first turning trajectory according to the navigation map information at different turning intersections, and then adjust and obtain a suitable second turning trajectory in combination with the vehicle perception information, so as to realize the automatic turning passage of the vehicle at the intersection, and improve the robustness of turning passage in automatic driving.

[0010] Other features and advantages of the embodiments of the present application will be described in the subsequent description, and partly become apparent from the description, or can be understood by practicing the embodiments of the present application. The purposes and other advantages of the embodiments of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown.

[0013] Figure 2 A flow chart of a method for planning a turning trajectory at an intersection proposed in an embodiment of the present application is shown.

[0014] Figure 3 A schematic diagram showing a turning trajectory of a vehicle at a target intersection provided in an embodiment of the present application.

[0015] Figure 4 A flow chart of another intersection turning trajectory planning method provided in an embodiment of the present application is shown.

[0016] Figure 5 A flow chart of another intersection turning trajectory planning method provided in an embodiment of the present application is shown.

[0017] Figure 6 A structural block diagram of a turning trajectory planning device for an intersection proposed in one embodiment of the present application is shown.

[0018] Figure 7 A structural block diagram of a computer-readable storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] In order to make those skilled in the art better understand the present application scheme, the technical scheme in the present application embodiment will be clearly and completely described below in conjunction with the drawings in the present application embodiment. Obviously, the described embodiment is only a part of the present application embodiment, rather than all the embodiments. The components of the present application embodiment usually 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 present application for protection, but merely represents the selected embodiment 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 belong to the scope of protection of the present application.

[0020] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0021] See also Figure 1 , Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown, where the vehicle 100 includes a processor 111 , a memory 112 , and a perception sensor 113 .

[0022] The processor 111 may be a microcontroller unit (MCU), and the microcontroller unit has a built-in memory 112, and the memory 112 stores a program that can execute the contents of the following embodiments, and the processor 111 can execute the program stored in the memory 112. Furthermore, the processor 111 is connected to the cloud, and data can be exchanged between the processor 111 and the cloud, so that the relevant data obtained by the perception sensor 113 can be uploaded to the cloud for further processing, and the processor 111 can also receive information from the cloud to perform related operations.

[0023] Among them, the processor 111 may include one or more processing cores. The processor 111 uses various interfaces and lines to connect various parts of the entire vehicle 100, and executes various functions and processes data of the vehicle 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 112, and calling data stored in the memory 112. Optionally, the processor 111 can be implemented in at least one hardware form of a network processor (Neural network Processing Unit, NPU), a digital signal processing (Digital Signal Processing, DSP), a field programmable gate array (Field-Programmable Gate Array, FPGA), and a programmable logic array (Programmable Logic Array, PLA). The processor 111 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), a network processor (Neural network Processing Unit, NPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing display content; the NPU is responsible for processing multimedia data such as video and images; and the modem is used to process wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor 111, but may be implemented separately through a communication chip.

[0024] The memory 112 may include a random access memory (RAM), and may also include a read-only memory (RAM) and a double data rate synchronous dynamic random access memory (DDR). The memory 112 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 112 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 turning trajectory planning function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data (such as perception information) created by the vehicle 100 during use, etc.

[0025] The perception sensor 113 may include sensors such as an on-board camera and a millimeter-wave radar, which are used to detect and output perception information about lanes and intersections around the vehicle. For example, the on-board camera may include a front-view camera and a side-view camera, which are used to obtain real-time images around the vehicle and identify perception information such as lane line information, curb information, traffic light information, and front obstacle information from the image; the millimeter-wave radar may include a front millimeter-wave radar and a corner millimeter-wave radar, which are used to measure the distance between the vehicle and surrounding objects, thereby determining the specific location of the perception information in combination with the information obtained by the camera.

[0026] See also Figure 2 , Figure 2 A method flow chart of a method for planning a turning trajectory at an intersection provided by an embodiment of the present application is shown. The method can be applied to Figure 1 In the vehicle shown, specifically, the method comprises the following steps:

[0027] S110: Obtain navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize environmental information of a target intersection where the vehicle is located, and the target intersection is a turning intersection on a road where the vehicle is currently located.

[0028] As an implementation method, the navigation map information can be obtained based on SD (Standard Definition) Map, a standard definition navigation map. Generally speaking, SD navigation stores road-level elements with a resolution of about 5m-10m. Further, after the driver sets the navigation starting point and navigation destination, the SD navigation can generate a navigation route based on the navigation starting point and navigation destination, thereby obtaining all intersections that require turning in the route based on the navigation route as intersections to be turned. Therefore, the navigation map information may include: lane information, intersection turn signals, intersection turn action signals and turning key point information, wherein the lane information refers to the lane attributes of each lane related to the intersection to be turned output by the navigation map, so that the lane that can be used for turning before the intersection to be turned, and the lane to be entered after the turning behavior is completed at the intersection to be turned can be obtained based on the lane information; the intersection turn signal refers to the signal issued in advance by the navigation map before the vehicle arrives at the intersection to be turned to prompt that the intersection ahead can turn left or right. Generally speaking, when the intersection turn signal is issued The vehicle is far away from the stop line of the intersection to be turned, where the stop line of the intersection to be turned may refer to the stop line corresponding to the lane before entering the intersection to be turned; the intersection turning action signal refers to the turning action command signal issued by the navigation map when the vehicle arrives at the intersection to be turned. Generally speaking, the vehicle is close to the stop line of the intersection to be turned when the intersection turning action signal is issued; the key point refers to the key point that provides route decision-making during the process of the vehicle turning at the intersection to be turned. If the intersection to be turned of the road where the vehicle is currently located is taken as the target intersection, the turning key point information refers to the information of multiple key points within a preset range of the target intersection.

[0029] As an implementation method, the vehicle positioning information can be obtained based on the vehicle's global positioning system (GPS) to locate the specific position of the vehicle. It is understandable that based on the vehicle positioning information, the specific position of the vehicle during the entire driving process and the specific lane it is in can be obtained, thereby providing a certain position reference for the turning trajectory planning process.

[0030] As an implementation method, vehicle perception information can be obtained based on perception sensors carried on the vehicle. Specifically, the perception sensors can include sensors such as cameras, laser radars, or millimeter-wave radars. The cameras are used to capture images of the vehicle's surrounding environment, and the laser radars or millimeter-wave radars are used to detect the distance between the vehicle and objects around the vehicle. Thus, the perception sensors can obtain information about the turning intersection where the vehicle is located in real time and accurately. Therefore, the turning intersection of the road where the vehicle is currently located is taken as the target intersection, and the vehicle perception information can be used to characterize the environmental information of the target intersection. Furthermore, the vehicle perception information can include: the target intersection and objects such as lane lines, stop lines, zebra crossings, curbs, obstacles, traffic lights, ground signs, etc. around the target intersection, as well as the relative position information between the above objects and the vehicle.

[0031] As an implementation method, navigation map information, vehicle positioning information and vehicle perception information can be continuously acquired at preset time intervals to ensure that the latest navigation map information, vehicle positioning information and vehicle perception information can be obtained during vehicle driving, especially to enable the vehicle perception information to reflect the latest road conditions around the vehicle, thereby ensuring that the planned turning trajectory can be adjusted based on the latest vehicle perception information in subsequent methods.

[0032] S120: Based on the navigation map information, a first turning trajectory corresponding to the target intersection is generated, wherein the navigation map information at least includes information of a plurality of key points within a preset range of the target intersection.

[0033] As an implementation mode, according to the description of the navigation map information in step S110, the navigation map information at least includes turning key point information, i.e., information of multiple key points within a preset range of the target intersection. Therefore, based on the turning key point information related to the target intersection in the navigation map information, a first turning trajectory corresponding to the target intersection can be generated. Further, the navigation map information can also include lane information, intersection turning signals, intersection turning action signals, etc. Therefore, it is also possible to combine the lane information and intersection turning signals in the navigation map information to determine whether the target intersection has turning conditions. Then, before the vehicle reaches the target intersection, it is known that the vehicle needs to perform a turning behavior at the target intersection. Then, according to the intersection turning action signal in the navigation map information, it is known that at the moment when the navigation map sends the intersection turning action signal, the vehicle is close to the stop line of the target intersection. Then, based on the turning key point information related to the target intersection in the navigation map information, a first turning trajectory corresponding to the target intersection can be generated.

[0034] As an implementation, a method for generating a first turning trajectory corresponding to a target intersection based on navigation map information may be: before the vehicle is about to reach the stop line position of the target intersection, generating the first turning trajectory according to turning key point information in the navigation map information.

[0035] Specifically, information of multiple key points within a preset range of the target intersection can be obtained according to navigation map information, wherein the key points can refer to road intersections, the starting point and the end point of the road, and a series of points used to describe the shape of the road. By connecting multiple key points, the curved part of the road can be mapped into a series of adjacent straight line segments; the preset range can refer to a circular range with the center point of the target intersection as the center, and the preset range can cover the road surface of the entire target intersection. Then, based on the vehicle kinematic model, a smoothing operation is performed on the sub-trajectory route between each two adjacent key points, wherein the vehicle kinematic model mainly focuses on the change of the vehicle's position, speed, acceleration and other motion states over time and the relationship between these states. Before the smoothing operation is performed on the sub-trajectory route of the straight segment, the shape of the desired smoothed trajectory, the curvature change and other requirements can be determined according to the vehicle driving scene and task, and then the sub-trajectory route between each two key points is smoothed into a suitable curve trajectory by common curve fitting methods such as polynomial fitting and spline curve fitting, so that each sub-trajectory route after the smoothing operation is combined as the first turning trajectory of the target intersection.

[0036] For further information, see Figure 3 , Figure 3 A schematic diagram of a turning trajectory of a vehicle at a target intersection shown in an embodiment of the present application is shown. For ease of understanding, Figure 3 Take the example of a vehicle turning left at the target intersection, and Figure 3 The key points A, B, C and D of the target intersection are shown in FIG. It can be seen that by connecting every two key points, a series of straight line segments that can be roughly used to plan the vehicle turning trajectory, i.e., sub-trajectory routes, can be obtained. Then, the sub-trajectory routes (dashed line parts) between every two key points are smoothed to obtain the first turning trajectory (solid line part). In some embodiments, in order to reduce the amount of calculation, only the sub-trajectory routes formed by the key points in the target intersection can be smoothed, while the sub-trajectory routes formed by the key points in the lanes related to the target intersection are not smoothed, such as Figure 3 As shown, only the sub-trajectory route formed by the key point B and the key point C located at the target intersection is smoothed.

[0037] As an implementation method, the vehicle can turn left or right at the target intersection. Since there are certain differences in the traffic rules that the vehicle needs to follow when turning left and turning right, the method shown in this embodiment can be further optimized in actual application according to the differences between left-turning and right-turning behaviors. The specific trajectory smoothing algorithm will not be repeated here.

[0038] Therefore, in this embodiment, by utilizing the information of multiple key points within a preset range of the target intersection contained in the navigation map information and combining it with the vehicle kinematic model, a smooth curvature operation is performed on the straight line trajectory formed by the key points in the multiple target intersections obtained based on the navigation map information. This can also generate a first turning trajectory for the vehicle to use for turning. Even when the vehicle's own perception and detection is limited, it can also ensure that the vehicle can turn based on the navigation map information, thereby improving the traffic efficiency at the intersection.

[0039] S130: Based on the navigation map information, the vehicle positioning information and the vehicle perception information, the first turning trajectory is adjusted to obtain a second turning trajectory.

[0040] Specifically, according to the description of the navigation map information, the vehicle positioning information and the vehicle perception information in step S110, it can be known that, in combination with the vehicle positioning information and the navigation map information, the lane information around the vehicle when the vehicle travels to the stop line of the target intersection can be obtained, and in combination with the vehicle positioning information and the vehicle perception information, the actual situation of the intersection when the vehicle travels to the stop line of the target intersection can be obtained, that is, the perception information such as the lane line information, the curb information, the traffic light information and the information of the obstacle ahead can be obtained, including obtaining the actual distance information between the lane line, the curb, the traffic light and the obstacle ahead and the vehicle. Therefore, after obtaining the first turning trajectory based on the navigation map information, the first turning trajectory is adjusted in combination with the navigation map information, the vehicle positioning information and the vehicle perception information to obtain a more refined second turning trajectory that is more in line with the actual driving environment of the vehicle, thereby improving the robustness of turning traffic at the intersection, and for various different turning intersections in the city, the appropriate turning trajectory can be adjusted and generated in real time based on the vehicle perception information and the vehicle positioning information obtained in real time, ensuring that the vehicle can automatically and smoothly drive through the intersection.

[0041] As an implementation method, based on the navigation map information, the vehicle positioning information and the vehicle perception information, the method of adjusting the first turning trajectory to obtain the second turning trajectory may be: combining the navigation map information and the vehicle positioning information to obtain the turning lane where the vehicle is currently located, then obtaining the real-time position of the vehicle according to the vehicle positioning information, thereby confirming whether the vehicle is already in the turning lane and driving to the stop line of the target intersection in combination with the vehicle perception information, when the vehicle drives to the stop line position of the target intersection, adjusting the first turning trajectory to obtain the second turning trajectory according to the vehicle perception information obtained when the vehicle drives at the stop line position of the target intersection. Specifically, taking the vehicle perception information including the zebra crossing, curb, obstacle, stop line, traffic light and other information in the target intersection as an example, the first turning trajectory can be adjusted according to the curb, zebra crossing and obstacle information to avoid the first turning trajectory, so that the generated second turning trajectory can bypass or avoid the curb, zebra crossing and obstacle, and the first turning trajectory can be adjusted according to the stop line and traffic light information to reduce the speed or stop the vehicle at a suitable position or pass.

[0042] Therefore, a method for planning an intersection turning trajectory provided in an embodiment of the present application is applied to a vehicle, and the method includes: obtaining navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize the environmental information of a target intersection where the vehicle is located, and the target intersection is a turning intersection on the road where the vehicle is currently located; based on the navigation map information, generating a first turning trajectory corresponding to the target intersection, the navigation map information at least includes information on multiple key points within a preset range of the target intersection; based on the navigation map information, the vehicle positioning information and the vehicle perception information, adjusting the first turning trajectory to obtain a second turning trajectory. Therefore, the present application generates a first turning trajectory for passing a target intersection through navigation map information, and, based on the first turning trajectory, uses vehicle positioning information and vehicle perception information to adjust the first turning trajectory to obtain a second turning trajectory that is more accurate and more in line with the actual traffic conditions of the road. As a result, the vehicle can adjust and generate appropriate turning trajectories for different turning intersections in real time, realize automatic turning at intersections, and improve the robustness of turning in automatic driving. In addition, since the navigation map information is obtained based on a standard-definition navigation map, automatic turning at intersections can be achieved without a high-precision map, thereby reducing the cost of automatic driving.

[0043] See also Figure 4 , Figure 4 A flowchart of another method for planning a turning trajectory at an intersection provided by an embodiment of the present application is shown. The method can be applied to Figure 1 In the vehicle shown, specifically, the method comprises the following steps:

[0044] S210: Obtain navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize environmental information of surrounding roads and a target intersection of the vehicle, and the target intersection is an intersection of a road where the vehicle is currently located.

[0045] S220: Based on the navigation map information, a first turning trajectory corresponding to the target intersection is generated, wherein the navigation map information at least includes information of a plurality of key points within a preset range of the target intersection.

[0046] The specific implementation of steps S210 - S220 may refer to the specific implementation of steps S110 - S120 in the above embodiment, which will not be described in detail here.

[0047] S230: Determine the turning lane in which the vehicle is currently located based on the navigation map information and the vehicle positioning information; determine the stop line position of the turning lane based on the vehicle perception information obtained when the vehicle is traveling in the turning lane.

[0048] As an implementation method, the vehicle perception information may include, but is not limited to, the perception information of the target intersection and the lane lines, stop lines, zebra crossings, curbs, obstacles, traffic lights, ground signs and other objects around the target intersection, as well as the relative position information between the above objects and the vehicle. Furthermore, the navigation map information also includes lane information, that is, the lane attributes of each lane related to the target intersection are reflected, and the current position of the vehicle can be determined based on the vehicle positioning information. Therefore, the turning lane where the vehicle is currently located can be obtained by combining the navigation map information and the vehicle positioning information, and the stop line position of the turning lane can be further determined based on the vehicle perception information obtained when the vehicle is traveling in the turning lane. In other words, the moment when the vehicle reaches the stop line position of the turning lane can be clearly determined by combining the vehicle positioning information and the vehicle perception information obtained when the vehicle is traveling in the turning lane.

[0049] S240: When it is determined according to the vehicle positioning information that the vehicle has traveled to the stop line position, the first turning trajectory is adjusted based on the vehicle positioning information and at least one of the vehicle perception information acquired when the vehicle travels in the turning lane to obtain a second turning trajectory.

[0050] In this embodiment, according to the above analysis, it can be known that the moment when the vehicle reaches the stop line position of the turning lane can be clearly determined by combining the vehicle positioning information and the vehicle perception information obtained when the vehicle is traveling in the turning lane. Therefore, when the vehicle is traveling in the turning lane, the vehicle positioning information and the vehicle perception information are obtained, and further when the vehicle travels to the stop line position of the turning lane, the vehicle positioning information and the vehicle perception information are obtained. It can be understood that the vehicle positioning information and the vehicle perception information obtained at this time can better reflect the accurate position of the vehicle in the turning lane and the target intersection, and reflect the accurate road conditions of the turning lane and the target intersection. Therefore, when the vehicle travels to the stop line position, based on at least one of the vehicle positioning information and the vehicle perception information obtained when the vehicle travels in the turning lane, the first turning trajectory is adjusted to obtain a second turning trajectory that is more in line with the conditions of the turning lane and the target intersection.

[0051] As an implementation mode, when the vehicle reaches the stop line position, the current position of the vehicle can be determined based on the vehicle positioning information, so that the current position of the vehicle is used as the starting point of the turn, and then the first turning trajectory is adjusted based on the turning starting point to obtain the second turning trajectory, so that the second turning trajectory includes the turning starting point. Specifically, when the vehicle reaches the stop line position of the turning lane, after the current position of the vehicle is determined, the current position of the vehicle can be used as the turning starting point, and the first turning trajectory can be fitted and adjusted using a suitable curve fitting model, so that the curve trajectory of the first turning trajectory is close to or even includes the turning starting point, and the adjusted curve trajectory is used as the second turning trajectory, that is, the second turning trajectory includes the turning starting point. For example, if the first turning trajectory is a simple smooth curve, a polynomial regression model, an exponential or logarithmic model can be used for fitting. If the first turning trajectory cannot be well fitted to the turning starting point, a more complex model such as a neural network model can be used for fitting. It is understandable that since the first turning trajectory is generated based on the rough key point information in the navigation map when the vehicle is still some distance away from the stop line, there may be a certain error between the first turning trajectory and the actual driving position of the vehicle. Therefore, when the vehicle reaches the stop line, the current actual position of the vehicle is used as the starting point of the turn to fit and adjust the first turning trajectory so that the adjusted second turning trajectory includes the starting point of the turn, thereby making the second turning trajectory more consistent with the actual driving conditions of the vehicle.

[0052] As an implementation mode, when the vehicle reaches the stop line position, the position of the curb in the target intersection is determined based on the vehicle perception information obtained when the vehicle is traveling in the turning lane, thereby adjusting the first turning trajectory based on the curb position in the target intersection to obtain the second turning trajectory, so that the second turning trajectory does not overlap with the curb position in the target intersection. Specifically, at the moment when the vehicle reaches the stop line position of the turning lane, the position of the curb in the target intersection can be determined based on the vehicle perception information obtained when the vehicle is traveling in the turning lane, and further, based on the vehicle perception information obtained when the vehicle is traveling to the stop line position of the turning lane, thereby determining the curb position in the target intersection based on the curb information in the vehicle perception information, and fitting and adjusting the first turning trajectory through a curve fitting model, so that the curve trajectory of the first turning trajectory does not overlap with the curb position in the target intersection, and using the adjusted curve trajectory as the second turning trajectory, that is, so that the second turning trajectory does not overlap with the curb position in the target intersection. It is understandable that since the first turning trajectory is generated based on the rough key point information in the navigation map, that is, the possible existence of the curb in the target intersection in actual situation and the influence of the curb position on the turning trajectory are not taken into account in the process of generating the first turning trajectory. Therefore, when the vehicle reaches the stop line, the first turning trajectory is fitted and adjusted based on the actual position of the curb in the target intersection, so that the adjusted second turning trajectory does not coincide with the curb position in the target intersection, thereby making the second turning trajectory more in line with the actual driving conditions of the vehicle.

[0053] Therefore, a method for planning an intersection turning trajectory is proposed in an embodiment of the present application. The method is applied to a vehicle, including: obtaining navigation map information, vehicle positioning information and vehicle perception information, the vehicle perception information being used to characterize environmental information of a target intersection where the vehicle is located, the target intersection being a turning intersection on the road where the vehicle is currently located; generating a first turning trajectory corresponding to the target intersection based on the navigation map information, the navigation map information at least including information on multiple key points within a preset range of the target intersection; determining a turning lane where the vehicle is currently located based on the navigation map information and the vehicle positioning information, determining a stop line position of the turning lane based on vehicle perception information obtained when the vehicle is traveling in the turning lane, and when it is determined that the vehicle has traveled to the stop line position based on the vehicle positioning information, adjusting the first turning trajectory based on at least one of the vehicle positioning information and the vehicle perception information obtained when the vehicle is traveling in the turning lane to obtain a second turning trajectory. Therefore, the present application generates a first turning trajectory for passing through a target intersection through a relatively low-precision navigation map, and when the vehicle reaches the stop line position, the first turning trajectory is adjusted based on the vehicle positioning information and at least one of the vehicle perception information obtained when the vehicle is traveling in the turning lane to obtain a second turning trajectory. Thereby, the second turning trajectory is more in line with the conditions of the turning lane and the target intersection, thereby improving the accuracy of the turning trajectory generated by the low-precision navigation map.

[0054] See also Figure 5 , Figure 5 A method flow chart of another method for planning a turning trajectory at an intersection provided by an embodiment of the present application is shown. The method can be applied to Figure 1 In the vehicle shown, specifically, the method comprises the following steps:

[0055] S310: Obtain navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize environmental information of the surrounding roads of the vehicle and a target intersection, wherein the target intersection is an intersection of the road where the vehicle is currently located.

[0056] S320: Generate a first turning trajectory corresponding to the target intersection based on the navigation map information, wherein the navigation map information at least includes information of a plurality of key points within a preset range of the target intersection.

[0057] S330: Based on the navigation map information, the vehicle positioning information and the vehicle perception information, the first turning trajectory is adjusted to obtain a second turning trajectory.

[0058] The specific implementation of steps S310 - S330 may refer to the specific implementation of steps S110 - S130 in the above embodiment, which will not be described in detail here.

[0059] S340: According to the second turning trajectory, control the vehicle to perform a turning behavior at the target intersection, and during the process of the vehicle performing the turning behavior, update the second turning trajectory based on the vehicle perception information obtained during the process of the vehicle performing the turning behavior, so that the vehicle completes the turning behavior according to the updated second turning trajectory.

[0060] In this embodiment, after the second turning trajectory is obtained, the vehicle is controlled to perform a turning behavior at the target intersection according to the second turning trajectory. It is understandable that, since unexpected situations may still occur at the target intersection during the vehicle's turning behavior, such as pedestrians appearing on the zebra crossing and obstacles existing at the intersection, during the vehicle's turning behavior, the second turning trajectory is continuously updated in real time based on the vehicle perception information obtained during the vehicle's turning behavior, so that the vehicle continues to perform the turning behavior according to the updated second turning trajectory until the turning behavior is completed, ensuring that the turning trajectory of the vehicle during the turning process can cope with various actual road conditions at the target intersection.

[0061] As an implementation mode, the obstacle position at the target intersection can be determined based on the vehicle perception information obtained during the vehicle turning behavior, and then the second turning trajectory is updated based on the obstacle position at the target intersection, so that the updated second turning trajectory does not overlap with the obstacle position at the target intersection. For example, taking the vehicle perception information including zebra crossings, obstacles, traffic lights and other information at the target intersection as an example, the second turning trajectory can be adjusted for trajectory avoidance constraints based on the zebra crossing and obstacle information, so that the updated second turning trajectory can bypass or avoid zebra crossings and obstacles, and the first turning trajectory can be adjusted for trajectory deceleration or braking constraints based on the zebra crossing and traffic light information, so that the generated second turning trajectory can decelerate or brake or pass the vehicle at an appropriate position based on the zebra crossing or traffic light signal.

[0062] See also Figure 6 , Figure 6 The structure block diagram of a road damage identification device 400 proposed in an embodiment of the present application is shown, including:

[0063] An information acquisition module 401 is used to acquire navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize environmental information of the surrounding roads of the vehicle and a target intersection, wherein the target intersection is an intersection of the road where the vehicle is currently located;

[0064] A trajectory generating module 402, configured to generate a first turning trajectory corresponding to the target intersection based on navigation map information, wherein the navigation map information at least includes information of a plurality of key points within a preset range of the target intersection;

[0065] The trajectory adjustment module 403 is used to adjust the first turning trajectory based on the navigation map information, the vehicle positioning information and the vehicle perception information to obtain a second turning trajectory.

[0066] Optionally, the trajectory generation module 402 is also used to obtain information of multiple key points within a preset range of the target intersection based on the navigation map information; based on the vehicle kinematic model, perform a smoothing operation on the sub-trajectory route between each two adjacent key points; and use each sub-trajectory route after the smoothing operation is completed as the first turning trajectory of the target intersection.

[0067] Optionally, the trajectory adjustment module 403 is also used to determine the turning lane in which the vehicle is currently located based on the navigation map information and the vehicle positioning information; determine the stop line position of the turning lane according to the vehicle perception information obtained when the vehicle is traveling in the turning lane; when it is determined according to the vehicle positioning information that the vehicle has traveled to the stop line position, adjust the first turning trajectory based on at least one of the vehicle positioning information and the vehicle perception information obtained when the vehicle is traveling in the turning lane to obtain a second turning trajectory.

[0068] Optionally, the trajectory adjustment module 403 is also used to determine the current position of the vehicle based on the vehicle positioning information, and use the current position of the vehicle as the starting point of a turn; adjust the first turning trajectory based on the turning starting point to obtain the second turning trajectory, wherein the second turning trajectory includes the turning starting point.

[0069] Optionally, the trajectory adjustment module 403 is also used to determine the curb position in the target intersection based on the vehicle perception information obtained when the vehicle is traveling in the turning lane; based on the curb position in the target intersection, adjust the first turning trajectory to obtain the second turning trajectory, and the second turning trajectory does not overlap with the curb position in the target intersection.

[0070] Optionally, the trajectory adjustment module 403 is also used to control the vehicle to perform a turning behavior at the target intersection according to the second turning trajectory, and to update the second turning trajectory based on vehicle perception information obtained during the vehicle's turning behavior, so that the vehicle completes the turning behavior according to the updated second turning trajectory.

[0071] Optionally, the trajectory adjustment module 403 is also used to determine the position of the obstacle in the target intersection based on the vehicle perception information obtained during the vehicle's turning behavior; based on the obstacle position in the target intersection, update the second turning trajectory so that the updated second turning trajectory does not overlap with the obstacle position in the target intersection.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0073] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.

[0074] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0075] See also Figure 7 , which shows a block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable medium 500 stores program code, which can be called by a processor to execute the method described in the above method embodiment.

[0076] The computer-readable storage medium 500 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium 500 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 500 has storage space for program code 510 that performs any method steps in the above method. These program codes can be read from or written to one or more computer program products. The program code 510 can be compressed, for example, in an appropriate form.

[0077] As an implementation mode, the present application also provides a computer program product. The computer program product includes a computer program / instruction, and the computer program / instruction implements the steps of the above method when executed by a processor.

[0078] 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 it. 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 method for planning a turning trajectory at an intersection, characterized in that: Applied to a vehicle, the method comprises: Obtaining navigation map information, vehicle positioning information, and vehicle perception information, wherein the vehicle perception information is used to characterize environmental information of a target intersection where the vehicle is located, and the target intersection is a turning intersection on a road where the vehicle is currently located; Based on the navigation map information, generating a first turning trajectory corresponding to the target intersection, the navigation map information at least including information of a plurality of key points within a preset range of the target intersection; Based on the navigation map information, the vehicle positioning information and the vehicle perception information, the first turning trajectory is adjusted to obtain a second turning trajectory.

2. The method according to claim 1, characterized in that The step of generating a first turning trajectory corresponding to the target intersection based on the navigation map information includes: According to the navigation map information, obtaining information of a plurality of key points within a preset range of the target intersection; Based on the vehicle kinematic model, a smoothing operation is performed on the sub-trajectory route between every two adjacent key points; Each sub-trajectory route after the smoothing operation is completed is used as the first turning trajectory of the target intersection.

3. The method according to claim 1, characterized in that The adjusting the first turning trajectory based on the navigation map information, the vehicle positioning information and the vehicle perception information to obtain the second turning trajectory includes: Based on the navigation map information and the vehicle positioning information, determining a turning lane where the vehicle is currently located; Determining a stop line position of the turning lane according to vehicle perception information acquired when the vehicle is traveling in the turning lane; When it is determined according to the vehicle positioning information that the vehicle has traveled to the stop line position, the first turning trajectory is adjusted based on the vehicle positioning information and at least one of the vehicle perception information acquired when the vehicle travels in the turning lane to obtain a second turning trajectory.

4. The method according to claim 3, characterized in that When it is determined according to the vehicle positioning information that the vehicle has traveled to the stop line position, adjusting the first turning trajectory based on the vehicle positioning information to obtain a second turning trajectory includes: Based on the vehicle positioning information, determine the current position of the vehicle, and use the current position of the vehicle as the starting point of the turn; The first turning trajectory is adjusted based on the turning starting point to obtain the second turning trajectory, wherein the second turning trajectory includes the turning starting point.

5. The method according to claim 3, characterized in that: When it is determined according to the vehicle positioning information that the vehicle has traveled to the stop line position, adjusting the first turning trajectory based on the vehicle perception information acquired when the vehicle travels in the turning lane to obtain a second turning trajectory includes: Determining a curb position in the target intersection based on vehicle perception information acquired when the vehicle is traveling in the turning lane; Based on the curb position in the target intersection, the first turning trajectory is adjusted to obtain the second turning trajectory, and the second turning trajectory does not overlap with the curb position in the target intersection.

6. The method according to claim 1, characterized in that After obtaining the second turning trajectory, the method further includes: According to the second turning trajectory, the vehicle is controlled to perform a turning behavior at the target intersection, and during the process of the vehicle performing the turning behavior, the second turning trajectory is updated based on the vehicle perception information obtained during the process of the vehicle performing the turning behavior, so that the vehicle completes the turning behavior according to the updated second turning trajectory.

7. The method according to claim 6, characterized in that The updating of the second turning trajectory based on vehicle perception information acquired during the process of the vehicle performing the turning behavior includes: Determining the position of the obstacle in the target intersection according to the vehicle perception information obtained during the turning behavior of the vehicle; Based on the position of the obstacle in the target intersection, the second turning trajectory is updated so that the updated second turning trajectory does not overlap with the position of the obstacle in the target intersection.

8. A device for planning a turning trajectory at an intersection, characterized in that: Applied to a vehicle, the device comprises: An information acquisition module, used to acquire navigation map information, vehicle positioning information and vehicle perception information, wherein the vehicle perception information is used to characterize the environmental information of a target intersection where the vehicle is located, and the target intersection is a turning intersection of the road where the vehicle is currently located; A trajectory generation module, configured to generate a first turning trajectory corresponding to the target intersection based on the navigation map information, wherein the navigation map information at least includes information of a plurality of key points within a preset range of the target intersection; The trajectory adjustment module is used to adjust the first turning trajectory based on the navigation map information, the vehicle positioning information and the vehicle perception information to obtain a second turning trajectory.

9. A vehicle, characterized in that: include: A perception sensor, wherein the perception sensor is used to obtain vehicle perception information; 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, the one or more applications configured to execute the method of claims 1-7.

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

Images