CN114518767A - Unmanned aerial vehicle three-dimensional path planning method based on oblique photography model - Google Patents
Unmanned aerial vehicle three-dimensional path planning method based on oblique photography model Download PDFInfo
- Publication number
- CN114518767A CN114518767A CN202011298469.XA CN202011298469A CN114518767A CN 114518767 A CN114518767 A CN 114518767A CN 202011298469 A CN202011298469 A CN 202011298469A CN 114518767 A CN114518767 A CN 114518767A
- Authority
- CN
- China
- Prior art keywords
- path
- unmanned aerial
- point
- aerial vehicle
- 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 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims description 9
- 230000004888 barrier function Effects 0.000 claims description 5
- 238000013138 pruning Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Processing Or Creating Images (AREA)
- Instructional Devices (AREA)
Abstract
The invention provides an unmanned aerial vehicle three-dimensional path planning method based on a slant photography model, which converts the slant photography model into an octree map, achieves the purposes of avoiding model errors and calculating errors by setting the resolution of the octree map and adjusting a multi-resolution path planning algorithm, and finally smoothes the obtained path to form a waypoint suitable for the unmanned aerial vehicle to fly. The method can accurately construct the scene map, can compress the memory occupation of the scene map, is suitable for the unmanned aerial vehicle to execute the flight task in the real scene, has quick and efficient path planning algorithm, can calculate the optimal route in a short time, and can avoid the risk of collision.
Description
Technical Field
The invention belongs to the technical field of path planning, and particularly relates to an unmanned aerial vehicle three-dimensional path planning method based on an oblique photography model.
Background
In recent years, civil unmanned aerial vehicles have become a focus of attention of many people, and research and application of unmanned aerial vehicles is no longer limited to detection and confrontation of military unmanned aerial vehicles in military operations, and more applications of civil unmanned aerial vehicles in various fields, such as aerial photography in the film and television industry, disaster monitoring in agriculture, security and protection in life, traffic patrol, and post-disaster search and rescue in emergencies. However, to accomplish the above task, the unmanned aerial vehicle must have the capability of autonomous flight. And path planning is the key link in unmanned aerial vehicle autonomous flight, and outstanding path planning algorithm is even in complicated flight environment, also can be perfect avoid the barrier, plans out a flight path that journey cost is little and satisfy unmanned aerial vehicle constraint condition, and to a great extent has reduced unmanned aerial vehicle self energy loss, can reach the target point fast simultaneously.
In the existing three-dimensional path planning method, a simple three-dimensional environment is usually built by using some conventional three-dimensional shapes, and the effect of a path planning algorithm is tested. And the shapes of the obstacles in the real scene are diversified, and the practicability of the path planning algorithm is difficult to show only by using a simple three-dimensional environment. There is therefore a need for a method that combines real geographic information with algorithms to truly meet the actual needs.
The oblique photography technology is a high and new technology developed in the international photogrammetry field in the last ten years, and acquires abundant high-resolution textures of the top surface and the side view of a building by synchronously acquiring images from a vertical angle, four oblique angles and five different visual angles. The method can truly reflect the ground and object conditions, acquire object texture information with high precision, and generate a real three-dimensional city model through advanced positioning, fusion, modeling and other technologies. The advantage of such a tilted photography model is that it provides rich and accurate environmental information.
In the prior art documents, as a method for dynamically planning the path of an unmanned aerial vehicle based on two-three-dimensional integration, patent publication No. CN110488871A uses an oblique photography model, but only uses height information of the model, the shape and space occupation of an obstacle are all represented in a fuzzy manner, and the environment is not accurately modeled. The oblique photography model occupies a large space, geographic information data are not easy to extract, three-dimensional optimal path planning of the unmanned aerial vehicle is difficult to achieve, and the effect of real-time high speed is achieved.
Disclosure of Invention
The present invention has been made to solve the above problems, and an object of the present invention is to provide a method for planning a three-dimensional path of an unmanned aerial vehicle based on a tilted photography model.
The invention provides an unmanned aerial vehicle three-dimensional path planning method based on a tilted photography model, which is used for planning the flight path of an unmanned aerial vehicle to avoid obstacles and has the characteristics that the method comprises the following steps: step 1, obtaining a three-dimensional oblique photography model; step 2, processing the three-dimensional oblique photography model by using a point cloud tool PCL to obtain a point cloud map, then processing the point cloud map by using an octree-based three-dimensional map creation tool Octmap, and converting the point cloud map into an octree map; step 3, planning a path on the octree map to obtain each path point, and further obtaining a planned path; and 4, pruning the planned path, and converting the pruned path into longitude and latitude coordinates according to the longitude and latitude coordinates of the central point of the oblique photography model and the coordinates of the octree map at the same position, namely generating a path point for the real actual flight of the unmanned aerial vehicle.
The unmanned aerial vehicle three-dimensional path planning method based on the oblique photography model provided by the invention can also have the following characteristics: in step 2, when the point cloud map is converted into the octree map, the maximum resolution of the octree map is adjusted according to the size and application requirements of the unmanned aerial vehicle, and then expansion processing of the barrier is completed, wherein the maximum resolution of the octree map is the side length of a minimum leaf node, and the side length is greater than the volume side length of the unmanned aerial vehicle.
The unmanned aerial vehicle three-dimensional path planning method based on the oblique photography model provided by the invention can also have the following characteristics: the path planning in step 3 adopts a multi-resolution a-x algorithm, and specifically includes the following substeps: step 3-1, selecting a starting point and an end point of the unmanned aerial vehicle flight on an octree map; step 3-2, detecting whether the starting point and the end point are idle, returning to the step 3-1 for re-selection when detecting that the starting point and the end point are not idle, and entering the next step if detecting that the starting point and the end point are idle; 3-3, finding out a barrier-free non-minimum leaf node closest to the starting point and a barrier-free non-minimum leaf node closest to the end point, and then taking the two minimum leaf nodes as the starting point and the end point of a path planning algorithm; 3-4, searching other nodes in the path according to the starting point and the end point obtained in the step 3-3, forming a bounding box by taking the current path point as the center, traversing octree nodes in the bounding box, finding out nodes which are free of obstacles and have side lengths larger than the minimum leaf node, detecting the position relation between the nodes and the current path point, selecting nodes connected with the current path point surface as neighbor nodes of the current path point, and screening out the path points of the next step to further obtain all path points in the path; and 3-5, traversing all the obtained path points to obtain a planned path.
The unmanned aerial vehicle three-dimensional path planning method based on the oblique photography model provided by the invention can also have the following characteristics: in step 4, the path is pruned by using a verloede algorithm.
Action and Effect of the invention
According to the unmanned aerial vehicle three-dimensional path planning method based on the oblique photography model, the adopted octree is a tree-shaped data structure used for describing a three-dimensional space, compression and storage of three-dimensional data are achieved, a convenient data base is provided for path planning, and therefore the method can be combined with the oblique photography technology to accurately depict the environment, so that the path planning result of the unmanned aerial vehicle meets the flight requirement of a real scene, and the safety of the unmanned aerial vehicle body is guaranteed. In addition, the path planning algorithm is combined with the octree, the search step length is not limited to a single scale, and the search step length is selected in a self-adaptive mode according to the data structure of the three-dimensional map, so that the multi-resolution path planning algorithm is formed. Therefore, the method provided by the invention is fast and efficient, greatly improves the search efficiency, can find the shortest collision-free path in a short time, and reduces the resource consumption of the unmanned aerial vehicle.
In conclusion, the three-dimensional path planning method of the unmanned aerial vehicle based on the oblique photography model accurately constructs a real scene according to the existing oblique photography model, combines the path planning algorithm with the constructed three-dimensional map to carry out rapid and efficient path planning, forms an airway point capable of guiding the unmanned aerial vehicle to execute a flight task, overcomes the defect that a simulation map in the traditional method is separated from the actual scene, improves the efficiency and accuracy of the path planning algorithm, and enables the actual demand of executing the flight task in the real scene to be met.
Drawings
Fig. 1 is a flow chart of the unmanned aerial vehicle three-dimensional path planning method based on oblique photography model of the present invention;
FIG. 2 is a schematic view of a tilted photography model of the present invention;
FIG. 3 is an octree map generated by the present invention;
FIG. 4 is a schematic diagram of the comparison of the generated path in the octree map and in the oblique photography model according to the present invention;
FIG. 5 is a schematic overall flow chart of the unmanned aerial vehicle three-dimensional path planning method based on oblique photography model with a path planning algorithm;
FIG. 6 is a schematic diagram of an unclipped path and a clipped path generated by the path planning of the present invention.
Detailed Description
In order to make the technical means and functions of the present invention easy to understand, the present invention is specifically described below with reference to the embodiments and the accompanying drawings.
Fig. 1 is a flow chart of the unmanned aerial vehicle three-dimensional path planning method based on oblique photography model.
As shown in fig. 1, the present invention provides a method for planning a three-dimensional path of an unmanned aerial vehicle based on a tilted photography model, for planning a flight path of the unmanned aerial vehicle to avoid an obstacle, comprising the following steps:
FIG. 2 is a schematic diagram of a tilted photography model of the present invention.
Step 1, a three-dimensional oblique photography model is obtained, as shown in fig. 2.
Fig. 3 is an octree map generated by the present invention, fig. 4 is a schematic diagram of a comparison of a generated path in the octree map and in an oblique photography model in an embodiment of the present invention, in which fig. 4(a) is a schematic diagram of a generated path in the octree map, and fig. 4(b) is a schematic diagram of a generated path in an oblique photography model.
And 2, processing the three-dimensional oblique photography model by using a point cloud tool PCL to obtain a point cloud map, then processing the point cloud map by using an octree-based three-dimensional map creation tool Octmap, and converting the point cloud map into an octree map, as shown in figures 3 and 4.
In the invention, although the oblique photography model has strong authenticity and is more delicate in scene depiction, the oblique photography model is not beneficial to code reading. Therefore, the model is converted into an octree map, and the multi-resolution characteristic and the data compression characteristic of the octree are utilized to carry out three-dimensional path planning. In the process, a point cloud tool PCL is needed, the model is firstly converted into a point cloud map with a format of pcd, then the point cloud map is converted into an octree map by using an octree-based three-dimensional map creation tool Octmap, and the octree resolution is adjusted according to the size of the unmanned aerial vehicle and the application requirement.
In addition, when the point cloud map is converted into an octree map, the maximum resolution of the octree map is adjusted according to the size and application requirements of the unmanned aerial vehicle, and then expansion processing of the barrier is completed, wherein the maximum resolution of the octree map is the side length of a minimum leaf node, and the side length is larger than the volume side length of the unmanned aerial vehicle.
And 3, planning a path on the octree map to obtain each path point, and further obtaining the planned path.
Fig. 5 is a schematic overall flow chart of the unmanned aerial vehicle three-dimensional path planning method based on oblique photography model and provided with a path planning algorithm.
In the present invention, the path planning uses a multi-resolution a-algorithm, as shown in fig. 5, specifically includes the following sub-steps:
and 3-1, selecting a starting point and an end point of the unmanned aerial vehicle flight on the octree map.
And 3-2, detecting whether the starting point and the end point are idle, returning to the step 3-1 for re-selection when detecting that the starting point and the end point are not idle, and entering the next step if detecting that the starting point and the end point are idle.
And 3-3, finding out a non-obstacle non-minimum leaf node closest to the starting point and a non-obstacle non-minimum leaf node closest to the end point, and then taking the two minimum leaf nodes as the starting point and the end point of a path planning algorithm.
Fig. 6 is a schematic diagram of an unclipped path generated by the path planning of the present invention and a clipped path, where fig. 6(a) is a schematic diagram of an unclipped path generated by the path planning, and fig. 6(b) is a schematic diagram of a clipped path.
And 3-4, searching other nodes in the path according to the starting point and the end point obtained in the step 3-3, forming a bounding box by taking the current path point as the center, traversing octree nodes in the bounding box, finding out nodes which are free of obstacles and have side lengths larger than the minimum leaf node, detecting the position relation between the nodes and the current path point, selecting nodes connected with the surface of the current path point as neighbor nodes of the current path point, and screening out the path points of the next step to further obtain all the path points in the path.
And 3-5, traversing all the obtained path points to obtain the planned path, as shown in fig. 6 (a).
In the above algorithm, the algorithm body framework is used as a, and the cost function f (n) in the algorithm is expressed as follows: f (n) ═ G (n) + H (n), n denotes the current point, H is set to the euclidean distance between the current point and the end point, G denotes the actual path distance from the start point to the current point, a is also correspondingly converted to multi-resolution a since the application scene is an octree map, and the search step is no longer fixed.
And 4, as shown in fig. 6(b), pruning the planned path, and then converting the pruned path into longitude and latitude coordinates according to the longitude and latitude coordinates of the central point of the oblique photography model and the coordinates of the octree map at the same position, namely generating a path point for the real actual flight of the unmanned aerial vehicle.
In the invention, the route is pruned by adopting a Florede algorithm, and redundant route points between two points are deleted if the two points can pass through without obstacles, so that a smooth and efficient route is formed, and finally, route points suitable for the flight of the unmanned aerial vehicle are generated, thereby reducing the resource consumption of the unmanned aerial vehicle.
The embodiment is as follows:
the present embodiment is specifically described by taking an example in which an obj-format oblique photography model is converted into an octree map.
1. Obtaining a three-dimensional oblique photography model
2. Map model conversion
Firstly, processing an oblique photography model by using a point cloud tool PCL to obtain a point cloud map, and then converting the point cloud map into an octree map by using an octree-based three-dimensional map creation tool Octmap. The original obj model is 63MB, the actual geographic size is 150m × 150m × 60m, the converted octree map is only 64KB, the storage space is greatly reduced, and the edge details of the map are well preserved. In the generation of the octree map, the depth is set to be 16 layers, the size of the octree is 150m multiplied by 60m, the point cloud is traversed, octree nodes at positions with the point cloud are set to be occupied, and the rest are set to be idle. The maximum resolution is 2m, and the volume of the obstacle is expanded outwards by utilizing the structural characteristics of the octree, which is equivalent to the expansion treatment of all the obstacles. The unmanned aerial vehicle can keep away from the barrier when flying according to the planned route, so that the error of the map generated in the manufacturing process can be avoided to a certain extent.
3. Path planning
(1) And when the algorithm is initialized, detecting whether the positions of the starting point and the end point are free, and returning to prompt reselection if the positions of the starting point and the end point are occupied. And if the node is idle, finding an idle node with the layer number less than 16 closest to the starting point and an idle node with the layer number less than 16 closest to the end point, and taking the two secondary leaflet nodes as the starting point and the end point of the path planning algorithm. Therefore, the path points can be selected on the nodes with larger side length, and the calculation efficiency is improved.
(2) And when searching for the neighbor node, forming a cube bounding box by taking the current path point as the center, traversing the octree nodes in the bounding box, finding out idle nodes with the number of layers less than 16, detecting the position relation between the nodes and the current point, and selecting the nodes connected with the current point surface as the neighbor nodes of the current point. The screening mode is to calculate the difference value of the current point and the three coordinates of the center position of the node, if the difference value of only one coordinate is equal to half of the sum of the side lengths of the two nodes, the adjacent mode of the current point is that the current point is connected with the surface, wherein, the formula of the side length of the bounding box is as follows: the side length is equal to the current node side length × 0.5+ the maximum resolution node side length × 0.5.
After the algorithm is operated, a path containing a plurality of waypoints can be obtained, and the unmanned aerial vehicle can be ensured to pass through between every two waypoints without collision.
4. Path pruning and coordinate transformation
(1) The path points obtained by path planning are bent, so that the flight time and resource consumption of the unmanned aerial vehicle are increased, and the path points are screened out. Assuming that the obtained path points S0, S1, S2 … … traverse downward from the starting point S0 as the current point to S1, a line is established between S0 and S1, the idle states of the octree nodes on the line are queried, if all the nodes are idle, the smooth traffic is indicated, and then a line is established between S0 and S2 and the state is queried, and so on. Until a query arrives at an occupied node between S0 and a point (e.g., S4), all path points between S0 and the last path point (S3) of the point are deleted, and the point (S4) is used as the current point and then the query is traversed downward until the end point. This results in an unobstructed path with a minimum of waypoints.
(2) And performing coordinate conversion on the obtained path points according to the longitude and latitude coordinates of the central point of the oblique photography model and the coordinates of the same position of the octree map to generate the path points which can enable the unmanned aerial vehicle to actually fly.
Effects and effects of the embodiments
According to the unmanned aerial vehicle three-dimensional path planning method based on the oblique photography model, the adopted octree is a tree-shaped data structure used for describing a three-dimensional space, compression and storage of three-dimensional data are achieved, a convenient data base is provided for path planning, so that the environment can be accurately depicted by combining the octree with the oblique photography technology, the path planning result of the unmanned aerial vehicle meets the flight requirement of a real scene, and the safety of the unmanned aerial vehicle body is guaranteed. In addition, the path planning algorithm is combined with the octree, the search step length is not limited to the search step length of a single scale, but the search step length is selected in a self-adaptive mode according to the data structure of the three-dimensional map, and the multi-resolution path planning algorithm is formed. Therefore, the method of the embodiment is fast, efficient and greatly improves the searching efficiency, can find the shortest collision-free path in a short time, and reduces the resource consumption of the unmanned aerial vehicle.
In summary, according to the three-dimensional path planning method for the unmanned aerial vehicle based on the oblique photography model, the actual scene is accurately constructed according to the existing oblique photography model, the path planning algorithm is combined with the constructed three-dimensional map, the path planning is rapidly and efficiently carried out, and the route points capable of guiding the unmanned aerial vehicle to execute the flight mission are formed.
The above embodiments are preferred examples of the present invention, and are not intended to limit the scope of the present invention.
Claims (4)
1. A three-dimensional path planning method of an unmanned aerial vehicle based on a tilted photography model is used for planning the flight path of the unmanned aerial vehicle to avoid obstacles, and is characterized by comprising the following steps:
step 1, obtaining a three-dimensional oblique photography model;
step 2, processing the three-dimensional oblique photography model by using a point cloud tool PCL to obtain a point cloud map, then processing the point cloud map by using an octree-based three-dimensional map creation tool Octmap, and converting the point cloud map into an octree map;
step 3, planning a path on the octree map to obtain each path point, and further obtaining a planned path;
and 4, pruning the planned path, and converting the pruned path into longitude and latitude coordinates according to the longitude and latitude coordinates of the central point of the oblique photography model and the coordinates of the octree map at the same position, namely generating a path point for the real actual flight of the unmanned aerial vehicle.
2. The oblique photography model-based unmanned aerial vehicle three-dimensional path planning method according to claim 1, wherein:
wherein, in the step 2, when the point cloud map is converted into the octree map, the maximum resolution of the octree map is adjusted according to the size and the application requirements of the unmanned aerial vehicle, so as to complete the expansion treatment of the barrier,
the maximum resolution of the octree map is the side length of the smallest leaf node, and the side length is larger than the volume side length of the unmanned aerial vehicle.
3. The oblique photography model-based unmanned aerial vehicle three-dimensional path planning method according to claim 1, wherein:
the path planning in step 3 adopts a multi-resolution a-x algorithm, and specifically includes the following sub-steps:
step 3-1, selecting a starting point and an end point of the unmanned aerial vehicle flight on the octree map;
3-2, detecting whether the starting point and the end point are idle, returning to the step 3-1 for reselection when non-idle is detected, and entering the next step if idle is detected;
3-3, finding out a non-obstacle non-minimum leaf node which is closest to the starting point and a non-obstacle non-minimum leaf node which is closest to the end point, and then taking the two minimum leaf nodes as the starting point and the end point of a path planning algorithm;
3-4, searching other nodes in the path according to the starting point and the end point obtained in the step 3-3, forming a bounding box by taking the current path point as the center, traversing octree nodes in the bounding box, finding out nodes which are free of obstacles and have side lengths larger than the minimum leaf node, detecting the position relationship between the nodes and the current path point, selecting nodes connected with the surface of the current path point as neighbor nodes of the current path point, and screening out the path points of the next step to further obtain all the path points in the path;
and 3-5, traversing all the obtained path points to obtain the planned path.
4. The oblique photography model-based unmanned aerial vehicle three-dimensional path planning method according to claim 1, wherein:
in the step 4, the path is pruned by using a verloede algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011298469.XA CN114518767A (en) | 2020-11-19 | 2020-11-19 | Unmanned aerial vehicle three-dimensional path planning method based on oblique photography model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011298469.XA CN114518767A (en) | 2020-11-19 | 2020-11-19 | Unmanned aerial vehicle three-dimensional path planning method based on oblique photography model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114518767A true CN114518767A (en) | 2022-05-20 |
Family
ID=81595056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011298469.XA Pending CN114518767A (en) | 2020-11-19 | 2020-11-19 | Unmanned aerial vehicle three-dimensional path planning method based on oblique photography model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114518767A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001033271A (en) * | 1999-06-30 | 2001-02-09 | Gya Min-Chun | Flight route plan, topography-avoidance and status recognition system, for general purpose aircraft |
| CN106017472A (en) * | 2016-05-17 | 2016-10-12 | 成都通甲优博科技有限责任公司 | Global path planning method, global path planning system and unmanned aerial vehicle |
| CN106802668A (en) * | 2017-02-16 | 2017-06-06 | 上海交通大学 | Based on the no-manned plane three-dimensional collision avoidance method and system that binocular is merged with ultrasonic wave |
| CN107816999A (en) * | 2017-09-25 | 2018-03-20 | 华南理工大学 | A kind of unmanned boat navigation path contexture by self method based on ant group algorithm |
| CN107924188A (en) * | 2016-07-04 | 2018-04-17 | 深圳市大疆创新科技有限公司 | Flight path planning, control method and the system of a kind of unmanned plane |
| CN109282822A (en) * | 2018-08-31 | 2019-01-29 | 北京航空航天大学 | Construct storage medium, the method and apparatus of navigation map |
| CN109697753A (en) * | 2018-12-10 | 2019-04-30 | 智灵飞（北京）科技有限公司 | A kind of no-manned plane three-dimensional method for reconstructing, unmanned plane based on RGB-D SLAM |
| CN109900276A (en) * | 2019-04-01 | 2019-06-18 | 河北工业大学 | The real-time emergency route planing method in station based on point-line-surface barrier model construction |
| CN109974693A (en) * | 2019-01-31 | 2019-07-05 | 中国科学院深圳先进技术研究院 | Unmanned plane localization method, device, computer equipment and storage medium |
| CN110672100A (en) * | 2019-09-17 | 2020-01-10 | 南京师范大学 | Rapid terrain path planning parallelization method based on multi-resolution |
| CN111880573A (en) * | 2020-07-31 | 2020-11-03 | 电子科技大学 | Four-rotor autonomous navigation method based on visual inertial navigation fusion |
-
2020
- 2020-11-19 CN CN202011298469.XA patent/CN114518767A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001033271A (en) * | 1999-06-30 | 2001-02-09 | Gya Min-Chun | Flight route plan, topography-avoidance and status recognition system, for general purpose aircraft |
| CN106017472A (en) * | 2016-05-17 | 2016-10-12 | 成都通甲优博科技有限责任公司 | Global path planning method, global path planning system and unmanned aerial vehicle |
| CN107924188A (en) * | 2016-07-04 | 2018-04-17 | 深圳市大疆创新科技有限公司 | Flight path planning, control method and the system of a kind of unmanned plane |
| CN106802668A (en) * | 2017-02-16 | 2017-06-06 | 上海交通大学 | Based on the no-manned plane three-dimensional collision avoidance method and system that binocular is merged with ultrasonic wave |
| CN107816999A (en) * | 2017-09-25 | 2018-03-20 | 华南理工大学 | A kind of unmanned boat navigation path contexture by self method based on ant group algorithm |
| CN109282822A (en) * | 2018-08-31 | 2019-01-29 | 北京航空航天大学 | Construct storage medium, the method and apparatus of navigation map |
| CN109697753A (en) * | 2018-12-10 | 2019-04-30 | 智灵飞（北京）科技有限公司 | A kind of no-manned plane three-dimensional method for reconstructing, unmanned plane based on RGB-D SLAM |
| CN109974693A (en) * | 2019-01-31 | 2019-07-05 | 中国科学院深圳先进技术研究院 | Unmanned plane localization method, device, computer equipment and storage medium |
| CN109900276A (en) * | 2019-04-01 | 2019-06-18 | 河北工业大学 | The real-time emergency route planing method in station based on point-line-surface barrier model construction |
| CN110672100A (en) * | 2019-09-17 | 2020-01-10 | 南京师范大学 | Rapid terrain path planning parallelization method based on multi-resolution |
| CN111880573A (en) * | 2020-07-31 | 2020-11-03 | 电子科技大学 | Four-rotor autonomous navigation method based on visual inertial navigation fusion |
Non-Patent Citations (1)
| Title |
|---|
| 黄明吉等: "《数字化成形与数字化成形与先进制造技术》", vol. 978, 31 August 2020, 北京：机械工业出版社, pages: 44 - 53 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111928862B (en) | Method for on-line construction of semantic map by fusion of laser radar and visual sensor | |
| CN109828607B (en) | Unmanned aerial vehicle path planning method and system for irregular obstacles | |
| CN102426019B (en) | Unmanned aerial vehicle scene matching auxiliary navigation method and system | |
| CN111402339B (en) | Real-time positioning method, device, system and storage medium | |
| CN105865449A (en) | Laser and vision-based hybrid location method for mobile robot | |
| CN103900573B (en) | A kind of underwater research vehicle multiple constraint Route planner based on S57 standard electronic sea chart | |
| CN113776534B (en) | Unmanned aerial vehicle three-dimensional time-varying airspace navigation method based on three-dimensional subdivision grid | |
| CN110969648B (en) | 3D target tracking method and system based on point cloud sequence data | |
| US20230046926A1 (en) | 3d building generation using topology | |
| CN114509065B (en) | Map construction method, system, vehicle terminal, server and storage medium | |
| CN113985429A (en) | Unmanned aerial vehicle environment scanning and reconstructing method based on three-dimensional laser radar | |
| CN113741503B (en) | Autonomous positioning unmanned aerial vehicle and indoor path autonomous planning method thereof | |
| Li et al. | Robust localization for intelligent vehicles based on compressed road scene map in urban environments | |
| CN113763551A (en) | Point cloud-based rapid repositioning method for large-scale mapping scene | |
| CN115371662A (en) | Static map construction method for removing dynamic objects based on probability grid | |
| Wu et al. | A non-rigid hierarchical discrete grid structure and its application to UAVs conflict detection and path planning | |
| CN113721254A (en) | Vehicle positioning method based on road fingerprint space incidence matrix | |
| CN113838129A (en) | Method, device and system for obtaining pose information | |
| CN114518767A (en) | Unmanned aerial vehicle three-dimensional path planning method based on oblique photography model | |
| CN114543788B (en) | Multi-layer global perception map construction method and system universal to structural unstructured environment | |
| CN112146660B (en) | Indoor map positioning method based on dynamic word vector | |
| CN111486847B (en) | Unmanned aerial vehicle navigation method and system | |
| KR20230026916A (en) | 3d mapping method with time series information using drone | |
| CN115544189A (en) | Semantic map updating method, device and computer storage medium | |
| Feld et al. | Approximated environment features with application to trajectory annotation |
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 |