Path planning information collection method, path planning method and electronic device
By adjusting the position of vertical sampling points and collecting horizontal sampling points based on environmental information in the dynamic programming algorithm, the problem of poor path planning effect caused by poor sampling points in the prior art is solved, and the success rate of path planning is improved and accuracy.
Patent Information
- Application Number
- CN202111016391.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-31
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2041-08-31
AI Technical Summary
The existing dynamic programming algorithm does not consider environmental factors in path planning, resulting in poor position of vertical sampling points, resulting in a large number of horizontal sampling points being unavailable, affecting the effectiveness of path planning.
Adjust the position of the longitudinal sampling points according to the environmental information to adapt to the distribution of environmental information, and collect horizontal sampling points from left to right to ensure that the sampling points are distributed reasonably and suitable for the actual environment.
It improves the success rate and effectiveness of path planning, ensures that the sampling points are reasonably distributed in the actual environment, and enhances the accuracy and availability of path planning.
Smart Images

Figure CN113739805B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of autonomous driving technology, and in particular to a path planning information collection method, a path planning method and an electronic device. Background Art
[0002] With the development of artificial intelligence technology, autonomous driving technology has become more mature. Autonomous driving technology can be briefly divided into perception, prediction, positioning, decision-making, planning and control. Planning usually refers to the path planning method. The main task is to reasonably explore the environment space based on the current vehicle information and finally plan a path that is easy for the controller to execute and collision-free.
[0003] The dynamic programming algorithm is one of the most common path planning methods in the field of autonomous driving. The dynamic programming algorithm requires inputs such as a reference path and environmental information. The reference path represents the path that the vehicle originally needs to travel (due to obstacles around the path, etc., it is necessary to call the dynamic programming algorithm to generate an obstacle avoidance path), and the environmental information refers to the obstacle information around the vehicle, the passable area information and other conditions. Common description forms are obstacle points or distance transformation diagrams.
[0004] The calculation process of the dynamic programming algorithm mainly includes sampling, connection and screening.
[0005] Sampling refers to sampling along the direction of the reference path (also called "longitudinal") to obtain a series of straight lines (also called "layers") perpendicular to the reference path (also called "transverse"), and then sampling on these straight lines according to the principle of equal intervals or equal quantities to obtain a series of transverse sampling points.
[0006] Connection means using curve connection to connect the sampling points on two adjacent layers.
[0007] Screening means that for each sampling point on each layer, only the best connection curve connected to the previous layer is selected and retained through a predetermined selection criterion.
[0008] The connection and screening between layers are the subtasks that the dynamic programming algorithm needs to complete. After completing all subtasks, a complete dynamic programming trajectory can be obtained by sequentially finding the optimal connection curve of the end point and its corresponding node.
[0009] Based on the above introduction, it can be found that the effect of dynamic planning path depends largely on the location of sampling points in the sampling step. A good sampling point location can greatly improve the success rate of path search. However, an unreasonable sampling point location will seriously limit the generation of inter-layer connection paths, resulting in a reduction in dynamic planning solutions and affecting the effect of path planning. Summary of the invention
[0010] The embodiments of the present invention aim to solve at least one of the above technical problems.
[0011] In a first aspect, an embodiment of the present invention provides a method for collecting path planning information, including:
[0012] Get the reference path;
[0013] According to the environmental information of the reference path, a plurality of longitudinal sampling points are acquired on the reference path, wherein the plurality of longitudinal sampling points are adapted to the distribution of the environmental information;
[0014] A plurality of transverse sampling points are collected on the left side and / or the right side of the plurality of longitudinal sampling points for path planning.
[0015] In a second aspect, an embodiment of the present invention provides a path planning method, including:
[0016] Collecting path planning information using the path planning information collection method of any embodiment of the present invention;
[0017] A planned path is determined according to the path planning information.
[0018] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-mentioned path planning information collection methods and / or path planning methods of the present invention.
[0019] In a fourth aspect, an embodiment of the present invention provides a mobile object, comprising a main body and an electronic device according to any embodiment of the present invention mounted on the main body.
[0020] In a fifth aspect, an embodiment of the present invention provides a storage medium, in which one or more programs including execution instructions are stored. The execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute any one of the above-mentioned path planning information collection methods and / or path planning methods of the present invention.
[0021] In a sixth aspect, an embodiment of the present invention further provides a computer program product, the computer program product comprising a computer program stored on a storage medium, the computer program comprising program instructions, and when the program instructions are executed by a computer, the computer executes any one of the above-mentioned path planning information collection methods and / or path planning methods.
[0022] In an embodiment of the present invention, a plurality of longitudinal sampling points are obtained on the reference path based on the environmental information of the reference path, wherein the plurality of longitudinal sampling points are adapted to the distribution of the environmental information, and the sampling points are obtained in combination with the environmental information, so that the obtained sampling points are more suitable for the external environment actually detected, which helps to plan a path that conforms to the actual external environment. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.
[0024] Figure 1 It is a schematic diagram of sampling results in a dynamic programming method in the prior art;
[0025] Figure 2 A flow chart of an embodiment of a method for collecting path planning information of the present invention;
[0026] Figure 3 A schematic diagram of another embodiment of the method for collecting path planning information of the present invention;
[0027] Figure 4 A schematic diagram of adjusting the initial longitudinal sampling point in the present invention;
[0028] Figure 5 A schematic diagram of another embodiment of the method for collecting path planning information of the present invention;
[0029] Figure 6 A schematic diagram of another embodiment of the method for collecting path planning information of the present invention;
[0030] Figure 7 It is a schematic diagram of adjusting the initial longitudinal sampling point in the present invention;
[0031] Figure 8 A schematic diagram of an embodiment of determining the traversable boundary of a certain waypoint in the present invention;
[0032] Fig. 9 A schematic diagram of another embodiment of determining the traversable boundary of a certain waypoint in the present invention;
[0033] Fig.10 A schematic diagram of another embodiment of determining the traversable boundary of a certain waypoint in the present invention;
[0034] Fig.11 A schematic diagram of sampling points collected by the path information collection method of the present invention;
[0035] Fig.12 It is a schematic structural diagram of an embodiment of an electronic device of the present invention. DETAILED DESCRIPTION
[0036] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other without conflict.
[0037] It should also be noted that, in this article, the terms "include" and "comprise" include not only those elements, but also other elements not explicitly listed, or elements inherent to such processes, methods, articles or equipment. In the absence of further restrictions, the elements defined by the sentence "include..." do not exclude the existence of other identical elements in the process, method, article or equipment that includes the elements.
[0038] like Figure 1 The figure is a schematic diagram of sampling results in the dynamic programming method in the prior art. The black box is an obstacle, the black curve is a reference path, the five longitudinal sampling points on the reference path are evenly spaced, and the transverse sampling points on both sides of each longitudinal sampling point (sampling points outside the reference path) are also evenly spaced.
[0039] However, in the process of implementing the present invention, the inventors found that: due to not considering environmental factors, the fourth longitudinal sampling point (from left to right) is located on the obstacle, and the multiple transverse sampling points corresponding to the fourth longitudinal sampling point are also located on the obstacle, and these sampling points are not available. In addition, due to not considering environmental factors, some transverse sampling points corresponding to the second and third longitudinal sampling points (from left to right) are also located on the obstacle and cannot be used for path planning.
[0040] Therefore, there are at least the following problems in the existing dynamic programming algorithm:
[0041] The longitudinal sampling of existing dynamic programming algorithms often adopts a fixed interval or vehicle speed-related strategy. Once the longitudinal sampling position is not good, a large number of lateral sampling points in this layer will be unavailable (for example, Figure 1 The fourth longitudinal sampling point and the corresponding transverse sampling point in );
[0042] The existing dynamic programming algorithms often use fixed interval or fixed number of horizontal sampling schemes. Due to the lack of awareness of the negative impact of environmental information, it is inevitable that a large number of sampling points will be unavailable when the environment is not good (such as crossing a narrow area). Figure 1 The second and third longitudinal sampling points and the corresponding transverse sampling points in the graph).
[0043] In order to overcome the technical problems found, the inventor proposes a path information collection method, which can be applied to electronic devices. The electronic device can be a vehicle system or a control unit of an aircraft or underwater robot, etc., and the present invention is not limited to this.
[0044] like Figure 2 As shown, an embodiment of the present invention provides a path planning information collection method, comprising:
[0045] S10, obtaining a reference path. Exemplarily, the reference path can be obtained by referring to the mature methods in the prior art, and the present invention is not limited to this.
[0046] S20. Acquire a plurality of longitudinal sampling points on the reference path according to the environmental information of the reference path, wherein the plurality of longitudinal sampling points are adapted to the distribution of the environmental information.
[0047] Exemplarily, the environmental information of the reference path includes environmental information on or on both sides of the reference path.
[0048] S30, collecting a plurality of transverse sampling points on the left side and / or the right side of the plurality of longitudinal sampling points for path planning.
[0049] In this embodiment, sampling points are obtained in combination with environmental information, and the multiple longitudinal sampling points are adapted to the distribution of environmental information, so that the obtained sampling points are more suitable for the external environment actually detected, and the distribution of sampling points is more reasonable, which helps to plan a path that conforms to the actual external environment.
[0050] Exemplarily, the environmental information includes obstacle information, and the obstacle information includes boundary position information of the obstacle; the plurality of longitudinal sampling points are adapted to the distribution of the environmental information, including: at least one longitudinal sampling point among the plurality of longitudinal sampling points is distributed close to the obstacle.
[0051] In this embodiment, the environmental information includes obstacle information, and at least one of the multiple longitudinal sampling points is distributed close to the obstacle, which helps to subsequently sample more information near the obstacle in the horizontal direction. When the sampling points are fixed, the information near the obstacle is sampled mainly, so that the road conditions near the obstacle can be considered in detail, which helps to plan the obstacle avoidance path more accurately.
[0052] like Figure 3FIG. 1 is a schematic diagram of another embodiment of the method for collecting path planning information of the present invention. In this embodiment, a plurality of longitudinal sampling points are obtained on the reference path according to the environmental information of the reference path, including:
[0053] S21. Sample a plurality of initial longitudinal sampling points at equal intervals on the reference path.
[0054] Exemplarily, a plurality of initial longitudinal sampling points are sampled at preset intervals on the reference path. The preset intervals may be set according to actual conditions. For example, for a case where the computing power is strong and the precision requirement is high, the preset interval may be set smaller; for a case where the computing power is weak and the precision requirement is not too high, the preset interval may be set larger. The present invention is not limited to this.
[0055] S22. Adjust the multiple initial longitudinal sampling points according to the obstacle information to obtain multiple longitudinal sampling points.
[0056] Exemplarily, after obtaining multiple initial longitudinal sampling points, adjustment is performed in combination with obstacle information: initial longitudinal sampling points that meet preset conditions among the multiple initial longitudinal sampling points are replaced with longitudinal sampling points near the obstacle, so as to facilitate transverse sampling of more information near the obstacle.
[0057] like Figure 4 The figure shows a schematic diagram of adjusting the initial longitudinal sampling points in the present invention, wherein the black boxes are obstacles, the black dotted lines are the boundaries of the road, the black solid lines are the reference paths, O1-O5 are five initial longitudinal sampling points, O′1, O′2 and O′3 are longitudinal sampling points after adjustment corresponding to O1, O2 and O3 respectively, and the arrows indicate the adjustment direction of each initial longitudinal sampling point.
[0058] In this embodiment, multiple initial longitudinal sampling points are first collected at equal intervals, and then the multiple initial longitudinal sampling points are dynamically adjusted according to obstacle information, so that longitudinal sampling points with more reasonable distribution are quickly determined when the initial longitudinal sampling points are fixed.
[0059] In some embodiments, the environmental information also includes road boundary information, which can be used to determine the boundary of the road. Figure 5 FIG. 1 is a schematic diagram of another embodiment of the path planning information collection method of the present invention. In this embodiment, adjusting the multiple initial longitudinal sampling points according to the obstacle information to obtain multiple longitudinal sampling points includes:
[0060] S221 , judging whether there is an obstacle within a preset range corresponding to each of the initial longitudinal sampling points to determine whether the corresponding initial longitudinal sampling point needs to be adjusted.
[0061] Exemplarily, it also includes determining a preset range: the preset range of each initial longitudinal sampling point is an area enclosed by a preset boundary corresponding to each initial longitudinal sampling point and a road boundary, wherein the preset boundary corresponding to each initial longitudinal sampling point is a straight line passing through the midpoint of the reference path between the initial longitudinal sampling point and the adjacent initial longitudinal sampling point. Optionally, the preset boundary may be perpendicular to the reference path, or the acute angle between the preset boundary and the reference path may be greater than a preset angle threshold. For example, the preset angle threshold is 50 degrees. For the first longitudinal sampling point among the multiple initial longitudinal sampling points, for example, Figure 4 For the longitudinal sampling point O1 in the image, since there is no adjacent longitudinal sampling point on its left side, a preset boundary line L1 is set at a distance of half the preset interval on its left side. Similarly, for the longitudinal sampling point O5, a preset boundary line can be set at a distance of half the preset interval on its right side. Finally, a partition corresponding to each initial longitudinal sampling point (i.e., a respective preset range) is obtained.
[0062] For example, Figure 4 As shown, the preset boundaries L1-L5 are the boundaries for regional division. The area formed by the preset boundaries L1, L2 and the boundary of the road is the preset range corresponding to the preset range O1. There is an obstacle at the upper end of the preset range, and the current O1 is far away from the obstacle, so it is moved to O′1. It should be noted that the movement is limited to the preset range of O1. O4 is already above the obstacle (i.e., infinitely close to the obstacle), so there is no need to move. There is no obstacle near O5, so there is no need to move.
[0063] S222: Adjust the initial longitudinal sampling points that need to be adjusted based on the obstacle information.
[0064] In this embodiment, only the initial longitudinal sampling points that meet the preset range are adjusted, so that some sampling points are close to obstacles, which is convenient for more sampling of road conditions with obstacles, and avoids all sampling points being too concentrated near obstacles, affecting the balance of sampling points on the entire path.
[0065] like Figure 6 FIG. 1 is a schematic diagram of another embodiment of the path planning information collection method of the present invention. In this embodiment, the initial longitudinal sampling points that need to be adjusted are adjusted in combination with the obstacle information, including:
[0066] S2221, determining a plurality of candidate longitudinal sampling points within a preset range corresponding to an initial longitudinal sampling point that needs to be adjusted, wherein the plurality of candidate longitudinal sampling points are distributed on reference paths on both sides of the initial longitudinal sampling point that needs to be adjusted;
[0067] S2222: Determine the safety distance between the plurality of candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted, based on the obstacle information and the road boundary information;
[0068] S2223. Determine the sampling point corresponding to the minimum safety distance as the adjusted longitudinal sampling point.
[0069] In this embodiment, the longitudinal sampling point with the smallest safety distance is selected as the final longitudinal sampling point. The smaller the safety distance, the more complex the road condition. Therefore, selecting this sampling point for subsequent lateral collection helps to obtain road condition information of more complex sections, thereby performing more accurate path planning.
[0070] like Figure 7 The diagram shows the adjustment of the initial longitudinal sampling point in the present invention. In this embodiment, O1 is taken as an example to illustrate, and multiple candidate longitudinal sampling points are determined on the reference path between the two boundaries (inclusive) of O1, and then the safety distance of each candidate longitudinal sampling point is compared one by one. For places without obstacles, the safety distance is the distance between the two dotted lines (road boundaries), and for places with obstacles, the safety distance is the distance between the boundary of the obstacle and the road boundary (or the boundary of another obstacle). In this embodiment, it is determined by comparison that the safety distance H1 of O′1 is the smallest, so that the candidate longitudinal sampling point is determined to be the adjusted longitudinal sampling point. When the longitudinal sampling points after the translation of two adjacent initial longitudinal sampling points coincide, only one longitudinal sampling point is retained.
[0071] In some embodiments, a distance transformation map is used to determine the safe distance of sampling points, wherein the sampling points include the multiple candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted.
[0072] Exemplarily, combining the obstacle information and the road boundary information to determine the safety distance between the multiple candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted includes: combining the obstacle information and the road boundary information to determine the safety distance from the sampling point (any one of the multiple candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted) to the road boundary direction.
[0073] Exemplarily, combining the obstacle information and the road boundary information to determine a safe distance from a sampling point to a road boundary direction includes:
[0074] Using a distance transformation graph, at least one safety distance is determined from the sampling point to the road boundary direction; wherein,
[0075] When there is only one obstacle between the sampling point and the road boundary, and the only obstacle is located above the road boundary, the at least one safety distance is unique (corresponding to Figure 8 in the case of
[0076] When there is only one obstacle between the sampling point and the road boundary, and the only obstacle is outside the road boundary, the at least one safety distance is two (corresponding to Fig. 9 in the case of
[0077] When there are multiple obstacles between the sampling point and the road boundary, the at least one safety distance is multiple (corresponding to Fig.10 in the case).
[0078] In some embodiments, the distance transformation map may be used to calculate the safety distances on both sides of multiple candidate longitudinal sampling points on the reference path and the initial longitudinal sampling point that needs to be adjusted. Figure 8 FIG. 1 is a schematic diagram of an embodiment of determining a traversable boundary of a certain waypoint (eg, an alternative longitudinal sampling point or an initial longitudinal sampling point) in the present invention.
[0079] The dot O1 represents a waypoint, the rectangular box represents the vehicle model frame corresponding to O1; the black rectangles obs1 and obs2 represent obstacles; R1, R2, and R3 represent the radius corresponding to the center of the circle O1, O2, and O3 respectively. H1 finally obtains the shortest distance of the waypoint along the horizontal direction.
[0080] According to the distance transformation diagram, the distance value of the waypoint position O1 can be read. This distance value represents the distance between O1 and the nearest obstacle, which means that there is no obstacle at least within this distance in the horizontal direction of O1. It can be assumed that this distance is R1, and O2 is the position obtained after moving R1 length in the horizontal direction. Similarly, according to the distance transformation diagram, the distance value of O2 to the nearest obstacle can be read, recorded as R2. Similarly, O2 can be translated to obtain O3, and then R3. When the distance transformation value read from the position after translation is small enough or 0, it can be considered that the position is very close to the obstacle or is already on the obstacle. The safe distance of the waypoint in this direction can be obtained by accumulating all translation distances. The same can be obtained on the other side.
[0081] In the figure above, the safety distance H1 is:
[0082] H1=R1+R2+R3
[0083] like Fig. 9 FIG. 2 is a schematic diagram of another embodiment of determining the passable boundary of a certain waypoint in the present invention. Assume that O3 continues to translate out of the obstacle and obtains a position O that is very close to the obstacle. 21 , for O21 After performing the same operation as O1, if there is a road boundary so that the distance transformation value read after the translation is small enough or 0, the distance H2 from a certain waypoint to the road boundary after it passes the nearest obstacle obs2 can be obtained. In the above figure, H2 is:
[0084] H2=2R′1+R′2
[0085] like Fig.10 FIG. 2 is a schematic diagram of another embodiment of determining the passable boundary of a certain waypoint in the present invention. Assume that O3 continues to translate out of the obstacle and obtains a position O that is very close to the obstacle. 31 , for O 31 After performing the same operation as O1, if there is an obstacle obs3 that makes the distance transformation value of the translated position small enough or 0, the distance H3 from a certain waypoint to the next nearest obstacle after it passes the nearest obstacle can be obtained. In the above figure, H3 is:
[0086] H3=2R″1+R″2
[0087] The embodiment of the present invention improves the dynamic programming algorithm and uses the method for calculating the safety distance proposed in the present invention to move the longitudinal sampling points within the designated area to the area with a smaller safety distance, so that the distribution of the longitudinal sampling points tends to the area with denser obstacles, thereby ensuring the rationality of the longitudinal sampling points.
[0088] In some embodiments, the method further includes: for each of the longitudinal sampling points, selecting a safety distance greater than a preset threshold from the corresponding at least one safety distance;
[0089] The collecting of multiple transverse sampling points on the left and / or right sides of the multiple longitudinal sampling points for path planning includes: collecting multiple transverse sampling points within a safety distance range greater than a preset threshold of each longitudinal sampling point for path planning. The preset threshold is the width of the mobile device (e.g., the width of a vehicle).
[0090] In this embodiment, lateral sampling is performed only in the passable area, thereby avoiding invalid sampling points and the interference of invalid sampling points on path planning.
[0091] like Fig.11 The schematic diagram of the sampling points collected by the path information collection method of the present invention is shown in FIG. It can be seen from the figure that the main sampling points are concentrated in the passable area for sampling, avoiding the collection of invalid sampling points on obstacles.
[0092] In some embodiments, after all longitudinal optimized sampling points are obtained, the transverse sampling points can be determined according to the size of the traversable space, and the principle is as follows:
[0093] If the safety distance H on both sides of the corresponding longitudinal sampling point is greater than the threshold H threshold , then take equal number of samples within the safety distance H to obtain the horizontal sampling points;
[0094] If the safety distance H on both sides of the corresponding longitudinal sampling point is less than the threshold H threshold , then after crossing the nearest obstacle on both sides, the distance to the next nearest obstacle is H 2 The same number of samples are taken internally to obtain horizontal sampling points;
[0095] Among them, the threshold H threshold The setting can refer to the minimum passable width of the vehicle, so that the vehicle can threshold As long as the internal energy can pass smoothly.
[0096] According to the above principles, we can get a complete horizontal and vertical sampling diagram. Fig.11 , where curve S is the dynamic programming result obtained based on the path sampling information.
[0097] In the embodiment of the present invention, based on the adjustment of the longitudinal sampling point, the H or H 2 The horizontal sampling points are distributed at a safe distance so that when crossing a narrow area or a scene completely blocked by obstacles, the horizontal sampling points will not be covered by a large number of obstacles and become invalid, thereby improving the success rate of dynamic planning search.
[0098] In some embodiments, the present invention further provides a path planning method, comprising:
[0099] Collecting path planning information using the path planning information collection method of any of the aforementioned embodiments of the present invention;
[0100] A planned path is determined according to the path planning information.
[0101] In some embodiments, the path planning method includes the following steps:
[0102] Get the reference path.
[0103] According to the environmental information of the reference path, a plurality of longitudinal sampling points are acquired on the reference path, wherein the plurality of longitudinal sampling points are adapted to the distribution of the environmental information.
[0104] Collecting a plurality of transverse sampling points on the left side and / or the right side of the plurality of longitudinal sampling points for path planning;
[0105] The planned path is determined according to the collected path planning information.
[0106] In this embodiment, sampling points are obtained in combination with environmental information, and the multiple longitudinal sampling points are adapted to the distribution of environmental information, so that the obtained sampling points are more suitable for the external environment actually detected, and the distribution of sampling points is more reasonable, which helps to plan a path that conforms to the actual external environment.
[0107] In some embodiments, the environmental information includes obstacle information, and the obstacle information includes boundary position information of the obstacle; the plurality of longitudinal sampling points are adapted to the distribution of the environmental information, including: at least one longitudinal sampling point among the plurality of longitudinal sampling points is distributed close to the obstacle.
[0108] In some embodiments, acquiring a plurality of longitudinal sampling points on the reference path according to the environmental information of the reference path includes:
[0109] A plurality of initial longitudinal sampling points are sampled at equal intervals on the reference path.
[0110] The multiple initial longitudinal sampling points are adjusted according to the obstacle information to obtain multiple longitudinal sampling points.
[0111] In some embodiments, adjusting the multiple initial longitudinal sampling points according to the obstacle information to obtain multiple longitudinal sampling points includes:
[0112] It is determined whether there is an obstacle within a preset range corresponding to each of the initial longitudinal sampling points to determine whether the corresponding initial longitudinal sampling point needs to be adjusted.
[0113] The initial longitudinal sampling points that need to be adjusted are adjusted in combination with the obstacle information.
[0114] In some embodiments, the environmental information further includes road boundary information, and the initial longitudinal sampling points that need to be adjusted are adjusted in combination with the obstacle information, including:
[0115] Selecting a plurality of candidate longitudinal sampling points from the reference path within the preset range, wherein the plurality of candidate longitudinal sampling points are distributed on both sides of the corresponding initial longitudinal sampling point;
[0116] Determine the safety distance between the plurality of candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted in combination with the obstacle information and the road boundary information;
[0117] The sampling point corresponding to the minimum safety distance is determined as the adjusted longitudinal sampling point.
[0118] In some embodiments, it also includes: for each of the longitudinal sampling points, screening out a safety distance greater than a preset threshold from the corresponding at least one safety distance; the collecting of multiple horizontal sampling points on the left and / or right side of the multiple longitudinal sampling points for path planning includes: collecting multiple horizontal sampling points within the safety distance range greater than the preset threshold of each longitudinal sampling point for path planning. Wherein, the preset threshold is the width of the mobile device. .
[0119] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of combined actions, but those skilled in the art should be aware that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.
[0120] In some embodiments, an embodiment of the present invention provides a non-volatile computer-readable storage medium, which stores one or more programs including execution instructions, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to execute any of the above-mentioned path planning information collection methods (or path planning methods) of the present invention.
[0121] In some embodiments, an embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes any one of the above-mentioned path planning information collection methods (or path planning methods).
[0122] In some embodiments, an embodiment of the present invention also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a path planning information collection method (or a path planning method).
[0123] In some embodiments, the present invention further provides a mobile device, including a mobile body and the electronic device described in the above embodiments. The mobile device may be an unmanned vehicle, such as an unmanned sweeper, an unmanned floor scrubber, an unmanned logistics vehicle, an unmanned taxi, or a robot.
[0124] Fig.12 is a schematic diagram of the hardware structure of an electronic device for executing a path planning method provided by another embodiment of the present application, such as Fig.12 As shown, the device includes:
[0125] One or more processors 1210 and memory 1220, Fig.12 A processor 1210 is taken as an example.
[0126] The device for executing the path planning method may further include: an input device 1230 and an output device 1240 .
[0127] The processor 1210, the memory 1220, the input device 1230 and the output device 1240 may be connected via a bus or other means. Fig.12 The example of connecting through bus is taken in the following.
[0128] The memory 1220 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the path planning method in the embodiment of the present application. The processor 1210 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 1220, that is, the path planning method of the above method embodiment is implemented.
[0129] The memory 1220 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the path planning device, etc. In addition, the memory 1220 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 non-volatile solid-state storage device. In some embodiments, the memory 1220 may optionally include a memory remotely arranged relative to the processor 1210, and these remote memories may be connected to the path planning device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0130] The input device 1230 can receive input digital or character information and generate signals related to user settings and function control of the path planning device. The output device 1240 can include display devices such as a display screen.
[0131] The one or more modules are stored in the memory 1220, and when executed by the one or more processors 1210, the path planning method in any of the above method embodiments is executed.
[0132] The above-mentioned product can execute the method provided in the embodiment of the present application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of the present application.
[0133] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:
[0134] (1) Mobile communication devices: These devices are characterized by their mobile communication functions and their main purpose is to provide voice and data communications. These terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
[0135] (2) Ultra-mobile personal computer devices: These devices fall into the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access features. These terminals include: PDA, MID and UMPC devices, such as iPad.
[0136] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players (such as iPods), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
[0137] (4) Other onboard electronic devices with data interaction functions, such as on-board devices installed in vehicles.
[0138] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0139] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for collecting path planning information, comprising: Get the reference path; According to the environmental information of the reference path, a plurality of longitudinal sampling points are acquired on the reference path, wherein the plurality of longitudinal sampling points are adapted to the distribution of the environmental information; the environmental information includes obstacle information, and according to the environmental information of the reference path, a plurality of longitudinal sampling points are acquired on the reference path, comprising: Sampling a plurality of initial longitudinal sampling points at equal intervals on the reference path; adjusting the plurality of initial longitudinal sampling points according to the obstacle information to obtain a plurality of longitudinal sampling points; Collecting a plurality of transverse sampling points on the left side and / or the right side of the plurality of longitudinal sampling points for path planning; The environmental information also includes road boundary information; and adjusting the multiple initial longitudinal sampling points according to the obstacle information to obtain multiple longitudinal sampling points includes: Determine whether there is an obstacle within a preset range corresponding to each of the initial longitudinal sampling points to determine whether the corresponding initial longitudinal sampling point needs to be adjusted; the preset range corresponding to each of the initial longitudinal sampling points is an area surrounded by a preset boundary corresponding to the initial longitudinal sampling point and a road boundary, wherein the preset boundary corresponding to the initial longitudinal sampling point is a straight line passing through the initial longitudinal sampling point and the midpoint of a reference path between adjacent initial longitudinal sampling points; The initial longitudinal sampling points that need to be adjusted are adjusted in combination with the obstacle information.
2. The method according to claim 1, characterized in that The environmental information includes obstacle information; The plurality of longitudinal sampling points are adapted to the distribution of the environmental information, including: At least one longitudinal sampling point among the plurality of longitudinal sampling points is distributed close to an obstacle.
3. The method according to claim 1, characterized in that The adjusting the initial longitudinal sampling point that needs to be adjusted in combination with the obstacle information includes: Determine a plurality of candidate longitudinal sampling points within a preset range corresponding to the initial longitudinal sampling point that needs to be adjusted, wherein the plurality of candidate longitudinal sampling points are distributed on reference paths on both sides of the initial longitudinal sampling point that needs to be adjusted; Determine the safety distance between the plurality of candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted in combination with the obstacle information and the road boundary information; The sampling point corresponding to the minimum safety distance is determined as the adjusted longitudinal sampling point.
4. The method according to claim 3, characterized in that Determining the safety distances between the plurality of candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted in combination with the obstacle information and the road boundary information includes: In combination with the obstacle information and the road boundary information, a safe distance from a sampling point to a road boundary direction is determined, wherein the sampling point is one of the multiple candidate longitudinal sampling points and the initial longitudinal sampling point that needs to be adjusted.
5. The method according to claim 4, characterized in that Combining the obstacle information and the road boundary information, determining a safe distance from the sampling point to the road boundary direction includes: Using a distance transformation graph, at least one safety distance is determined from the sampling point to the road boundary direction; wherein, When there is a unique obstacle between the sampling point and the road boundary, and the unique obstacle is located above the road boundary, the at least one safety distance is unique; When there is only one obstacle between the sampling point and the road boundary, and the only obstacle is outside the road boundary, the at least one safety distance is two; When there are multiple obstacles between the sampling point and the road boundary, the at least one safety distance is multiple.
6. The method according to claim 5, characterized in that Also includes: For each of the longitudinal sampling points, screening out a safety distance greater than a preset threshold from the corresponding at least one safety distance; The collecting of multiple transverse sampling points on the left side and / or right side of the multiple longitudinal sampling points for path planning includes: A plurality of transverse sampling points are collected within a safety distance range greater than a preset threshold value of each longitudinal sampling point for path planning.
7. A path planning method, comprising: Collecting path planning information according to any one of claims 1 to 6; A planned path is determined according to the path planning information.
8. An electronic device, comprising: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the method described in any one of claims 1 to 7. 9 . A mobile device comprising a body and the electronic device according to claim 8 mounted on the body.
10. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Road traffic condition detection device based on panorama computer vision
CN102136194A
Outdoor automatic obstacle dodging AGV navigation method based on multiple sensors
CN106774313A
Control systems, control methods and controllers for an autonomous vehicle
CN110588653A
Vehicle lane changing route planning method and device, terminal and storage medium
CN111443709A
Locally planned road adaptive sampling method
CN111898804A
