Multi-obstacle bypass decision-making method and device, electronic equipment and program product

Abstract

According to the multi-obstacle bypassing decision-making method and device, the electronic equipment and the program product provided by the invention, a plurality of obstacles in a target range are traversed, and respective bypassing characteristics of the obstacles are determined; the bypassing characteristics comprise left-side bypassing, right-side bypassing, two-side bypassing and non-bypassing; making a detour decision for the obstacles whose detour characteristics are left-side detour, right-side detour and non-detour; acquiring obstacles whose bypassing characteristics are bypassing on two sides, and determining whether other obstacles exist nearby the obstacles and are combined into a first set; and traversing all the first sets, determining detour characteristics of the first sets, and determining a detour decision based on the detour characteristics of the first sets. According to the multi-obstacle decision-making method, the multi-obstacle decision-making device, the electronic equipment and the program product disclosed by the invention, through a two-step decision-making scheme, the combination of the obstacles is realized, the accuracy of a detour decision is improved, and the calculation amount of the detour decision for the obstacles is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving, and in particular to a method, device, electronic equipment and program product for making decisions on bypassing multiple obstacles in autonomous driving. Background Art

[0002] Mainstream autonomous driving is mainly divided into several modules according to its functions, including mapping, positioning, perception, prediction, decision-making planning and control. The decision-making planning module needs to rely on information such as obstacles perceived upstream to plan a safe, comfortable and stable path that bypasses obstacles. There are currently two main frameworks for path planning. One is to plan in the XY coordinate system, which is relatively accurate, but time-consuming and requires high computing power; the other is to plan in the SL coordinate system, and then obtain the path under XY based on the coordinate conversion. This method is relatively less time-consuming and requires relatively low computing power, but it has high requirements for the generation of feasible space. In the SL coordinate system, in order to generate a reasonable feasible space, it is necessary to make correct left and right decisions on obstacles, especially when there are multiple obstacles.

[0003] When generating feasible spaces for multiple obstacles in the SL coordinate system, one method is to generate a rough path by sampling, and decide the final obstacle avoidance decision based on the evaluation of the feasibility, safety, comfort, etc. of the rough path. This method is very time-consuming and is not conducive to the realization of autonomous driving on low-computing platforms; the other method is to merge some obstacles first through some rules, and then make decisions on the merged obstacles. At present, some existing merging methods are relatively simple, resulting in many decision errors in the obstacle avoidance decisions using the latter method, making the final generated feasible space short, and eventually causing the vehicle to stop. At present, the merging of multiple obstacles mainly considers the distance between two obstacles. It is believed that obstacles are merged only when the distance is less than the vehicle's passable width. However, when the obstacle distance is greater than the vehicle's passable width, there are still many situations where the two obstacles are actually not circumventable. In this case, it is likely that the decision contradictions between the two obstacles will result in the failure to generate a feasible path; some other methods change the original structure of the perceived obstacles when merging obstacles, which will further occupy the feasible space and reduce the possibility of generating a feasible path. Summary of the invention

[0004] The technical problem to be solved by the present disclosure is to overcome the defects in the prior art and provide a method, device, electronic device and program product for making decisions on bypassing multiple obstacles with accurate decisions and small calculation amount.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] A multi-obstacle bypass decision method, comprising:

[0007] Traversing multiple obstacles within the target range, and determining the detour characteristics of each obstacle; the detour characteristics include detour on the left, detour on the right, detour on both sides, and no detour;

[0008] Making detour decisions for obstacles with detour characteristics of left-side detour, right-side detour, and obstacles that cannot be detoured;

[0009] Obstacles with the detour characteristic of detour on both sides are obtained, and whether there are other obstacles nearby are merged into a first set;

[0010] Traversing all first sets, determining the detour characteristics of the first sets,

[0011] A detour decision is determined based on the first set of detour characteristics.

[0012] Preferably, before the step of determining the detour characteristics of each obstacle, the method further includes:

[0013] Filter out obstacles that do not require detour decisions.

[0014] Preferably, the traversing multiple obstacles within the target range and determining the circumvention characteristics of the obstacles comprises:

[0015] The detour characteristics of the obstacle are determined according to the relationship between the shortest distance between the two sides of the obstacle and the two side boundaries of the road and the minimum travel distance.

[0016] Preferably, traversing all first sets and determining the detour characteristics of the first sets includes:

[0017] Determine the detour characteristics of the first set according to the relationship between the shortest distance between the two sides of the first set and the two sides of the road boundary and the minimum travel distance; or,

[0018] The detour characteristics of the first set are determined according to the detour characteristics of the obstacles in the first set.

[0019] Preferably, the step of obtaining the detour characteristic of the obstacles to be detoured on both sides and determining whether there are other obstacles nearby to be combined into a first set includes:

[0020] Each of the obstacles bypassed on both sides is taken as a separate first set;

[0021] Obtaining other obstacles within a preset range around the obstacle with the detour characteristic of detouring on both sides;

[0022] Determining one by one whether the obstacles with the detour characteristics of being detoured on both sides need to be merged with the remaining obstacles according to the merging method;

[0023] In response to the need for merging, the remaining obstacles and the obstacles with the detour characteristic of detour on both sides are merged into a first set;

[0024] If the remaining obstacles already belong to another first set, the two first sets are merged into a new first set.

[0025] Preferably, the merging method comprises:

[0026] Acquire information of a first obstacle and a second obstacle to be determined; the information includes coordinate information of the obstacles;

[0027] Based on the information of the first obstacle and the second obstacle, it is determined whether a vehicle can pass between the first obstacle and the second obstacle, and whether the two obstacles need to be merged.

[0028] Preferably, judging whether a vehicle can pass between the first obstacle and the second obstacle based on the information of the first obstacle and the second obstacle, and determining whether the two obstacles need to be merged, includes:

[0029] In response to the interval between the first obstacle and the second obstacle in the road width direction being greater than or equal to the minimum travel distance of the vehicle, determining that the first obstacle and the second obstacle do not need to be merged;

[0030] In response to the interval distance between the first obstacle and the second obstacle in the road width direction being less than the minimum vehicle travel distance, it is determined whether the first obstacle and the second obstacle need to be merged based on whether the first obstacle and the second obstacle have an overlapping part in the road advancing direction.

[0031] Preferably, judging whether a vehicle can pass between the first obstacle and the second obstacle based on the information of the first obstacle and the second obstacle and determining whether the two need to be merged includes, in response to an overlapping portion of the first obstacle and the second obstacle projected in the advancing direction of the road, determining whether the first obstacle and the second obstacle need to be merged according to the Euclidean distance between the first obstacle and the second obstacle;

[0032] In response to the first obstacle and the second obstacle having no overlapping projections in the road advancing direction, it is determined whether merging is required according to the detour direction between the first obstacle and the second obstacle and information of the first obstacle and the second obstacle.

[0033] Preferably, judging whether a vehicle can pass between the first obstacle and the second obstacle based on the information of the first obstacle and the second obstacle and determining whether the two obstacles need to be merged specifically includes:

[0034] Determine the center positions of the inner contour circle and the outer contour circle of the first obstacle and the second obstacle based on the detour direction between the first obstacle and the second obstacle;

[0035] Determine the center coordinates of the inner contour circles and the outer contour circles of the first obstacle and the second obstacle based on the radius of the inner contour circles and the radius of the outer contour circles of the first obstacle and the second obstacle, the center positions of the inner contour circles and the outer contour circles of the first obstacle and the second obstacle, the information of the first obstacle and the second obstacle, and the road width;

[0036] In response to the distance between the center of the first obstacle and the center of the second obstacle being greater than or equal to the sum of the radius of the inner contour circle and the radius of the outer contour circle of the first obstacle and the second obstacle, it is determined that the first obstacle and the second obstacle do not need to be merged, otherwise, the first obstacle and the second obstacle are merged;

[0037] The radii of the inner contour circle and the outer contour circle are determined by the parameters of the vehicle, and the inner contour circle and the outer contour circle of the same obstacle are concentrically arranged.

[0038] Another aspect of the present disclosure provides a multi-obstacle bypass decision-making device, comprising:

[0039] A first traversal module is used to traverse multiple obstacles within the target range and determine the detour characteristics of each obstacle; the detour characteristics include left detour, right detour, two-side detour and no detour;

[0040] A first decision module is used to make a detour decision for obstacles with detour characteristics of left detour, right detour and non-detourable obstacles;

[0041] A merging module, used for obtaining an obstacle with a detour characteristic of detouring on both sides, and determining whether there are other obstacles nearby to be merged into a first set;

[0042] A second traversal module, configured to traverse all first sets and determine the detour characteristics of the first sets;

[0043] The second decision module is used to determine a detour decision based on the detour characteristics of the first set.

[0044] Another aspect of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that when the processor executes the computer program, it implements any one of the above-mentioned multi-obstacle bypass decision methods.

[0045] Another aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any one of the above-described multi-obstacle bypass decision methods.

[0046] Another aspect of the present disclosure provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the multi-obstacle bypass decision method described in any one of the above is implemented.

[0047] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0048] The positive progressive effect of the present disclosure lies in that the multi-obstacle decision-making method, device, electronic device and program product of the present disclosure, through a two-step decision-making scheme, first makes a bypass decision for all single obstacles except the bypass on both sides, and then considers whether to merge the remaining obstacles into a first set based on the bypass characteristics of the obstacles for bypass on both sides, and then makes a bypass decision for the first set, which not only realizes the merging of obstacles to facilitate bypass decisions and improves the accuracy of merging, thereby improving the accuracy of bypass decisions, but also reduces the amount of calculation for bypass decisions made on obstacles and increases the feasible space for decision-making vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a multi-obstacle bypass decision method provided in Example 1 of the present disclosure;

[0050] Figure 2 It is a flowchart of the method for making decisions on bypassing multiple obstacles according to Embodiment 2 of the present disclosure;

[0051] Figure 3 This is a flowchart of a multi-obstacle bypass decision method according to Embodiment 2 of the present disclosure;

[0052] Figure 4 It is a flowchart of the merging method in the multi-obstacle bypass decision method of Embodiment 3 of the present disclosure;

[0053] Figure 5 It is a program flow chart of step S32 of the merging method in the multi-obstacle bypass decision method of embodiment 3 of the present disclosure;

[0054] Figure 6 A schematic diagram of bypassing obstacles in the multi-obstacle bypassing decision method of Embodiment 3 of the present disclosure;

[0055] Figure 7 It is a flowchart of step S3222 of the merging method in the multi-obstacle bypass decision method in Embodiment 3 of the present disclosure;

[0056] Figure 8 Schematic diagram of the coordinates of the center of obstacle 1 in the multi-obstacle bypass decision method of embodiment 3 of the present disclosure;

[0057] Fig. 9 It is a structural schematic diagram of a multi-obstacle bypass decision-making device of Embodiment 4 of the present disclosure;

[0058] Fig.10 This is a schematic diagram of the structure of an electronic device according to Embodiment 5 of the present disclosure. DETAILED DESCRIPTION

[0059] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0060] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0061] In the embodiments of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0062] Example 1

[0063] Figure 1 A flowchart of a method for bypassing multiple obstacles provided in an embodiment of the present disclosure. The method includes:

[0064] S11, traversing multiple obstacles within the target range, and determining the detour characteristics of each obstacle; the detour characteristics include detour on the left, detour on the right, detour on both sides, and no detour;

[0065] S12, making a detour decision for the obstacle having detour characteristics of left-side detour, right-side detour, and obstacle that cannot be detoured;

[0066] S13, obtaining an obstacle with a detour characteristic of detouring on both sides, and determining whether there are other obstacles nearby to be merged into a first set;

[0067] S14, traversing all first sets to determine the detour characteristics of the first sets,

[0068] S15: Determine a detour decision based on the detour characteristics of the first set.

[0069] Generally, the detour characteristics determine the detour decision. For example, for an obstacle or the first set whose detour characteristics are left-side detour, a left-side detour decision is made; for an obstacle or the first set whose detour characteristics are right-side detour, a right-side detour decision is made; for an obstacle or the first set whose detour characteristics are unavoidable, an unavoidable detour decision is made.

[0070] For obstacles or the first set whose bypassing characteristics are bypassing on both sides, a decision can be made according to a single obstacle decision method, which can be to select a side with more space for bypassing, or to determine the bypass decision for the obstacle in combination with the bypass decisions of other obstacles.

[0071] In the step S11, multiple obstacles within the target range are traversed to determine the detour characteristics of the obstacles, specifically including determining the detour characteristics of the obstacles according to the relationship between the shortest distance between the two sides of the obstacle and the two sides of the road boundary and the vehicle body width.

[0072] If the shortest distances between the left and right sides of the obstacle and the boundaries of both sides of the road are greater than or equal to the minimum travel distance, the bypass characteristic of the obstacle is determined to be bypassing on both sides; if the shortest distance between only one side and the corresponding side of the road is greater than or equal to the minimum travel distance, the obstacle is determined to be bypassed on that side, for example, bypassing on the left or bypassing on the right; if the shortest distances between both sides of the obstacle and both sides of the road are less than the minimum travel distance, the obstacle is determined to be unable to be bypassed.

[0073] The minimum clearance distance is related to the width of the vehicle body, and is usually the width of the vehicle body plus a safety distance.

[0074] This step first makes detour decisions for some obstacles and then performs merging, which can reduce the amount of merging calculations and improve the accuracy of the decision.

[0075] In S13, for obstacles with the detour characteristic of detouring on both sides, determine whether there are other obstacles nearby to merge into the first set. Taking the obstacles with the detour characteristic of detouring on both sides as the benchmark, the remaining obstacles are traversed and merged. The principle of merging is based on the requirement that vehicles cannot pass between the two obstacles, and the detour characteristics of the two obstacles themselves are taken into consideration. This not only reduces the amount of calculation, but also only merges based on the obstacles with the detour characteristic of detouring on both sides, further reducing the amount of calculation. The merging method usually uses the Euclidean distance to make a judgment, or uses the method of first expanding the obstacles and then verifying whether the expanded obstacles intersect to make a judgment. Other merging methods can also be used.

[0076] In step S14, if there is a merged first set in step S13, the detour characteristics of the first set need to be determined in this step. Specifically, the detour characteristics of the first set are determined based on the relationship between the shortest distance between the two sides of the first set and the two side boundaries of the road and the width of the vehicle body. Since detour decisions have been made for some obstacles in S12, in S13 and S14, if there are other obstacles merged with the obstacles to be detoured on either side to form a first set, then for any first set containing at least two obstacles, the detour characteristics and detour decisions of the first set need to be re-determined. For obstacles that have not been merged into the first set, the detour decisions made in step S12 are still executed.

[0077] In this way, bypass decisions are first made for some obstacles, and then the obstacles for which bypass decisions have not been made are merged into the first set, and then bypass decisions are made for the merged first set. This can avoid omission of obstacle bypass decisions, and for the second bypass decision, only the first set needs to be decided, and there is no need to check the remaining obstacles that have not been merged into the first set. This greatly reduces the amount of calculation, not only realizes the merging of obstacles, but also improves the accuracy of merging and bypassing decisions.

[0078] Before step S11, the method further includes:

[0079] S10, screen out obstacles that do not require a detour decision. The screened obstacles that do not require a detour decision include obstacles that are too far away from the road, obstacles that are far behind the vehicle, and dynamic obstacles that cross the road, etc. Of course, there can be other screening methods.

[0080] In this step, screening is performed first, which can further reduce the amount of calculation for detour decisions and improve the accuracy of detour decisions.

[0081] The multi-obstacle decision method of this embodiment adopts a two-step decision scheme. It first makes a detour decision on some obstacles, then merges the obstacles bypassed on both sides, and then makes a decision on the first merged set. Only some obstacles need to be merged, which improves the accuracy of the detour decision, increases the feasible space finally generated, and reduces the amount of calculation for the detour decision made on the obstacles.

[0082] Example 2

[0083] like Figure 2 The flowchart of the multi-obstacle decision method of the embodiment 2 is shown. In this embodiment, steps S21, S22, S24 and S25 are the same as those of the embodiment 1, wherein step S23 specifically includes:

[0084] S231, taking each obstacle with a detour characteristic of detour on both sides as a separate first set;

[0085] S232, obtaining other obstacles within a preset range around the obstacle with the detour characteristic of detouring on both sides;

[0086] S233, judging one by one whether the obstacle with the detour characteristic of being detoured on both sides needs to be merged with the remaining obstacles according to the merging method;

[0087] S234, in response to the need for merging, merging the remaining obstacles and the obstacles with the detour characteristic of detour on both sides into a first set;

[0088] S235: If the remaining obstacles already belong to another first set, merge the two first sets into a new first set.

[0089] like Figure 3 As shown, it is a flow chart of the method for making decisions on bypassing multiple obstacles in this embodiment; in step S231, the obstacles bypassed on both sides of each bypass characteristic are firstly taken as a separate first set, that is, Figure 3 As shown, all obstacles that can be circumvented on both sides, that is, all obstacles with the bypassing characteristic of bypassing on both sides are traversed as main obstacles, and each of the main obstacles is regarded as an obstacle set, that is, as the first set.

[0090] Step S232, obtaining the remaining obstacles within a preset range around the obstacle with the detour characteristic of detouring on both sides; the preset range can be set as needed, for example, considering the minimum passing width of the vehicle and expanding a certain range.

[0091] In step S233, each main obstacle is traversed, specifically, all obstacles near the current main obstacle are searched, and it is determined one by one whether the obstacle with the detour characteristic of detouring on both sides needs to be merged with the remaining obstacles according to the merging method; if it needs to be merged, the remaining obstacles are merged with the main obstacle into the first set. It should be noted here that the remaining obstacles can be obstacles other than the current main obstacle, such as obstacles with the detour characteristic of detouring on the left, detouring on the right, or obstacles that cannot be detoured, or other main obstacles other than the current main obstacle. As long as the obstacles are within the preset range around the current main obstacle, they can be used for judgment. However, if the remaining obstacles are other main obstacles with detour on both sides, for example, they already belong to a first set, the two first sets are merged into a new first set.

[0092] After the merging method, multiple first sets are obtained. Therefore, in step S24: traverse all first sets to determine the detour characteristics of the first sets. The method for determining the detour characteristics is as described in Example 1. There are two ways to determine whether the detour characteristics are left-side detour, right-side detour, unable to detour, or both-side detour. The first is to determine the detour characteristics of the first set based on the relationship between the shortest distance between the two sides of the first set and the two sides of the road boundary and the minimum travel distance; at this time, the range of the first set is the range that includes all obstacles.

[0093] In another implementation manner, the detour characteristics of the first set may be determined according to the detour characteristics of all obstacles in the first set. For example, if the detour characteristic of any obstacle among all obstacles in the first set is that it cannot be detoured, then the detour characteristics in the first set are that it cannot be detoured.

[0094] If all obstacles in the first set must include a main obstacle that can be bypassed on both sides, and if the bypass characteristics of the remaining obstacles are any single type of bypassing on the left side, bypassing on the right side, or bypassing on both sides, then the bypass characteristics of the first set are the single type of bypass characteristics, for example, bypassing on the left side, bypassing on the right side, or bypassing on both sides.

[0095] If the detour characteristics of the remaining obstacles are either a single type of detour on the left or right side or a double-sided detour, then the detour characteristics of the first set are the single type of detour characteristics.

[0096] If the detour characteristics of the remaining obstacles include both left-side detour and right-side detour, the detour characteristics of the first set are that detour is impossible.

[0097] In step S25, for all the first set of bypass decisions, if the bypass characteristics of all the first set are bypassable on both sides, the decision is directly made in the manner of a single obstacle. If the bypass characteristics in the first set are bypassing on the left or right side, the first set is determined to be a bypass decision for bypassing on the left or bypassing on the right. For the first set or a single obstacle that can be bypassed on both sides, the decision can be made in the manner of a single obstacle decision, which can be to select a side with more space for bypassing, or to determine the bypass decision for the obstacle in combination with the bypass decisions of the remaining obstacles.

[0098] In this embodiment, the merging method may adopt an existing method, such as a method of expanding obstacles to see whether there is an intersection, or a method of judging by Euclidean distance.

[0099] In this embodiment, each obstacle that can be bypassed on both sides is used as a basis for traversal, and then the remaining obstacles are merged to obtain a first set, and then a bypass decision is made for the first set. This not only makes the merger accurate and reasonable, but also reduces a certain amount of calculation, and ultimately ensures the accuracy of the decision, thereby increasing the feasible space for the vehicle that is finally generated.

[0100] Example 3

[0101] In this embodiment, if Figure 4 , 5 As shown, it is a flowchart of the multi-obstacle bypass decision method of this embodiment and a program flow chart of the merging method.

[0102] In this embodiment, the other steps are the same as those in Embodiments 1 and 2, but the difference is the method of combining.

[0103] like Figure 4 As shown, the merging method of this embodiment includes:

[0104] S31, obtaining information of the first obstacle and the second obstacle to be judged; the information includes coordinate information of the obstacle; preferably, the coordinate information of the obstacle in the SL coordinate system, that is, the method uses the SL coordinate system to judge whether the two obstacles need to be merged.

[0105] S32: Based on the information of the first obstacle and the second obstacle, determine whether a vehicle can pass between the first obstacle and the second obstacle, and determine whether the two need to be merged. The specific determination method is whether a vehicle can bypass between the first obstacle and the second obstacle to determine whether the two need to be merged.

[0106] The step S32 specifically includes:

[0107] S321: In response to the interval between the first obstacle and the second obstacle in the road width direction being greater than or equal to the minimum travel distance of vehicles, determining that the first obstacle and the second obstacle do not need to be merged.

[0108] Specifically, in this method, Figure 5 As shown, in step S31, the information of two obstacles, i.e., the coordinate information of the first obstacle and the second obstacle in the SL coordinate system, has been obtained. The order of the two obstacles can be determined according to the projections of the two obstacles on the reference line S. For example, the distant obstacle can be set as the first obstacle, i.e., obstacle 1, and the near obstacle can be set as the second obstacle, i.e., obstacle 2. Figure 6If the distance between the first obstacle and the second obstacle in the width L direction, that is, the shortest distance between the projections of the first obstacle and the second obstacle in the road width direction, is greater than or equal to the minimum vehicle travel distance, it means that a vehicle can definitely pass between the two obstacles, and at this time, it is considered that the two obstacles do not need to be merged.

[0109] S322: In response to the interval distance between the first obstacle and the second obstacle in the road width direction being less than the minimum travel distance of the vehicle, determine whether the first obstacle and the second obstacle need to be merged based on whether the first obstacle and the second obstacle have an overlapping portion in the direction of road advancement.

[0110] Wherein, in step S322, determining whether the first obstacle and the second obstacle need to be merged based on whether the first obstacle and the second obstacle have overlapping parts in the direction of the road specifically includes:

[0111] S3221: In response to an overlapping portion of the projections of the first obstacle and the second obstacle in the direction of the road, determine whether the first obstacle and the second obstacle need to be merged according to the Euclidean distance between the first obstacle and the second obstacle.

[0112] When the vehicle passes transversely and the first obstacle and the second obstacle have an overlapping part in the projection in the direction of the road, and the Euclidean distance between the first obstacle and the second obstacle is greater than or equal to the minimum travel distance of the vehicle, it is determined that the first obstacle and the second obstacle do not need to be merged. If the Euclidean distance between the first obstacle and the second obstacle is less than the minimum travel distance of the vehicle, they need to be merged.

[0113] Specifically, if the interval between the first obstacle and the second obstacle in the road width direction L is less than the minimum travel distance of the vehicle, and the projections of the first obstacle and the second obstacle in the forward direction of the road have an overlapping part, that is, there is an overlapping part between the projections of the first main obstacle and the second obstacle in the road S direction, then it is necessary to determine whether the Euclidean distance between the two obstacles, that is, the shortest straight-line distance, is greater than or equal to the minimum travel distance of the vehicle. For example, at this time, the vehicle may be allowed to pass obliquely between the two obstacles. If the Euclidean distance between the two obstacles is greater than or equal to the minimum travel distance, the first obstacle and the second obstacle do not need to be merged, otherwise they need to be merged.

[0114] S3222: In response to the first obstacle and the second obstacle having no overlapping projections in the direction of the road, determine whether merging is required based on the detour direction between the first obstacle and the second obstacle and information about the first obstacle and the second obstacle.

[0115] At this time, if the interval between the first obstacle and the second obstacle in the road width direction is not enough for the vehicle to pass, and the first obstacle and the second obstacle are completely staggered front and back, that is, there is no overlapping part in the direction of road advancement, then the vehicle needs to bypass between the first and second obstacles; that is, determine whether to merge based on the bypass direction between the first obstacle and the second obstacle, and the information of the first obstacle and the second obstacle.

[0116] Judging whether merging is necessary based on such steps is not only fast and accurate, but also can improve judgment efficiency and reduce calculation difficulty.

[0117] Specifically, in step S3222, determining whether to merge the first obstacle and the second obstacle according to the detour direction between the first obstacle and the second obstacle and the information of the first obstacle and the second obstacle includes: Figure 7 As shown,

[0118] S32221: determining the center positions of the inner contour circle and the outer contour circle of the first obstacle and the second obstacle based on the detour direction between the first obstacle and the second obstacle;

[0119] S32222: determining the center coordinates of the inner contour circles and the outer contour circles of the first obstacle and the second obstacle based on the radii of the inner contour circles and the outer contour circles of the first obstacle and the second obstacle, the center positions of the inner contour circles and the outer contour circles of the first obstacle and the second obstacle, the information of the first obstacle and the second obstacle, and the road width;

[0120] S32223, in response to the distance between the center of the first obstacle and the center of the second obstacle being greater than or equal to the sum of the radius of the inner contour circle and the radius of the outer contour circle of the first obstacle and the second obstacle, determining that the first obstacle and the second obstacle do not need to be merged, otherwise, the first obstacle and the second obstacle are merged.

[0121] The radii of the inner contour circle and the outer contour circle are determined by the parameters of the vehicle, and the inner contour circle and the outer contour circle of the same obstacle are concentrically arranged. Figure 6 As shown, the radius of the path circle is the turning radius of the vehicle, which can be calculated based on the vehicle wheelbase and the maximum steering angle. The inner contour circle radius is obtained by subtracting half the vehicle width from the path circle radius. The outer contour circle radius is calculated based on the vehicle width, the distance from the front of the vehicle to the center of the rear axle, and the minimum turning radius of the vehicle.

[0122] In step S3231, based on the detour direction between the first obstacle and the second obstacle, the center positions of the inner contour circle and the outer contour circle of the first obstacle and the second obstacle are determined; the detour direction includes the left-right position relationship and the front-back position relationship of the first obstacle and the second obstacle, and whether the vehicle detours on the left or right side of the first obstacle and the second obstacle; for example Figure 6 As shown, obstacle 1 and obstacle 2 are located in front and back positions, and obstacle 1 is located slightly to the right of obstacle 2. When the vehicle is driving, it can bypass from the left side of obstacle 2 and bypass from the right side of obstacle 1, or it can bypass from the right side of obstacle 2 and bypass from the left side of obstacle 1. Figure 6 The diagram shows the left side of obstacle 2 and the right side of obstacle 1. Therefore, it can be determined that the center of the inner and outer contour circles of the obstacle are located on the side of the obstacle relative to the detour direction, that is, Figure 6 In the figure, the center of the first obstacle, namely obstacle 1, is on its left side, while the center of the second obstacle, namely obstacle 2, is on its right side.

[0123] After determining the center orientation, the center coordinates of the inner contour circle and outer contour circle of the first obstacle and the second obstacle are determined based on the radii of the inner contour circle and the outer contour circle of the first obstacle and the second obstacle, the road width, and the information of the first obstacle and the second obstacle.

[0124] by Figure 8 For example, obstacle 1 at this time is bypassed on the right, so the centers of its inner and outer contour circles are on the left side of the obstacle. It is necessary to obtain the road width in advance. Because the center of the circle is on the left side of the obstacle, the point on the right side of the obstacle is used as the reference point.

[0125] Before calculating the center of the contour circle, it is necessary to obtain the road width information on both sides of the obstacle. It is also necessary to obtain the relevant information of the obstacle in advance, such as the position in XY coordinates, and then convert it into the position in SL coordinates, where:

[0126] start_l is the minimum l of the obstacle projection in the sl coordinate system;

[0127] end_l is the maximum l of the obstacle projection in the sl coordinate system;

[0128] start_s is the minimum s of the obstacle projection in the sl coordinate system;

[0129] end_s is the maximum s of the obstacle projection in the sl coordinate system;

[0130] start_l_point is the point where the minimum l of the obstacle is projected in the sl coordinate system;

[0131] end_l_point is the point where the maximum l of the obstacle is projected in the sl coordinate system;

[0132] start_s_point is the point where the minimum s of the obstacle is projected in the sl coordinate system;

[0133] end_s_point is the point where the maximum s of the obstacle is projected in the sl coordinate system;

[0134] The following takes right around obstacle 1 as an example to introduce the calculation formula of the center of the circular path. Figure 8 shown.

[0135] Solve the l coordinate of the center of the contour circle around obstacle 1. Take the start_l of obstacle 1 as the reference point, determine the l where the road boundary is located according to the width of the right side of the obstacle, and then use the road boundary as the reference to determine the l where the center of the circle is located according to the radius of the outer contour circle;

[0136] That is: the center of the circle l = obstacle strart_l-the passable width on the right side of the obstacle + the radius of the outer contour circle

[0137] To solve the s coordinate of the center of the contour circle around obstacle 1, take the start_l_point and start_s_point of obstacle 1 as reference points respectively, and calculate the distance from the reference point to the center of the circle in the s direction based on the l at the reference point and the radius of the inner contour circle according to the Pythagorean theorem, and then calculate the s coordinate of the corresponding center of the circle, and take the smaller value of the two as the final s coordinate of the center of the circle; calculation formula: s at the center of the circle = s at the obstacle reference point + s distance from the reference point to the center of the circle.

[0138] At the same time, if obstacle 1 is circled to the left, the l coordinate of the center of the contour circle is determined based on the end_l and left boundary of the obstacle, and the s coordinate of the center of the contour circle is determined based on the start_s_point and end_l_point of obstacle 1.

[0139] When going left around obstacle 2, the l coordinate of the center of the contour circle is determined based on the end_l and left boundary of the obstacle, and the s coordinate of the center of the contour circle is determined based on the end_s_point and end_l_point of obstacle 2.

[0140] When going around obstacle 2 to the right, the l coordinate of the center of the contour circle is determined based on the start_l and right boundary of the obstacle, and the s coordinate of the center of the contour circle is determined based on the end_s_point and start_l_point of obstacle 2.

[0141] Therefore, the choice of the benchmark depends on the detour of the obstacle, the front-to-back relationship of the obstacle, the coordinate information of the obstacle and the road width.

[0142] Therefore, in step S30233, in response to the distance between the center of the first obstacle and the center of the second obstacle being greater than or equal to the sum of the radius of the inner contour circle and the radius of the outer contour circle of the first obstacle and the second obstacle, it is determined that the first obstacle and the second obstacle do not need to be merged, otherwise, the first obstacle and the second obstacle are merged. In this extreme case, it means that the vehicle has just passed between the first obstacle and the second obstacle.

[0143] This embodiment can reduce the workload of calculation by gradually judging whether two obstacles are to be merged. Moreover, through the step-by-step judgment steps, first the interval distance in the reference line direction is used, then whether the obstacles overlap in the forward direction is judged by the Euclidean distance between the two obstacles, and finally the distance relationship between the radius of the contour circle of the two obstacles and the center of the circle is used to judge whether to merge. The merging method is more reliable and comprehensive, with higher accuracy, and can also ensure the accuracy of multi-obstacle decision-making.

[0144] Example 4

[0145] Corresponding to the aforementioned embodiments 1-3 of the method for making a decision on bypassing multiple obstacles, the present disclosure also provides an embodiment of a device for making a decision on bypassing multiple obstacles.

[0146] Fig. 9 A schematic diagram of a module of a multi-obstacle bypass decision-making device provided by an exemplary embodiment of the present disclosure, the device comprising:

[0147] The first traversal module 1 is used to traverse multiple obstacles within the target range and determine the detour characteristics of each obstacle; the detour characteristics include left detour, right detour, two-side detour and no detour;

[0148] A first decision module 2 is used to make a detour decision for obstacles with detour characteristics of left detour, right detour and non-detourable obstacles;

[0149] A merging module 3 is used to obtain an obstacle with a detour characteristic of detouring on both sides, and determine whether there are other obstacles nearby to be merged into a first set;

[0150] The second traversal module 4 is used to traverse all first sets and determine the detour characteristics of the first sets.

[0151] The second decision module 5 is used to determine a detour decision based on the detour characteristics of the first set, and further includes a screening module 6, which is used to screen out obstacles that do not require detour decisions before determining the detour decisions for the obstacles.

[0152] The merging module 3 is specifically configured to treat each obstacle having the detour characteristic of detouring on both sides as a separate first set;

[0153] Obtaining other obstacles within a preset range around the obstacle with the detour characteristic of detouring on both sides;

[0154] Determining one by one whether the obstacles with the detour characteristics of being detoured on both sides need to be merged with the remaining obstacles according to the merging method;

[0155] In response to the need for merging, the remaining obstacles and the obstacles with the detour characteristic of detour on both sides are merged into a first set;

[0156] If the remaining obstacles already belong to another first set, the two first sets are merged into a new first set.

[0157] The second traversal module 4 is used to determine the detour characteristics of the first set according to the relationship between the shortest distance between the two sides of the first set and the two sides of the road boundary and the minimum travel distance; or,

[0158] The detour characteristics of the first set are determined according to the detour characteristics of the obstacles in the first set.

[0159] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0160] Example 5

[0161] Fig.10 This is a structural diagram of an electronic device shown in an example embodiment of the present disclosure, the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, and when the processor executes the computer program, the multi-obstacle bypass decision method described in any of the above embodiments is implemented. Fig.10 The electronic device 90 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0162] like Fig.10 As shown, the electronic device 90 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including the memory 92 and the processor 91).

[0163] The bus 93 includes a data bus, an address bus, and a control bus.

[0164] The memory 92 may include a volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922 , and may further include a read-only memory (ROM) 923 .

[0165] The memory 92 may also include a program tool 925 (or utility) having a set (at least one) of program modules 924, such program modules 924 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0166] The processor 91 executes various functional applications and data processing by running the computer program stored in the memory 92, such as the multi-obstacle bypass decision method provided in any of the above embodiments.

[0167] The electronic device 90 may also communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 95. Furthermore, the electronic device 90 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 96. As shown, the network adapter 96 communicates with other modules of the electronic device 90 via a bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0168] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0169] Example 6

[0170] The embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the multi-obstacle bypass decision method provided in any of the above embodiments is implemented.

[0171] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0172] Example 7

[0173] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for making decisions regarding bypassing multiple obstacles.

[0174] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0175] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A multi-obstacle bypass decision method, characterized in that: include, Traversing multiple obstacles within the target range, and determining the detour characteristics of each obstacle; the detour characteristics include detour on the left, detour on the right, detour on both sides, and no detour; Making detour decisions for obstacles with detour characteristics of left-side detour, right-side detour, and obstacles that cannot be detoured; Obstacles with the detour characteristic of detour on both sides are obtained, and whether there are other obstacles nearby are merged into a first set; Traversing all first sets, determining the detour characteristics of the first sets, A detour decision is determined based on the first set of detour characteristics.

2. The multi-obstacle bypass decision method according to claim 1, characterized in that: Before the step of determining the detour characteristics of each obstacle, the method further includes: Filter out obstacles that do not require detour decisions.

3. The multi-obstacle bypass decision method according to claim 1, characterized in that: The traversing multiple obstacles within the target range and determining the detour characteristics of each of the obstacles; include, The detour characteristics of the obstacle are determined according to the relationship between the shortest distance between the two sides of the obstacle and the two side boundaries of the road and the minimum travel distance.

4. The multi-obstacle bypass decision method according to claim 1, characterized in that: The traversing all the first sets to determine the detour characteristics of the first sets, include, Determine the detour characteristics of the first set according to the relationship between the shortest distance between the two sides of the first set and the two sides of the road boundary and the minimum travel distance; or, The detour characteristics of the first set are determined according to the detour characteristics of the obstacles in the first set.

5. The multi-obstacle bypass decision method according to claim 1, characterized in that: Obstacles with detour characteristics of detour on both sides are obtained, and whether there are other obstacles nearby are merged into a first set; include, Each obstacle bypassed on both sides of the bypass characteristic is taken as a separate first set; Obtaining other obstacles within a preset range around the obstacle with the detour characteristic of detouring on both sides; Determining one by one whether the obstacles with the detour characteristics of being detoured on both sides need to be merged with the remaining obstacles according to the merging method; In response to the need for merging, the remaining obstacles and the obstacles with the detour characteristic of detour on both sides are merged into a first set; If the remaining obstacles already belong to another first set, the two first sets are merged into a new first set.

6. The multi-obstacle bypass decision method according to claim 5, characterized in that: The merging method comprises: Acquire information of a first obstacle and a second obstacle to be determined; the information includes coordinate information of the obstacles; Based on the information of the first obstacle and the second obstacle, it is determined whether a vehicle can pass between the first obstacle and the second obstacle, and whether the two obstacles need to be merged.

7. The multi-obstacle bypass decision method according to claim 6, characterized in that: The determining whether a vehicle can pass between the first obstacle and the second obstacle based on the information of the first obstacle and the second obstacle, and determining whether the two obstacles need to be merged, includes: In response to the interval between the first obstacle and the second obstacle in the road width direction being greater than or equal to the minimum travel distance of the vehicle, determining that the first obstacle and the second obstacle do not need to be merged; In response to the interval distance between the first obstacle and the second obstacle in the road width direction being less than the minimum vehicle travel distance, it is determined whether the first obstacle and the second obstacle need to be merged based on whether the first obstacle and the second obstacle have an overlapping part in the road advancing direction.

8. The multi-obstacle bypass decision method according to claim 6, characterized in that: The determining whether a vehicle can pass between the first obstacle and the second obstacle based on the information of the first obstacle and the second obstacle, and determining whether the two obstacles need to be merged, includes: In response to the first obstacle and the second obstacle having an overlapping portion projected in the direction of the road, determining whether the first obstacle and the second obstacle need to be merged according to the Euclidean distance between the first obstacle and the second obstacle; In response to the first obstacle and the second obstacle having no overlapping projections in the road advancing direction, it is determined whether merging is required according to the detour direction between the first obstacle and the second obstacle and information of the first obstacle and the second obstacle.

9. The multi-obstacle bypass decision method according to claim 6, characterized in that: The determining whether a vehicle can pass between the first obstacle and the second obstacle based on the information of the first obstacle and the second obstacle, and determining whether the two obstacles need to be merged, specifically includes: Determine the center positions of the inner contour circle and the outer contour circle of the first obstacle and the second obstacle based on the detour direction between the first obstacle and the second obstacle; Determine the center coordinates of the inner contour circles and the outer contour circles of the first obstacle and the second obstacle based on the radius of the inner contour circles and the radius of the outer contour circles of the first obstacle and the second obstacle, the center positions of the inner contour circles and the outer contour circles of the first obstacle and the second obstacle, the information of the first obstacle and the second obstacle, and the road width; In response to the distance between the center of the first obstacle and the center of the second obstacle being greater than or equal to the sum of the radius of the inner contour circle and the radius of the outer contour circle of the first obstacle and the second obstacle, it is determined that the first obstacle and the second obstacle do not need to be merged, otherwise, the first obstacle and the second obstacle are merged; The radii of the inner contour circle and the outer contour circle are determined by the parameters of the vehicle, and the inner contour circle and the outer contour circle of the same obstacle are concentrically arranged.

10. A multi-obstacle bypass decision-making device, characterized in that: The device is implemented by the method according to any one of claims 1 to 9, including: A first traversal module is used to traverse multiple obstacles within the target range and determine the detour characteristics of each obstacle; the detour characteristics include left detour, right detour, two-side detour and no detour; A first decision module is used to make a detour decision for obstacles with detour characteristics of left detour, right detour and non-detourable obstacles; A merging module, used for obtaining an obstacle with a detour characteristic of detouring on both sides, and determining whether there are other obstacles nearby to be merged into a first set; A second traversal module is used to traverse all first sets and determine the detour characteristics of the first sets. The second decision module is used to determine a detour decision based on the detour characteristics of the first set.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: When the processor executes the computer program, the multi-obstacle bypass decision method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the multi-obstacle bypass decision method according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the multi-obstacle bypass decision method as described in any one of claims 1 to 9 is implemented.

Images