CN116907530A - Path planning method, device, equipment and storage medium - Google Patents
Path planning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116907530A CN116907530A CN202310911117.4A CN202310911117A CN116907530A CN 116907530 A CN116907530 A CN 116907530A CN 202310911117 A CN202310911117 A CN 202310911117A CN 116907530 A CN116907530 A CN 116907530A
- Authority
- CN
- China
- Prior art keywords
- target
- road
- path planning
- determining
- map
- 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 105
- 238000000605 extraction Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000010276 construction Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000000903 blocking effect Effects 0.000 claims description 26
- 239000013598 vector Substances 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 238000009499 grossing Methods 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 23
- 238000004422 calculation algorithm Methods 0.000 description 21
- 238000004891 communication Methods 0.000 description 8
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 239000000872 buffer Substances 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004132 cross linking Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003363 endpoint correction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3833—Creation or updating of map data characterised by the source of data
- G01C21/3852—Data derived from aerial or satellite images
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The invention discloses a path planning method, a device, equipment and a storage medium, comprising the following steps: acquiring a target satellite image, wherein the target satellite image is an image obtained by preprocessing an initial satellite image; extracting and processing roads according to the target satellite images, and determining target road information; establishing a topological relation among roads according to the target road information, and determining a target topological map; and carrying out global path planning on the travelling track of the target vehicle according to the target topological map. According to the technical scheme, the problems of complicated map construction and road network connection in the traditional method are solved, the path planning process is simplified, accurate and efficient road information extraction is realized, the accuracy and the efficiency of the path planning implementation process are improved, the flexibility and the universality of the path planning are ensured, the method is suitable for various road environments, and global coverage can be realized.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a path planning method, apparatus, device, and storage medium.
Background
Path planning is one of the main research contents of motion planning and is also the basis of intelligent vehicle navigation and control. The path is a sequence of points or curves connecting the start and end positions, and the path planning is a strategy for constructing the path. The path planning method has a plurality of advantages and disadvantages, and the application range is different.
The method of path planning according to the high-precision map is a conventional technology of path planning, but the construction of the high-precision map and the connection of a road network are very complicated, and correspondingly, the method of path planning based on the road network information provided by the high-precision map is complex in the implementation process, and in the practical application process, the method cannot be well suitable for complex and changeable terrain environments, and cannot obtain an optimal path planning result.
Disclosure of Invention
The invention provides a path planning method, a device, equipment and a storage medium, which solve the problems of complicated map construction and road network connection in the traditional method, simplify the path planning process, realize accurate and efficient road information extraction, improve the accuracy and efficiency of the path planning implementation process, ensure the flexibility and universality of path planning, are suitable for various road environments, and can realize global coverage.
In a first aspect, an embodiment of the present disclosure provides a path planning method, including:
acquiring a target satellite image, wherein the target satellite image is an image obtained by preprocessing an initial satellite image;
extracting and processing roads according to the target satellite images, and determining target road information;
establishing a topological relation among roads according to the target road information, and determining a target topological map;
and carrying out global path planning on the travelling track of the target vehicle according to the target topological map.
In a second aspect, an embodiment of the present disclosure provides a path planning apparatus, including:
the image acquisition module is used for acquiring a target satellite image, wherein the target satellite image is an image obtained by preprocessing an initial satellite image;
the road information determining module is used for extracting and processing roads according to the target satellite images and determining target road information;
the topological map construction module is used for establishing a topological relation among roads according to the target road information and determining a target topological map;
and the path planning module is used for carrying out global path planning on the travelling track of the target vehicle according to the target topological map.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
At least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the path planning method provided by the embodiments of the first aspect described above.
In a fourth aspect, embodiments of the present disclosure provide a computer readable storage medium storing computer instructions for causing a processor to execute the path planning method provided in the foregoing first aspect embodiment.
The embodiment of the invention provides a path planning method, a path planning device, path planning equipment and a path planning storage medium, wherein a target satellite image is an image obtained by preprocessing an initial satellite image; extracting and processing roads according to the target satellite images, and determining target road information; establishing a topological relation among roads according to the target road information, and determining a target topological map; and carrying out global path planning on the travelling track of the target vehicle according to the target topological map. According to the technical scheme, the problems of complicated map construction and road network connection in the traditional method are solved, the path planning process is simplified, accurate and efficient road information extraction is realized, the accuracy and the efficiency of the path planning implementation process are improved, the flexibility and the universality of the path planning are ensured, the method is suitable for various road environments, and global coverage can be realized.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a path planning method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a path planning method according to a second embodiment of the present invention;
fig. 3 is an exemplary showing a program running flow involved in a path planning method according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a path planning apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and "object" in the description of the present invention and the claims and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a path planning method according to an embodiment of the present invention, where the method may be implemented by a path planning device, and the device may be implemented in hardware and/or software.
As shown in fig. 1, the method includes:
s101, acquiring a target satellite image, wherein the target satellite image is an image obtained by preprocessing an initial satellite image.
In this embodiment, the target satellite image can be understood as an image that can be directly used for road extraction, and is a clear and accurate image that has been processed. An initial satellite image may be understood as an unprocessed image taken directly from the satellite.
Specifically, the target satellite image with clearer image and better quality after the preprocessing step is obtained. The method comprises the following steps of preprocessing an initial satellite image to obtain an optimized target satellite image: the method comprises the steps of acquiring high-resolution remote sensing images (initial satellite images) acquired by satellites, wherein optional satellites comprise earth observation satellites, civil satellites, commercial satellites and the like. It should be noted that the resolution of the satellite images is high enough to facilitate the extraction of road information, and is usually required to be above the meter level; the obtained initial satellite image is subjected to preprocessing such as image denoising, enhancement, registration and the like, so that the quality of the image is improved, and the road information in the image is more obvious and clear.
The image denoising processing is performed on the initial satellite image, and a wavelet transform denoising algorithm can be used for performing wavelet denoising on the initial satellite image to obtain a denoised intermediate image. The wavelet transformation is a signal analysis method, can decompose signals into components with different scales and frequencies, and can remove noise through wavelet transformation and simultaneously keep characteristic information of images as far as possible. It will be appreciated that other algorithms or models may be used to perform image denoising on the initial satellite image, which is not limited in this embodiment.
And (3) carrying out image enhancement processing on the denoised intermediate image, and carrying out image enhancement by adopting a self-adaptive histogram equalization algorithm to obtain an enhanced intermediate image. The self-adaptive histogram equalization algorithm is an improvement on the traditional histogram equalization algorithm, and can enhance the contrast of the image and simultaneously avoid enhancing noise. It will be appreciated that other algorithms or models may be used to perform image denoising on the initial satellite image, which is not limited in this embodiment.
And carrying out influence registration processing on the enhanced intermediate image, and carrying out image registration by adopting a Scale-invariant feature transform (SIFT) algorithm to obtain a registered target satellite image. The SIFT algorithm is an image registration and feature extraction algorithm, and can realize the invariance of rotation, scaling and translation of images.
S102, extracting and processing roads according to the target satellite images, and determining target road information.
In this embodiment, the target road information may be understood as information that can completely represent the road in the target satellite image.
Specifically, image information and reference point position information are acquired according to a target satellite image, a coordinate system is established, so that all pixel point positions of the target satellite image are acquired, road extraction is carried out on the target satellite image, a plurality of road segments are extracted, the extracted road segments are integrated and corrected, a complete road map is obtained, and target road information is determined according to the complete road map. After the target road information is determined, the target road information is stored in a corresponding storage area, such as a memory.
S103, establishing a topological relation among roads according to the target road information, and determining a target topological map.
In the present embodiment, the topological relation between roads can be understood as a mesh topological relation formed according to the intersection situation between roads. The target topology map may be understood as a topology map file formed according to the target road information and the topology relationship between the roads.
A complete road network (road network) is constructed on the basis of road extraction and connection, a topological relation between roads needs to be established, and the connection mode of the roads and the relation between road sections are determined so as to realize the requirement of global path planning. In the topological relation, the intersection or bifurcation point of the road is represented by a node, and the road section connecting the nodes is represented by an edge. In building a road network, nodes and edges need to be defined and identified for subsequent path searching and planning.
Specifically, according to the edges and nodes of the roads determined from the target road information, constructing a topological relation among the roads, and writing other parameter information from the target road information into the topological relation to form a target topological map with complete information. The other parameter information includes road length, width, longitude, latitude, road number, passable attribute, etc., and the specific parameter information is determined according to the actual situation, which is not limited in this embodiment.
S104, carrying out global path planning on the travelling track of the target vehicle according to the target topological map.
In the present embodiment, the target vehicle may be understood as an application body for performing path planning, may be an unmanned intelligent vehicle, or may be a manned vehicle, and the present embodiment is not limited to this. The travel track of the target vehicle can be understood as a motion track determined by the path planning method provided by the embodiment of the invention, and the motion track is determined according to the target topological map and preset task points. The mission point is understood to be a point of position through which the target vehicle must travel, for example, an ammunition replenishment point through which the military vehicle is to pass.
Specifically, the position of the target vehicle is taken as an initial task point, the position of a task point preset by the target vehicle is obtained, and the task point is displayed in a target topological map according to the position information such as longitude and latitude of each task point position. Taking the position of the task point where the target vehicle is located as a first task point, adopting a preset path planning algorithm to carry out path planning among the task points from the target topological map, merging path planning results among the task points, and carrying out smoothing treatment to form a complete global path planning track aiming at all the task points of the target vehicle, so that the target vehicle can travel according to the travelling track.
In this embodiment, by acquiring a target satellite image, the target satellite image is an image obtained by preprocessing an initial satellite image; carrying out road extraction and processing according to the target satellite image, and determining target road information; establishing a topological relation among roads according to the target road information, and determining a target topological map; and carrying out global path planning on the travelling track of the target vehicle according to the target topological map. According to the technical scheme, the problems of complicated map construction and road network connection in the traditional method are solved, the path planning process is simplified, accurate and efficient road information extraction is realized, the accuracy and the efficiency of the path planning implementation process are improved, the flexibility and the universality of the path planning are ensured, the method is suitable for various road environments, and global coverage can be realized.
As a first alternative embodiment of the embodiments, on the basis of the above embodiments, the first alternative embodiment further optimizes and increases:
a1 When the road blocking signal is received and the current road condition is determined to be unable to pass according to the road blocking signal, the target topological map is corrected.
In this embodiment, the road blocking signal may be understood as a signal received by the vehicle, where there is an obstacle in front of the signal, which may be a blocking signal obtained by the lidar, or may be a path planned by a local path determined by satellite information received in real time.
Specifically, in the process that the vehicle advances according to the result of the path planning, pose information of the vehicle is received in real time, when a road blocking signal is received, whether the received road blocking signal is effective or not is judged according to the persistence of the signal, and when the road blocking signal is effective, the current road condition is determined that the vehicle cannot pass. The judging of whether the road blocking signal is valid is as follows: when a road blocking signal of the laser radar is received, receiving the road blocking signal for 30 times within 1 second, and judging that the road blocking signal is valid; when a road blocking signal of local planning track blocking is received, 10 times of blocking signals are received within 1 second, and the signals are judged to be valid.
When a road blocking signal is received and the current road condition cannot be passed according to the road blocking signal, recording the current vehicle position as a first task point, the position of the last passing road end point of the vehicle as a second task point, sequentially inserting the remaining unreached task points into a task point list, setting a replay variable in a task request as true, representing the current modified task, and sending the task request. And permanently modifying the current target topological map according to the re-planned task request, newly adding blocking position nodes in the target topological map, modifying the passing attribute of two end points of a blocking road as non-passable and modifying edges in the corresponding topological network, and newly adding a connecting path between the blocking position nodes and the end point nodes of the road passing by the blocking position nodes so as to realize the modification of the target topological map.
b1 And (3) carrying out path re-planning on the travelling track of the target vehicle according to the corrected target topological map.
In this embodiment, a path is planned by using an a-x algorithm according to the corrected target topology map, and paths between every two task points in the first three task points are sequentially planned, so as to realize local path planning of the first three task points during re-planning. And combining the curves after planning of the first three local paths with the paths planned subsequently so as to avoid repeated planning and improve the efficiency. And carrying out path smoothing processing on the combined paths according to a set smoothing curve algorithm to form a new travelling track plan of the target vehicle, and completing path re-planning.
According to the path planning method provided by the alternative embodiment, when the road blocking signal is received and the current road condition is determined to be unable to pass according to the road blocking signal, the path is planned again for the current planned path, so that the real-time requirement of emergency is difficult to meet, and the flexibility and the universality of application are ensured.
Example two
Fig. 2 is a flowchart of a path planning method according to a second embodiment of the present invention, where any of the foregoing embodiments is further optimized, and the method may be implemented by a path planning device, and the device may be implemented in hardware and/or software.
As shown in fig. 2, the method includes:
s201, acquiring a target satellite image, wherein the target satellite image is an image obtained by preprocessing an initial satellite image.
S202, extracting roads according to the target satellite images, and obtaining road segments and road information of the road segments.
In this embodiment, the road segment may be understood as a road of a segment extracted from the target satellite image, and the road information of the road segment may be understood as information capable of representing the content of the road segment, for example, may include content information such as longitude and latitude, position number, path length, and the like of each position in the road segment.
Specifically, image information and reference point position information are acquired according to a target satellite image, a coordinate system is established, so that all pixel point positions of the target satellite image are acquired, road extraction is carried out on the target satellite image, a plurality of road segments are extracted, and road information of each road segment is obtained. The method for extracting the road segments and the road information of the road segments may be a conventional image processing method, a machine learning method, a deep learning method, a manual extraction method, or the like, which is not limited in this embodiment.
Among them, the conventional image processing method includes a method based on edge detection, a method based on region growing, a method based on morphological processing, and the like. Edge detection can be performed by a channel operator and the like, region growth can be performed according to characteristics such as colors, textures and the like, parameters are required to be manually adjusted by the methods, the parameters are affected by illumination, shadows and the like, and errors may exist in an extraction result. The machine learning method comprises a method based on a support vector machine, a decision tree, a random forest and other classification algorithms, wherein the method needs to train a classifier in advance and classify test data, and a part of images need to be manually marked for training, so that the quality and the quantity of training data have great influence on the extraction effect. The deep learning method comprises a convolutional neural network (ConvolutionalNeuralNetwork, CNN), a full convolutional neural network (Fully ConvolutionalNetworks, FCN), an image segmentation U-Net and the like, and is used for automatically performing feature learning and classification based on a large amount of data, is suitable for processing large-scale data, has relatively good extraction effect, and requires a large amount of computing resources and data sets. The manual extraction method is a method for extracting the road by manually identifying the road area in the influence of the satellite, and the method does not need special algorithm and technical support, but requires a great deal of manpower and time cost, and the extraction result is influenced by personal subjective factors.
Under special conditions such as poor satellite image quality, insignificant difference of road area and background, manual extraction can be an effective road extraction method. However, in practical applications, because of the high time and cost of manual extraction, the method is generally only suitable for road extraction in small-scale data sets or specific areas requiring high accuracy, and for large-scale data sets or global path planning requiring high efficiency, an automatic road extraction method is generally adopted.
The embodiments of the present invention preferably employ deep learning based full convolutional neural networks (FCNs) for road extraction. FCN is an image semantic segmentation algorithm in the field of deep learning, and has the following advantages: the training and the prediction can be carried out end to end, the manual feature extraction is not needed, and the efficiency and the accuracy of road extraction are improved; the method can adapt to the changes of various road shapes and sizes, and is suitable for road extraction in different areas; the method can adaptively process the influence factors such as illumination, shadow and the like, and the extraction result is relatively stable and reliable; when complex scenes are processed, a plurality of convolution layers can be utilized for feature extraction, and accuracy and robustness of road extraction are improved. For a particular implementation, a FCN network that is pre-trained on a large dataset, such as deephbvv3+ or U-Net, may be employed, and then tuned on its own dataset.
And S203, performing connection matching and correction processing on the road segments according to the road information so as to enable the road segments to be connected into an overall map, and determining the road information of the overall map.
In this embodiment, the overall map may be understood as a more complete map formed by combining, connecting, matching, correcting and adjusting a plurality of road segments. The road information of the overall map may be understood as information capable of representing overall road content obtained after a plurality of road segments are connected and matched, and may include, for example, content information such as longitude and latitude, position number, path length, and the like of each position in the overall map.
Specifically, the extracted road segments are integrated and modified, i.e., the road segments or road areas extracted from the target satellite images are connected together to form a connected road network. The purpose of the road connection is to build a complete road network for global path planning. In forming the overall map, road segment matching and intersection connection are included. And determining the longitude and latitude, the road node number, the path length, the path passable attribute and other content information of each position in the map according to the integral map after connection matching and correction processing.
Specifically, in the road extraction process, multiple road segments may be generated, where the segments need to be matched and connected, and the matching may be performed based on a topology structure or road characteristics such as a shape, a direction, a length, and the like, so as to find a matching relationship between adjacent road segments, thereby performing connection. In road connection, it is particularly necessary to consider the connection of intersections, which are key parts of a road network, that connect different roads together in a cross-linking manner. When connecting intersections, the types of the intersections, steering rules and road topology relations are required to be considered, so that the accuracy and the rationality of connection are ensured, and only one coincident road point exists at the intersection end points of different roads.
For example, the road end point correction is performed on the junction by adopting the local amplification mode, two roads S1 and S2 are provided, the S1 is the road processed first, the end point is s1_end, the distance between one end point s2_end of the S2 and s1_end is smaller than the preset threshold R (for example, may be 5 meters), and then s2_end is deleted from S2, and s1_end is used as a new end point of S2. According to the method, the method is popularized to all the intersection points, and only the unique overlapping points of the intersection can be ensured.
S204, determining the road information of the whole map as target road information, wherein the target road information is in a set structure body format.
In this embodiment, the configuration format is understood to be a configuration that is preset to represent the target road information, and is a Map configuration, and the configuration is composed of a header, a road element vector, and a waypoint element vector.
Specifically, road information of a complete road Map is determined as target road information, the target road information can be expressed as a Map structure body, the structure body is composed of a header data head, a road element vector and a road point element vector, and the data head can comprise a Map version, a Map date, a Map coordinate system and a Map boundary as required; the road element vector comprises all road nodes, and each road node stores the road direction, the road number, the road length, the number of road points and the IDs of the road points of each road; the waypoint element vector contains all waypoint numbers, longitudes, latitudes. After the target road information is determined, the target road information is stored in a corresponding storage area according to a set storage format, wherein the set storage format can be a public map (OpenStreetMap, OSM) standard format.
S205, constructing a topological map structure body and analyzing target road information, wherein the topological map structure body comprises a map version, node vectors and side vectors.
In this embodiment, the topology map structure may be understood as a topology structure, and the map version may be understood as a version number of the topology map structure. A node vector may be understood as a crossing node in a topological map structure where at least two edges intersect in a topological relationship. An edge vector can be understood as an edge in a topological map structure that topologically connects two nodes.
Road network establishment is a process of constructing a complete road network based on road extraction and connection. The process involves establishing a topological relationship between roads, determining a connection mode of the roads and a relationship between road segments, and realizing the requirement of global path planning. In a road network, nodes represent intersections or bifurcation points of roads, and edges represent road segments connecting the nodes. In building a road network, nodes and edges need to be defined and identified for subsequent path searching and planning.
Specifically, a topological map structure is constructed, wherein a structure Graph is composed of a version, a node vector and an edge vector, the node vector comprises all road crossing points, and each crossing point stores a road point number, longitude and latitude; the edge vector contains all edge elements, which may include traffic attributes, road numbers, starting waypoints, arrival waypoints, and cost values as needed. The cost value is understood to be the length of the road or the travel distance of the vehicle on the road (which may be a single-pass distance or a multi-pass distance such as round trip).
S206, determining topological map nodes according to the road end point information in the target road information.
In the present embodiment, the road end point information can be understood as basic information of end points at both ends of the road. The topological map nodes are cross nodes where at least two edges in the topological relation in the topological map intersect.
Specifically, traversing road elements in the topological map structure, creating topological map nodes by using two end points of the road, and creating new nodes for the end points which are not created as corresponding nodes in the two end points.
S207, determining a topological map edge according to the road path information in the target road information.
In the present embodiment, the road path information can be understood as basic information of the road path. The topological graph edge is a line (edge) connecting two nodes on topological relation in the topological graph.
Specifically, road elements in the topological map structure are traversed to create topological map edges on roads, and bidirectional or unidirectional edges are created according to the road directions.
And S208, writing the road traffic attribute, the road cost value, the topological map nodes and the topological map edges in the target road information into a topological map structure body, and determining the target topological map.
In this embodiment, the road traffic attribute may be understood as whether the current road is traffic or not, including traffic and traffic-impossible attributes. Road cost value may be understood as the length of a road or the actual distance travelled by a vehicle on the road.
Specifically, the road traffic attribute is defaulted to be passable, the road number is the actual number of the road, the starting point is two end points respectively, and the cost value can be selected according to the requirement of the road length or other attribute values. After the topological map nodes and the topological map edges are determined, the road traffic attribute, the road number, the starting point, the cost value, the topological map nodes and the topological map edges are written into the topological map structure body, so that a target topological map with complete topological information is formed. It will be appreciated that there are many serialization and anti-serialization tools or libraries that may be used to sequence the structural information in a C++ environment, including Boost serialization (Boost. Serialization), data serialization protocol buffers, binary standard MessagePack, which is preferred in this embodiment.
S209, carrying out local path planning on each two task points in the target vehicle task point set according to the target topological map, and determining a local path planning result between each two task points.
In this embodiment, the task point set of the target vehicle may be understood as a task point set determined by summarizing the necessary positions of the target vehicle. A mission point may be understood as a location point that a target vehicle must travel to perform a mission, and may be, for example, a supply point for a military vehicle. Each task point has its own task point information including task point number, longitude, latitude, altitude, task point type. The local path planning result can be understood as a path planning result between every two adjacent task points.
Specifically, the position of the target vehicle is taken as an initial task point, task point information of task points preset by the target vehicle is obtained, and the task points are displayed in the target topological map according to the task point information of each task point. Taking the position of the task point where the target vehicle is located as a first task point, and adopting a preset path planning algorithm to plan the path between every two task points from the target topological map, wherein the set path planning algorithm can be an algorithm A or other algorithms, and the embodiment is not limited to the algorithm.
S210, merging local path planning results between every two task points, and performing smoothing processing on the merged paths to determine a global path planning result.
In this embodiment, the global path planning result may be understood as a result obtained by combining the local path planning results and used for knowing the whole travel track of the target vehicle.
Specifically, the paths corresponding to the multi-section local path planning result are combined into an integral path, and the combined integral path is subjected to smoothing treatment to form a complete global path planning track aiming at all task points of the target vehicle, so that the target vehicle can run according to the running track.
Among other things, path smoothing may improve path comfort, feasibility, and visualization effects. The path smoothing process aims to reduce the tortuosity and variability of the path, making it smoother and more continuous, to improve the navigation effect. Common path smoothing techniques and methods include B-Spline (B-Spline), cubic Spline (Cubic Spline), bezier curve (beziercurrve), kalman filter (kalman filter), and least square method-based curve fitting, and in this embodiment, these path smoothing techniques and methods may be selected and/or combined according to practical application requirements to obtain better smoothing effect. It can be appreciated that the present embodiment preferably adopts a smoothing method based on Cubic Spline (Cubic Spline), and the smoothed path has continuous curvature, so as to meet the general road feature requirement.
In this embodiment, by acquiring a target satellite image, the target satellite image is an image obtained by preprocessing an initial satellite image; extracting a road according to the target satellite image to obtain a road segment and road information of the road segment; performing connection matching and correction processing on the road segments according to the road information so as to enable the road segments to be connected into an overall map, and determining the road information of the overall map; determining road information of the overall map as target road information, wherein the target road information is in a set structure body format; constructing a topological map structure body and analyzing target road information, wherein the topological map structure body comprises a map version, node vectors and side vectors; determining topological map nodes according to the road endpoint information in the target road information; determining a topological map edge according to the road path information in the target road information; writing road traffic attributes, road cost values, topological map nodes and topological map edges in the target road information into a topological map structure body, and determining a target topological map; carrying out local path planning on each two task points in the target vehicle travelling track according to the target topological map, and determining a local path planning result between each two task points; and merging local path planning results between every two task points, and carrying out smoothing treatment on the merged paths to determine a global path planning result. According to the technical scheme, the problems of complicated map construction and road network connection in the traditional method are solved, the path planning process is simplified, accurate and efficient road information extraction is realized, the accuracy and the efficiency of the path planning implementation process are improved, the flexibility and the universality of the path planning are ensured, the method is suitable for various road environments, and global coverage can be realized.
As a first optional embodiment of the embodiment, on the basis of the foregoing embodiment, the step of optimally adding S209 a local path planning result for each two task points in the target vehicle task point set according to the target topology map, and determining a local path planning result between each two task points includes:
a1 The current pose of the target vehicle is determined to be a current task point and is stored in an initial task point set to form a target task point set, and the initial task point set comprises at least two preset task points.
In this embodiment, the current task point may be understood as a task point where the current vehicle is located, that is, a new task point position is added to the current position (pose) of the vehicle based on the set of task points that have been set originally. The initial set of task points may be understood as a set of task points that the target vehicle must pass through, including at least two preset task points. The target task point set may be understood as a task point set formed by determining the current position of the target vehicle as the current task point and adding the current task point to the initial task point set.
Specifically, the current pose of the target vehicle is determined as a current task point, the current task point is added to an initial task point set to form a target task point set comprising the current position and the necessary position of the vehicle, wherein the initial task point set comprises at least two preset task points, and the target task point set comprises at least three task points.
b1 And (3) carrying out road consistency judgment on each two task points in the target task point set according to the target topological map, and determining a consistency judgment result.
In this embodiment, the consistency determination result may be understood as a determination result for determining whether the two task points are on the same road, including that the roads on which the two task points are located are consistent and that the roads on which the two task points are located are inconsistent.
Specifically, for every two task points in the target task point set, determining whether the two task points are on the same road from the target topological map, if so, determining that the consistency judgment result is that the roads on which the two task points are located are consistent; if not, determining that the consistency judgment result is that the roads where the two task points are located are inconsistent.
c1 Determining a local path planning result between every two task points according to the consistency judging result.
In this embodiment, local path planning between different task points is performed according to different consistency determination results, so as to obtain a corresponding local path planning result.
Further, c 1) determining a local path planning result between every two task points according to the consistency judgment result, including:
c11 And if the consistency judgment result is that the roads where the two task points are located are consistent, carrying out connectivity judgment on the two task points, and determining a local path planning result between the two task points according to the connectivity judgment result.
In this embodiment, the connectivity determination result may be understood as a result of whether two task points can pass (whether there is a shielding obstacle), that is, whether the two task points can directly travel from the first task point position to the second task point position on the path of the current two task points, where the connectivity determination result includes two results that can be communicated and cannot be communicated.
Specifically, when the consistency judgment result is that the roads where the two task points are located are consistent, carrying out connectivity judgment on the two task points to obtain a connectivity judgment result, and if the connectivity judgment result is that the two task points can be communicated, directly obtaining all the road points between the two task points from the roads to be planning results; if the connectivity judgment result is that connectivity is not available, judging that planning is unsuccessful, and not allowing traffic between the two task points, and ending planning.
c12 When the consistency judgment result is that the roads where the two task points are located are inconsistent and one of the task points is not a cross road point, correcting the target topological map, and carrying out local path planning again according to the corrected target topological map to determine a local path planning result between the two task points.
In this embodiment, when the consistency determination result indicates that the roads on which the two task points are located are inconsistent, the target topology map needs to be temporarily modified. Specifically, whether each task point in the two task points is a cross road point is judged, if any task point is not a cross road point, one task point is added as a temporary topology node, the traffic attribute of the topology edge of the road where the task point is located is modified to be non-traffic, and the temporary topology edge is added according to the information from the task point to the two end points of the road where the task point is located, so that the correction of the target topology map is completed. And (3) carrying out path planning between the two task points again by adopting an A-algorithm according to the corrected target topological map, and determining a local path planning result between the two task points.
For more specific explanation of the present invention, fig. 3 is an exemplary illustration of the program running process involved in a path planning method according to the second embodiment of the present invention. As shown in fig. 3, determining a map data interface, a vehicle pose interface, and a task information interface as input interfaces; carrying out off-line topology according to the data transmitted by each interface, specifically analyzing an xml map file transmitted by a map data interface, acquiring map basic elements according to the analyzed file, and carrying out off-line construction of a topology map according to the acquired map basic elements; editing an online topological map (ROUTE topology) according to the offline constructed topological map, specifically, acquiring the offline topological map, acquiring the current pose of a target vehicle, acquiring information of each task point in an initial task point set, and constructing the topological map on line according to the current pose and the set task point to form the target topological map, wherein if a path re-planning instruction sent by a path re-planning request interface is received, the target topological map is required to be revised again according to the current position and other information of the vehicle; after the construction of the target topological map is completed, carrying out segmented local path planning between every two task points according to the acquired information of the target topological map, combining the local path planning of each segment to form a complete global path, issuing the complete global path, using a global path interface as an output interface, outputting the planned global path, and controlling the vehicle to travel according to the global path.
Example III
Fig. 4 is a schematic structural diagram of a path planning apparatus according to a third embodiment of the present invention. As shown in fig. 4, the apparatus includes:
the image acquisition module 31 is configured to acquire a target satellite image, where the target satellite image is an image obtained by preprocessing an initial satellite image;
the road information determining module 32 is configured to perform road extraction and processing according to the target satellite image, and determine target road information;
the topology map construction module 33 is configured to establish a topology relationship between roads according to the target road information, and determine a target topology map;
and the path planning module 34 is used for carrying out global path planning on the travelling track of the target vehicle according to the target topological map.
The route planning device adopted by the technical scheme solves the problems of complicated map construction and road network connection in the traditional method, simplifies the route planning process, realizes accurate and efficient road information extraction, improves the accuracy and efficiency of the route planning implementation process, ensures the flexibility and universality of route planning, is suitable for various road environments, and can realize global coverage.
Optionally, the road information determining module 32 is specifically configured to:
Extracting a road according to the target satellite image to obtain a road segment and road information of the road segment;
performing connection matching and correction processing on the road segments according to the road information so as to enable the road segments to be connected into an overall map, and determining the road information of the overall map;
and determining the road information of the overall map as target road information, wherein the target road information is in a set structural body format.
Optionally, the topology map construction module 33 is specifically configured to:
constructing a topological map structure body and analyzing the target road information, wherein the topological map structure body comprises a map version, node vectors and edge vectors;
determining topological map nodes according to the road endpoint information in the target road information;
determining a topological map edge according to the road path information in the target road information;
and writing the road traffic attribute, the road cost value, the topological map nodes and the topological map edges in the target road information into the topological map structure body to determine a target topological map.
Optionally, the path planning module 34 includes:
the local planning sub-module is used for carrying out local path planning on each two task points in the target vehicle travelling track according to the target topological map, and determining a local path planning result between each two task points;
And the global planning sub-module is used for merging the local path planning results between every two task points, smoothing the merged paths and determining the global path planning result.
Optionally, the global planning sub-module includes:
the task point set construction unit is used for determining the current pose of the target vehicle as a current task point, storing the current pose of the target vehicle into an initial task point set to form a target task point set, wherein the initial task point set comprises at least two preset task points;
the consistency judging unit is used for carrying out road consistency judgment on each two task points in the target task point set according to the target topological map and determining a consistency judging result;
and the planning result determining unit is used for determining a local path planning result between every two task points according to the consistency judging result.
Optionally, the planning result determining unit is specifically configured to:
when the consistency judging result is that the roads where the two task points are located are consistent, carrying out connectivity judgment on the two task points, and determining a local path planning result between the two task points according to the connectivity judging result;
when the consistency judging result is that the roads where the two task points are located are inconsistent and one of the task points is not a cross road point, correcting the target topological map, carrying out local path planning again according to the corrected target topological map, and determining a local path planning result between the two task points.
Optionally, the path planning device further includes:
the topological map correction module is used for correcting the target topological map when the road blocking signal is received and the current road condition is determined to be unable to pass according to the road blocking signal;
and the path re-planning module is used for re-planning the path of the traveling track of the target vehicle according to the corrected target topological map.
The path planning device provided by the embodiment of the invention can execute the path planning method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 shows a schematic diagram of an electronic device 40 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein. The electronic device 40 may also include a vehicle having processing computing capabilities.
As shown in fig. 5, the electronic device 40 includes at least one processor 41, and a memory communicatively connected to the at least one processor 41, such as a Read Only Memory (ROM) 42, a Random Access Memory (RAM) 43, etc., in which the memory stores a computer program executable by the at least one processor, and the processor 41 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 42 or the computer program loaded from the storage unit 48 into the Random Access Memory (RAM) 43. In the RAM43, various programs and data required for the operation of the electronic device 40 may also be stored. The processor 41, the ROM42 and the RAM43 are connected to each other via a bus 44. An input/output (I/O) interface 45 is also connected to bus 44.
Various components in electronic device 40 are connected to I/O interface 45, including: an input unit 46 such as a keyboard, a mouse, etc.; an output unit 47 such as various types of displays, speakers, and the like; a storage unit 48 such as a magnetic disk, an optical disk, or the like; and a communication unit 49 such as a network card, modem, wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 41 may be various general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 41 performs the various methods and processes described above, such as a path planning method.
In some embodiments, the path planning method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 48. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 40 via the ROM42 and/or the communication unit 49. When the computer program is loaded into RAM43 and executed by processor 41, one or more steps of the path planning method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to perform the path planning method in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of path planning, comprising:
acquiring a target satellite image, wherein the target satellite image is an image obtained by preprocessing an initial satellite image;
extracting and processing roads according to the target satellite images, and determining target road information;
establishing a topological relation among roads according to the target road information, and determining a target topological map;
and carrying out global path planning on the travelling track of the target vehicle according to the target topological map.
2. The method of claim 1, wherein the determining the target road information from the road extraction and processing of the target satellite image comprises:
extracting a road according to the target satellite image to obtain a road segment and road information of the road segment;
performing connection matching and correction processing on the road segments according to the road information so as to enable the road segments to be connected into an overall map, and determining the road information of the overall map;
and determining the road information of the overall map as target road information, wherein the target road information is in a set structural body format.
3. The method of claim 1, wherein establishing a topological relation between roads according to the target road information, and determining a target topological map, comprises:
constructing a topological map structure body and analyzing the target road information, wherein the topological map structure body comprises a map version, node vectors and edge vectors;
determining topological map nodes according to the road endpoint information in the target road information;
determining a topological map edge according to the road path information in the target road information;
And writing the road traffic attribute, the road cost value, the topological map nodes and the topological map edges in the target road information into the topological map structure body to determine a target topological map.
4. The method of claim 1, wherein the global path planning of the travel track of the target vehicle according to the target topology map comprises:
carrying out local path planning on each two task points in a task point set of a target vehicle according to the target topological map, and determining a local path planning result between each two task points;
and merging the local path planning results between every two task points, smoothing the merged paths, and determining the global path planning result of the travelling track of the target vehicle.
5. The method of claim 4, wherein the performing local path planning for each two task points in the target vehicle task point set according to the target topology map, and determining a local path planning result between each two task points, comprises:
determining the current pose of a target vehicle as a current task point, and storing the current pose of the target vehicle into an initial task point set to form a target task point set, wherein the initial task point set comprises at least two preset task points;
Carrying out road consistency judgment on every two task points in the target task point set according to the target topological map, and determining a consistency judgment result;
and determining a local path planning result between every two task points according to the consistency judging result.
6. The method of claim 5, wherein determining a local path planning result between each two task points based on the consistency determination result comprises:
when the consistency judging result is that the roads where the two task points are located are consistent, carrying out connectivity judgment on the two task points, and determining a local path planning result between the two task points according to the connectivity judging result;
when the consistency judging result is that the roads where the two task points are located are inconsistent and one of the task points is not a cross road point, correcting the target topological map, carrying out local path planning again according to the corrected target topological map, and determining a local path planning result between the two task points.
7. The method as recited in claim 1, further comprising:
when a road blocking signal is received and the current road condition is determined to be unable to pass according to the road blocking signal, correcting the target topological map;
And carrying out path re-planning on the travelling track of the target vehicle according to the corrected target topological map.
8. A path planning apparatus, comprising:
the image acquisition module is used for acquiring a target satellite image, wherein the target satellite image is an image obtained by preprocessing an initial satellite image;
the road information determining module is used for extracting and processing roads according to the target satellite images and determining target road information;
the topological map construction module is used for establishing a topological relation among roads according to the target road information and determining a target topological map;
and the path planning module is used for carrying out global path planning on the travelling track of the target vehicle according to the target topological map.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform a path planning method according to any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to perform a path planning method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310911117.4A CN116907530A (en) | 2023-07-24 | 2023-07-24 | Path planning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310911117.4A CN116907530A (en) | 2023-07-24 | 2023-07-24 | Path planning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116907530A true CN116907530A (en) | 2023-10-20 |
Family
ID=88354600
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310911117.4A Pending CN116907530A (en) | 2023-07-24 | 2023-07-24 | Path planning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116907530A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117765727A (en) * | 2023-12-12 | 2024-03-26 | 佛山职业技术学院 | Intelligent control system for automobile road surface planning |
-
2023
- 2023-07-24 CN CN202310911117.4A patent/CN116907530A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117765727A (en) * | 2023-12-12 | 2024-03-26 | 佛山职业技术学院 | Intelligent control system for automobile road surface planning |
| CN117765727B (en) * | 2023-12-12 | 2024-06-07 | 佛山职业技术学院 | Intelligent control system for automobile road surface planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11145073B2 (en) | Computer vision systems and methods for detecting and modeling features of structures in images | |
| KR102378859B1 (en) | Method of determining quality of map trajectory matching data, device, server and medium | |
| US10430659B2 (en) | Method and apparatus for urban road recognition based on laser point cloud, storage medium, and device | |
| CN111462275B (en) | Map production method and device based on laser point cloud | |
| CN111220993B (en) | Target scene positioning method and device, computer equipment and storage medium | |
| US20210302585A1 (en) | Smart navigation method and system based on topological map | |
| WO2020052530A1 (en) | Image processing method and device and related apparatus | |
| CN114812581B (en) | Cross-country environment navigation method based on multi-sensor fusion | |
| CN110543885B (en) | Method for interactively extracting high-resolution remote sensing image road and generating road network | |
| CN113989451B (en) | High-precision map construction method and device and electronic equipment | |
| CN116907530A (en) | Path planning method, device, equipment and storage medium | |
| CN114547866B (en) | Prefabricated part intelligent detection method based on BIM-unmanned aerial vehicle-mechanical dog | |
| CN114564545A (en) | System and method for extracting ship experience course based on AIS historical data | |
| CN115294293B (en) | Method for automatically compiling high-precision map road reference line based on low-altitude aerial photography result | |
| CN112991487A (en) | System for multithreading real-time construction of orthoimage semantic map | |
| WO2023155580A1 (en) | Object recognition method and apparatus | |
| CN115167433A (en) | Method and system for robot to independently explore environmental information by fusing global vision | |
| CN113592891A (en) | Unmanned vehicle passable area analysis method and navigation grid map manufacturing method | |
| CN117576652A (en) | Road object identification method and device, storage medium and electronic equipment | |
| US20210325196A1 (en) | Vector Tile Navigation | |
| CN113932796A (en) | High-precision map lane line generation method and device and electronic equipment | |
| CN114419338B (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN111127474B (en) | Airborne LiDAR point cloud assisted orthophoto mosaic line automatic selection method and system | |
| CN114418858A (en) | Remote sensing image embedding method, device, equipment and storage medium | |
| Kaur et al. | Automatic road detection of satellite images—A survey |
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 |