CN114863300A - Shortest path generation method and device - Google Patents
Shortest path generation method and device Download PDFInfo
- Publication number
- CN114863300A CN114863300A CN202210478933.6A CN202210478933A CN114863300A CN 114863300 A CN114863300 A CN 114863300A CN 202210478933 A CN202210478933 A CN 202210478933A CN 114863300 A CN114863300 A CN 114863300A
- Authority
- CN
- China
- Prior art keywords
- path
- target
- point
- distance
- connection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012360 testing method Methods 0.000 claims abstract description 70
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 230000008859 change Effects 0.000 claims description 14
- 238000005316 response function Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 description 18
- 239000011159 matrix material Substances 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000013480 data collection Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a shortest path generation method and a device, wherein the method comprises the following steps: and carrying out corner detection on the target map, generating all target corners in the target map, and generating an initial path starting from a path starting point and connecting all the target corners with the path starting point by a shortest path distance based on all the target corners. The initial path realizes the local optimal connection relation among all target corner points. Furthermore, test nodes are randomly generated in the target map, the connection relation of the initial path is optimized according to the test nodes, the global optimal connection relation of the target map is achieved, the shortest path is generated according to the optimization result, and the generation quality and the accuracy of the path are further improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a shortest path generating method and apparatus.
Background
As the diversification of unmanned aerial vehicle tasks increases, unmanned aerial vehicles need to perform high-risk tasks in high-threat dynamic environments rich in uncertainty factors. Traditional remote control based on a ground control station or automatic control strategies based on programming cannot meet the development requirements of unmanned aerial vehicle systems. The path planning is a vital part of unmanned aerial vehicle navigation, is an indispensable precondition for the unmanned aerial vehicle to complete a predetermined task, and becomes an inevitable requirement for planning the flight path of the unmanned aerial vehicle. The path planning is to design a safe and flyable route for the unmanned aerial vehicle. On one hand, the survival probability of the unmanned aerial vehicle needs to be guaranteed, and on the other hand, task execution can be best achieved.
At present, a numerical method and a planning method based on a graph are commonly adopted when unmanned aerial vehicle path planning is carried out. Numerical methods such as Mixed Integer Linear Programming (MILP), which typically require solving non-convex optimization problems, require not only specialized commercial software (e.g., cplex) but are time consuming; and a graph-based planning method such as a random road map (PRM) algorithm needs to geometrically divide a task area in advance, and is not easily combined with a kinematic constraint condition of an aircraft. Traditional intelligent algorithms such as genetic algorithm, ant colony algorithm, greedy algorithm, simulated annealing method, RRT algorithm, etc. However, the group intelligence algorithm is easy to fall into local optimization, and because the implementation of the operator has many parameters, such as cross rate and mutation rate, the selection of the parameters may cause the problem of solving premature convergence; and the traditional intelligent algorithm can only provide a solution close to the optimal solution, and cannot ensure or globally optimize the solution.
Disclosure of Invention
The application provides a shortest path generation method and device, which are used for improving the unmanned aerial vehicle search path generation precision.
In a first aspect, the present application provides a shortest path generating method, including:
carrying out corner detection on a target map to generate all target corners in the target map;
generating an initial path starting from a path starting point, wherein all the target corner points are connected with the path starting point by a shortest path distance;
randomly generating a test node in the target map;
and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
The corner points are local feature representations of image pixels, the target map is subjected to comprehensive corner point detection, the communication conditions among the regions in the target map can be established through the position relationship among the corner points, the conditions of all the regions in the target map are obtained, and unmanned aerial vehicle path planning is facilitated. And establishing and generating an initial path starting from the path starting point and connecting all the target corner points with the path starting point by the shortest path distance based on the connection relation among all the target corner points, the path starting point and the search end point, thereby realizing the local optimal path connection relation among all the target corner points. Furthermore, test nodes are randomly generated on the target map, and when the path distance of any target corner point connected with the path starting point through the test node is smaller than the shortest path distance of the target corner point and the path starting point, the path distance of the target corner point connected with the path starting point through the test node is shorter. Based on the method, the connection relation of the search path tree is added, the path from the starting point of the path to the searching end point through the target corner point is shortened, and the generation quality and the accuracy of the search path are improved.
In an implementation manner, the corner detection specifically includes:
acquiring a gray value of a first pixel point in the target map;
moving the first pixel point in the x direction and the y direction respectively by a preset distance;
acquiring a gray scale change value of the first pixel point after the first pixel point moves the preset distance;
and judging whether the first pixel point is the target corner point according to a corner point response function.
In an implementation manner, the generating all the target corner points in the target map specifically includes:
performing the corner detection on all pixel points in the target map to generate all target corners in the target map;
and performing position detection on all the target corner points, and when detecting that the target corner points are positioned in an obstacle area in the target map, moving the detected target corner points to an adjacent feasible area so as to enable all the target corner points to be positioned in the feasible area in the target map.
In one implementation, the generating an initial path starting from a path starting point and connecting all the target corner points with the path starting point by a shortest path distance specifically includes:
all the target angular points, the path starting points and the path end points are connected in a straight line mode, and an angular point connection set is generated;
extracting a straight-line connecting path which is not blocked by an obstacle area in the target map in the corner connecting set to generate an initial connecting path set;
and optimizing the initial connection path set to generate the initial path.
In an implementation manner, the optimizing an initial connection path set to generate the initial path specifically includes:
acquiring all target corner points which are directly connected with the starting point of the path in the initial connection path set, recording the connection relation between the target corner points and the starting point of the path and the corresponding direct connection path distance, and generating a first connection set;
acquiring a target corner point which cannot be directly connected with the starting point of the path in the initial connection path set, and generating a first set to be connected;
adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and updating the connection relation between the target corner points in the first connection set and the path starting points;
and generating an initial path which starts from a path starting point, is connected with the path starting point by the shortest path distance from all the target corner points according to the updated first connection set.
In an implementation manner, the adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and adding a connection relationship between a target corner point in the first connection set and the path starting point specifically includes:
adding a first target corner point to be connected in the first set to be connected; wherein the adding operation specifically comprises: acquiring all connection target angular points connected with the first target angular point to be connected in the first connection set; taking the path distance of the first connection target angular point connected with the path starting point through the first target angular point to be connected as a first path distance; taking the direct connection path distance between the first connection target corner point and the path starting point as a second path distance; when the first path distance is smaller than the second path distance, taking the second path distance as the shortest path distance between the first connection target corner point and the path starting point; updating the connection relation corresponding to the second path distance to the first connection set;
and sequentially executing the adding operation on all the connecting target angular points connected with the first target angular point to be connected to generate a first updating connection set.
In one implementation, the generating, according to the updated first connection set, an initial path starting from a path starting point and connecting all the target corner points with the path starting point by a shortest path distance further includes:
sequentially executing the adding operation on all target corner points to be connected in the first set to be connected according to the linear distance between the target corner points and the starting point of the path;
adding the target corner points to be connected to the updated connected set generated by the previous target corner points to be connected until all the target corner points to be detected in the first set to be connected complete the adding operation, and generating a final updated connected set;
and extracting the path connection relation in the final updated connection set to generate the initial path.
In an implementation manner, when a path distance between any one of the target corner points and the path starting point through the test node is smaller than a shortest path distance between the target corner point and the path starting point, updating a connection relationship of the initial path to generate a shortest path specifically includes:
performing an update operation on the node; wherein the update operation specifically includes: performing an update operation on the test node; wherein the update operation specifically includes: acquiring all target corner points directly connected with the test node in the initial path within a preset range; obtaining the shortest path distance between all target angle points directly connected with the test node and the path starting point, and generating a first search path distance set; acquiring path distances of all target corner points directly connected with the test nodes and the path starting points through the test nodes, and generating a second search path distance set; when any one of the second search path distance sets is smaller than the first search path distance corresponding to the first search path distance set, acquiring a target corner point corresponding to the path distance; and taking the second search path as the shortest path between the corresponding target corner point and the path starting point, and updating the connection relation of the initial path.
In an embodiment, when a path distance between any of the target corner points and the path starting point through the test node is smaller than a shortest path distance between the target corner point and the path starting point, the method updates a connection relationship of the initial path to generate a shortest path, and further includes:
executing a test node generation instruction for preset times;
and executing the updating operation on the generated test node every time until the last updating operation is finished, and generating the shortest path.
In a second aspect, the present application further provides a shortest path generating apparatus, including: the device comprises an angular point generating module, a path generating module and a path optimizing module;
the corner generation module is used for detecting corners of a target map and generating all target corners in the target map;
the path generation module is used for generating an initial path which starts from a path starting point, and all the target corner points are connected with the path starting point by a shortest path distance;
the path optimization module is used for randomly generating test nodes in the target map; and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
In a third aspect, the present application further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the shortest path generating method as described above is implemented.
In a fourth aspect, the present application further provides a computer-readable storage medium comprising a stored computer program, wherein when the computer program runs, a device in which the computer-readable storage medium is located is controlled to execute the shortest path generating method as described above.
Drawings
Fig. 1 is a schematic flowchart of a shortest path generating method according to an embodiment of the present invention;
fig. 2 is a block diagram of a shortest path generating apparatus according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The terms "first" and "second," and the like in the description and claims of this application and in the drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
First, some terms in the present application are explained so as to be easily understood by those skilled in the art.
(1) Corner points: usually, local maxima of curvature in the contour of the object are decisive for the understanding of the contour characteristics of the object. A corner point is generally considered to be a point of a two-dimensional image that varies in brightness distance or the intersection of two lines.
(2) Harris corner detection: the core of the algorithm is to move the small window of this feature from all directions by using a local window to move across the image. If the gray level of the area in the window changes greatly, then the corner point is considered to be encountered in the window. As shown in the figure, if the gray scale of the image in the window is not changed, no corner point exists in the window; if the gray scale of the image in the window is changed greatly when the window moves in a certain direction, but the gray scale of the image in the window is not changed in other directions, then the image in the window may be a straight line segment. The feature value is used, so that the corner points in any direction can be detected.
(3) Greedy algorithm: meaning that the choice that seems best at the current time is always made when solving the problem. That is, rather than being considered from a global optimum, the algorithm results in a locally optimal solution in some sense.
(4) Node definition: there is no other node above the current node, and this node is called root node; the father node is a node above the current node, and the node above is called as a father point of the node below; a leaf node is a node that is not located above the current node.
Example 1
Referring to fig. 1, fig. 1 is a schematic flowchart of a shortest path generating method according to an embodiment of the present invention. The embodiment of the invention provides a shortest path generation method, which comprises the following steps from step 101 to step 104:
step 101: carrying out corner detection on a target map to generate all target corners in the target map;
step 102: generating an initial path which starts from a path starting point, and all the target corner points and the path starting point are connected by a shortest path distance;
step 103: randomly generating a test node in the target map;
step 104: and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
In the embodiment of the present invention, the detecting the corner of the target map specifically includes: acquiring a gray value of a first pixel point in the target map; moving the first pixel point in the x direction and the y direction respectively by a preset distance; acquiring a gray scale change value of the first pixel point after the first pixel point moves the preset distance; and judging whether the first pixel point is the target corner point according to a corner point response function.
In a specific embodiment, the corner detection judgment is performed on the target map according to a Harris corner detection method. Setting the gray value of any pixel point (x, y) on the target image as I (x, y), and obtaining the gray value change values which take the pixel point (x, y) as the center and respectively move the distance u and the distance v along the directions x and y. The gradation variation expression can be expressed by the following formula:
E(u,v)＝∑ x,y w(x,y)[I(x+u,y+v)-I(x,y)] 2 ；
wherein E (u, v) is a gradation change value; w (x, y) is a window function, and a Gaussian function is generally adopted;
and (3) deforming the gray scale change expression based on a Taylor formula to obtain a simplified formula as follows:
in the formula, Ix and Iy are gradient operators in x and y directions, respectively:
the self-correlation matrix M of the pixel points is obtained by the derivative of the image gray level,
the autocorrelation matrix M is a 2 x 2 matrix and the expression is directly related to the gray scale variation at the center (x, y) of the matrix. The eigenvalues of M are λ 1, λ 2, which symbolize the rate of change of the grey scale in the x, y direction, respectively, in the center point (x, y) of the matrix.
Introducing a corner response function to judge whether the pixel point is a target corner or not; wherein the corner response function is as follows:
R＝detM-k(trace M) 2 ；
in the formula, k is a correction value, generally 0.02-0.04, R is a response function, and when | R | is small, the gray level change of the area where the pixel point is located is small and the pixel point is located in a flat area of the target image. And when the absolute value of R < 0, the pixel point is in the edge area of the target image. When | R | is large, it means that the gray scale changes significantly when the pixel moves in any direction, i.e. the target corner point to be found. Further, the Harris corner detection is performed on all pixel points in the target map, so that all target corners in the target map are generated.
As an optimization method of this embodiment, after generating all target corner points in a target map, position detection is further performed on all the target corner points, and when a target corner point is detected to be located in an obstacle area in the target map, the detected target corner point is moved to a feasible area adjacent to the obstacle area, so that it is ensured that all the detected target corner points are located in the feasible area of the target map.
In the embodiment of the present invention, generating an initial path starting from a path starting point and connecting all the target corner points and the path starting point by a shortest path distance specifically includes: all the target angular points, the path starting points and the path end points are connected in a straight line mode, and an angular point connection set is generated; extracting a linear connection path which is not blocked by an obstacle area in the target area in the corner connection set to generate an initial connection path set; and optimizing the initial connection path set to generate the initial path.
And connecting every two straight lines among all the generated target angular points, the path starting point and the path end point to generate an inter-angular-point connection set. Under the influence of the actual terrain of the target map, the target corner points are connected with each other, or a straight line connecting path directly connecting each target corner point with the starting point and the searching end point of the path passes through the obstacle area of the target map. In order to ensure that the linear connection paths among all target angular points and between all the target angular points and the path starting point and the search end point can be directly communicated, the linear connection paths influenced by the obstacle area of the target map are removed, the linear connection paths which are not influenced by the obstacle area of the target map in the angular point connection set are extracted, and an initial connection path set is generated.
Optimizing the generated initial path connection path set, and generating an initial path in which all target corner points are connected with the path starting point by a shortest path, specifically comprising: acquiring all target corner points which are directly connected with the starting point of the path in the initial connection path set, recording the connection relation between the target corner points and the starting point of the path and the corresponding direct connection path distance, and generating a first connection set; acquiring a target corner point which cannot be directly connected with the starting point of the path in the initial connection path set, and generating a first set to be connected; adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and updating the connection relation between the target corner points in the first connection set and the path starting points; and generating an initial path which starts from a path starting point, is connected with the path starting point by the shortest path distance from all the target corner points according to the updated first connection set.
Adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and adding a connection relation between the target corner points in the first connection set and the path starting points, specifically including: adding a first target corner point to be connected in the first set to be connected; wherein the adding operation specifically comprises: acquiring all connection target angular points connected with the first target angular point to be connected in the first connection set; taking a path distance of a first connecting target corner point connected with the path starting point through the first target corner point to be connected as a first path distance; taking the direct connection path distance between the first connection target corner point and the path starting point as a second path distance; when the first path distance is smaller than the second path distance, taking the second path distance as the shortest path distance between the first connection target corner point and the path starting point; updating the connection relation corresponding to the second path distance to the first connection set; and sequentially executing the adding operation on all the connecting target angular points connected with the first target angular point to be connected to generate a first updating connection set.
In a specific embodiment, the initial path is generated by using a greedy strategy. And taking all target corner points which can be directly connected with the starting point of the path as a first connection set, and recording the path distance between the starting point of the path and each target corner point. And taking a target angular point which cannot be directly connected with the starting point of the path as a first to-be-connected set, and sequentially adding the target angular points to be connected in the first to-be-connected set to the first to-be-connected set on the premise of not changing the connection relation between the target angular points to be connected and the rest target angular points according to the distance from the starting point of the path from small to large. Taking a target corner point M to be connected as a reference case, setting the target corner point M to be connected as a target corner point in a first connected set, which is closest to the starting point of the path, and adding the target corner point to be connected to the first connected set, wherein the following adding operations are specifically executed:
acquiring all target corner points connected with M in a first connection set, setting that a plurality of target corner points connected with M exist in the first connection set, selecting one connection target corner point C, setting a direct connection path distance of the connection target corner point as a first path distance S1, setting a path distance of the connection target corner point C connected with a path starting point through the target corner point M to be connected as a second path distance S2, if the second path distance S2 is smaller than the first path distance S1, considering that a shortest path distance between the target corner point C and the path starting point is S2, setting the shortest path distance between the target corner point C and the path starting point as S2, and updating the best path connection relation between the path starting point and the target corner point C in the first connection set to be connected with the target corner point C through the target corner point M to be connected.
And after determining the shortest path distances between the target corners connected with the target corner M to be connected and the path starting points in the first connection set, responding and updating the path connection relationship between the path starting points and the connection corner points to generate a first updated connection set.
And sequentially executing the adding operation on all the target corner points to be connected in the first target corner point to be connected according to the linear distance from the starting point of the path, and adding the target corner points to be connected to the updated connection set generated by the previous target corner points to be connected. That is, when adding operation is performed on the second target corner point to be connected, the connection relationship between each target corner point and the path starting point in the first updated connection set is taken as a basis, if the path connection relationship related to the second corner point to be connected exists, the first updated connection set is updated, and the updated first updated connection set is taken as the second updated connection set corresponding to the second target corner point to be connected. And sequentially adding all the target corner points to be connected in the first set to be connected until the addition of all the target corner points to be connected in the first set to be connected is completed, and generating a final updated connection set.
Based on the adding operation, all the target angular points in the final updating connection set are connected with the starting point of the path in the shortest path, the connection relation between the starting point of the path in the final updating connection set and each target angular point is extracted, and an initial path which takes the starting point of the path and is connected between each target angular point and the starting point of the path in the shortest path distance is generated.
Since the initial path actually implements the local optimal solution, rather than implementing the optimal solution interpretation from the overall path, as a preferred case of the embodiment of the present invention, after the initial path is generated, the method further includes: randomly generating a test node in the target map; and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
Performing an update operation on the test node; wherein the update operation specifically includes: acquiring all target corner points directly connected with the test node in the initial path within a preset range; obtaining the shortest path distance between all target angle points directly connected with the test node and the path starting point, and generating a first search path distance set; acquiring path distances of all target corner points directly connected with the test nodes and the path starting points through the test nodes, and generating a second search path distance set; when any one of the second search path distance sets is smaller than the first search path distance corresponding to the first search path distance set, acquiring a target corner point corresponding to the path distance; and taking the second search path as the shortest path between the corresponding target corner point and the path starting point, and updating the connection relation of the initial path.
In a specific embodiment, an RRT (rapid distance transform) search algorithm is introduced, a search path tree with a path starting point as a root node is generated according to the initial path, and each target corner point is a target node in the search path tree. Initializing information of the search path tree, including: the position coordinates of each target node, and the last connection parent node of each corner point. And generating a test node X in a feasible area in the target map, and searching for a target node Y which has a direct connection relation with the test node in a preset range. The preset range may be correspondingly set and adjusted according to the size of the target map, for example, the size may be set to 1/40, which is higher or lower than the overall size of the target map, and is not limited herein. And if the path distance of the test node X connected with the path starting point through the target node Y is the shortest path distance, adding the test node X to the search path, rearranging the test node X, and if the path distance of the peripheral nodes from the path starting point through the test node X as the father node is shorter than the original connection path, executing updating operation.
In an embodiment of the present invention, a terminal device for generating a shortest path is further provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor implements the shortest path generating method described above when executing the computer program.
In an embodiment of the present invention, a computer-readable storage medium is further provided, where the computer-readable storage medium includes a stored computer program, and when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the shortest path generating method described above.
Illustratively, the computer program may be partitioned into one or more modules that are stored in the memory and executed by the processor to implement the invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, the instruction segments describing the execution process of the computer program in the shortest path generation based device.
The data collection device based on the path generation device may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The scanning device based data collection device may include, but is not limited to, a processor, memory, and a display. It will be understood by those skilled in the art that the above components are merely examples of the shortest path generating device based data collecting device, and do not constitute a limitation of the shortest path generating device based data collecting device, and may include more or less components than the described components, or some components in combination, or different components, for example, the shortest path generating device based data collecting device may further include an input-output device, a network access device, a bus, etc.
The processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor is a control center of the shortest path generating device based data collecting device, and various interfaces and lines are used to connect various parts of the data collecting device of the entire shortest path generating device.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the apparatus for data collection based on the shortest path generating apparatus by running or executing the computer programs and/or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, a text conversion function, etc.), and the like; the storage data area may store data (such as audio data, text message data, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device. The device-integrated module of the data collection of the shortest path generating device may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice. One of ordinary skill in the art can understand and implement it without inventive effort.
The embodiment of the invention provides a shortest path generation method, wherein each corner is a local characteristic embodiment of an image pixel, the target map is comprehensively detected, the communication condition among the regions in the target map can be established through the position relation among the corners, the condition of each partial region in the target map is obtained, and the unmanned aerial vehicle path planning is facilitated. And establishing and generating an initial path starting from the path starting point and connecting all the target corner points with the path starting point by the shortest path distance based on the connection relation among all the target corner points, the path starting point and the search end point, thereby realizing the local optimal path connection relation among all the target corner points. Furthermore, test nodes are randomly generated on the target map, and when the path distance of any target corner point connected with the path starting point through the test node is smaller than the shortest path distance of the target corner point and the path starting point, the path distance of the target corner point connected with the path starting point through the test node is shorter. Based on the method, the connection relation of the search path tree is added, the path from the starting point of the path to the searching end point through the target corner point is shortened, and the generation quality and the accuracy of the search path are improved.
Example 2
Referring to fig. 2, fig. 2 is a block diagram of a shortest path generating apparatus according to an embodiment of the present invention. The embodiment of the invention also provides a shortest path generating device, which comprises an angular point generating module 201, a path generating module 202 and a path optimizing module 203;
the corner generating module 201 is configured to perform corner detection on a target map, and generate all target corners in the target map;
the path generating module 202 is configured to generate an initial path starting from a path starting point, where all the target corner points are connected with the path starting point by a shortest path distance;
the path optimization module 203 is used for randomly generating test nodes in the target map; and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
The corner generating module 201 is configured to perform corner detection on a target map, and generate all target corners in the target map, which specifically includes: acquiring a gray value of a first pixel point in the target map; moving the first pixel point in the x direction and the y direction respectively by a preset distance; acquiring a gray scale change value of the first pixel point after the first pixel point moves the preset distance; and judging whether the first pixel point is the target corner point or not according to a corner point response function. Performing the corner detection on all pixel points in the target map to generate all target corners in the target map;
and performing position detection on all the target corner points, and when detecting that the target corner points are positioned in an obstacle area in the target map, moving the detected target corner points to an adjacent feasible area so as to enable all the target corner points to be positioned in the feasible area in the target map.
In a specific embodiment, the corner detection judgment is performed on the target map according to a Harris corner detection method. Setting the gray value of any pixel point (x, y) on the target image as I (x, y), and obtaining the gray value change values which take the pixel point (x, y) as the center and respectively move the distance u and the distance v along the directions x and y. The gradation variation expression can be expressed by the following formula:
E(u,v)＝∑ x,y w(x,y)[I(x+u,y+v)-
I(x,y)] 2 ；
wherein E (u, v) is a gradation change value; w (x, y) is a window function, and a Gaussian function is generally adopted;
and (3) deforming the gray scale change expression based on a Taylor formula to obtain a simplified formula as follows:
in the formula, Ix and Iy are gradient operators in x and y directions, respectively:
the self-correlation matrix M of the pixel points is obtained by the derivative of the image gray level,
the autocorrelation matrix M is a 2 x 2 matrix and the expression is directly related to the gray scale variation at the center (x, y) of the matrix. The eigenvalues of M are λ 1, λ 2, which symbolize the rate of change of the grey scale in the x, y direction, respectively, in the center point (x, y) of the matrix.
Introducing a corner response function to judge whether the pixel point is a target corner or not; wherein the corner response function is as follows:
R＝detM-k(trace M) 2 ；
in the formula, k is a correction value, generally 0.02-0.04, R is a response function, and when | R | is small, the gray level change of the area where the pixel point is located is small and the pixel point is located in a flat area of the target image. And when the absolute value of R < 0, the pixel point is in the edge area of the target image. When | R | is large, it means that the gray scale changes significantly when the pixel moves in any direction, i.e. the target corner point to be found. Further, the Harris corner detection is performed on all pixel points in the target map, so that all target corners in the target map are generated.
As an optimization method of this embodiment, after generating all target corner points in a target map, position detection is further performed on all the target corner points, and when a target corner point is detected to be located in an obstacle area in the target map, the detected target corner point is moved to a feasible area adjacent to the obstacle area, so that it is ensured that all the detected target corner points are located in the feasible area of the target map.
The path generating module 202 is configured to generate an initial path starting from a path starting point, where all the target corner points are connected with the path starting point by a shortest path distance, and specifically includes: all the target angular points, the path starting points and the path end points are connected in a straight line mode, and an angular point connection set is generated; extracting a straight-line connection path which is not blocked by an obstacle area in the target map in the corner connection set to generate an initial connection path set; and optimizing the initial connection path set to generate the initial path.
Wherein, the optimizing the initial connection path set to generate the initial path specifically includes: acquiring all target corner points which are directly connected with the starting point of the path in the initial connection path set, recording the connection relation between the target corner points and the starting point of the path and the corresponding direct connection path distance, and generating a first connection set; acquiring a target corner point which cannot be directly connected with the starting point of the path in the initial connection path set, and generating a first set to be connected; adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and updating the connection relation between the target corner points in the first connection set and the path starting points; and generating an initial path which starts from a path starting point, is connected with the path starting point by the shortest path distance from all the target corner points according to the updated first connection set.
Adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and adding a connection relation between the target corner points in the first connection set and the path starting points, specifically: adding a first target corner point to be connected in the first set to be connected; wherein the adding operation specifically comprises: acquiring all connection target angular points connected with the first target angular point to be connected in the first connection set; taking the path distance of the first connection target angular point connected with the path starting point through the first target angular point to be connected as a first path distance; taking the direct connection path distance between the first connection target corner point and the path starting point as a second path distance; when the first path distance is smaller than the second path distance, taking the second path distance as the shortest path distance between the first connection target corner point and the path starting point; updating the connection relation corresponding to the second path distance to the first connection set; and sequentially executing the adding operation on all the connecting target angular points connected with the first target angular point to be connected to generate a first updating connection set.
Generating an initial path starting from a path starting point and connecting all the target corner points with the path starting point by a shortest path distance according to the updated first connection set, wherein the method further comprises the following steps: sequentially executing the adding operation on all target corner points to be connected in the first set to be connected according to the linear distance between the target corner points and the starting point of the path; adding the target corner points to be connected to the updated connected set generated by the previous target corner points to be connected until all the target corner points to be detected in the first set to be connected complete the adding operation, and generating a final updated connected set; and extracting the path connection relation in the final updated connection set to generate the initial path.
In a specific embodiment, a greedy policy is adopted to generate the initial path. And taking all target corner points which can be directly connected with the starting point of the path as a first connection set, and recording the path distance between the starting point of the path and each target corner point. And taking the target corner points which cannot be directly connected with the starting points of the paths as a first to-be-connected set, and sequentially adding the target corner points to be connected in the first to-be-connected set to the first to-be-connected set on the premise of not changing the connection relation between the target corner points to be connected and the other target corner points according to the distance from the target starting points to the target starting points from small to large. Taking a target corner point M to be connected as a reference case, setting the target corner point M to be connected as a target corner point in a first connected set, which is closest to the starting point of the path, and adding the target corner point to be connected to the first connected set, wherein the following adding operations are specifically executed:
acquiring all target corner points connected with M in a first connection set, setting that a plurality of target corner points connected with M exist in the first connection set, selecting one connection target corner point C, setting a direct connection path distance of the connection target corner point as a first path distance S1, setting a path distance of the connection target corner point C connected with a path starting point through the target corner point M to be connected as a second path distance S2, if the second path distance S2 is smaller than the first path distance S1, considering that a shortest path distance between the target corner point C and the path starting point is S2, setting the shortest path distance between the target corner point C and the path starting point as S2, and updating the best path connection relation between the path starting point and the target corner point C in the first connection set to be connected with the target corner point C through the target corner point M to be connected.
And after determining the shortest path distances between the target corners connected with the target corner M to be connected and the path starting points in the first connection set, responding and updating the path connection relationship between the path starting points and the connection corner points to generate a first updated connection set.
And sequentially executing the adding operation on all the target corner points to be connected in the first target corner point to be connected according to the linear distance from the starting point of the path, and adding the target corner points to be connected to the updated connection set generated by the previous target corner points to be connected. That is, when adding operation is performed on the second target corner point to be connected, the connection relationship between each target corner point in the first updated connection set and the path starting point is used as a basis, if the path connection relationship related to the second target corner point exists, the first updated connection set is updated, and the updated first updated connection set is used as the second updated connection set corresponding to the second target corner point to be connected. And sequentially adding all the target corner points to be connected in the first set to be connected until the addition of all the target corner points to be connected in the first set to be connected is completed, and generating a final updated connection set.
Based on the adding operation, all the target angular points in the final updating connection set are connected with the starting point of the path in the shortest path, the connection relation between the starting point of the path in the final updating connection set and each target angular point is extracted, and an initial path which takes the starting point of the path and is connected between each target angular point and the starting point of the path in the shortest path distance is generated.
As the initial path actually implements local optimal solution, rather than optimal solution interpretation from the overall path, as a preferred case of the embodiment of the present invention, the initial path is generated and then further includes a path optimization module 203 for randomly generating test nodes in the target map; and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
The method specifically comprises the following steps: performing an update operation on the test node; wherein the update operation specifically includes: performing an update operation on the test node; wherein the update operation specifically includes: acquiring all target corner points directly connected with the test node in the initial path within a preset range; obtaining the shortest path distance between all target angle points directly connected with the test node and the path starting point, and generating a first search path distance set; acquiring path distances of all target corner points directly connected with the test nodes and the path starting points through the test nodes, and generating a second search path distance set; when any one of the second search path distance sets is smaller than the first search path distance corresponding to the first search path distance set, acquiring a target corner point corresponding to the path distance; and taking the second search path as the shortest path between the corresponding target corner point and the path starting point, and updating the connection relation of the initial path. Executing a test node generation instruction for preset times; and executing the updating operation on the generated test node every time until the last updating operation is finished, and generating the shortest path.
In a specific embodiment, an RRT (rapid distance transform) search algorithm is introduced, a search path tree with a path starting point as a root node is generated according to the initial path, and each target corner point is a target node in the search path tree. Initializing information of the search path tree, including: the position coordinates of each target node, and the last connection parent node of each corner point. And generating a test node X in a feasible area in the target map, and searching for a target node Y which has a direct connection relation with the test node in a preset range. The preset range may be correspondingly set and adjusted according to the size of the target map, for example, the size may be set to 1/40, which is higher or lower than the overall size of the target map, and is not limited herein. And if the path distance of the test node X connected with the path starting point through the target node Y is the shortest path distance, adding the test node X to the search path, rearranging the test node X, and if the path distance of the peripheral nodes from the path starting point through the test node X as the father node is shorter than the original connection path, executing updating operation.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
The embodiment of the invention provides a shortest path generating device which comprises an angular point generating device, a path generating device and a path optimizing device. The corner generating device is used for detecting corners of the target map and generating all target corners in the target map. The corner points are local feature representations of image pixels, the target map is subjected to comprehensive corner point detection, the communication conditions among the regions in the target map can be established through the position relationship among the corner points, the conditions of all the regions in the target map are obtained, and unmanned aerial vehicle path planning is facilitated. And establishing and generating an initial path starting from the path starting point and connecting all the target corner points with the path starting point by the shortest path distance based on the connection relation among all the target corner points, the path starting point and the search end point, thereby realizing the local optimal path connection relation among all the target corner points. Furthermore, test nodes are randomly generated on the target map, and when the path distance of any target corner point connected with the path starting point through the test node is smaller than the shortest path distance of the target corner point and the path starting point, the path distance of the target corner point connected with the path starting point through the test node is shorter. Based on the method, the connection relation of the search path tree is added, the path from the starting point of the path to the searching end point through the target corner point is shortened, and the generation quality and the accuracy of the search path are improved.
It should be noted that the embodiment of the shortest path generating apparatus described above is merely illustrative, where the modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical units, that is, may be located in one place, or may also be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and substitutions can be made without departing from the technical principle of the present invention, and these modifications and substitutions should also be regarded as the protection scope of the present invention.
Claims (10)
1. A shortest path generating method, comprising:
carrying out corner detection on a target map to generate all target corners in the target map;
generating an initial path starting from a path starting point, wherein all the target corner points are connected with the path starting point by a shortest path distance;
randomly generating a test node in the target map;
and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
2. The shortest path generating method according to claim 1, wherein the corner point detecting specifically includes:
acquiring a gray value of a first pixel point in the target map;
moving the first pixel point in the x direction and the y direction respectively by a preset distance;
acquiring a gray scale change value of the first pixel point after the first pixel point moves the preset distance;
and judging whether the first pixel point is the target corner point according to a corner point response function.
3. The method for generating a shortest path according to claim 2, wherein the generating all the target corner points in the target map specifically includes:
performing the corner detection on all pixel points in the target map to generate all target corners in the target map;
and performing position detection on all the target corner points, and when detecting that the target corner points are positioned in an obstacle area in the target map, moving the detected target corner points to an adjacent feasible area so as to enable all the target corner points to be positioned in the feasible area in the target map.
4. The method as claimed in claim 1, wherein the generating an initial path starting from a path starting point and connecting all the target corner points with the path starting point by a shortest path distance includes:
all the target angular points, the path starting points and the path end points are connected in a straight line mode, and an angular point connection set is generated;
extracting a straight-line connecting path which is not blocked by an obstacle area in the target map in the corner connecting set to generate an initial connecting path set;
and optimizing the initial connection path set to generate the initial path.
5. The method for generating a shortest path according to claim 4, wherein the optimizing with the initial connection path set to generate the initial path specifically includes:
acquiring all target corner points which are directly connected with the starting point of the path in the initial connection path set, recording the connection relation between the target corner points and the starting point of the path and the corresponding direct connection path distance, and generating a first connection set;
acquiring a target corner point which cannot be directly connected with the starting point of the path in the initial connection path set, and generating a first set to be connected;
adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and updating the connection relation between the target corner points in the first connection set and the path starting points;
and generating an initial path which starts from a path starting point, is connected with the path starting point by the shortest path distance from all the target corner points according to the updated first connection set.
6. The shortest path generating method according to claim 5, wherein the adding all target corner points to be connected in the first set to be connected to the first connection set according to a shortest path connection principle, and adding a connection relationship between a target corner point in the first connection set and the path starting point specifically includes:
adding a first target corner point to be connected in the first set to be connected; wherein the adding operation specifically comprises: acquiring all connection target angular points connected with the first target angular point to be connected in the first connection set; taking the path distance of the first connection target angular point connected with the path starting point through the first target angular point to be connected as a first path distance; taking the direct connection path distance between the first connection target corner point and the path starting point as a second path distance; when the first path distance is smaller than the second path distance, taking the second path distance as the shortest path distance between the first connection target corner point and the path starting point; updating the connection relation corresponding to the second path distance to the first connection set;
and sequentially executing the adding operation on all the connecting target angular points connected with the first target angular point to be connected to generate a first updating connection set.
7. The shortest path generating method according to claim 6, wherein the generating an initial path starting from a path starting point and connecting all the target corner points with the path starting point by a shortest path distance according to the updated first connection set further comprises:
sequentially executing the adding operation on all target corner points to be connected in the first set to be connected according to the linear distance between the target corner points and the starting point of the path;
adding the target corner points to be connected to the updated connected set generated by the previous target corner points to be connected until all the target corner points to be detected in the first set to be connected complete the adding operation, and generating a final updated connected set;
and extracting the path connection relation in the final updated connection set to generate the initial path.
8. The method as claimed in claim 1, wherein the step of updating the connection relationship of the initial path to generate the shortest path when the path distance between any one of the target corner points and the starting point of the path through the test node is smaller than the shortest path distance between the target corner point and the starting point of the path includes:
performing an update operation on the test node; wherein the update operation specifically includes: acquiring all target corner points directly connected with the test node in the initial path within a preset range; obtaining the shortest path distance between all target angle points directly connected with the test node and the path starting point, and generating a first search path distance set; acquiring path distances of all target corner points directly connected with the test nodes and the path starting points through the test nodes, and generating a second search path distance set; when any one of the second search path distance sets is smaller than the first search path distance corresponding to the first search path distance set, acquiring a target corner point corresponding to the path distance; and taking the second search path as the shortest path between the corresponding target corner point and the path starting point, and updating the connection relation of the initial path.
9. The method as claimed in claim 8, wherein the step of updating the connection relationship of the initial path to generate the shortest path when the path distance between any of the target corner points and the starting point of the path through the test node is smaller than the shortest path distance between the target corner point and the starting point of the path further comprises:
executing a test node generation instruction for preset times;
and executing the updating operation on the generated test node every time until the last updating operation is finished, and generating the shortest path.
10. A shortest path generating apparatus, comprising: the device comprises an angular point generating module, a path generating module and a path optimizing module;
the corner generation module is used for detecting corners of a target map and generating all target corners in the target map;
the path generation module is used for generating an initial path which starts from a path starting point, and all the target corner points are connected with the path starting point by a shortest path distance;
the path optimization module is used for randomly generating test nodes in the target map; and when the distance of the path connecting any target corner point with the starting point of the path through the test node is smaller than the distance of the shortest path between the target corner point and the starting point of the path, updating the connection relation of the initial path to generate the shortest path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210478933.6A CN114863300A (en) | 2022-04-29 | 2022-04-29 | Shortest path generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210478933.6A CN114863300A (en) | 2022-04-29 | 2022-04-29 | Shortest path generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114863300A true CN114863300A (en) | 2022-08-05 |
Family
ID=82635300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210478933.6A Pending CN114863300A (en) | 2022-04-29 | 2022-04-29 | Shortest path generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114863300A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115309161A (en) * | 2022-08-23 | 2022-11-08 | 南京信息工程大学 | Mobile robot path planning method, electronic equipment and storage medium |
-
2022
- 2022-04-29 CN CN202210478933.6A patent/CN114863300A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115309161A (en) * | 2022-08-23 | 2022-11-08 | 南京信息工程大学 | Mobile robot path planning method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111289998A (en) | Obstacle detection method, obstacle detection device, storage medium, and vehicle | |
| CN112086010A (en) | Map generation method, map generation device, map generation equipment and storage medium | |
| CN112595337A (en) | Obstacle avoidance path planning method and device, electronic device, vehicle and storage medium | |
| CN111310828A (en) | Target detection model fine-tuning method and device for ADAS scene | |
| US20200082039A1 (en) | Obstacle distribution simulation method, device and terminal based on a probability graph | |
| CN109579857B (en) | Method and equipment for updating map | |
| CN111681172A (en) | Method, equipment and system for cooperatively constructing point cloud map | |
| CN114036253A (en) | High-precision map data processing method and device, electronic equipment and medium | |
| CN110782774A (en) | Crowdsourcing road data distributed processing method and device | |
| CN114387410A (en) | Road data fusion map generation method and device and electronic equipment | |
| CN112991307A (en) | Defect circle fitting method and device for drilling blasting and medium | |
| CN114863300A (en) | Shortest path generation method and device | |
| US11354461B2 (en) | Method and device for simulating a distribution of obstacles | |
| CN110287817B (en) | Target recognition and target recognition model training method and device and electronic equipment | |
| CN114111813B (en) | High-precision map element updating method and device, electronic equipment and storage medium | |
| CN113743456B (en) | Scene positioning method and system based on unsupervised learning | |
| CN111598000A (en) | Face recognition method, device, server and readable storage medium based on multiple tasks | |
| CN111368860A (en) | Relocation method and terminal equipment | |
| CN116642508A (en) | Path planning method and device for improving A star algorithm and robot | |
| CN110363847B (en) | Map model construction method and device based on point cloud data | |
| CN111160073A (en) | License plate type identification method and device and computer readable storage medium | |
| CN111507154B (en) | Method and apparatus for detecting lane line elements using transversal filter mask | |
| CN111435086B (en) | Navigation method and device based on splicing map | |
| CN113834497A (en) | Automatic driving route planning method and device | |
| CN112965917A (en) | Test method, device, equipment and storage medium for automatic driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |