Method and system for searching passage space of unmanned vehicle

Abstract

The invention provides a method and a system for searching a passage space of an unmanned vehicle. The method comprises the following steps: generating a blocked obstacle list, determining boundary information of a road in front of the unmanned vehicle, and then determining N-level topological nodes of a to-be-passed space; generating M alternative paths for the unmanned vehicle to pass through according to the connection relationship among the N-level topological nodes, and determining the minimum passing width of the vehicle; respectively calculating the cost of M alternative paths according to a self-defined cost weight value and the calculated first cost and the second cost of the topological node on each alternative path; and based on a self-defined space screening rule, determining a final passage space of the unmanned vehicle according to a self-defined minimum value of the passage width of the unmanned vehicle, the cost of the M alternative paths and the minimum passage width of the vehicle. According to the method and the system, the topological node connection diagram conforming to the traffic environment under the complex road condition can be generated, excessive computing power is not consumed, and the optimal vehicle traffic space can be provided for downstream trajectory planning.

Description

Technical Field

[0001] The present invention relates to the field of path planning, and more particularly, to a method and system for searching for a passage space for an unmanned vehicle. Background Art

[0002] In autonomous vehicle path planning, the autonomous driving planning module is generally divided into lateral path planning and longitudinal speed planning. Lateral path planning generates a spatial path that does not include time information, allowing for maneuvers such as avoiding and circumventing static obstacles. However, in complex road conditions with numerous obstacles, the vehicle must select a reasonable passageway for subsequent path planning. Currently, there is a lack of effective methods for determining a reasonable passageway in complex road conditions with numerous obstacles. Summary of the Invention

[0003] In order to solve the technical problem in the prior art of lacking an effective implementation method for determining reasonable passage space under complex road conditions with many obstacles, the present invention provides a method and system for searching passage space for unmanned vehicles.

[0004] According to one aspect of the present invention, a method for searching for a space for an unmanned vehicle to pass through is provided, comprising: Generate a list of blocked obstacles based on the current speed of the autonomous vehicle, the customized minimum scanning distance and scanning time, and the speed of the blocked obstacles in front of the autonomous vehicle, and determine the road boundary information in front of the autonomous vehicle; Determining, based on information about each blocking obstacle in the blocking obstacle list and the road boundary information, an N-level topological node of the proposed passage space, wherein the topological node represents a space in the proposed passage space between blocking obstacles or between blocking obstacles and the road boundary intended for passage of the unmanned vehicle; Generate M alternative paths for the unmanned vehicle to pass based on the connection relationship between the N-level topological nodes in the planned passage space, as well as the minimum vehicle passage width between the topological nodes with connection relationships; Calculate the first cost of the N-level topological nodes in the intended traversable space and the second cost between the topological nodes with connection relationships according to the self-defined cost function; Calculate the costs of the M alternative paths based on the first cost and the second cost of the topological nodes on each alternative path according to the custom cost weight value; Based on the customized space screening rules, the final passage space for the unmanned vehicle is determined according to the customized minimum passage width of the unmanned vehicle, the cost of the M alternative paths and the minimum passage width of the vehicle.

[0005] According to another aspect of the present invention, a system for searching for a space for unmanned vehicles to pass through is provided, the system comprising: The pre-processing module is used to generate a list of blocked obstacles based on the current speed of the unmanned vehicle, the customized minimum scanning distance and scanning time, and the running speed of the blocked obstacles in front of the unmanned vehicle, and determine the road boundary information in front of the unmanned vehicle; a topology node module, configured to determine an N-level topology node of the proposed traversable space based on information about each blocking obstacle in the blocking obstacle list and the road boundary information, wherein the topology node represents a space in the proposed traversable space between blocking obstacles or between blocking obstacles and road boundaries intended for passage of unmanned vehicles; The alternative path module is used to generate M alternative paths for the unmanned vehicle to pass based on the connection relationship between the N-level topological nodes in the proposed passage space, as well as the minimum vehicle passage width between the topological nodes with connection relationships; A first calculation module is used to calculate the first cost of the N-level topological nodes in the intended traversable space and the second cost between the topological nodes having a connection relationship according to a user-defined cost function; A second calculation module is used to calculate the costs of the M alternative paths respectively according to the user-defined cost weight value, the first cost and the second cost of the topological node on each alternative path; The result output module is used to determine the final passage space of the unmanned vehicle based on the customized space screening rules, the customized minimum passage width of the unmanned vehicle, the costs of M alternative paths and the minimum passage width of the vehicle.

[0006] According to another aspect of the present invention, the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above aspects of the present invention is implemented.

[0007] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor for reading the executable instructions from the memory and executing the instructions to implement the method described in any one of the above aspects of the present invention.

[0008] The method and system for searching for unmanned vehicle passage space described in the present invention include generating a list of blocked obstacles and determining road boundary information in front of the unmanned vehicle; determining N-level topological nodes of the proposed passage space based on information of each blocked obstacle in the blocked obstacle list and the road boundary information; generating M alternative paths for the unmanned vehicle to pass through and a minimum vehicle passage width between topological nodes with a connection relationship based on the connection relationship between the N-level topological nodes of the proposed passage space; calculating a first cost of the N-level topological nodes of the proposed passage space and a second cost between topological nodes with a connection relationship based on a custom cost function; calculating the costs of the M alternative paths based on the first cost and the second cost of the topological nodes on each alternative path according to a custom cost weight value; and determining the final passage space for the unmanned vehicle based on a custom space screening rule and a custom minimum unmanned vehicle passage width, the costs of the M alternative paths, and the minimum vehicle passage width. The method and system can generate a topological node connection diagram that conforms to the traffic environment under complex road conditions without wasting too much computing power. The highly adaptive search algorithm avoids the loss of traffic space to the greatest extent, thereby providing optimal vehicle traffic space for downstream trajectory planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings: Figure 1 Flowchart of a method for searching for a passage space for an unmanned vehicle according to a preferred embodiment of the present invention; Figure 2 Schematic diagram of road boundary confirmation of an unmanned vehicle in different driving scenarios according to a preferred embodiment of the present invention; Figure 3 An exemplary diagram of a second pre-selected segmentation point and a third pre-selected segmentation point according to a preferred embodiment of the present invention; Figure 4 is an example diagram of a fourth pre-selected segmentation point according to a preferred embodiment of the present invention; Figure 5 A schematic diagram showing the correspondence between type information representing a second pre-selected segmentation point and portions to be deleted in its corresponding front and back edge information according to a preferred embodiment of the present invention; Figure 6 A schematic diagram of generating and updating a concerned edge list according to a preferred embodiment of the present invention; Figure 7 Schematic diagram of generating an upper boundary segmentation line and a lower boundary segmentation line according to a preferred embodiment of the present invention; Figure 8 A schematic diagram of generating topology nodes according to a preferred embodiment of the present invention; Figure 92 is a schematic structural diagram of a system for searching for unmanned vehicle passage spaces according to a preferred embodiment of the present invention; Figure 10 Schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0010] Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to provide a thorough and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments shown in the accompanying drawings is not intended to limit the present invention. In the accompanying drawings, identical elements are denoted by the same reference numerals.

[0011] Unless otherwise specified, the terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have meanings consistent with the context of their relevant fields and should not be interpreted as idealized or overly formal.

[0012] Exemplary Methods Figure 1 FIG. 1 is a flow chart of a method for searching for unmanned vehicle passage space according to a preferred embodiment of the present invention. Figure 1 As shown, the method for searching for unmanned vehicle passage space described in this preferred embodiment starts from step 101.

[0013] In step 101, a list of blocked obstacles is generated based on the current speed of the unmanned vehicle, the customized minimum scanning distance and scanning time, and the running speed of the blocked obstacles in front of the unmanned vehicle, and the road boundary information in front of the unmanned vehicle is determined.

[0014] Preferably, generating a list of blocked obstacles based on the current speed of the unmanned vehicle, a customized minimum scanning distance and scanning time, and the speed of the blocked obstacles in front of the unmanned vehicle, and determining the road boundary information in front of the unmanned vehicle include: Based on the current speed of the autonomous vehicle, the minimum scanning distance and scanning time are customized to determine the scanning range for obstacles in front of the autonomous vehicle, including: According to the current speed v of the unmanned vehicle and the custom scanning time t y Calculate the current scanning distance d y , and its calculation formula is: d y =v*t y According to the current scanning distance d yand custom minimum scanning distance d min Determine the actual scanning distance d f , whose expression is: d f =max{d y , d min} In the Frenet coordinate system, the current position of the unmanned vehicle is taken as the starting point in the longitudinal direction, and the actual scanning distance d is taken as the starting point in the longitudinal direction. f The distance from the starting point to the end point is taken as the longitudinal length. In the horizontal direction, the longitudinal length is discretized, and the left and right side boundaries of the lane are traversed for each discretized sampling point. The minimum value from the left and right side boundaries is taken as the horizontal width. Determine the scanning range and road boundary information of the blocking obstacle in front of the vehicle in the Frenet coordinate system according to the longitudinal length and the lateral width; The blocking obstacles within the scanning range whose running speed is not greater than the user-defined speed threshold are numbered, and a blocking obstacle list is generated after obtaining coordinate information of a discrete point sequence representing their positions in the Frenet coordinate system.

[0015] In this preferred embodiment, in the Frenet coordinate system, starting from the current position of the unmanned vehicle and ending at the longitudinal preview position, the blocking obstacles whose lateral position, longitudinal position, and speed meet the requirements within this scanning range are obtained. The speed requirement here is a static or slow blocking obstacle, and the longitudinal position requirement is determined based on the boundary bounds on both sides of the current scene. Figure 2 Schematic diagram of road boundary confirmation for an unmanned vehicle in different driving scenarios according to a preferred embodiment of the present invention. Figure 2 As shown, starting from the current position of the unmanned vehicle, when it is in Figure 2 Comparing the obstacle detour state (seeing around the left side of the obstacle) with the obstacle-free cruising state (seeing above), it's clear that the left road boundary, marked in black, is expanded. Furthermore, for larger obstructions, to ensure the safety of the autonomous vehicle, a buffer distance can be set on all four sides of the vehicle to appropriately expand the obstruction, thereby sacrificing a small amount of space for greater safety. The buffer distance can be set as a fixed value for each side, or as an overall buffer distance with both length and width, then determined based on the angle between the obstruction and a reference line parallel to the road boundary. There are no restrictions here.

[0016] In step 102, N-level topological nodes of the proposed passage space are determined based on the information of each blocked obstacle in the blocked obstacle list and the road boundary information, wherein the topological nodes represent the space between blocked obstacles or between blocked obstacles and road boundaries in the proposed passage space intended for unmanned vehicles to pass.

[0017] Preferably, the determining of the N-level topological nodes of the proposed passage space according to the information of each blocked obstacle in the blocked obstacle list and the road boundary information includes: Determining an initial pre-selected segmentation point based on information about each blocking obstacle in the blocking obstacle list and the road boundary information, and generating an initial pre-selected segmentation point list, wherein attribute information of each initial pre-selected segmentation point includes position coordinate information, front and rear edge information, type information, segmentation line generation direction information, and associated obstacle information, wherein the position coordinate information includes a horizontal coordinate and a vertical coordinate, and the front and rear edge information includes front edge information and rear edge information, wherein the front edge and rear edge are determined in a counterclockwise rotation manner with the pre-selected segmentation point as the center; Based on the position coordinate information, the initial pre-selected segmentation points in the initial pre-selected segmentation point list are divided into N+1 groups of initial pre-selected segmentation points according to their vertical coordinates from near to far, wherein the vertical coordinates of each group of initial pre-selected segmentation points are the same, and from near to far refers to from the current position of the unmanned vehicle to the front of the unmanned vehicle; For each group of initial pre-selected segmentation points, sort them from left to right according to the horizontal axis, filter out duplicate pre-selected segmentation points, and generate the final pre-selected segmentation points of the corresponding group. Then, generate the final pre-selected segmentation point list based on the N+1 groups of final pre-selected segmentation points. Based on the position coordinate information, the road boundary information and the information of each blocking obstacle in the blocking obstacle list, the final pre-selected segmentation point in the final pre-selected segmentation point list that does not meet the custom segmentation point filtering rule is used as an important key point; Generate an N+1 level cyclic key point list according to the N+1 groups of final pre-selected segmentation points in the final pre-selected segmentation point list, and generate an updated attention edge list of the corresponding level based on the type information and the preceding and following edge information of the final pre-selected segmentation points in each level of the cyclic key point list; For the n-th level loop key point list, the direction information and position coordinate information of the segmentation line of each important key point are generated, as well as the road boundary information and the n-th level focus edge list to determine the n-th level upper boundary segmentation line and the lower boundary segmentation line, and the n-th level upper boundary list and the lower boundary list are generated according to the upper boundary segmentation line and the lower boundary segmentation line, wherein the upper boundary segmentation line is a line segment representing the upper boundary of the topological node, and the lower boundary segmentation line is a line segment representing the lower boundary of the topological node, 1≤n≤N+1; For each upper boundary dividing line in the j-th level upper boundary list, the corresponding j-1 level topological node is generated respectively according to the lower boundary dividing line in the j-1 level lower boundary list to be adapted that satisfies the topological node generation rule, wherein, 2≤j≤N+1, when j=2, the j-1 level lower boundary list to be adapted is the first level lower boundary list, when 2<j≤N+1, the j-1 level lower boundary list to be adapted is the set of the j-1 level lower boundary list and the j-2 level lower boundary list to be adapted after filtering out the lower boundary dividing line marked as adapted, the lower boundary dividing line marked as adapted satisfies the custom topological node generation rule, and the j-1 level topological node of the intended passable space is the set of the j-1 level topological nodes generated corresponding to all upper boundary dividing lines in the j-level upper boundary list.

[0018] In this preferred embodiment, the steps of generating the topological nodes of the space where the unmanned vehicle is to pass are specifically divided into generating an initial pre-selected segmentation point list, filtering the initial pre-selected segmentation point list to generate a final pre-selected segmentation point list, determining the important key points in the final pre-selected segmentation point list, generating a cyclic key point list and a focus edge list based on the final pre-selected segmentation point list, generating an upper boundary list and a lower boundary list composed of an upper boundary segmentation line and a lower boundary segmentation line respectively, and generating topological nodes based on the segmentation lines.

[0019] Preferably, determining the pre-selected segmentation points based on the information of each blocking obstacle in the blocking obstacle list and the road boundary information to generate an initial pre-selected segmentation point list includes: The start point and the end point of the scanning range are used as first pre-selected segmentation points, wherein the front and rear edge information, type information and obstacle information in the attribute information of the first pre-selected segmentation points are default values, and the segmentation line generation direction information is generated towards both sides of the road; using four vertices of each blocking obstacle in the blocking obstacle list as second pre-selected segmentation points, wherein segmentation line generation direction information in the attribute information of the second pre-selected segmentation point is determined according to the value assigned to the type information, the segmentation line generation direction information being at least one of generation toward both sides of the road, generation toward the left side of the road, and generation toward the right side of the road, and the value assigned to the type information in the attribute information of the second pre-selected segmentation point is determined according to whether, when the blocking obstacle is considered as a rectangle, the rectangle has sides parallel to the road boundary; The front and rear edges of the four vertices of each blocking obstacle in the blocking obstacle list intersect with the left and right boundaries of the road, and the intersection point of the dividing line generated into the road boundary is used as the third pre-selected dividing point, wherein the front and rear edge information and the type information in the attribute information of the third pre-selected dividing point are default values, the dividing line generation direction information of the third pre-selected dividing point intersecting with the left boundary of the road is generated toward the right side of the road, and the dividing line generation direction information of the third pre-selected dividing point intersecting with the right boundary of the road is generated toward the left side of the road; When the absolute value of the difference between the horizontal coordinates of any two adjacent road boundary sampling points is greater than a custom threshold, the road boundary sampling point that makes the unmanned vehicle's passage width smaller is used as the fourth pre-selected segmentation point, wherein the front and rear edge information, type information, and obstacle information in the attribute information of the fourth pre-selected segmentation point are default values, and the segmentation line generation direction information of the fourth pre-selected segmentation point located on the left side of the road is generated toward the right side of the road, and the segmentation line generation direction information of the fourth pre-selected segmentation point located on the right side of the road is generated toward the left side of the road; The set of the first pre-selected segmentation point, the second pre-selected segmentation point, the third pre-selected segmentation point and the fourth pre-selected segmentation point is used as an initial pre-selected segmentation point list.

[0020] In this preferred embodiment, the default values for front and rear edge information, type information, and obstacle information are set to NULL, indicating that the corresponding attributes do not exist. There are three types of dividing line generation direction information: generating to the left of the road, generating to the right of the road, and generating to both sides of the road. The corresponding values can be left, right, and both, respectively.

[0021] Figure 3 : is an example diagram of the second pre-selected segmentation point and the third pre-selected segmentation point according to a preferred embodiment of the present invention. Figure 3 As shown, when the blocking obstacle is regarded as a rectangle, whether the rectangle has sides equal to the road boundary, the position of the blocking obstacle has two situations A and B. When the position is situation A, the values assigned to its type information are UL, UR, DL and DR respectively, and when the position is situation B, the values assigned to its type information are U, W, L and R respectively. Since the front and back edges are determined by rotating counterclockwise with the preselected segmentation point as the center, when the second preselected segmentation point of the blocking obstacle B is assigned to L, the endpoints of its front edge are assigned to U and L, and the endpoints of its back edge are assigned to L and W. The principles for determining the front and back edges of other second preselected segmentation points are similar and will not be repeated here. Figure 2 It can be seen that the values of the second pre-selected segmentation point type information U, W, L and R, and the features of UL, UR, DL and DR in the coordinate system are: U: The ordinates of the other endpoints of the front and back edges are both smaller than their own ordinates. W: The ordinates of the other endpoints of the front and back edges are both greater than their own ordinates L: The ordinate of the rear endpoint is smaller than its own ordinate, and the ordinate of the front endpoint is larger than its own ordinate R: The ordinate of the front endpoint is smaller than its own ordinate, and the ordinate of the back endpoint is larger than its own ordinate UL: The ordinate of the front endpoint is equal to its own ordinate, and the ordinate of the back endpoint is less than its own ordinate. UR: The ordinate of the rear endpoint is equal to its own ordinate, and the ordinate of the front endpoint is less than its own ordinate. DL: The ordinate of the rear endpoint is equal to its own ordinate, and the ordinate of the front endpoint is greater than its own ordinate. DR: The ordinate of the front endpoint is equal to its own ordinate, and the ordinate of the back endpoint is greater than its own ordinate. Since the type information of the second pre-selected segmentation points of the blocking obstacles C and D is the same as that of the blocking obstacle B, Figure 3 Further, according to Figure 3 It can be seen that in order to segment the interior space in front of the unmanned vehicle that is to be passed based on the road boundary information, the segmentation line of the second pre-selected segmentation point can be in three situations: X1, X2 and X3. The corresponding segmentation line generation direction information is generated to the left side of the road, to the right side of the road and to both sides of the road. In addition, Figure 3 In the internal space that the autonomous vehicle intends to pass through, in addition to the vertices of the blocked obstacles, there are also intersections between the blocked obstacles and the boundaries on both sides of the road. Figure 3 It can be seen that the above-mentioned intersection point can generate a dividing line with the intended passage space only when the front and rear edges of the point assigned with the value L of the blocking obstacle located on the right boundary of the road intersect with the right boundary of the road, and the front and rear edges of the point assigned with the value R of the blocking obstacle located on the left boundary of the road intersect with the left boundary of the road, that is, D1, D2 and D3. The intersection point similar to D1, D2 and D3 is used as the third pre-selected dividing point, where the dividing line generation direction of the third pre-selected dividing point intersecting with the left boundary of the road is generated toward the right side of the road, and the generation direction of the third pre-selected dividing point intersecting with the right boundary of the road is generated toward the left side of the road. The third pre-selected dividing point is also a special point other than the vertex of the blocking obstacle. Therefore, the assignment of its type information and the assignment of its front and rear edge information are also NULL.

[0022] Figure 4 : is an example diagram of the fourth pre-selected segmentation point according to a preferred embodiment of the present invention. Figure 4 As shown in Figure 2, after the unmanned vehicle determines the interior space to be passed based on the road boundary information, when traversing the boundary values on both sides of the road according to the longitudinal coordinates, there may be a situation where the horizontal coordinates of the boundary values of the road boundary sampling points on both sides of the road change significantly, such as Figure 4For points D4 and D5, and D6 and D7, when the absolute value of the difference in their horizontal coordinates exceeds a custom threshold, it is considered that the width of the interior space the autonomous vehicle intends to pass through has changed significantly. This change requires special attention. These road boundary sampling points are designated as special points and recorded as the fourth pre-selected segmentation points. Specifically, to ensure the safe passage of the autonomous vehicle, a solution should be designed that minimizes the vehicle's passage width. Therefore, road boundary sampling points that minimize the vehicle's passage width are selected. Specifically, for points D4 and D5, D5 is selected as the fourth pre-selected segmentation point, and for points D6 and D7, D6 is selected as the fourth pre-selected segmentation point. Since the fourth pre-selected segmentation point is also a special point, its type information, front and rear edge information, and obstacle information are assigned NULL values. The direction of the segmentation line is determined by whether it is located on the left or right road boundary. If the sampling point is on the left road boundary, the segmentation line is generated toward the right; otherwise, it is generated toward the left.

[0023] Preferably, based on the position coordinate information, the road boundary information and the information of each blocking obstacle in the blocking obstacle list, the final pre-selected segmentation point in the final pre-selected segmentation point list that does not meet the custom segmentation point filtering rule is used as an important key point, wherein the segmentation point filtering rule includes: Filtering out the first pre-selected segmentation point and the fourth segmentation point, as well as other final pre-selected segmentation points outside the range determined by the road boundary information, of the position coordinate information; The final preselected segmentation points whose position coordinate information is within a range determined by the coordinate information of the discrete point sequence representing the position of the blocking obstacle in the Frenet coordinate system are filtered out.

[0024] In this preferred embodiment, filtering out the final pre-selected segmentation points whose position coordinate information is within the range determined by the coordinate information of the discrete point sequence representing the position of the blocking obstacle in the Frenet coordinate system means that when a final pre-selected segmentation point is located inside other obstacles, it is impossible to generate a segmentation line. Therefore, when generating the upper boundary segmentation line and the lower boundary segmentation line, such final pre-selected segmentation points do not need to be considered. Therefore, when determining the segmentation points that can generate the segmentation line, such segmentation points should be filtered out.

[0025] Preferably, generating an N+1-level cyclic key point list based on the N+1 groups of final pre-selected segmentation points in the final pre-selected segmentation point list, and generating an updated attention edge list of the corresponding level based on the type information and preceding and following edge information of the final pre-selected segmentation points in each level of the cyclic key point list, includes: Generate a list of loop key points of the corresponding level according to each group of final pre-selected segmentation points; Generate the initial attention edge list of level n according to the front and back edge information of the second pre-selected segmentation point in the level n loop key point list and the updated attention edge list of level n-1. When n=1, the updated attention edge list of level n-1 is an empty set. Delete the attention edges in the n-level initial attention edge list whose maximum vertical coordinate is less than the vertical coordinate of the final pre-selected segmentation point in the n-level loop key point list, and delete the corresponding attention edges that meet the custom type information-attention edge deletion list to generate the n-level updated attention edge list, wherein the type information-attention edge deletion list is a list that represents the correspondence between the type information of the second pre-selected segmentation point and the corresponding parts to be deleted in the preceding and following edge information.

[0026] Figure 5 Schematic diagram of the correspondence between the type information representing the second pre-selected segmentation point and the corresponding parts to be deleted in the front and back edge information according to the preferred embodiment of the present invention. Figure 5 As shown, there are eight types of type information values assigned to the second pre-selected segmentation point: W, U, L, R, UL, UR, DL, and DR. Examples are given below using values of W and L, respectively. Following the counterclockwise direction to determine the definitions of the leading and trailing edges, the leading and trailing edges when the second segmentation point type information is assigned to W and L are shown in the figure. For the final pre-selected segmentation point type information assigned to W, both the leading and trailing edges must be considered when updating the focused edges, both represented by solid black lines. At this point, the corresponding focused edges do not need to be deleted. For the final pre-selected segmentation point type information assigned to L, only the leading edge, represented by a solid black line, needs to be considered when updating the focused edges, while the trailing edge, represented by a dashed black line, needs to be deleted. The principles for determining the updated focused edges for the second pre-selected segmentation points of other types of information are similar and will not be elaborated on. After determining the focused edges that need to be updated and the portions that need to be deleted in the leading and trailing edges of the second pre-selected segmentation point for each type of information, a corresponding table is established to generate the corresponding type information-focused edge deletion list.

[0027] Figure 6 Schematic diagram of generating and updating the concerned edge list according to a preferred embodiment of the present invention. Figure 6As shown in the figure, the loop key point lists from level n-1 to level n+4 are intercepted, and their corresponding loop key point sets are {DL1, DR1, DL2}, {UL1, UR1}, {W1}, {L1, UL2}, {R1}, and {U1}. Assuming that the n-1 level update attention edge list corresponding to the n-1 loop key point list is {E1, E3, E5, E7}, then according to the defined second pre-selected split point type and the preceding and following edges, the preceding and following edges corresponding to UL1 and UR1 in the n-level loop key point list are E4 and E1, E3 and E4, respectively. Therefore, the n-level initial attention edge list is {E4, E1, E3, E5, E7}. According to the type information - attention edge deletion list, it is known that E4 needs to be deleted from both the preceding and following edges of UL1 and UR1. Therefore, the n-level update attention edge list is the same as the n-1 level update attention edge list, both of which are {E1, E3, E5, E7}. For the n+1th level loop keypoint list, the preceding and following edges of W1 are E10 and E11, so the initial n+1th level attention edge list is {E1, E3, E5, E7, E10, E11}. However, since the maximum ordinates of E1 and E3 are less than the ordinate of the final preselected split point W1 in the n+1th level loop keypoint list, they should be deleted. However, W1 does not have any edges that need to be deleted in the type information - attention edge deletion list. Therefore, the n+1th level updated attention edge list should be {E5, E7, E10, E11}. Similarly, the n+2th level updated attention edge list can be determined as {E5, E7, E9, E11}, the n+3th level updated attention edge list as {E9, E12}, and the n+4th level updated attention edge list as {E9, E12}.

[0028] Preferably, for the n-th level cyclic key point list, the upper boundary segmentation line and the lower boundary segmentation line of the n-th level are determined based on the segmentation line of each important key point, the road boundary information, and the n-th level focus edge list, including: For each important key point in the n-th level cyclic key point list, obtaining a road boundary sampling point in the dividing line generation direction according to the dividing line generation direction information, wherein when the dividing line generation direction information is generated toward both sides of the road, the road boundary sampling point includes a road left boundary sampling point and a road right boundary sampling point; The important key point and its corresponding road boundary sampling point are connected to generate a line segment. When the line segment does not intersect with any other focus edge in the n-th level update focus list except the focus edge where the important key point is located, the road boundary sampling point corresponding to the important key point is determined as the anchor point. When the line segment intersects with any other focus edge in the n-th level update focus list except the focus edge where the important key point is located, the intersection point closest to the important key point is taken as the anchor point. The intersection point closest to the important key point is not on the blocking obstacle to which the important key point belongs. When generating the upper boundary segmentation line, the minimum ordinate of the focus edge where the intersection point closest to the important key point is located is smaller than the ordinate of the important key point. When generating the lower boundary segmentation line, the maximum ordinate of the focus edge where the intersection point closest to the important key point is located is larger than the ordinate of the important key point. When there are two anchor points, the anchor point closer to the left side boundary sampling point of the road is the left anchor point, and the anchor point closer to the right side boundary sampling point of the road is the right anchor point. Specifically: When the direction information of generating the segmentation line of the important key point is to generate it toward the right side of the road, generating a segmentation line with coordinate position information of {key point, anchor point}; When the direction information of the segmentation line generation of the important key point is to generate it towards the left side of the road, if the position coordinate information of the segmentation line that has been generated contains the important key point, then no segmentation line is generated for the important key point; otherwise, a segmentation line with the coordinate position information of {anchor point, key point} is generated; When the dividing line generation direction information of the important key point is generated towards both sides of the road, if the position coordinate information of the already generated dividing line contains the important key point, the dividing line is not generated for the important key point; otherwise, a dividing line with the generated coordinate position information of {left anchor point, right anchor point} is generated.

[0029] Figure 7 Schematic diagram of generating upper boundary segmentation line and lower boundary segmentation line according to a preferred embodiment of the present invention. Figure 7As shown in the figure, for the important key points in the n-1th to n+4th level cyclic key point lists, according to their segmentation line generation direction information, the road boundary sampling points in the segmentation line generation direction are M1, M2, M4, M6, M8, M9 and M10, while the important key points UR2 and DR2 coincide with the road boundary sampling points. Furthermore, for DL1 in the n-1th level cyclic key point list, when the lower boundary segmentation line is generated, it is connected to the corresponding road boundary sampling point M1 to generate a line segment {DL1, M1}, and this line segment does not intersect with the other three focus edges except the focus edge E1 where DL1 is located in the n-1th level update focus list {E1, E3, E5, E7}, so M1 can be determined as the anchor point. Since the segmentation line generation direction of DL1 is generated toward the left side of the road, the coordinate position information format of the generated segmentation line is {anchor point, key point}, i.e., {M1, DL1}. Correspondingly, for DR1, when the lower boundary segmentation line is generated, the segmentation line generation direction is generated toward the right side of the road. When it is connected with the road boundary sampling point on the right side of the road to form a line segment, the closest intersection point with it is DL2. At this time, DL2 is the anchor point, and the coordinate position information format of the generated segmentation line is {key point, anchor point}, i.e., {DR2, DL2}. Similarly, for U1 in the n+4th level cyclic key point list, since its segmentation line generation direction can be generated to both sides of the road, or to the left and right sides of the road respectively, specifically, according to the meaning of the upper boundary segmentation line and the lower boundary segmentation line, when generating the upper boundary segmentation line, since the topological node where the U1 point is located must be divided into two by its front and rear edges E9 and E12, the segmentation line can only be generated to the left and right sides of the road at the U1 point, respectively, expressed as {M9, U1} and {U1, M10}. When generating the lower boundary segmentation line, since the unmanned vehicle has passed through the two topological nodes divided by the front and rear edges E9 and E12 of the U1 point, the segmentation line can be generated to both sides of the road at the U1 point, expressed as {M9, M10}. Similarly, for point W1 in the n+1th level loop key point list, when generating the upper boundary segmentation line, since the unmanned vehicle has not yet entered the two topological nodes divided by its front and rear edges E10 and E11, the segmentation line generation direction is toward both sides of the road, and the generated upper boundary segmentation line is represented as {M4, M5}. When generating the lower boundary segmentation line, since the unmanned vehicle has entered the two topological nodes divided by its front and rear edges E10 and E11, the segmentation line generation direction can only be toward the left side of the road and toward the right side of the road respectively. The generated segmentation lines are represented as {M4, W1} and {W1, M5} respectively.In addition, for point DR1 in the n-1th level loop key point list, when generating the lower boundary segmentation line, according to the above analysis, the segmentation line is {DR1, DL2}. For DL2, since its segmentation line generation direction is toward the left side of the road, and it intersects with E3 in the focus edge list at DR1, DR1 is the closest intersection point to it, and the segmentation line corresponding to point DR2 is also {DR1, DL2}, which is equivalent to the segmentation lines of DR1 and DL2 being repeated. Since DR1 is on the left side of the coordinate system, a segmentation line is only generated for DR1, and no segmentation line is generated for DL2.

[0030] Based on the above analysis, combined Figure 7 It can be seen that the upper boundary segmentation line list and the lower boundary segmentation line list corresponding to the n-1th level to the n+4th level cyclic key point list are shown in Table 1.

[0031] Table 1 Cycle Key List Upper Bound List Lower Bound List Level n+4 {M9,U1},{U1,M10} {M9,M10} Level n+3 {R1, M8} {R1, M8} Level n+2 {M6,L},{M7,UL2} {M6,L1},{M7,UR2} Level n+1 {M4,M5} {M4,W1},{W1,M5} Level n {M2,UL1},{UR1,M3} {M2,UR1},{UL1,M3} Level n-1 {M1,DR1},{DL1,DL2},{DR1,DR2} {M1,DL1},{DR1,DL2} Preferably, for each upper boundary dividing line in the j-th level upper boundary list, the corresponding j-1-th level topological node is generated according to the lower boundary dividing line in the j-1-th level lower boundary list to be adapted that satisfies the topological node generation rule, wherein the topological node generation rule includes: For each upper boundary segmentation line in the j-th level upper boundary list, take the midpoint of the upper boundary segmentation line and the midpoint of each lower boundary segmentation line in the j-1-th level to-be-adapted lower boundary list to form a line segment; When the line segment does not intersect with all blocked obstacles, a polygon containing upper and lower boundary segmentation line information, left and right obstacle information or road boundary information is generated as a topological node, and the lower boundary segmentation line corresponding to the line segment is marked as adapted.

[0032] Figure 8 Schematic diagram of generating topological nodes according to a preferred embodiment of the present invention. Figure 8 As shown in Figure 1, when j=n, assuming that the n-1th level lower boundary list in Table 1 is the n-1th level lower boundary list to be adapted, then according to the topological node generation rule, for the upper boundary dividing lines {M2,UL1} and {UR1,M3} in the n-1th level upper boundary list, when their midpoints are connected with the midpoints of the lower boundary dividing lines {M1,DL1} and {DR1,DL2} in the n-1th level lower boundary list to be adapted to form line segments, only the line segments formed by connecting the midpoints of {M2,UL1} and {M1,DL1}, and {UR1,M3} and {DR1,DL2} do not intersect with the blocking obstacles, so two topological nodes are generated, which are marked as No respectively. n-1，1 and No n-1，2, and the lower boundary dividing lines {M1, DL1} and {DR1, DL2} are marked as adapted. Based on this reasoning, the n-th level topological node No can be generated in sequence. n，1 and No n，2 , the n+1th level topological node No n+1，1 and No n+1，2 However, when generating a topological node based on all the upper boundary splitters in the n+3th level upper boundary list, that is, {R1, M8}, only the lower boundary splitter {M7, UR2} in the n+2th level lower boundary list is adapted, generating a topological node No. n+2，1 , the unadapted lower boundary dividing line {M6, L1} needs to be used as the lower boundary dividing line in the n+3th level to be adapted lower boundary list, and the upper boundary dividing line {M9, U1} in the n+4th level upper boundary dividing line list generates the topological node No n+3，1 , and the upper boundary dividing line {U1, M10} generates a topological node with another lower boundary dividing line {R1, M8} in the n+3th level lower boundary list to be adapted. n+3，2 .

[0033] In step 103, M alternative paths for the unmanned vehicle to pass through are generated based on the connection relationship between the N-level topological nodes of the planned passage space, as well as the minimum passage width of the vehicle between the topological nodes with the connection relationship.

[0034] Preferably, the method of generating M alternative paths for the unmanned vehicle to pass through based on the connection relationship between N-level topological nodes of the intended passage space, and the minimum passage width of the vehicle between the topological nodes with the connection relationship, includes: Traverse the i-th level topological nodes and the i+1-th level topological nodes of the intended traversable space according to the custom topological node connection rules, wherein the topological node connection rules include: Based on the upper boundary segmentation line information of the i-th level topological node and the lower boundary segmentation line information of the i+1-th to N-th level topological nodes, when the upper boundary segmentation line of a topological node in the i-th level topological node intersects with the lower boundary segmentation line of a topological node in the i+1-th to N-th level topological nodes, it is determined that there is a connection relationship between the two topological nodes, and the minimum vehicle passage width between the two topological nodes with a connection relationship is the length of the shortest line segment between any two points on the edge of the polygon formed by the two topological nodes in the direction perpendicular to the boundaries on both sides of the road; The topological nodes with connection relationships in the N-level topological nodes of the planned passage space are connected in sequence to generate M alternative paths for the unmanned vehicle to pass.

[0035] In this preferred embodiment, Figure 8 The topological nodes from level n-1 to level n+3 are shown, No n-1，1The upper boundary dividing line and No n，1 The lower boundary dividing line intersects, No n-1，2 The upper boundary dividing line and No n，2 The lower boundary dividing line intersects, No n，1 The upper boundary dividing line and No n+1，1 The lower boundary dividing line intersects, No n，2 The upper boundary dividing line and No n+1，2 The lower boundary dividing line intersects, No n+1，1 The upper boundary dividing line and No n+3，1 The lower boundary dividing line intersects, No n+1，2 The upper boundary dividing line and No n+2，1 The lower boundary dividing line intersects, and No n+2，1 The upper boundary dividing line and No n+3，2 The lower boundary dividing line intersects, according to the topological node connection rule, Figure 8 Two alternative paths for the unmanned vehicle to pass can be formed, and the topological nodes of one path are No n-1，1 , No n+1，1 and No n+3，1 , and the topological nodes of the other path are No n-1，2 , No n，2 , Node n+1，2 , No n+2，1 and No n+3，2 Furthermore, according to the definition of the minimum width of vehicles between two topological nodes with a connection relationship, Figure 8 The minimum width of vehicles passing between the topological nodes with connection relationships can be clearly seen, such as No n+1，1 and No n+3，1 They are all trapezoidal, and the length of the shortest line segment perpendicular to the right boundary of the road is obviously {M6,L1}, that is, No n+1，1 and No n+3，1 The minimum width for vehicles to pass between them is {M6, L1}, and the minimum width for vehicles to pass between other topological nodes with connection relationships is similar, which will not be repeated here.

[0036] In step 104 , a first cost of the N-level topological nodes in the intended traversable space and a second cost between the topological nodes having a connection relationship are calculated according to a self-defined cost function.

[0037] Preferably, the calculating of the first cost of the N-level topological nodes of the intended traversable space and the second cost between the topological nodes having a connection relationship according to the self-defined cost function includes: Calculate the width cost, history trajectory cost, wheel orientation cost and deformation cost of the N-level topological nodes in the proposed traversable space respectively according to the custom node width cost function, node history trajectory cost function, node wheel orientation cost function and node deformation cost function in the SL coordinate system, wherein the first cost includes width cost, history trajectory cost, wheel orientation cost and deformation cost; The lateral offset cost between topological nodes having a connection relationship is calculated according to a user-defined lateral offset cost function, wherein the second cost refers to the lateral offset cost between the topological nodes.

[0038] The first cost and the second cost in this preferred embodiment can be set according to the needs of actual application, and the present invention does not limit them.

[0039] In step 105 , the costs of M candidate paths are calculated based on the user-defined cost weight value, the first cost and the second cost of the topological node on each candidate path.

[0040] Preferably, the first cost and the second cost of the topological node on each alternative path are used to calculate the costs of the M alternative paths respectively according to the user-defined cost weight value, and the calculation formula is: Where, 1≤m≤M, is the cost of the mth alternative path, L is the total cost included in the first cost, cost l and are the lth cost and its corresponding weight value in the first cost respectively; K is the total number of costs included in the second cost, cost k and are the kth cost in the second cost and its corresponding weight value respectively.

[0041] In this preferred embodiment, considering the different importance of different costs in determining the proposed passable space, different weight values can be set for different costs based on the calculation, thereby improving the accuracy of selecting the optimal proposed passable space.

[0042] In step 106 , based on the customized space screening rules, the final passage space for the unmanned vehicle is determined according to the customized minimum passage width of the unmanned vehicle, the costs of the M alternative paths and the minimum passage width of the vehicle.

[0043] Preferably, the method of determining the final passage space for the unmanned vehicle based on the customized space screening rule according to the customized minimum passage width of the unmanned vehicle, the costs of the M alternative paths and the minimum passage width of the vehicle includes: Based on the customized spatial screening rules, the final path of the unmanned vehicle is determined according to the customized minimum width of the unmanned vehicle, the costs of the M alternative paths, and the minimum width of the vehicle. The spatial screening rules include: Starting from the starting point, the minimum vehicle passage width and the minimum unmanned vehicle passage width in each alternative path are compared. When the minimum vehicle passage width is smaller than the minimum unmanned vehicle passage width, the two topological nodes with a connection relationship corresponding to the minimum vehicle passage width are pruned. When there is at least one alternative path that has not been clipped, the alternative path with the lowest cost is selected as the final path for the autonomous vehicle; When there are no alternative paths that have not been clipped, the longest part of the unclipped topological nodes among the M alternative paths is selected in order from the starting point to the end point, and the final path for the unmanned vehicle is generated by splicing them together; Traverse the longitudinal space of the unmanned vehicle's final passage path, detect the topological node to which the scanned position belongs according to the custom distance step size, and determine the boundary information of the unmanned vehicle's final passage space based on the blocked obstacle information and road boundary information on both sides of the topological node.

[0044] In this preferred embodiment, Figure 8 The two alternative paths shown are assumed to be the alternative path close to the left edge of the road, No n+1，1 and No n+3，1 If the minimum width {M6, L1} between vehicles is less than the minimum width of the self-defined unmanned vehicle, then the topological node No of the alternative path needs to be n+1，1 and No n+3，1 If the alternative path near the right edge of the road is not clipped, the final path of the autonomous vehicle will be the alternative path.

[0045] The method for searching for unmanned vehicle passage space described in this preferred embodiment can generate a topological node connection diagram that conforms to the passage environment under complex road conditions through blocking obstacle screening, topological node generation, node cost calculation, optimal passage path search and optimal passage space acquisition without wasting too much computing power. The highly adaptive search algorithm avoids the loss of passage space to the greatest extent, thereby providing the optimal vehicle passage space for downstream trajectory planning.

[0046] Exemplary Systems Figure 9 FIG. 1 is a schematic diagram of a system for searching for unmanned vehicle passage space according to a preferred embodiment of the present invention. Figure 9 As shown, the system 900 for searching for unmanned vehicle passage spaces according to this preferred embodiment includes: Pre-processing module 901, for generating a list of blocked obstacles based on the current speed of the unmanned vehicle, a customized minimum scanning distance and scanning time, and the speed of the blocked obstacles in front of the unmanned vehicle, and determining the road boundary information in front of the unmanned vehicle; A topology node module 902 is configured to determine an N-level topology node of the proposed passage space based on the information of each blocking obstacle in the blocking obstacle list and the road boundary information, wherein the topology node represents the space between blocking obstacles or between blocking obstacles and the road boundary in the proposed passage space intended for passage of the unmanned vehicle; The alternative path module 903 is used to generate M alternative paths for the unmanned vehicle to pass based on the connection relationship between the N-level topological nodes of the intended passage space, and the minimum passage width of the vehicle between the topological nodes with the connection relationship; A first calculation module 904 is configured to calculate, according to a user-defined cost function, a first cost of N-level topological nodes in a proposed traversable space and a second cost between topological nodes having a connection relationship; A second calculation module 905 is configured to calculate the costs of the M candidate paths according to the user-defined cost weight value, the first cost and the second cost of the topological node on each candidate path; The result output module 906 is used to determine the final passage space of the unmanned vehicle based on the customized space screening rules, according to the customized minimum passage width of the unmanned vehicle, the costs of the M alternative paths and the minimum passage width of the vehicle.

[0047] Preferably, the pre-processing module 901 generates a list of blocked obstacles based on the current speed of the unmanned vehicle, a customized minimum scanning distance and scanning time, and the speed of the blocked obstacles in front of the unmanned vehicle, and determines the road boundary information in front of the unmanned vehicle, including: Based on the current speed of the autonomous vehicle, the minimum scanning distance and scanning time are customized to determine the scanning range for obstacles in front of the autonomous vehicle, including: According to the current speed v of the unmanned vehicle and the custom scanning time t y Calculate the current scanning distance d y , and its calculation formula is: d y =v*t y According to the current scanning distance d y and custom minimum scanning distance d min Determine the actual scanning distance d f , whose expression is: d f =max{d y , d min} In the Frenet coordinate system, the current position of the unmanned vehicle is taken as the starting point in the longitudinal direction, and the actual scanning distance d is taken as the starting point in the longitudinal direction. f The distance from the starting point to the end point is taken as the longitudinal length. In the horizontal direction, the longitudinal length is discretized, and the left and right side boundaries of the lane are traversed for each discretized sampling point. The minimum value from the left and right side boundaries is taken as the horizontal width. Determine the scanning range and road boundary information of the blocking obstacle in front of the vehicle in the Frenet coordinate system according to the longitudinal length and the lateral width; The blocking obstacles within the scanning range whose running speed is not greater than the user-defined speed threshold are numbered, and a blocking obstacle list is generated after obtaining coordinate information of a discrete point sequence representing their positions in the Frenet coordinate system.

[0048] Preferably, the topology node module 902 determines the N-level topology nodes of the proposed passage space according to the information of each blocked obstacle in the blocked obstacle list and the road boundary information, including: Determining an initial pre-selected segmentation point based on information about each blocking obstacle in the blocking obstacle list and the road boundary information, and generating an initial pre-selected segmentation point list, wherein attribute information of each initial pre-selected segmentation point includes position coordinate information, front and rear edge information, type information, segmentation line generation direction information, and associated obstacle information, wherein the position coordinate information includes a horizontal coordinate and a vertical coordinate, and the front and rear edge information includes front edge information and rear edge information, wherein the front edge and rear edge are determined in a counterclockwise rotation manner with the pre-selected segmentation point as the center; Based on the position coordinate information, the initial pre-selected segmentation points in the initial pre-selected segmentation point list are divided into N+1 groups of initial pre-selected segmentation points according to their vertical coordinates from near to far, wherein the vertical coordinates of each group of initial pre-selected segmentation points are the same, and from near to far refers to from the current position of the unmanned vehicle to the front of the unmanned vehicle; For each group of initial pre-selected segmentation points, sort them from left to right according to the horizontal axis, filter out duplicate pre-selected segmentation points, and generate the final pre-selected segmentation points of the corresponding group. Then, generate the final pre-selected segmentation point list based on the N+1 groups of final pre-selected segmentation points. Based on the position coordinate information, the road boundary information and the information of each blocking obstacle in the blocking obstacle list, the final pre-selected segmentation point in the final pre-selected segmentation point list that does not meet the custom segmentation point filtering rule is used as an important key point; Generate an N+1 level cyclic key point list according to the N+1 groups of final pre-selected segmentation points in the final pre-selected segmentation point list, and generate an updated attention edge list of the corresponding level based on the type information and the preceding and following edge information of the final pre-selected segmentation points in each level of the cyclic key point list; For the n-th level loop key point list, the direction information and position coordinate information of the segmentation line of each important key point are generated, as well as the road boundary information and the n-th level focus edge list to determine the n-th level upper boundary segmentation line and the lower boundary segmentation line, and the n-th level upper boundary list and the lower boundary list are generated according to the upper boundary segmentation line and the lower boundary segmentation line, wherein the upper boundary segmentation line is a line segment representing the upper boundary of the topological node, and the lower boundary segmentation line is a line segment representing the lower boundary of the topological node, 1≤n≤N+1; For each upper boundary dividing line in the j-th level upper boundary list, generate its corresponding j-1th level topological node according to the lower boundary dividing line in the j-1th level lower boundary list to be adapted that satisfies the topological node generation rule, wherein 2≤j≤N+1, when j=2, the j-1th level lower boundary list to be adapted is the first level lower boundary list, when 2<j≤N+1, the j-1th level lower boundary list to be adapted is the set of the j-1th lower boundary list and the j-2th level lower boundary list to be adapted after filtering out the lower boundary dividing line marked as adapted, the lower boundary dividing line marked as adapted satisfies the custom topological node generation rule, and the j-1th level topological node of the intended passable space is the set of the j-1th level topological nodes generated corresponding to all upper boundary dividing lines in the j-th level upper boundary list.

[0049] Preferably, the topology node module 902 determines the pre-selected segmentation points according to the information of each blocked obstacle in the blocked obstacle list and the road boundary information, and generates an initial pre-selected segmentation point list, including: The start point and the end point of the scanning range are used as first pre-selected segmentation points, wherein the front and rear edge information, type information and obstacle information in the attribute information of the first pre-selected segmentation points are default values, and the segmentation line generation direction information is generated towards both sides of the road; using four vertices of each blocking obstacle in the blocking obstacle list as second pre-selected segmentation points, wherein segmentation line generation direction information in the attribute information of the second pre-selected segmentation point is determined according to the value assigned to the type information, the segmentation line generation direction information being at least one of generation toward both sides of the road, generation toward the left side of the road, and generation toward the right side of the road, and the value assigned to the type information in the attribute information of the second pre-selected segmentation point is determined according to whether, when the blocking obstacle is considered as a rectangle, the rectangle has sides parallel to the road boundary; The front and rear edges of the four vertices of each blocking obstacle in the blocking obstacle list intersect with the left and right boundaries of the road, and the intersection point of the dividing line generated into the road boundary is used as the third pre-selected dividing point, wherein the front and rear edge information and the type information in the attribute information of the third pre-selected dividing point are default values, the dividing line generation direction information of the third pre-selected dividing point intersecting with the left boundary of the road is generated toward the right side of the road, and the dividing line generation direction information of the third pre-selected dividing point intersecting with the right boundary of the road is generated toward the left side of the road; When the absolute value of the difference between the horizontal coordinates of any two adjacent road boundary sampling points is greater than a custom threshold, the road boundary sampling point that makes the unmanned vehicle's passage width smaller is used as the fourth pre-selected segmentation point, wherein the front and rear edge information, type information, and obstacle information in the attribute information of the fourth pre-selected segmentation point are default values, and the segmentation line generation direction information of the fourth pre-selected segmentation point located on the left side of the road is generated toward the right side of the road, and the segmentation line generation direction information of the fourth pre-selected segmentation point located on the right side of the road is generated toward the left side of the road; The set of the first pre-selected segmentation point, the second pre-selected segmentation point, the third pre-selected segmentation point and the fourth pre-selected segmentation point is used as an initial pre-selected segmentation point list.

[0050] Preferably, the topology node module 902 selects the final pre-selected segmentation point in the final pre-selected segmentation point list that does not meet the custom segmentation point filtering rule as an important key point based on the position coordinate information, road boundary information and information of each blocking obstacle in the blocking obstacle list, wherein the segmentation point filtering rule includes: Filter out other final pre-selected segmentation points whose position coordinate information is outside the range determined by the first pre-selected segmentation point and the fourth segmentation point; The final preselected segmentation points whose position coordinate information is within a range determined by the coordinate information of the discrete point sequence representing the position of the blocking obstacle in the Frenet coordinate system are filtered out.

[0051] Preferably, the topology node module 902 generates an N+1-level cyclic key point list based on the N+1 groups of final pre-selected segmentation points in the final pre-selected segmentation point list, and generates an updated attention edge list of the corresponding level based on the type information and the preceding and following edge information of the final pre-selected segmentation points in each level of the cyclic key point list, including: Generate a list of loop key points of the corresponding level according to each group of final pre-selected segmentation points; Generate the initial attention edge list of level n according to the front and back edge information of the second pre-selected segmentation point in the level n loop key point list and the updated attention edge list of level n-1. When n=1, the updated attention edge list of level n-1 is an empty set. Delete the attention edges in the n-level initial attention edge list whose maximum vertical coordinate is less than the vertical coordinate of the final pre-selected segmentation point in the n-level loop key point list, and delete the corresponding attention edges that meet the custom type information-attention edge deletion list to generate the n-level updated attention edge list, wherein the type information-attention edge deletion list is a list that represents the correspondence between the type information of the second pre-selected segmentation point and the corresponding parts to be deleted in the preceding and following edge information.

[0052] Preferably, the topology node module 902 determines the upper boundary segmentation line and the lower boundary segmentation line of the nth level based on the segmentation line of each important key point, the road boundary information, and the nth level focus edge list for the nth level cycle key point list, including: For each important key point in the n-th level cyclic key point list, obtaining a road boundary sampling point in the dividing line generation direction according to the dividing line generation direction information, wherein when the dividing line generation direction information is generated toward both sides of the road, the road boundary sampling point includes a road left boundary sampling point and a road right boundary sampling point; The important key point and its corresponding road boundary sampling point are connected to generate a line segment. When the line segment does not intersect with any other focus edge in the n-th level update focus list except the focus edge where the important key point is located, the road boundary sampling point corresponding to the important key point is determined as the anchor point. When the line segment intersects with any other focus edge in the n-th level update focus list except the focus edge where the important key point is located, the intersection point closest to the important key point is taken as the anchor point. The intersection point closest to the important key point is not on the blocking obstacle to which the important key point belongs. When generating the upper boundary segmentation line, the minimum ordinate of the focus edge where the intersection point closest to the important key point is located is smaller than the ordinate of the important key point. When generating the lower boundary segmentation line, the maximum ordinate of the focus edge where the intersection point closest to the important key point is located is larger than the ordinate of the important key point. When there are two anchor points, the anchor point closer to the left side boundary sampling point of the road is the left anchor point, and the anchor point closer to the right side boundary sampling point of the road is the right anchor point. Specifically: When the direction information of generating the segmentation line of the important key point is to generate it toward the right side of the road, generating a segmentation line with coordinate position information of {key point, anchor point}; When the direction information of the segmentation line generation of the important key point is to generate it towards the left side of the road, if the position coordinate information of the segmentation line that has been generated contains the important key point, then no segmentation line is generated for the important key point; otherwise, a segmentation line with the coordinate position information of {anchor point, key point} is generated; When the dividing line generation direction information of the important key point is generated towards both sides of the road, if the position coordinate information of the already generated dividing line contains the important key point, the dividing line is not generated for the important key point; otherwise, a dividing line with the generated coordinate position information of {left anchor point, right anchor point} is generated.

[0053] Preferably, the topology node module 902 generates a corresponding j-1-level topology node for each upper boundary dividing line in the j-th level upper boundary list according to the lower boundary dividing line in the j-1-th level lower boundary list that satisfies the topology node generation rule, wherein the topology node generation rule includes: For each upper boundary segmentation line in the j-th level upper boundary list, take the midpoint of the upper boundary segmentation line and the midpoint of each lower boundary segmentation line in the j-1-th level to-be-adapted lower boundary list to form a line segment; When the line segment does not intersect with all blocked obstacles, a polygon containing upper and lower boundary segmentation line information, left and right obstacle information or road boundary information is generated as a topological node, and the lower boundary segmentation line corresponding to the line segment is marked as adapted.

[0054] Preferably, the alternative path module 903 generates M alternative paths for the unmanned vehicle to pass through based on the connection relationship between the N-level topological nodes of the intended passage space, and the minimum vehicle passage width between the topological nodes with the connection relationship, including: Traverse the i-th level topological nodes and the i+1-th level topological nodes of the intended traversable space according to the custom topological node connection rules, wherein the topological node connection rules include: Based on the upper boundary segmentation line information of the i-th level topological node and the lower boundary segmentation line information of the i+1-th to N-th level topological nodes, when the upper boundary segmentation line of a topological node in the i-th level topological node intersects with the lower boundary segmentation line of a topological node in the i+1-th to N-th level topological nodes, it is determined that there is a connection relationship between the two topological nodes, and the minimum vehicle passage width between the two topological nodes with a connection relationship is the length of the shortest line segment between any two points on the edge of the polygon formed by the two topological nodes in the direction perpendicular to the boundaries on both sides of the road; The topological nodes with connection relationships in the N-level topological nodes of the planned passage space are connected in sequence to generate M alternative paths for the unmanned vehicle to pass.

[0055] Preferably, the first calculation module 904 calculates the first cost of the N-level topological nodes in the intended traversable space and the second cost between the topological nodes having a connection relationship according to a self-defined cost function, including: Calculate the width cost, history trajectory cost, wheel orientation cost and deformation cost of the N-level topological nodes in the proposed traversable space respectively according to the custom node width cost function, node history trajectory cost function, node wheel orientation cost function and node deformation cost function in the SL coordinate system, wherein the first cost includes width cost, history trajectory cost, wheel orientation cost and deformation cost; The lateral offset cost between topological nodes having a connection relationship is calculated according to a user-defined lateral offset cost function, wherein the second cost refers to the lateral offset cost between the topological nodes.

[0056] Preferably, the first cost and the second cost of the topological node on each alternative path are used to calculate the costs of the M alternative paths respectively according to the user-defined cost weight value, and the calculation formula is: Where, 1≤m≤M, is the cost of the mth alternative path, L is the total cost included in the first cost, cost l and are the lth cost and its corresponding weight value in the first cost respectively; K is the total number of costs included in the second cost, cost k and are the kth cost in the second cost and its corresponding weight value respectively.

[0057] Preferably, the result output module 906 determines the final passage space for the unmanned vehicle based on a customized space screening rule, according to the customized minimum passage width of the unmanned vehicle, the costs of the M alternative paths, and the minimum passage width of the vehicle, including: Based on the customized spatial screening rules, the final path of the unmanned vehicle is determined according to the customized minimum width of the unmanned vehicle, the costs of the M alternative paths, and the minimum width of the vehicle. The spatial screening rules include: Starting from the starting point, the minimum vehicle passage width and the minimum unmanned vehicle passage width in each alternative path are compared. When the minimum vehicle passage width is smaller than the minimum unmanned vehicle passage width, the two topological nodes with a connection relationship corresponding to the minimum vehicle passage width are pruned. When there is at least one alternative path that has not been clipped, the alternative path with the lowest cost is selected as the final path for the autonomous vehicle; When there are no alternative paths that have not been clipped, the longest part of the unclipped topological nodes among the M alternative paths is selected in order from the starting point to the end point, and the final path for the unmanned vehicle is generated by splicing them together; Traverse the longitudinal space of the unmanned vehicle's final passage path, detect the topological node to which the scanned position belongs according to the custom distance step size, and determine the boundary information of the unmanned vehicle's final passage space based on the blocked obstacle information and road boundary information on both sides of the topological node.

[0058] The system for searching for unmanned vehicle passage space described in this preferred embodiment and the method for searching for unmanned vehicle passage space have the same steps of obtaining the optimal passage space through blocking obstacle screening, topological node generation, node cost calculation, and optimal passage path search, and the technical effects achieved are also the same, which will not be repeated here.

[0059] Exemplary electronic devices Figure 10 FIG. 1 is a schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. Figure 10 As shown, the electronic device includes one or more processors 1001 and a memory 1002 .

[0060] The processor 1001 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0061] Memory 1002 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and processor 1001 may execute these program instructions to implement the methods for searching for unmanned vehicle passage spaces described in the various embodiments disclosed above and / or other desired functions. In one example, the electronic device may further include an input device 1003 and an output device 1004, with these components interconnected via a bus system and / or other form of connection mechanism (not shown).

[0062] In addition, the input device 1003 may also include, for example, a keyboard, a mouse, and the like.

[0063] The output device 1004 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0064] Of course, to simplify, Figure 10Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application scenarios.

[0065] Exemplary computer program products and computer-readable storage media In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps in the method for searching for unmanned vehicle passage space according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0066] The computer program product may be written in any combination of one or more programming languages to implement the operations of the disclosed embodiments, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as C or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0067] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method for searching for unmanned vehicle passage space according to various embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0068] The computer-readable storage medium may be any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0069] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0070] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0071] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0072] The apparatus and method of the present disclosure may be implemented in many ways. For example, the apparatus and method of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers recording media that store programs for executing the method according to the present disclosure.

[0073] It should also be noted that, in the apparatus, equipment and method of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present disclosure. The above description of the disclosed aspects is provided to enable any technician in this field to make or use the present disclosure. Various modifications to these aspects will be very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown here, but to the widest range consistent with the principles and novel features disclosed herein.

[0074] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for searching for a space for an unmanned vehicle to pass through, characterized in that: The method comprises: Generate a list of blocked obstacles based on the current speed of the autonomous vehicle, the customized minimum scanning distance and scanning time, and the speed of the blocked obstacles in front of the autonomous vehicle, and determine the road boundary information in front of the autonomous vehicle; Determining, based on information about each blocking obstacle in the blocking obstacle list and the road boundary information, an N-level topological node of the proposed passage space, wherein the topological node represents a space in the proposed passage space between blocking obstacles or between blocking obstacles and the road boundary intended for passage of the unmanned vehicle; Generate M alternative paths for the unmanned vehicle to pass based on the connection relationship between the N-level topological nodes in the planned passage space, as well as the minimum vehicle passage width between the topological nodes with connection relationships; Calculate the first cost of the N-level topological nodes in the intended traversable space and the second cost between the topological nodes with connection relationships according to the self-defined cost function; Calculate the costs of the M alternative paths based on the first cost and the second cost of the topological nodes on each alternative path according to the custom cost weight value; Based on the customized space screening rules, the final passage space for the unmanned vehicle is determined according to the customized minimum passage width of the unmanned vehicle, the cost of the M alternative paths and the minimum passage width of the vehicle.

2. The method according to claim 1, characterized in that The method generates a list of blocked obstacles based on the current speed of the unmanned vehicle, the customized minimum scanning distance and scanning time, and the speed of the blocked obstacles in front of the unmanned vehicle, and determines the road boundary information in front of the unmanned vehicle, including: Based on the current speed of the autonomous vehicle, the minimum scanning distance and scanning time are customized to determine the scanning range for obstacles in front of the autonomous vehicle, including: According to the current speed v of the unmanned vehicle and the custom scanning time t y Calculate the current scanning distance d y , and its calculation formula is: d y =v*t y According to the current scanning distance d y and custom minimum scanning distance d min Determine the actual scanning distance d f , whose expression is: d f =max{d y ,d min } In the Frenet coordinate system, the current position of the unmanned vehicle is taken as the starting point in the longitudinal direction, and the actual scanning distance d is taken as the starting point in the longitudinal direction. f The distance from the starting point to the end point is taken as the longitudinal length. In the horizontal direction, the longitudinal length is discretized, and the left and right side boundaries of the lane are traversed for each discretized sampling point. The minimum value from the left and right side boundaries is taken as the horizontal width. Determine the scanning range and road boundary information of the blocking obstacle in front of the vehicle in the Frenet coordinate system according to the longitudinal length and the lateral width; The blocking obstacles within the scanning range whose running speed is not greater than the user-defined speed threshold are numbered, and a blocking obstacle list is generated after obtaining coordinate information of a discrete point sequence representing their positions in the Frenet coordinate system.

3. The method according to claim 1, characterized in that The determining of the N-level topological nodes of the proposed passage space according to the information of each blocked obstacle in the blocked obstacle list and the road boundary information includes: Determining an initial pre-selected segmentation point based on information about each blocking obstacle in the blocking obstacle list and the road boundary information, and generating an initial pre-selected segmentation point list, wherein attribute information of each initial pre-selected segmentation point includes position coordinate information, front and rear edge information, type information, segmentation line generation direction information, and associated obstacle information, wherein the position coordinate information includes a horizontal coordinate and a vertical coordinate, and the front and rear edge information includes front edge information and rear edge information, wherein the front edge and rear edge are determined in a counterclockwise rotation manner with the pre-selected segmentation point as the center; Based on the position coordinate information, the initial pre-selected segmentation points in the initial pre-selected segmentation point list are divided into N+1 groups of initial pre-selected segmentation points according to their vertical coordinates from near to far, wherein the vertical coordinates of each group of initial pre-selected segmentation points are the same, and from near to far refers to from the current position of the unmanned vehicle to the front of the unmanned vehicle; For each group of initial pre-selected segmentation points, sort them from left to right according to the horizontal axis, filter out duplicate pre-selected segmentation points, and generate the final pre-selected segmentation points of the corresponding group. Then, generate the final pre-selected segmentation point list based on the N+1 groups of final pre-selected segmentation points. Based on the position coordinate information, the road boundary information and the information of each blocking obstacle in the blocking obstacle list, the final pre-selected segmentation point in the final pre-selected segmentation point list that does not meet the custom segmentation point filtering rule is used as an important key point; Generate an N+1 level cyclic key point list according to the N+1 groups of final pre-selected segmentation points in the final pre-selected segmentation point list, and generate an updated attention edge list of the corresponding level based on the type information and the preceding and following edge information of the final pre-selected segmentation points in each level of the cyclic key point list; For the n-th level loop key point list, the direction information and position coordinate information of the segmentation line of each important key point are generated, as well as the road boundary information and the n-th level focus edge list to determine the n-th level upper boundary segmentation line and the lower boundary segmentation line, and the n-th level upper boundary list and the lower boundary list are generated according to the upper boundary segmentation line and the lower boundary segmentation line, wherein the upper boundary segmentation line is a line segment representing the upper boundary of the topological node, and the lower boundary segmentation line is a line segment representing the lower boundary of the topological node, 1≤n≤N+1; For each upper boundary dividing line in the j-th level upper boundary list, generate its corresponding j-1th level topological node according to the lower boundary dividing line in the j-1th level lower boundary list to be adapted that satisfies the topological node generation rule, wherein 2≤j≤N+1, when j=2, the j-1th level lower boundary list to be adapted is the first level lower boundary list, when 2<j≤N+1, the j-1th level lower boundary list to be adapted is the set of the j-1th lower boundary list and the j-2th level lower boundary list to be adapted after filtering out the lower boundary dividing line marked as adapted, the lower boundary dividing line marked as adapted satisfies the custom topological node generation rule, and the j-1th level topological node of the intended passable space is the set of the j-1th level topological nodes generated corresponding to all upper boundary dividing lines in the j-th level upper boundary list.

4. The method according to claim 3, characterized in that The step of determining the preselected segmentation points based on the information of each blocked obstacle in the blocked obstacle list and the road boundary information to generate an initial preselected segmentation point list includes: The start point and the end point of the scanning range are used as first pre-selected segmentation points, wherein the front and rear edge information, type information and obstacle information in the attribute information of the first pre-selected segmentation points are default values, and the segmentation line generation direction information is generated towards both sides of the road; using four vertices of each blocking obstacle in the blocking obstacle list as second pre-selected segmentation points, wherein segmentation line generation direction information in the attribute information of the second pre-selected segmentation point is determined according to the value assigned to the type information, the segmentation line generation direction information being at least one of generation toward both sides of the road, generation toward the left side of the road, and generation toward the right side of the road, and the value assigned to the type information in the attribute information of the second pre-selected segmentation point is determined according to whether, when the blocking obstacle is considered as a rectangle, the rectangle has sides parallel to the road boundary; The front and rear edges of the four vertices of each blocking obstacle in the blocking obstacle list intersect with the left and right boundaries of the road, and the intersection point of the dividing line generated into the road boundary is used as the third pre-selected dividing point, wherein the front and rear edge information and the type information in the attribute information of the third pre-selected dividing point are default values, the dividing line generation direction information of the third pre-selected dividing point intersecting with the left boundary of the road is generated toward the right side of the road, and the dividing line generation direction information of the third pre-selected dividing point intersecting with the right boundary of the road is generated toward the left side of the road; When the absolute value of the difference between the horizontal coordinates of any two adjacent road boundary sampling points is greater than a custom threshold, the road boundary sampling point that makes the unmanned vehicle's passage width smaller is used as the fourth pre-selected segmentation point, wherein the front and rear edge information, type information, and obstacle information in the attribute information of the fourth pre-selected segmentation point are default values, and the segmentation line generation direction information of the fourth pre-selected segmentation point located on the left side of the road is generated toward the right side of the road, and the segmentation line generation direction information of the fourth pre-selected segmentation point located on the right side of the road is generated toward the left side of the road; The set of the first pre-selected segmentation point, the second pre-selected segmentation point, the third pre-selected segmentation point and the fourth pre-selected segmentation point is used as an initial pre-selected segmentation point list.

5. The method according to claim 4, characterized in that Based on the position coordinate information, the road boundary information and the information of each blocking obstacle in the blocking obstacle list, the final pre-selected segmentation point in the final pre-selected segmentation point list that does not meet the custom segmentation point filtering rule is used as an important key point, wherein the segmentation point filtering rule includes: Filter out other final pre-selected segmentation points whose position coordinate information is outside the range determined by the first pre-selected segmentation point and the fourth segmentation point; The final preselected segmentation points whose position coordinate information is within a range determined by the coordinate information of the discrete point sequence representing the position of the blocking obstacle in the Frenet coordinate system are filtered out.

6. The method according to claim 5, characterized in that The step of generating an N+1-level cyclic key point list based on the N+1 groups of final pre-selected segmentation points in the final pre-selected segmentation point list, and generating an updated attention edge list of the corresponding level based on the type information and preceding and following edge information of the final pre-selected segmentation points in each level of the cyclic key point list, includes: Generate a list of loop key points of the corresponding level according to each group of final pre-selected segmentation points; Generate the initial attention edge list of level n according to the front and back edge information of the second pre-selected segmentation point in the level n loop key point list and the updated attention edge list of level n-1. When n=1, the updated attention edge list of level n-1 is an empty set. Delete the attention edges in the n-level initial attention edge list whose maximum vertical coordinate is less than the vertical coordinate of the final pre-selected segmentation point in the n-level loop key point list, and delete the corresponding attention edges that meet the custom type information-attention edge deletion list to generate the n-level updated attention edge list, wherein the type information-attention edge deletion list is a list that represents the correspondence between the type information of the second pre-selected segmentation point and the corresponding parts to be deleted in the preceding and following edge information.

7. The method according to claim 6, characterized in that For the n-th level cyclic key point list, the upper boundary segmentation line and the lower boundary segmentation line of the n-th level are determined based on the segmentation line of each important key point, the road boundary information, and the n-th level focus edge list, including: For each important key point in the n-th level cyclic key point list, obtaining a road boundary sampling point in the dividing line generation direction according to the dividing line generation direction information, wherein when the dividing line generation direction information is generated toward both sides of the road, the road boundary sampling point includes a road left boundary sampling point and a road right boundary sampling point; The important key point and its corresponding road boundary sampling point are connected to generate a line segment. When the line segment does not intersect with any other focus edge in the n-th level update focus list except the focus edge where the important key point is located, the road boundary sampling point corresponding to the important key point is determined as the anchor point. When the line segment intersects with any other focus edge in the n-th level update focus list except the focus edge where the important key point is located, the intersection point closest to the important key point is taken as the anchor point. The intersection point closest to the important key point is not on the blocking obstacle to which the important key point belongs. When generating the upper boundary segmentation line, the minimum ordinate of the focus edge where the intersection point closest to the important key point is located is smaller than the ordinate of the important key point. When generating the lower boundary segmentation line, the maximum ordinate of the focus edge where the intersection point closest to the important key point is located is larger than the ordinate of the important key point. When there are two anchor points, the anchor point closer to the left side boundary sampling point of the road is the left anchor point, and the anchor point closer to the right side boundary sampling point of the road is the right anchor point. Specifically: When the direction information of generating the segmentation line of the important key point is to generate it toward the right side of the road, generating a segmentation line with coordinate position information of {key point, anchor point}; When the direction information of the segmentation line generation of the important key point is to generate it towards the left side of the road, if the position coordinate information of the segmentation line that has been generated contains the important key point, then no segmentation line is generated for the important key point; otherwise, a segmentation line with the coordinate position information of {anchor point, key point} is generated; When the dividing line generation direction information of the important key point is generated towards both sides of the road, if the position coordinate information of the already generated dividing line contains the important key point, the dividing line is not generated for the important key point; otherwise, a dividing line with the generated coordinate position information of {left anchor point, right anchor point} is generated.

8. The method according to claim 6, characterized in that For each upper boundary segmentation line in the j-th level upper boundary list, a corresponding j-1-th level topological node is generated according to the lower boundary segmentation line in the j-1-th level lower boundary list that satisfies the topological node generation rule, wherein the topological node generation rule includes: For each upper boundary segmentation line in the j-th level upper boundary list, take the midpoint of the upper boundary segmentation line and the midpoint of each lower boundary segmentation line in the j-1-th level to-be-adapted lower boundary list to form a line segment; When the line segment does not intersect with all blocked obstacles, a polygon containing upper and lower boundary segmentation line information, left and right obstacle information or road boundary information is generated as a topological node, and the lower boundary segmentation line corresponding to the line segment is marked as adapted.

9. The method according to claim 1, characterized in that The method of generating M candidate paths for the unmanned vehicle to pass through based on the connection relationship between N-level topological nodes in the intended passage space and the minimum passage width of vehicles between topological nodes with connection relationships includes: Traverse the i-th level topological nodes and the i+1-th level topological nodes of the intended traversable space according to the custom topological node connection rules, wherein the topological node connection rules include: Based on the upper boundary segmentation line information of the i-th level topological node and the lower boundary segmentation line information of the i+1-th to N-th level topological nodes, when the upper boundary segmentation line of a topological node in the i-th level topological node intersects with the lower boundary segmentation line of a topological node in the i+1-th to N-th level topological nodes, it is determined that there is a connection relationship between the two topological nodes, and the minimum vehicle passage width between the two topological nodes with a connection relationship is the length of the shortest line segment between any two points on the edge of the polygon formed by the two topological nodes in the direction perpendicular to the boundaries on both sides of the road; The topological nodes with connection relationships in the N-level topological nodes of the planned passage space are connected in sequence to generate M alternative paths for the unmanned vehicle to pass.

10. The method according to claim 1, characterized in that The calculating, according to the self-defined cost function, of the first cost of the N-level topological nodes of the intended traversable space and the second cost between the topological nodes having a connection relationship includes: Calculate the width cost, history trajectory cost, wheel orientation cost and deformation cost of the N-level topological nodes in the proposed traversable space respectively according to the custom node width cost function, node history trajectory cost function, node wheel orientation cost function and node deformation cost function in the SL coordinate system, wherein the first cost includes width cost, history trajectory cost, wheel orientation cost and deformation cost; The lateral offset cost between topological nodes having a connection relationship is calculated according to a user-defined lateral offset cost function, wherein the second cost refers to the lateral offset cost between the topological nodes.

11. The method according to claim 1, wherein The costs of the M alternative paths are calculated based on the first cost and the second cost of the topological nodes on each alternative path according to the custom cost weight value. The calculation formula is: Where, 1≤m≤M, cost m is the cost of the mth alternative path, L is the total cost included in the first cost, cost l and are the lth cost and its corresponding weight value in the first cost respectively; K is the total number of costs included in the second cost, cost k and are the kth cost in the second cost and its corresponding weight value respectively.

12. The method according to claim 1, characterized in that The method of determining the final passage space for the unmanned vehicle based on the customized space screening rule according to the customized minimum passage width of the unmanned vehicle, the costs of the M alternative paths, and the minimum passage width of the vehicle includes: Based on the customized spatial screening rules, the final path of the unmanned vehicle is determined according to the customized minimum width of the unmanned vehicle, the costs of the M alternative paths, and the minimum width of the vehicle. The spatial screening rules include: Starting from the starting point, the minimum vehicle passage width and the minimum unmanned vehicle passage width in each alternative path are compared. When the minimum vehicle passage width is smaller than the minimum unmanned vehicle passage width, the two topological nodes with a connection relationship corresponding to the minimum vehicle passage width are pruned. When there is at least one alternative path that has not been clipped, the alternative path with the lowest cost is selected as the final path for the autonomous vehicle; When there are no alternative paths that have not been clipped, the longest part of the unclipped topological nodes among the M alternative paths is selected in order from the starting point to the end point, and the final path for the unmanned vehicle is generated by splicing them together; Traverse the longitudinal space of the unmanned vehicle's final passage path, detect the topological node to which the scanned position belongs according to the custom distance step size, and determine the boundary information of the unmanned vehicle's final passage space based on the blocked obstacle information and road boundary information on both sides of the topological node.

13. A system for searching for unmanned vehicle passage space, characterized in that: The system comprises: The pre-processing module is used to generate a list of blocked obstacles based on the current speed of the unmanned vehicle, the customized minimum scanning distance and scanning time, and the running speed of the blocked obstacles in front of the unmanned vehicle, and determine the road boundary information in front of the unmanned vehicle; a topology node module, configured to determine an N-level topology node of the proposed traversable space based on information about each blocking obstacle in the blocking obstacle list and the road boundary information, wherein the topology node represents a space in the proposed traversable space between blocking obstacles or between blocking obstacles and road boundaries intended for passage of unmanned vehicles; The alternative path module is used to generate M alternative paths for the unmanned vehicle to pass based on the connection relationship between the N-level topological nodes in the proposed passage space, as well as the minimum vehicle passage width between the topological nodes with connection relationships; A first calculation module is used to calculate the first cost of the N-level topological nodes in the intended traversable space and the second cost between the topological nodes having a connection relationship according to a user-defined cost function; A second calculation module is used to calculate the costs of the M alternative paths respectively according to the user-defined cost weight value, the first cost and the second cost of the topological node on each alternative path; The result output module is used to determine the final passage space of the unmanned vehicle based on the customized space screening rules, the customized minimum passage width of the unmanned vehicle, the costs of M alternative paths and the minimum passage width of the vehicle.

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

15. An electronic device, characterized in that: The electronic device comprises: A processor; a memory for storing the processor-executable instructions; the processor for reading the executable instructions from the memory and executing the instructions to implement the steps of the method according to any one of claims 1 to 12.

Images