Path planning method, device, equipment, medium, product and vehicle

Abstract

The invention relates to a path planning method, device and equipment, a medium, a product and a vehicle, and relates to the technical field of data processing. The technical problem that in the prior art, when the driving path of an automatic driving vehicle is planned, the accuracy of the planned driving path is poor, so that abnormal conditions occur when the vehicle runs, and comfort and safety are affected is at least solved. The method comprises the steps that the target transverse offset of the end point of a to-be-planned path of a vehicle relative to a reference line is determined, the to-be-planned path comprises a plurality of sampling points, and the reference line is a reference line corresponding to a lane where the vehicle runs currently; determining the transverse offset of each sampling point in a plurality of sampling points included in the to-be-planned path based on the target transverse offset; and planning a to-be-planned path based on the transverse offset of each sampling point in the plurality of sampling points.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and specifically to a path planning method, device, equipment, medium, product and vehicle. Background Art

[0002] With the continuous development of vehicle intelligent driving technology, path planning is a very important module in the autonomous driving system. The current path planning is to plan the driving path of the autonomous driving vehicle by decoupling the lateral planning and longitudinal planning. Specifically, according to the current initial state and terminal state of the vehicle, a set of lateral trajectories can be generated by polynomial interpolation, and then the cost function can be used to select the optimal path. This method does not consider the inter-frame continuity between the previous and next frames in time. If the inter-frame continuity is not handled well, it is not friendly to the downstream lateral control, and it is easy to cause the steering wheel to shake during actual vehicle control, which greatly affects comfort and safety.

[0003] In the related art, the curvature constraint and curvature change rate constraint of the vehicle from the current position to the target position on the target lane are determined by the target speed of the vehicle at the current position on the current lane. Therefore, the target path of the vehicle from the current position to the target position is determined based on the curvature constraint and the curvature change rate constraint. However, in this method, since the speed of the vehicle is a continuously changing process in a period of time in the future from the current moment, and this method only considers the target speed of the current lane, it cannot be well combined with the longitudinal planning results. Therefore, when the vehicle travels from the current position to the target position based on the planned path, the path will be uneven when the vehicle deviates laterally. Therefore, when the driving path of the autonomous driving vehicle is currently planned, the accuracy of the planned driving path is poor, which leads to abnormal conditions when the vehicle is driving, affecting comfort and safety. Summary of the invention

[0004] The present application provides a path planning method, device, equipment, medium, product and vehicle to at least solve the technical problem that when planning the driving path of an autonomous driving vehicle in the related art, the accuracy of the planned driving path is poor, which leads to abnormal conditions when the vehicle is driving, affecting comfort and safety. The technical solution of the present application is as follows:

[0005] According to a first aspect of the present application, a path planning method is provided, the method comprising: determining a target lateral offset of an end point of a to-be-planned path of a vehicle relative to a reference line, the to-be-planned path comprising a plurality of sampling points, the reference line being a reference line corresponding to a lane in which the vehicle is currently travelling; determining a lateral offset of each of the plurality of sampling points included in the to-be-planned path based on the target lateral offset; and planning the to-be-planned path based on the lateral offset of each of the plurality of sampling points.

[0006] According to the above technical means, the present application can determine the lateral offset of each of the multiple sampling points included in the path to be planned by determining the target lateral offset of the end point of the vehicle's path to be planned relative to the reference line. Therefore, the path to be planned is planned based on the lateral offset of each of the multiple sampling points. In this way, by determining the lateral offset corresponding to the end point of the current path to be planned, the reasonable lateral offset corresponding to each point in the path to be planned can be determined, so that when the vehicle travels from the current position to the end point of the path to be planned, it can gradually shift to the end point of the path to be planned during the driving process based on the lateral offset corresponding to each point. Therefore, when planning the driving path of the autonomous driving vehicle, a driving path with higher accuracy can be planned to avoid abnormal situations when the vehicle is driving, and enhance the comfort and safety of the autonomous driving vehicle.

[0007] In a possible implementation, the path to be planned includes a first subpath, and the first subpath is a path segment determined from a path planned in a previous cycle; the above-mentioned determining the lateral offset of each of the multiple sampling points included in the path to be planned based on the target lateral offset includes: determining the lateral offset of each of the multiple sampling points included in the path to be planned based on the first subpath and the target lateral offset.

[0008] According to the above technical means, the present application can determine the lateral offset of each of the multiple sampling points included in the path to be planned based on the first sub-path included in the path to be planned and the target lateral offset. Since the first sub-path is a path segment determined from the path planned in the previous cycle, when planning the current path, based on the path segment in the path planned in the previous cycle, the paths planned twice can be continuous, ensuring the stability between the paths.

[0009] In a possible implementation, the path to be planned also includes a second subpath, the first subpath and the second subpath are connected, and the first subpath is located before the second subpath; the determining the lateral offset of each of the multiple sampling points included in the path to be planned based on the first subpath and the target lateral offset includes: based on the first subpath and the reference line, determining the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath; and determining the lateral offset of each sampling point included in the second subpath based on the lateral offset of the last sampling point in the first subpath and the target lateral offset.

[0010] According to the above technical means, the present application can determine the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath. In this way, based on the lateral offset of the last sampling point in the first subpath and the target lateral offset, the lateral offset of each sampling point included in the second subpath is determined, and based on the path segments in the path planned in the previous cycle, a smooth transition effect between two adjacent planned paths can be achieved to ensure that no sudden change occurs between the two paths.

[0011] In a possible implementation, the determining of the lateral offset of each sampling point included in the second subpath based on the lateral offset of the last sampling point in the first subpath and the target lateral offset includes: acquiring a correspondence between an amount to be offset and a lateral offset speed, where the amount to be offset is a difference between the target lateral offset and the lateral offset of the sampling point; determining a lateral offset speed corresponding to the last sampling point in the first subpath based on the lateral offset of the last sampling point in the first subpath and the correspondence between the amount to be offset and the lateral offset speed; and calculating, for each sampling point included in the second subpath, a lateral offset of each sampling point based on the lateral offset speed and the lateral offset corresponding to a previous sampling point of each sampling point, where a previous sampling point of the first sampling point in the second subpath is the last sampling point in the first subpath.

[0012] According to the above technical means, the present application can determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the correspondence between the amount to be offset and the lateral offset speed when the lateral offset of the last sampling point in the first subpath is known. In this way, the lateral offset of the first sampling point in the second subpath can be determined based on the lateral offset speed and lateral offset corresponding to the last sampling point in the first subpath. And, for each sampling point included in the second subpath, the lateral offset of each sampling point is calculated based on the lateral offset speed and lateral offset corresponding to the previous sampling point of each sampling point. Thus, based on the lateral offset speed and lateral offset corresponding to the previous sampling point of two adjacent sampling points, the lateral offset of the next sampling point can be determined, which can ensure the effect of smooth transition between the two adjacent sampling points and ensure that no sudden change occurs between the two sampling points.

[0013] In a possible implementation, the above-mentioned planning of the path to be planned based on the lateral offset of each sampling point in the multiple sampling points includes: determining multiple curve functions for the multiple sampling points, each curve function in the multiple curve functions corresponds to at least one sampling point in the multiple sampling points, each curve function includes at least one adjustment parameter, and the multiple curve functions correspond to a preset cost function; under the constraint of a preset constraint condition, determining the value of at least one adjustment parameter included in each of the multiple curve functions when the preset cost function takes a minimum value, the preset constraint condition is used to constrain at least one of the following: a value range of each curve function, a value range of any order derivative of each curve function, the first sampling point in the multiple sampling points is the current position of the vehicle, and any order derivatives corresponding to the intersection of two adjacent curve functions in the multiple curve functions are equal; based on the value of at least one adjustment parameter included in each curve function, determine multiple curve functions to plan the path to be planned based on the multiple curve functions.

[0014] According to the above technical means, the present application can determine multiple curve functions for multiple sampling points, so that the multiple curve functions pass through multiple sampling points as much as possible, thereby determining the path to be planned through multiple curve functions. In addition, the preset cost function is constrained by the preset constraint condition, so that when the preset cost function takes the minimum value, the value of at least one adjustment parameter included in each of the multiple curve functions is determined, thereby determining multiple curve functions. In this way, based on the value of at least one adjustment parameter included in each determined curve function, the determined multiple curve functions can pass through multiple sampling points as much as possible, thereby accurately determining the path to be planned.

[0015] In a possible implementation, the method also includes: when there is a high-precision map corresponding to the current position of the vehicle, determining the center line of the lane in which the vehicle is currently traveling in the high-precision map as a reference line; when there is no high-precision map corresponding to the current position of the vehicle, determining the center line of the lane line obtained by the vehicle's perception device as the reference line.

[0016] According to the above technical means, the present application can determine the reference line in different ways according to whether the current position of the vehicle corresponds to a high-precision map. Thus, when the current position of the vehicle corresponds to a high-precision map, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line; and when the current position of the vehicle does not correspond to a high-precision map, the center line of the lane line obtained by the vehicle's sensing device is determined as the reference line. In this way, the reference line can be determined flexibly.

[0017] In a possible implementation, when there is a high-precision map corresponding to the current position of the vehicle, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line, including: when there is a high-precision map corresponding to the current position of the vehicle, and the high-precision map matches the perception data acquired by the perception device, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line.

[0018] According to the above technical means, when there is a high-precision map corresponding to the current position of the vehicle, the present application can further determine whether the high-precision map matches the perception data acquired by the perception device, thereby avoiding the mismatch between the high-precision map and the current position of the vehicle and determining an erroneous reference line, so as to further improve the accuracy of determining the reference line.

[0019] In a possible implementation, the above-mentioned determination of the target lateral offset of the end point of the vehicle's planned path relative to the reference line includes: obtaining the vehicle's driving decision, the driving decision is used to indicate whether the vehicle needs to perform any of the following: changing lanes, turning; based on the vehicle's driving decision, determining the end point of the path to be planned, and determining the distance between the end point of the path to be planned and the reference line as the target lateral offset.

[0020] According to the above technical means, the present application can determine the end point of the path to be planned based on the vehicle's driving decision, so as to determine the distance between the end point of the path to be planned and the reference line as the target lateral offset. In this way, by determining the distance between the end point of the path and the reference line, the target lateral offset corresponding to the path to be planned can be determined. Thus, the target lateral offset required for the vehicle to be offset in the path to be planned can be accurately determined.

[0021] According to a second aspect provided by the present application, a path planning device is provided, the path planning device comprising: a processing module and an acquisition module; the processing module is used to determine a target lateral offset of an end point of a to-be-planned path of a vehicle relative to a reference line, the to-be-planned path comprising a plurality of sampling points, and the reference line is a reference line corresponding to a lane in which the vehicle is currently traveling; the processing module is also used to determine a lateral offset of each of a plurality of sampling points included in the to-be-planned path based on the target lateral offset; the processing module is also used to plan the to-be-planned path based on the lateral offset of each of the plurality of sampling points.

[0022] In a possible implementation, the path to be planned includes a first sub-path, which is a path segment determined from a path planned in a previous cycle; and the processing module is specifically used to determine the lateral offset of each sampling point among a plurality of sampling points included in the path to be planned based on the first sub-path and the target lateral offset.

[0023] In a possible implementation, the path to be planned also includes a second subpath, the first subpath and the second subpath are connected, and the first subpath is located before the second subpath; the processing module is specifically used to determine, based on the first subpath and the reference line, the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath; the processing module is specifically used to determine the lateral offset of each sampling point included in the second subpath based on the lateral offset of the last sampling point in the first subpath and the target lateral offset.

[0024] In a possible implementation, the processing module is specifically used to obtain a correspondence between the amount to be offset and the lateral offset speed, where the amount to be offset is the difference between the target lateral offset and the lateral offset of the sampling point; the processing module is specifically used to determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the lateral offset of the last sampling point in the first subpath and the correspondence between the amount to be offset and the lateral offset speed; the processing module is specifically used to calculate the lateral offset of each sampling point included in the second subpath based on the lateral offset speed and the lateral offset corresponding to the previous sampling point of each sampling point, where the previous sampling point of the first sampling point in the second subpath is the last sampling point in the first subpath.

[0025] In a possible implementation, a processing module is specifically used to determine multiple curve functions for multiple sampling points, each of the multiple curve functions corresponds to at least one sampling point among the multiple sampling points, each curve function includes at least one adjustment parameter, and the multiple curve functions correspond to a preset cost function; the processing module is specifically used to determine, under the constraint of a preset constraint condition, the value of at least one adjustment parameter included in each of the multiple curve functions when the preset cost function takes a minimum value, the preset constraint condition is used to constrain at least one of the following: a value range of each curve function, a value range of any order derivative of each curve function, the first sampling point among the multiple sampling points is the current position of the vehicle, and any order derivatives corresponding to the intersection of two adjacent curve functions among the multiple curve functions are equal; the processing module is specifically used to determine multiple curve functions based on the value of at least one adjustment parameter included in each curve function, so as to plan the path to be planned based on the multiple curve functions.

[0026] In a possible implementation, the processing module is further used to determine the center line of the lane in which the vehicle is currently traveling in the high-precision map as a reference line when there is a high-precision map corresponding to the current position of the vehicle; the processing module is also used to determine the center line of the lane line obtained by the vehicle's sensing device as a reference line when there is no high-precision map corresponding to the current position of the vehicle.

[0027] In one possible implementation, the processing module is specifically used to determine the center line of the lane in which the vehicle is currently traveling in the high-precision map as a reference line when there is a high-precision map corresponding to the current position of the vehicle and the high-precision map matches the perception data acquired by the perception device.

[0028] In one possible implementation, an acquisition module is used to acquire a driving decision of a vehicle, where the driving decision is used to indicate whether the vehicle needs to perform any of the following: changing lanes, turning; and a processing module is specifically used to determine an end point of a path to be planned based on the driving decision of the vehicle, and to determine a distance between the end point of the path to be planned and a reference line as a target lateral offset.

[0029] According to the third aspect provided by the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory is used to store one or more programs, and the one or more programs include computer execution instructions. When the electronic device is running, the processor executes the computer execution instructions stored in the memory, and the electronic device executes the method of the above-mentioned first aspect and any possible implementation method thereof.

[0030] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the computer instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device executes the method of the above-mentioned first aspect and any possible implementation method thereof.

[0031] According to the fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, when the computer instructions are executed on an electronic device, the electronic device executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0032] According to a sixth aspect provided by the present application, a vehicle is provided, the vehicle comprising a path planning device as in the second aspect, and the vehicle is used to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0033] Therefore, the above technical features of the present application have the following beneficial effects:

[0034] (1) The present application can determine the target lateral offset of the end point of the vehicle's path to be planned relative to the reference line, and can determine the lateral offset of each sampling point in the path to be planned. Therefore, based on the lateral offset of each sampling point in the multiple sampling points, the path to be planned is planned. In this way, by determining the lateral offset corresponding to the end point of the current path to be planned, a reasonable lateral offset corresponding to each point in the path to be planned can be determined, so that when the vehicle travels from the current position to the end point of the path to be planned, it can gradually shift to the end point of the path to be planned during the driving process based on the lateral offset corresponding to each point. Therefore, when planning the driving path of the autonomous driving vehicle, a driving path with higher accuracy can be planned to avoid abnormal situations when the vehicle is driving, and enhance the comfort and safety of the autonomous driving vehicle.

[0035] (2) The present application can determine the lateral offset of each of the multiple sampling points included in the path to be planned based on the first subpath and the target lateral offset included in the path to be planned. Since the first subpath is a path segment determined from the path planned in the previous cycle, when planning the current path, based on the path segment in the path planned in the previous cycle, the paths planned twice can be continuous, ensuring the stability between the paths.

[0036] (3) The present application can determine the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath. In this way, based on the lateral offset of the last sampling point in the first subpath and the target lateral offset, the lateral offset of each sampling point included in the second subpath is determined, and based on the path segments in the path planned in the previous cycle, a smooth transition effect between two adjacent planned paths can be achieved to ensure that no sudden change occurs between the two paths.

[0037] (4) The present application can determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the correspondence between the offset to be offset and the lateral offset speed when the lateral offset of the last sampling point in the first subpath is known. In this way, the lateral offset of the first sampling point in the second subpath can be determined based on the lateral offset speed and lateral offset corresponding to the last sampling point in the first subpath. Moreover, for each sampling point included in the second subpath, the lateral offset of each sampling point is calculated based on the lateral offset speed and lateral offset corresponding to the previous sampling point of each sampling point. Thus, based on the lateral offset speed and lateral offset corresponding to the previous sampling point of two adjacent sampling points, the lateral offset of the next sampling point can be determined, which can ensure a smooth transition effect between the two adjacent sampling points and ensure that no sudden change occurs between the two sampling points.

[0038] (5) The present application can determine multiple curve functions for multiple sampling points, so that the multiple curve functions pass through multiple sampling points as much as possible, thereby determining the path to be planned through multiple curve functions. In addition, the preset cost function is constrained by the preset constraint condition, so that when the preset cost function takes the minimum value, the value of at least one adjustment parameter included in each of the multiple curve functions is determined, thereby determining multiple curve functions. In this way, based on the value of at least one adjustment parameter included in each determined curve function, the determined multiple curve functions can pass through multiple sampling points as much as possible, thereby accurately determining the path to be planned.

[0039] (6) The present application can determine the reference line in different ways depending on whether there is a high-precision map corresponding to the current position of the vehicle. Thus, when there is a high-precision map corresponding to the current position of the vehicle, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line; and when there is no high-precision map corresponding to the current position of the vehicle, the center line of the lane line obtained by the vehicle's sensing device is determined as the reference line. In this way, the reference line can be determined flexibly.

[0040] (7) When there is a high-precision map corresponding to the current position of the vehicle, the present application can further determine whether the high-precision map matches the perception data acquired by the perception device, thereby avoiding the mismatch between the high-precision map and the current position of the vehicle and determining an erroneous reference line, thereby further improving the accuracy of determining the reference line.

[0041] (8) The present application can determine the end point of the path to be planned based on the vehicle's driving decision, so as to determine the distance between the end point of the path to be planned and the reference line as the target lateral offset. In this way, by determining the distance between the end point of the path and the reference line, the target lateral offset corresponding to the path to be planned can be determined. Thus, the target lateral offset required for the vehicle to be offset in the path to be planned can be accurately determined.

[0042] It should be noted that the technical effects brought about by any implementation method in the second to sixth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0043] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0045] Figure 1is a schematic structural diagram of a path planning system according to an exemplary embodiment;

[0046] Figure 2 is a flow chart of a path planning method according to an exemplary embodiment;

[0047] Figure 3 is a schematic diagram of a Frenet coordinate system according to an exemplary embodiment;

[0048] Figure 4 is another schematic diagram of a Frenet coordinate system according to an exemplary embodiment;

[0049] Figure 5 is a flow chart of another path planning method according to an exemplary embodiment;

[0050] Figure 6 is a schematic diagram of a path planning result according to an exemplary embodiment;

[0051] Figure 7 is a schematic diagram of a 4-degree curve according to an exemplary embodiment;

[0052] Figure 8 is a flow chart of another path planning method according to an exemplary embodiment;

[0053] Fig. 9 is a block diagram of a path planning device according to an exemplary embodiment;

[0054] Fig.10 is a block diagram of an electronic device according to an exemplary embodiment;

[0055] Fig.11 The diagram is a schematic diagram showing the structure of a computer system according to an exemplary embodiment. DETAILED DESCRIPTION

[0056] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0057] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0058] The path planning method provided in the embodiment of the present application can be applicable to a path planning system. Figure 1 A schematic diagram of the structure of the path planning system is shown in FIG. Figure 1 As shown, the path planning system 10 includes: an electronic device 11, a sensing device 12 and a server 13. The electronic device 11 can be a vehicle computer or a vehicle-mounted computer in a vehicle, the sensing device 12 can be a camera and a radar device in the vehicle, etc., and the server 13 can provide a high-precision map for the electronic device, or perform path planning based on data provided by the electronic device.

[0059] The electronic device 11 is used to determine a target lateral offset of an end point of a to-be-planned path of the vehicle relative to a reference line, where the to-be-planned path includes a plurality of sampling points and the reference line is a reference line corresponding to a lane in which the vehicle is currently traveling.

[0060] The electronic device 11 is used to determine the lateral offset of each sampling point among the multiple sampling points included in the path to be planned based on the target lateral offset.

[0061] The electronic device 11 is used to plan a path to be planned based on the lateral offset of each sampling point among the multiple sampling points.

[0062] In a possible implementation, the path to be planned includes a first sub-path, which is a path segment determined from the path planned in the previous cycle; the electronic device 11 is used to determine the lateral offset of each sampling point among the multiple sampling points included in the path to be planned based on the first sub-path and the target lateral offset.

[0063] In a possible implementation, the path to be planned also includes a second subpath, the first subpath and the second subpath are connected, and the first subpath is located before the second subpath; the electronic device 11 is used to determine, based on the first subpath and the reference line, the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath; based on the lateral offset of the last sampling point in the first subpath and the target lateral offset, determine the lateral offset of each sampling point included in the second subpath.

[0064] In a possible implementation, the electronic device 11 is used to obtain a correspondence between the amount to be offset and the lateral offset speed, where the amount to be offset is the difference between the target lateral offset and the lateral offset of the sampling point; determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the lateral offset of the last sampling point in the first subpath and the correspondence between the amount to be offset and the lateral offset speed; and calculate the lateral offset of each sampling point included in the second subpath based on the lateral offset speed and lateral offset corresponding to the previous sampling point of each sampling point, where the previous sampling point of the first sampling point in the second subpath is the last sampling point in the first subpath.

[0065] In a possible implementation, the electronic device 11 is used to determine multiple curve functions for multiple sampling points, each of the multiple curve functions corresponds to at least one sampling point among the multiple sampling points, each curve function includes at least one adjustment parameter, and the multiple curve functions correspond to a preset cost function; under the constraint of a preset constraint condition, determine the value of at least one adjustment parameter included in each of the multiple curve functions when the preset cost function takes a minimum value, and the preset constraint condition is used to constrain at least one of the following: a value range of each curve function, a value range of any order derivative of each curve function, the first sampling point among the multiple sampling points is the current position of the vehicle, and any order derivatives corresponding to the intersection of two adjacent curve functions in the multiple curve functions are equal; based on the value of at least one adjustment parameter included in each curve function, multiple curve functions are determined to plan the path to be planned based on the multiple curve functions.

[0066] In a possible implementation, the electronic device 11 is used to determine the center line of the lane in which the vehicle is currently traveling in the high-precision map as a reference line when there is a high-precision map corresponding to the current position of the vehicle; and to determine the center line of the lane line obtained by the vehicle's perception device as a reference line when there is no high-precision map corresponding to the current position of the vehicle.

[0067] In a possible implementation, the electronic device 11 is used to determine the center line of the lane in which the vehicle is currently traveling in the high-precision map as a reference line when there is a high-precision map corresponding to the current position of the vehicle and the high-precision map matches the perception data acquired by the perception device.

[0068] In a possible implementation, the electronic device 11 is used to obtain a driving decision of the vehicle, where the driving decision is used to indicate whether the vehicle needs to perform any of the following: changing lanes, turning; based on the driving decision of the vehicle, determining the end point of the path to be planned, and determining the distance between the end point of the path to be planned and the reference line as the target lateral offset.

[0069] For ease of understanding, the path planning method provided in this application is specifically introduced below with reference to the accompanying drawings.

[0070] Figure 2 is a flow chart of a path planning method according to an exemplary embodiment, which is applied to an electronic device, such as Figure 2 As shown, the path planning method includes the following S201-S203:

[0071] S201. Determine a target lateral offset of an end point of a to-be-planned path of the vehicle relative to a reference line.

[0072] The path to be planned includes multiple sampling points, the reference line is a reference line corresponding to the lane in which the vehicle is currently traveling, and in the driving direction of the vehicle, the driving time required between any two adjacent sampling points among the multiple sampling points is equal.

[0073] Optionally, when planning the driving path of the autonomous driving vehicle, it is necessary to first determine a reference line, and then determine the lateral offset of the end point (or sampling point) of the planned path relative to the reference line based on the determined reference line.

[0074] In some embodiments, when there is a high-precision map corresponding to the current position of the vehicle, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line; or, when there is no high-precision map corresponding to the current position of the vehicle, the center line of the lane line obtained by the vehicle's perception device is determined as the reference line.

[0075] It can be understood that when determining the reference line, if a high-precision map currently exists and the high-precision map matches the actual environment, the lane center line of the high-precision map is extracted as the reference line. If there is no high-precision map, or the high-precision map does not meet the usage conditions, the lane center line is generated as the reference line based on the lane line perceived by the vehicle's perception device.

[0076] It should be noted that the points of the lane centerline (i.e., reference line) can be represented by the geodetic coordinate system (UTM coordinate system), and this application can further convert the map points from the UTM coordinate system to the dead reckoning coordinate system (DR coordinate system). That is, the vehicle has a positioning coordinate at the initial position, and the coordinates of the vehicle in the subsequent process are determined by dead reckoning. The process of dead reckoning will gradually introduce errors, but the error has no effect in the process of planning and use, and the continuous DR coordinates are very suitable for planning and control.

[0077] In addition, the reference line perceived by the vehicle's perception device can be represented by the vehicle coordinate system (VCS coordinate system), and in order to achieve the unification of the reference line determined based on the perception device and the reference line determined based on the high-precision map, the present application can convert the reference line determined based on the perception device from the vehicle coordinate system to the track-reckoning coordinate system.

[0078] In some embodiments, the reference line can be a set of points with a spacing of about 0.5 m. The reference line is converted into a dead reckoning coordinate system for representation in order to ensure the consistency between the reference line determined based on the sensing device and the reference line determined based on the high-precision map. If the reference line is represented by a geodetic coordinate system, when the vehicle moves from a location without a high-precision map to a location with a high-precision map (or in and out of a tunnel, etc.), the fusion of high-precision positioning may jump, causing abnormal vehicle performance.

[0079] In the embodiment of the present application, the present application can determine the reference line in different ways according to whether the current position of the vehicle corresponds to a high-precision map. Thus, when the current position of the vehicle corresponds to a high-precision map, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line; and when the current position of the vehicle does not correspond to a high-precision map, the center line of the lane line obtained by the vehicle's sensing device is determined as the reference line. In this way, the reference line can be determined flexibly.

[0080] In some embodiments, when there is a high-precision map corresponding to the current position of the vehicle, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as a reference line, including: when there is a high-precision map corresponding to the current position of the vehicle, and the high-precision map matches the perception data acquired by the perception device, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line.

[0081] In the embodiment of the present application, when there is a high-precision map corresponding to the current position of the vehicle, the present application can further determine whether the high-precision map matches the perception data acquired by the perception device, thereby avoiding the mismatch between the high-precision map and the current position of the vehicle and determining an erroneous reference line, so as to further improve the accuracy of determining the reference line.

[0082] Further, such as Figure 3 As shown, the reference line represented in the dead reckoning coordinate system can also be converted to the Frenet coordinate system (i.e., the reference line is represented in the Frenet coordinate system). The conversion method is to find the point closest to the current position of the vehicle as the origin of the Frenet coordinate system, and the direction along the reference line is the S direction, and the direction perpendicular to the reference line is the L direction to generate the Frenet coordinate system.

[0083] In some embodiments, in a path planning method provided by an embodiment of the present application, the above-mentioned step S201 may specifically include: obtaining a driving decision of the vehicle, the driving decision being used to indicate whether the vehicle needs to perform any of the following: changing lanes, turning; based on the driving decision of the vehicle, determining the end point of the path to be planned, and determining the distance between the end point of the path to be planned and the reference line as the target lateral offset.

[0084] It can be understood that the driving decision is used to determine whether the vehicle needs to execute instructions such as changing lanes or deviating to avoid obstacles, so as to determine the L position of the end point of the vehicle's planned path relative to the reference line (that is, the distance L between the end point and the reference line in the L direction). end ). Assuming that based on the vehicle's driving decision, it is determined that the vehicle needs to shift 0.5m to the right, the L position of the end point of the planned path is L end = 0.5, and the time to reach the offset position t end .

[0085] In the embodiment of the present application, the present application can determine the end point of the path to be planned based on the driving decision of the vehicle, so as to determine the distance between the end point of the path to be planned and the reference line as the target lateral offset. In this way, by determining the distance between the end point of the path and the reference line, the target lateral offset corresponding to the path to be planned can be determined. Thus, the target lateral offset required for the vehicle to be offset in the path to be planned can be accurately determined.

[0086] S202: Determine a lateral offset of each sampling point in a plurality of sampling points included in the path to be planned based on the target lateral offset.

[0087] In some embodiments, the path to be planned includes a first sub-path, which is a path segment determined from the path planned in the previous cycle; in a path planning method provided in an embodiment of the present application, the above step S202 may specifically include: determining the lateral offset of each sampling point among the multiple sampling points included in the path to be planned based on the first sub-path and the target lateral offset.

[0088] For example, Figure 4 As shown in , the path segments in the path planned in the previous cycle can be converted to the current Frenet coordinate system, and the point closest to the current positioning of the vehicle (i.e., the DR positioning of the vehicle) is taken as the planning starting point of this cycle (S init ,L init ).exist Figure 4It includes the path segments in the path planned in the previous cycle, the rough trajectory of the current cycle, the trajectory planned in the current cycle, and the curve fitting error example. It should be noted that if the vehicle switches from non-autonomous driving to autonomous driving (that is, there is no path planned in the previous cycle), the path planned in the previous cycle can be not used, and the current positioning of the vehicle can be converted to the Frenet coordinate system as the planning starting point of this cycle.

[0089] It should be noted that the first subpath can be marked as path last .

[0090] Optionally, the length of the path segment in the path planned in the previous cycle that needs to be maintained in this cycle (i.e., the length of the first sub-path) can be determined according to the scenario, and the preview distance of the lateral control that needs to be known can be determined. For example, if the control preview distance is 1.5 times the time interval (i.e., the distance traveled by the vehicle per unit time), then the length of the path segment in the path planned in the previous cycle should be as large as possible. 1.5 times the time interval. The purpose of this is to ensure that the control preview points at different times are a continuous and smooth path in a global coordinate system, which can make the control more precise and respond to algorithm requirements more timely. If inter-frame continuity processing (i.e., the continuity between the paths planned in two adjacent cycles) is not performed, it is difficult to ensure that the preview points are continuous and smooth, which will have a significant impact on the control performance.

[0091] In the embodiment of the present application, the present application can determine the lateral offset of each sampling point in the plurality of sampling points included in the path to be planned based on the first sub-path included in the path to be planned and the target lateral offset. Since the first sub-path is a path segment determined from the path planned in the previous cycle, when planning the current path, based on the path segment in the path planned in the previous cycle, the paths planned twice can be continuous, thereby ensuring the stability between the paths.

[0092] In some embodiments, the path to be planned further includes a second sub-path, the first sub-path is connected to the second sub-path, and the first sub-path is located before the second sub-path; Figure 5 As shown, in a path planning method provided by an embodiment of the present application, the above step of "determining the lateral offset of each sampling point in the multiple sampling points included in the path to be planned based on the first sub-path and the target lateral offset" may specifically include S501-S502.

[0093] S501: Based on a first subpath and a reference line, determine a distance between a last sampling point in the first subpath and the reference line as a lateral offset of the last sampling point in the first subpath.

[0094] It can be understood that the path to be planned includes two parts, the first part of the path (ie, the first sub-path) is the length of the path segment in the path planned in the previous cycle, and the second part (ie, the second sub-path) is the path planned in this cycle.

[0095] Optionally, a rough trajectory can be generated in the Frenet coordinate system. The rough trajectory is composed of a series of points with equal time intervals. For example, a point is sampled every 0.1s to obtain the above-mentioned multiple sampling points. Among them, the i-th sampling point can be simply represented by an array as (i, S i ,l i ,t i ), where S i , l i They represent the coordinate values ​​of the sampling point in the S direction and the L direction in the Frenet coordinate system, respectively. i Indicates the time point corresponding to the coordinate point in the current planning cycle.

[0096] In this way, multiple sampling points are obtained with the same time interval as the length range of the path to be planned. For example, if a path with a time interval of 8 seconds is to be planned (i.e., the current cycle is 8 seconds), the length of the path to be planned is the driving distance planned for 8 seconds along the S direction in the Frenet coordinate system. Figure 6 As shown in the figure, the longitudinal planning result of the planned path in the current cycle is shown, where t represents time, the current moment starts from 0, and S represents the distance the vehicle travels forward. init -S plan ), according to the vehicle's uniform speed, one point is sampled every 0.1 seconds, so the coordinate values ​​of 81 sampling points in total for 8 seconds have been determined, and the time and driving distance corresponding to each sampling point are (t i ,S i ), for example, the time corresponding to the 21st sampling point is 2 seconds, then the corresponding driving distance S i that is Figure 6 The value of S corresponding to t=2.

[0097] Exemplary, combined Figure 4 As shown in the figure, the first segment of the path is the first sub-path, and the second and third segments of the path are the second sub-path. The first segment of the path is the path segment in the path planned in the previous cycle, and the second segment of the path is the transition from the last sampling point in the first segment of the path to the target lateral offset (i.e., L end ), the third segment is to continue driving a certain distance after reaching the target lateral offset. i ,l i ,t i ), further traverse each sampling point in turn to determine the l of each sampling point i That's it.

[0098] For the sampling points in the first segment of the path, according to the S of each sampling point i , the corresponding L coordinate value can be matched in the path planned in the previous cycle as l i , thereby determining the distance between each sampling point in the first subpath and the reference line, so as to determine the lateral offset of the last sampling point in the first subpath.

[0099] S502: Determine the lateral offset of each sampling point included in the second subpath based on the lateral offset of the last sampling point in the first subpath and the target lateral offset.

[0100] Thus, after determining the lateral offset of the last sampling point in the first subpath, the lateral offset of the next sampling point (ie, the first sampling point in the second subpath) can be calculated based on the lateral offset of the last sampling point in the first subpath.

[0101] In the embodiment of the present application, the present application can determine the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath. In this way, based on the lateral offset of the last sampling point in the first subpath and the target lateral offset, the lateral offset of each sampling point included in the second subpath is determined, and based on the path segments in the path planned in the previous cycle, a smooth transition effect between two adjacent planned paths can be achieved to ensure that no mutation occurs between the two paths.

[0102] In some embodiments, in a path planning method provided by an embodiment of the present application, the above step S502 may specifically include S601-S603.

[0103] S601: Obtain a corresponding relationship between the amount to be offset and the lateral offset speed.

[0104] The amount to be offset is the difference between the target lateral offset and the lateral offset of the sampling point.

[0105] In some embodiments, for each sampling point included in the second subpath, the lateral offset of the next sampling point can be calculated by determining the corresponding lateral offset speed based on the correspondence between the amount to be offset and the lateral offset speed, when the lateral offset of the previous sampling point is known.

[0106] Specifically, the corresponding relationship between the amount to be offset and the lateral offset velocity can be expressed by an n-order curve, such as Figure 7 As shown, a 4-degree curve is shown, and the horizontal axis is the distance L of the current sampling point end The lateral position Δl, the ordinate is the corresponding lateral offset velocity Vlat ,First, according to the current actual driving environment and needs, three points are determined (i.e. Figure 7 Point 1 (Δl1, V lat1 )、Point 2(Δl2,V lat2 ) and point 3 (Δ l3 ,V lat3 )), and determine point 1 (Δ l1 ,V lat1 ), point 2 (Δ l2 ,V lat2 ) and point 3 (Δl3, V lat3 ) corresponding to the derivative (Δl1,V lat1’ ),(Δl2,V lat2’ ),(Δl3,V lat3’ ), so a 4-degree curve v can be fitted based on these 6 points lat =f(Δl).

[0107] S602: Determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the lateral offset of the last sampling point in the first subpath and the corresponding relationship between the amount to be offset and the lateral offset speed.

[0108] Further, based on Figure 7 The quadratic curve (i.e., the corresponding relationship between the amount to be offset and the lateral offset velocity) shown is based on the last sampling point (s last ,l last ), the lateral offset of the last sampling point can be determined, and thus Figure 7 The corresponding lateral displacement velocity v is determined from the quadratic curve shown in lat =f(|l last -L end |).

[0109] It should be noted that when determining the lateral offset velocity v of the sampling point lat When v lat A constraint is added to prevent the abnormal fitting curve from causing the vehicle performance to deteriorate, thereby ensuring the robustness of the algorithm.

[0110] S603 . For each sampling point included in the second subpath, calculate the lateral offset of each sampling point based on the lateral offset speed and lateral offset corresponding to the previous sampling point of each sampling point.

[0111] The previous sampling point of the first sampling point in the second subpath is the last sampling point in the first subpath.

[0112] In this way, after determining the lateral offset velocity corresponding to the last sampling point in the first subpath, the lateral offset amount l of the next sampling point (i.e., the first sampling point in the second subpath) can be calculated according to the lateral offset velocity corresponding to the last sampling point. current .

[0113] Specifically, if l last >L end , then l current =max(l last -v lat *Δt,L end ); if l_ last ≤L end , then l current =min(l last +v lat *Δt,L end ), where Δt represents the time interval between two sampling points (i.e., 0.1 seconds), min(a,b) represents the smaller of the two values, and max(a,b) represents the larger of the two values.

[0114] Thus, for each sampling point included in the second subpath, after determining the lateral offset of the first sampling point in the second subpath, it is possible to Figure 7 The lateral offset speed corresponding to the first sampling point in the second subpath is determined by the quadratic curve shown in FIG. 1 , so that the lateral offset amount of the second sampling point can be calculated based on the lateral offset speed and lateral offset amount corresponding to the first sampling point in the second subpath. In this way, the lateral offset amount of each sampling point included in the second subpath can be determined by looping the above steps.

[0115] In an embodiment of the present application, the present application can determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the correspondence between the amount to be offset and the lateral offset speed when the lateral offset of the last sampling point in the first subpath is known. In this way, the lateral offset of the first sampling point in the second subpath can be determined based on the lateral offset speed and lateral offset corresponding to the last sampling point in the first subpath. And, for each sampling point included in the second subpath, the lateral offset of each sampling point is calculated based on the lateral offset speed and lateral offset corresponding to the previous sampling point of each sampling point. Thus, based on the lateral offset speed and lateral offset corresponding to the previous sampling point of two adjacent sampling points, the lateral offset of the next sampling point can be determined, which can ensure the effect of smooth transition between the two adjacent sampling points and ensure that no sudden change occurs between the two sampling points.

[0116] S203: Plan a path to be planned based on the lateral offset of each sampling point among the multiple sampling points.

[0117] In this way, after the lateral offset of each sampling point in the path to be planned is determined, the path to be planned can be planned.

[0118] In an embodiment of the present application, the present application can determine the lateral offset of each of the multiple sampling points included in the path to be planned by determining the target lateral offset of the end point of the vehicle's path to be planned relative to the reference line. Thus, the path to be planned is planned based on the lateral offset of each of the multiple sampling points. In this way, by determining the lateral offset corresponding to the end point of the current path to be planned, the reasonable lateral offset corresponding to each point in the path to be planned can be determined, so that when the vehicle travels from the current position to the end point of the path to be planned, it can gradually shift to the end point of the path to be planned during the driving process based on the lateral offset corresponding to each point. Thus, when planning the driving path of the autonomous driving vehicle, a driving path with higher accuracy can be planned to avoid abnormal situations when the vehicle is driving, and enhance the comfort and safety of the autonomous driving vehicle.

[0119] In some embodiments, Figure 8 As shown, in a path planning method provided in an embodiment of the present application, the above step S203 may specifically include S801-S803.

[0120] S801. Determine multiple curve functions for multiple sampling points.

[0121] Each of the multiple curve functions corresponds to at least one sampling point among the multiple sampling points, each curve function includes at least one adjustment parameter, and the multiple curve functions correspond to a preset cost function.

[0122] Optionally, the present application utilizes a piecewise polynomial curve to smooth the rough trajectory, and multiple curve functions can be expressed by the following formula 1.

[0123] l i =a i0 +a i1 s+a i2 s 2 +a i3 s 3 +a i4 s 4 +a i5 s 5 Formula 1

[0124] Among them l i represents the i-th curve function, a i0 、a i1 、a i2 、a i3 、a i4 、a i5Represents the adjustment parameter in the i-th curve function.

[0125] Furthermore, a preset cost function Cost is constructed, and the preset cost function Cost is shown in Formula 2.

[0126]

[0127] in, Indicates that the planned trajectory is as close to the rough trajectory as possible. They represent the first-order derivative, second-order derivative, and third-order derivative of l with respect to s, respectively, and are used to make the planned trajectory more comfortable.

[0128] S802: Under the constraints of preset constraints, determine the value of at least one adjustment parameter included in each of the multiple curve functions when the preset cost function takes a minimum value.

[0129] Among them, the preset constraint conditions are used to constrain at least one of the following: the value range of each curve function, the value range of any order derivative of each curve function, the first sampling point among multiple sampling points is the current position of the vehicle, and the arbitrary order derivatives corresponding to the intersection points of two adjacent curve functions among multiple curve functions are equal.

[0130] Specifically, the preset constraint condition is shown in Formula 3.

[0131] l min ≤l≤l max

[0132] l' min ≤l'≤l' max

[0133] l” min ≤l”≤l” max

[0134] l"' min ≤l”'≤l”' max

[0135] a 10 = l init

[0136] a (i-1)0 +a (i-1)1 s+a (i-1)2 s 2 +a (i-1)3 s 3 +a (i-1)4 s 4 +a (i-1)5 s 5 =a i0 +a i1 s+a i2s 2 +a i3 s 3 +a i4 s 4 +a i5 s 5

[0137] a (i-1)1 +2a (i-1)2 s+3a (i-1)3 s 2 +4a (i-1)4 s 3 +5a (i-1)5 s 4 =a i1 +2a i2 s+3a i3 s 2 +4a i4 s 3 +5a i5 s 4

[0138] 2a (i-1)2 +6a (i-1)3 s+12a (i-1)4 s 2 +20a (i-1)5 s 3 =2a i2 +6a i3 s+12a i4 s 2 +20a i5 s 3

[0139] Formula 3

[0140] Among them, s in the preset constraint conditions represents the intersection point s of two curve functions connected in the first place. The first four inequalities are used to constrain l, the first-order derivative of l, the second-order derivative of l, and the third-order derivative of l must be within the constraint range. The fifth item indicates that the initial moment must pass through the planning starting point. The sixth to eighth items indicate that the intersection of the two curve functions connected in the first place, the first-order derivative (i.e., velocity) at the intersection, and the second-order derivative (i.e., acceleration) at the intersection must be equal.

[0141] In this way, under the constraints of the preset constraints, it is possible to determine the value of at least one adjustment parameter included in each of the multiple curve functions when the preset cost function takes the minimum value.

[0142] S803: Determine a plurality of curve functions based on a value of at least one adjustment parameter included in each curve function, so as to plan a path to be planned based on the plurality of curve functions.

[0143] Furthermore, the trajectory to be planned in the Frenet coordinate system can be converted to the DR coordinate system to obtain the path to be planned.

[0144] In an embodiment of the present application, the present application can determine multiple curve functions for multiple sampling points, so that the multiple curve functions pass through multiple sampling points as much as possible, thereby determining the path to be planned through multiple curve functions. In addition, the preset cost function is constrained by a preset constraint condition, so that when the preset cost function takes the minimum value, the value of at least one adjustment parameter included in each of the multiple curve functions is determined, thereby determining multiple curve functions. In this way, based on the value of at least one adjustment parameter included in each determined curve function, the determined multiple curve functions can pass through multiple sampling points as much as possible, thereby accurately determining the path to be planned.

[0145] This application uniformly converts the reference lines determined by the high-precision map and the reference lines determined by the perception device into the track-reckoning coordinate system to achieve the unification of the reference lines, so that the path planning can be seamlessly transitioned. And the continuity of the region of interest is processed by the inter-frame control of the planning trajectory (i.e., two adjacent cycles), that is, the continuity is achieved within the preview range of the control module, so that the stability of the trajectory and the flexibility of the trajectory are guaranteed. And by generating an n-order curve of the relationship between the relative position and the lateral speed relative to the lateral position of the target, and then using the curve lookup table to generate a rough trajectory, and finally using the optimization algorithm (cost function and constraints) to smooth the rough trajectory, the purpose of improving the robustness of the planning algorithm is achieved. And in the lateral planning process, the planning results of the longitudinal planning for a period of time in the future are considered. Good results have been achieved in the compatibility, stability, flexibility, robustness of the planning, and the rationality of the coordination of the longitudinal performance.

[0146] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the path planning device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0147] The embodiments of the present application can exemplarily divide the functional modules of the path planning device or electronic device according to the above method. For example, the path planning device or electronic device can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0148] Fig. 9 is a block diagram of a path planning device according to an exemplary embodiment. Fig. 9 The path planning device 900 includes: a processing module 901 and an acquisition module 902.

[0149] The processing module 901 is used to determine a target lateral offset of an end point of a to-be-planned path of the vehicle relative to a reference line, where the to-be-planned path includes a plurality of sampling points, and the reference line is a reference line corresponding to a lane in which the vehicle is currently traveling; the processing module 901 is also used to determine a lateral offset of each of the plurality of sampling points included in the to-be-planned path based on the target lateral offset; the processing module 901 is also used to plan the to-be-planned path based on the lateral offset of each of the plurality of sampling points.

[0150] In a possible implementation, the path to be planned includes a first sub-path, which is a path segment determined from a path planned in a previous cycle; the processing module 901 is specifically used to determine the lateral offset of each sampling point among multiple sampling points included in the path to be planned based on the first sub-path and the target lateral offset.

[0151] In a possible implementation, the path to be planned also includes a second subpath, the first subpath and the second subpath are connected, and the first subpath is located before the second subpath; the processing module 901 is specifically used to determine, based on the first subpath and the reference line, the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath; the processing module 901 is specifically used to determine the lateral offset of each sampling point included in the second subpath based on the lateral offset of the last sampling point in the first subpath and the target lateral offset.

[0152] In a possible implementation, the processing module 901 is specifically used to obtain a correspondence between the amount to be offset and the lateral offset speed, where the amount to be offset is the difference between the target lateral offset and the lateral offset of the sampling point; the processing module 901 is specifically used to determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the lateral offset of the last sampling point in the first subpath and the correspondence between the amount to be offset and the lateral offset speed; the processing module 901 is specifically used to calculate the lateral offset of each sampling point included in the second subpath based on the lateral offset speed and the lateral offset corresponding to the previous sampling point of each sampling point, where the previous sampling point of the first sampling point in the second subpath is the last sampling point in the first subpath.

[0153] In a possible implementation, the processing module 901 is specifically used to determine multiple curve functions for multiple sampling points, each of the multiple curve functions corresponds to at least one sampling point among the multiple sampling points, each curve function includes at least one adjustment parameter, and the multiple curve functions correspond to a preset cost function; the processing module 901 is specifically used to determine, under the constraint of a preset constraint condition, the value of at least one adjustment parameter included in each of the multiple curve functions when the preset cost function takes a minimum value, and the preset constraint condition is used to constrain at least one of the following: a value range of each curve function, a value range of any order derivative of each curve function, the first sampling point among the multiple sampling points is the current position of the vehicle, and any order derivatives corresponding to the intersection of two adjacent curve functions among the multiple curve functions are equal; the processing module 901 is specifically used to determine multiple curve functions based on the value of at least one adjustment parameter included in each curve function, so as to plan the path to be planned based on the multiple curve functions.

[0154] In a possible implementation, the processing module 901 is further used to determine the center line of the lane in which the vehicle is currently traveling in the high-precision map as a reference line when there is a high-precision map corresponding to the current position of the vehicle; the processing module 901 is also used to determine the center line of the lane line obtained by the vehicle's perception device as a reference line when there is no high-precision map corresponding to the current position of the vehicle.

[0155] In a possible implementation, the processing module 901 is specifically used to determine the center line of the lane in which the vehicle is currently traveling in the high-precision map as a reference line when there is a high-precision map corresponding to the current position of the vehicle and the high-precision map matches the perception data acquired by the perception device.

[0156] In one possible implementation, the acquisition module 902 is used to acquire the driving decision of the vehicle, and the driving decision is used to indicate whether the vehicle needs to perform any of the following: changing lanes, turning; the processing module 901 is specifically used to determine the end point of the path to be planned based on the driving decision of the vehicle, and determine the distance between the end point of the path to be planned and the reference line as the target lateral offset.

[0157] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0158] Fig.10 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Fig.10 As shown, the electronic device 1000 includes but is not limited to: a processor 1001 and a memory 1002 .

[0159] The memory 1002 is used to store executable instructions of the processor 1001. It can be understood that the processor 1001 is configured to execute instructions to implement the path planning method in the above embodiment.

[0160] It should be noted that those skilled in the art can understand that Fig.10 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Fig.10 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0161] The processor 1001 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 1002, and calling data stored in the memory 1002, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 1001 may include one or more processing units. Optionally, the processor 1001 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1001.

[0162] The memory 1002 may be used to store software programs and various data. The memory 1002 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a processing module, a storage module, etc.), etc. In addition, the memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0163] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1002 including instructions. The above instructions can be executed by the processor 1001 of the electronic device 1000 to implement the path planning method in the above embodiment.

[0164] In actual implementation, Fig. 9 The functions of the processing module 901 and the acquisition module 902 in Fig.10 The processor 1001 in the embodiment calls the computer program stored in the memory 1002. The specific execution process can refer to the description of the path planning method in the above embodiment, which will not be repeated here.

[0165] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0166] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 1001 of the electronic device 1000 to complete the path planning method in the above embodiment.

[0167] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned path planning method embodiment are implemented, and the same technical effect as the above-mentioned path planning method can be achieved. To avoid repetition, they will not be repeated here.

[0168] Fig.11 A schematic diagram of the structure of a computer system of an electronic device is shown. It should be noted that: Fig.11 The computer system of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0169] like Fig.11As shown, the computer system includes a central processing unit (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) or the program loaded from the storage part to the random access memory (RAM), such as executing the method in the above embodiment. In the RAM, various programs and data required for system operation are also stored. The CPU, ROM and RAM are connected to each other through a bus. The input / output (I / O) interface is also connected to the bus. The I / O interface is used to implement functions such as data input, output, communication, and storage, and the storage function can be specifically implemented by removable media.

[0170] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., are installed on the drive as needed so that a computer program read therefrom is installed into the storage part as needed.

[0171] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), various functions defined in the system of the present application are executed.

[0172] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0173] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0174] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0175] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0176] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0178] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A path planning method, characterized in that: The method comprises: Determine a target lateral offset of an end point of a to-be-planned path of the vehicle relative to a reference line, the to-be-planned path comprising a plurality of sampling points, the reference line being a reference line corresponding to a lane in which the vehicle is currently traveling; Determine, based on the target lateral offset, a lateral offset of each sampling point among the plurality of sampling points included in the path to be planned; The path to be planned is planned based on the lateral offset of each sampling point in the multiple sampling points.

2. The method according to claim 1, characterized in that The path to be planned includes a first sub-path, where the first sub-path is a path segment determined from a path planned in a previous cycle; The step of determining the lateral offset of each sampling point in the plurality of sampling points included in the path to be planned based on the target lateral offset comprises: Based on the first sub-path and the target lateral offset, a lateral offset of each sampling point in the plurality of sampling points included in the path to be planned is determined.

3. The method according to claim 2, characterized in that The path to be planned further includes a second sub-path, the first sub-path and the second sub-path are connected, and the first sub-path is located before the second sub-path; The determining, based on the first sub-path and the target lateral offset, the lateral offset of each sampling point in the plurality of sampling points included in the path to be planned comprises: Based on the first subpath and the reference line, determining the distance between the last sampling point in the first subpath and the reference line as the lateral offset of the last sampling point in the first subpath; Based on the lateral offset of the last sampling point in the first subpath and the target lateral offset, the lateral offset of each sampling point included in the second subpath is determined.

4. The method according to claim 3, characterized in that The determining, based on the lateral offset of the last sampling point in the first subpath and the target lateral offset, of each sampling point included in the second subpath comprises: Acquire a corresponding relationship between the amount to be offset and the lateral offset speed, wherein the amount to be offset is the difference between the target lateral offset and the lateral offset of the sampling point; Determine the lateral offset speed corresponding to the last sampling point in the first subpath based on the lateral offset of the last sampling point in the first subpath and the corresponding relationship between the amount to be offset and the lateral offset speed; For each sampling point included in the second subpath, a lateral offset of each sampling point is calculated based on the lateral offset speed and lateral offset corresponding to a previous sampling point of each sampling point, and a previous sampling point of a first sampling point in the second subpath is the last sampling point in the first subpath.

5. The method according to claim 1, characterized in that The planning of the path to be planned based on the lateral offset of each sampling point in the plurality of sampling points comprises: Determine a plurality of curve functions for the plurality of sampling points, each of the plurality of curve functions corresponds to at least one sampling point among the plurality of sampling points, each curve function includes at least one adjustment parameter, and the plurality of curve functions correspond to a preset cost function; Under the constraints of preset constraints, when it is determined that the preset cost function takes a minimum value, the value of the at least one adjustment parameter included in each of the multiple curve functions, the preset constraints are used to constrain at least one of the following: the value range of each curve function, the value range of any order derivative of each curve function, the first sampling point of the multiple sampling points is the current position of the vehicle, and the arbitrary order derivatives corresponding to the intersection points of two adjacent curve functions in the multiple curve functions are equal; Based on the value of the at least one adjustment parameter included in each curve function, the multiple curve functions are determined, so as to plan the path to be planned based on the multiple curve functions.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: In the case where there is a high-precision map corresponding to the current position of the vehicle, determining the center line of the lane in which the vehicle is currently traveling in the high-precision map as the reference line; When the current position of the vehicle does not correspond to the high-precision map, the center line of the lane line obtained by the perception device of the vehicle is determined as the reference line.

7. The method according to claim 6, characterized in that In the case where there is a high-precision map corresponding to the current position of the vehicle, determining the center line of the lane in which the vehicle is currently traveling in the high-precision map as the reference line includes: When the high-precision map corresponds to the current position of the vehicle and the high-precision map matches the perception data acquired by the perception device, the center line of the lane in which the vehicle is currently traveling in the high-precision map is determined as the reference line.

8. The method according to any one of claims 1 to 5, characterized in that The step of determining a target lateral offset of an end point of a to-be-planned path of the vehicle relative to a reference line comprises: Acquire a driving decision of the vehicle, where the driving decision is used to indicate whether the vehicle needs to perform any of the following: change lanes, turn; Based on the driving decision of the vehicle, an end point of the path to be planned is determined, and a distance between the end point of the path to be planned and the reference line is determined as the target lateral offset.

9. A path planning device, characterized in that: The path planning device comprises: a processing module; The processing module is used to determine a target lateral offset of an end point of a to-be-planned path of the vehicle relative to a reference line, the to-be-planned path includes a plurality of sampling points, and the reference line is a reference line corresponding to a lane in which the vehicle is currently traveling; The processing module is further used to determine the lateral offset of each sampling point among the multiple sampling points included in the path to be planned based on the target lateral offset; The processing module is further used to plan the path to be planned based on the lateral offset of each sampling point in the multiple sampling points.

10. An electronic device, characterized in that: include: A processor and a memory; wherein the memory is used to store one or more programs, and the one or more programs include computer-executable instructions. When the electronic device is running, the processor executes the computer-executable instructions stored in the memory, and the electronic device executes the method described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: When the computer instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device executes the method as claimed in any one of claims 1 to 8.

12. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 8.

13. A vehicle, characterized in that: The vehicle comprises the path planning device according to claim 9, and the vehicle is used to implement the method according to any one of claims 1-8.

Images