CN107478231A - Unmanned plane Route Planning Algorithm based on polygon obstacle detection - Google Patents
Unmanned plane Route Planning Algorithm based on polygon obstacle detection Download PDFInfo
- Publication number
- CN107478231A CN107478231A CN201710683093.6A CN201710683093A CN107478231A CN 107478231 A CN107478231 A CN 107478231A CN 201710683093 A CN201710683093 A CN 201710683093A CN 107478231 A CN107478231 A CN 107478231A
- Authority
- CN
- China
- Prior art keywords
- point
- polygon
- route
- unmanned plane
- obstacle
- 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
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
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
Abstract
The invention provides a kind of unmanned plane Route Planning Algorithm based on polygon obstacle detection, is broadly divided into connected graph and establishes and two big processes of Route Generation.The present invention draws preliminary bypass route to doing recurrence obstacle detection between point of contact based on doing the operation at point of contact for the original polygon of barrier from point, for starting point, optimizes route result plus convex closure operation is locally done for polygon.Generate the route of accurate global optimum.In the unmanned plane map test of various polygon barrier zones is currently included, the route of accurate global optimum can be produced, and solve route depression problem.A kind of unmanned plane Route Planning Algorithm based on polygon obstacle detection provided by the invention, however it is not limited to the route planning of unmanned plane.Can also arbitrarily it be selected according to scene for point of contact operation corresponding to concrete shape.
Description
Technical field
The present invention relates to unmanned plane route to advise technical field, and in particular to a kind of unmanned plane based on polygon obstacle detection
Route Planning Algorithm.
Background technology
Popularized with development and the market of unmanned air vehicle technique, unmanned plane is being taken photo by plane, inspection, agricultural plant protection, environmental protection, rescued after calamity
The civil area such as help also to be widely used.But the flight line in reality for unmanned plane has many complicated systems
, once be strayed into not only to unmanned plane in itself
It can cause to damage, and the security risk of personnel can be caused or even directly contribute accident.Therefore in unmanned machine operation preplanning one
Safe and global optimum the route that bar avoids all sensitive areas turns into urgent demand.
The route planning of unmanned plane during flying has many restraining factors.Except unmanned plane kinematics itself and mobility limit
In addition, the security in path restricts the actual environment being also from numerous and complicated, such as building, landform, trees, no-fly zone obstacle
Thing.Traditional unmanned plane Route Planning Algorithm has cell decomposition, and environment is broken down into the unit not being superimposed mutually, and connection is adjacent
Free location obtain feasible path.Free location is exactly the unit not intersected with any barrier, non-conterminous barrier
Isolated by some free locations.Then the free location sequence that P Passable is searched for by A* searching algorithms obtains path.The party
Method problem is first, and polygon is divided into unit can cause many areas that can be flown originally in no-fly zone periphery to be ensphered
No-fly area.Second, easily cause zigzag route.Thus accuracy is poor.Another is more commonly used in addition to cell decomposition
For Artificial Potential Field Method, environment is represented as an Artificial Potential Field, including gravitational field caused by target and barrier in this method
Caused repulsion field.There is the maximal potential bit line of the function of a continuous domain in the path obtained by potential field method.The problem of this method, exists
In extremely easy generation locally optimal solution but it is not the result of globally optimal solution.
All it is mostly dynamic Route Planning Algorithm in the technology of existing proposition, the road of global optimum generally can not be produced
Line.Part can be produced in global optimization's Route Planning Algorithm, mostly by barrier with external circle, boundary rectangle or with singly
Member splits barrier.These methods are all quite inaccurate, in the scene of reality, if the region of obstacle covering is close,
Cause very much continuous multiple barrier zones to be linked to be in maximum probability and very big a piece of be all unable to programme path.Elements method can also cause route knot
The excessive zigzag of fruit.These can all cause the experience being mutually on duty.
The content of the invention
The shortcomings that existing for prior art, the present invention is based on the behaviour for doing point of contact for the original polygon of barrier from point
Make, draw preliminary bypass route to recurrence obstacle detection is done between point of contact for starting point, convex closure is locally done plus for polygon
Operation optimizes route result.Generate the route of accurate global optimum.Currently including various polygon barrier zones
In the test of unmanned plane map, the route of accurate global optimum can be produced, and solve the technical problem of route depression.
The technical solution adopted by the present invention is：
A kind of unmanned plane Route Planning Algorithm based on polygon obstacle detection, including connected graph establish and Route Generation and
Optimization；
The connected graph is established and specifically includes following steps：
Step 11, all obstacle polygon datas in environment are loaded；
Step 12, if do not intersected for starting point o, terminal d line with any barrier zone, step 16 is skipped to, will
Starting point o, terminal d line add connected graph；
Step 13, chosen in all barrier zones run through for starting point o, terminal d lines near starting point o region,
Make tangent line operation to it from starting point o and terminal d respectively, each produce two point of contacts, be designated as to1, to2, td1, td2；
Step 14, the to1 in of obstacle polygon is added into connection between td1 and when to2 is to all between td2
Figure；
Step 15, (o, to1), (o, to2), (td1, d), (td2, d) are opened as beginning and end from step 12 successively
Establish vertical subgraph；
Step S16, starting point o, terminal d are added into connected graph；
The Route Generation and optimization specifically include following steps：
Step S21, establishes cost function, chooses the route of minimum cost；
Step S22, do local convex closure for the point in route on each barrier zone and handle.
Further, the cost function in the step S21 is used as parameter using length, angle of turn.
Further, the point of contact t of starting point o to obstacle polygon is defined as：Summits of the ray ot just through obstacle polygon
Or side.
Further, it is as follows to choose process for point of contact：
The summit of all obstacle polygons is traveled through, reservation meets the summit that point of contact defines；
Retain the summit farthest apart from starting point in conllinear point of contact.
Further, local convex closure processing specifically includes following steps in the step S22：
Step S221, the summit of deviation route on an obstacle polygon is added at random, as auxiliary magnet；
Step S222, to the point of all vertex culling depressions to be optimized；
Step S223, remove auxiliary magnet；
Step S224, remaining summit by original number sorting and is added into route result.
Further, the point of depression is removed in the step S222 using Graham ' s scan processes.
Further, the detection after optimization for remaining obstacle of periphery must be added during the Graham ' s scan, with
And the limitation that the first and last point on summit to be optimized does not simplify.
The beneficial effects of the present invention are locally do convex closure operation to polygon and optimize route result, it is accurate to generate
Global optimum route.
Brief description of the drawings
Fig. 1 is a kind of unmanned plane Route Planning Algorithm main procedure based on polygon obstacle detection.
Fig. 2 is that Route Generation and optimum results are shown.
Fig. 3 is polygon point of contact embodiment.
Fig. 4 is route result optimal enforcement example.
Embodiment
The invention provides a kind of unmanned plane Route Planning Algorithm based on detection of obstacles：1) on starting and terminal point line
Near the barrier zone of starting point, point of contact operation is done to it with starting and terminal point respectively；Using the point of contact of starting point and starting point as new
Starting and terminal point and using terminal point of contact to terminal as new beginning and end, does the algorithm main body process of recursive programming.2) from
Point-to-points side shape barrier zone does point of contact operation.3) the polygon part convex closure optimization operation based on virtual auxiliary magnet.
Hereinafter, the present invention is further elaborated in conjunction with the accompanying drawings and embodiments.
1) unmanned plane Route Planning Algorithm main procedure
Fig. 1 is a kind of flow chart of the unmanned plane Route Planning Algorithm main procedure based on detection of obstacles of the present invention, mainly
It is divided into connected graph to establish and two big processes of Route Generation and optimization.
The connected graph from origin-to-destination is initially set up, step is as follows：
Step S11, all obstacle polygon datas in environment are loaded first.
Step S12, if do not intersected for starting point o, terminal d lines with any barrier zone, skip to step 16, by o,
D line adds connected graph.
Step S13, choose in all barrier zones run through for starting point o terminal d lines near the region of starting point, point
It is not made from o and d tangent line operation be divided to each generation two point of contacts, by they be designated as to1, to2, td1, td2 (wherein to1,
Td1 is in the homonymy of od lines, and to2, td2 is in opposite side).
Step S14, the to1 in of barrier zone polygon is added between td1 and when to2 is to all between td2
Connected graph.
Step S15, (o, to1), (o, to2), (td1, d), (td2, d) are opened as beginning and end from step 2 successively
Establish vertical subgraph.
Step S16, o, d are added into connected graph.
So far connected graph, which is established, completes, and next generates and optimizes route, step is as follows：
Step S21：Cost function is used as with length, angle of turn etc., minimum cost is chosen with the method for Dynamic Programming
Route.
Step S22, do local convex closure for the point in route on each barrier zone and handle.
Fig. 2 is that the result after Route Generation and optimization is shown.
2) operated from point-to-points side Xing Zuo point of contacts
It is defined as the point of contact t of a point o to the polygon outside polygon A：Ray ot just through polygon A summit or
Side.
As shown in figure 3, point of contact to1 draws a ray just through the summit from o to it, and o can then be worn to to2 institutes injection line
Cross the side of a polygon.They are all point of contacts.
Choosing point of contact process in the specific implementation is：The summit of all polygons is traveled through, aperture, which closes, states point of contact definition
Summit.Retain the summit farthest apart from starting point in conllinear point of contact.
3) route result optimizes
In actual environment, the polygon of barrier zone is possible to include flexuose concave polygon, it is necessary to for route
Do local convex closure processing.Depression such as route segment 0-13 in Fig. 4 causes route result experience too poor, carries out the place of local convex closure
Result is point [0,1,8,9,13] after reason.
Optimizing main process is：
Step S221, the summit for deviateing this section of route on a polygon is added at random, as auxiliary magnet (such as Fig. 4 midpoints
14)。
Step S222, all these summits to be optimized are removed with the point of depression with Graham ' s scan processes, during
The detection after optimization for remaining obstacle of periphery, and the limitation that first and last point in summit to be optimized does not simplify must be added.
Step S223, remove auxiliary magnet (14).
Step S224, press original number sorting by remaining and add route result.
In the present invention to reach the optimal impact of performance, the C++ for being preferably based on Linux platform is realized.
Although the present invention is disclosed as above with preferred embodiment, it is not for limiting the present invention, any this area
Technical staff without departing from the spirit and scope of the present invention, may be by the methods and technical content of the disclosure above to this hair
Bright technical scheme makes possible variation and modification, therefore, every content without departing from technical solution of the present invention, according to the present invention
Any simple modifications, equivalents, and modifications made to above example of technical spirit, belong to technical solution of the present invention
Protection domain.
Claims (7)
- A kind of 1. unmanned plane Route Planning Algorithm based on polygon obstacle detection, it is characterised in that including connected graph establish and Route Generation and optimization；The connected graph is established and specifically includes following steps：Step 11, all obstacle polygon datas in environment are loaded；Step 12, if do not intersected for starting point o, terminal d line with any barrier zone, step 16 is skipped to, by starting point O, terminal d line adds connected graph；Step 13, chosen in all barrier zones run through for starting point o, terminal d lines near starting point o region, difference Make tangent line operation to it from starting point o and terminal d, each produce two point of contacts, be designated as to1, to2, td1, td2；Step 14, the to1 in of obstacle polygon is added into connected graph between td1 and when to2 is to all between td2；Step 15, (o, to1), (o, t02), (td1, d), (td2, d) are built as beginning and end since step 12 successively Vertical subgraph；Step S16, starting point o, terminal d are added into connected graph；The Route Generation and optimization specifically include following steps：Step S21, establishes cost function, chooses the route of minimum cost；Step S22, do local convex closure for the point in route on each barrier zone and handle.
- A kind of 2. unmanned plane Route Planning Algorithm based on polygon obstacle detection as claimed in claim 1, it is characterised in that Cost function in the step S21 is used as parameter using length, angle of turn.
- A kind of 3. unmanned plane Route Planning Algorithm based on polygon obstacle detection as claimed in claim 1, it is characterised in that The point of contact t of starting point o to obstacle polygon is defined as：Summits or side of the ray ot just through obstacle polygon.
- A kind of 4. unmanned plane Route Planning Algorithm based on polygon obstacle detection as claimed in claim 3, it is characterised in that It is as follows that process is chosen at point of contact：The summit of all obstacle polygons is traveled through, reservation meets the summit that point of contact defines；Retain the summit farthest apart from starting point in conllinear point of contact.
- A kind of 5. unmanned plane Route Planning Algorithm based on polygon obstacle detection as claimed in claim 4, it is characterised in that Local convex closure processing specifically includes following steps in the step S22：Step S221, the summit of deviation route on an obstacle polygon is added at random, as auxiliary magnet；Step S222, to the point of all vertex culling depressions to be optimized；Step S223, remove auxiliary magnet；Step S224, remaining summit by original number sorting and is added into route result.
- A kind of 6. unmanned plane Route Planning Algorithm based on polygon obstacle detection as claimed in claim 5, it is characterised in that The point of depression is removed in the step S222 using Graham ' s scan processes.
- A kind of 7. unmanned plane Route Planning Algorithm based on polygon obstacle detection as claimed in claim 6, it is characterised in that The detection after optimization for remaining obstacle of periphery, and the head on summit to be optimized must be added during the Graham ' s scan The not simplified limitation of end point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710683093.6A CN107478231A (en) | 2017-08-10 | 2017-08-10 | Unmanned plane Route Planning Algorithm based on polygon obstacle detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710683093.6A CN107478231A (en) | 2017-08-10 | 2017-08-10 | Unmanned plane Route Planning Algorithm based on polygon obstacle detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107478231A true CN107478231A (en) | 2017-12-15 |
Family
ID=60600081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710683093.6A Pending CN107478231A (en) | 2017-08-10 | 2017-08-10 | Unmanned plane Route Planning Algorithm based on polygon obstacle detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107478231A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108716919A (en) * | 2018-05-25 | 2018-10-30 | 南京航空航天大学 | Plant protection drone path planning method based on arbitrary polygon clear area |
| CN109033966A (en) * | 2018-06-25 | 2018-12-18 | 北京嘀嘀无限科技发展有限公司 | Detour detection model training method and device, and detour detection method and device |
| CN109634284A (en) * | 2019-01-15 | 2019-04-16 | 安徽工程大学 | The paths planning method of robot actuating station avoidance based on nested three points of algorithms |
| CN109828607A (en) * | 2019-04-03 | 2019-05-31 | 南京航空航天大学 | A kind of unmanned plane paths planning method and system towards irregular slalom object |
| CN110849373A (en) * | 2019-11-28 | 2020-02-28 | 中国航空工业集团公司沈阳飞机设计研究所 | Man-machine real-time airway re-planning method |
| CN111830983A (en) * | 2019-08-06 | 2020-10-27 | 清华大学 | Multi-agent group system navigation and obstacle avoidance method and device in dynamic environment |
| CN112148033A (en) * | 2020-10-22 | 2020-12-29 | 广州极飞科技有限公司 | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium |
| CN112379692A (en) * | 2020-11-23 | 2021-02-19 | 广州极飞科技有限公司 | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium |
| CN113190031A (en) * | 2021-04-30 | 2021-07-30 | 成都思晗科技股份有限公司 | Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle |
| CN113220027A (en) * | 2021-05-08 | 2021-08-06 | 北京大学 | Concave polygon area unmanned aerial vehicle flight path planning based on remote sensing task |
| CN114637305A (en) * | 2022-02-15 | 2022-06-17 | 山东省计算中心（国家超级计算济南中心） | Unmanned aerial vehicle shortest path planning method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101430732A (en) * | 2008-12-04 | 2009-05-13 | 上海交通大学 | Engine pipe laying system |
| CN101833699A (en) * | 2009-03-12 | 2010-09-15 | 北京博懋易通科技有限公司 | Heuristic route segment path-finding method for ship route design |
| CN103471592A (en) * | 2013-06-08 | 2013-12-25 | 哈尔滨工程大学 | Multi-unmanned aerial vehicle route planning method based on bee colony collaborative foraging algorithm |
| CN105929848A (en) * | 2016-06-28 | 2016-09-07 | 南京邮电大学 | Track planning method for multi-unmanned plane system in three-dimensional environment |
| WO2016164094A1 (en) * | 2015-04-07 | 2016-10-13 | Raytheon Company | Automated sensor platform routing and tracking for observing a region of interest while avoiding obstacles |
| CN106289255A (en) * | 2016-07-22 | 2017-01-04 | 云南师范大学 | Based on around barrier path planning across the trajectory bearing calibration of naval vessel, land |
| CN106846926A (en) * | 2017-04-13 | 2017-06-13 | 电子科技大学 | A kind of no-fly zone unmanned plane method for early warning |
-
2017
- 2017-08-10 CN CN201710683093.6A patent/CN107478231A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101430732A (en) * | 2008-12-04 | 2009-05-13 | 上海交通大学 | Engine pipe laying system |
| CN101833699A (en) * | 2009-03-12 | 2010-09-15 | 北京博懋易通科技有限公司 | Heuristic route segment path-finding method for ship route design |
| CN103471592A (en) * | 2013-06-08 | 2013-12-25 | 哈尔滨工程大学 | Multi-unmanned aerial vehicle route planning method based on bee colony collaborative foraging algorithm |
| WO2016164094A1 (en) * | 2015-04-07 | 2016-10-13 | Raytheon Company | Automated sensor platform routing and tracking for observing a region of interest while avoiding obstacles |
| CN105929848A (en) * | 2016-06-28 | 2016-09-07 | 南京邮电大学 | Track planning method for multi-unmanned plane system in three-dimensional environment |
| CN106289255A (en) * | 2016-07-22 | 2017-01-04 | 云南师范大学 | Based on around barrier path planning across the trajectory bearing calibration of naval vessel, land |
| CN106846926A (en) * | 2017-04-13 | 2017-06-13 | 电子科技大学 | A kind of no-fly zone unmanned plane method for early warning |
Non-Patent Citations (5)
| Title |
|---|
| 朱洪等: "《算法设计和分析》", 30 September 1989, 上海科学技术文献出版社 * |
| 王保丰，刘传凯: "《月球车遥操作中的计算机视觉技术》", 31 May 2016, 国防工业出版社 * |
| 王新民: "《无人机编队飞行技术》", 31 October 2015, 西北工业大学出版社 * |
| 理查德·布洛克利（RICHARD BLOCKEY）: "《动力学与控制》", 30 June 2016, 北京理工大学出版社 * |
| 郭继等: "《空间在轨装配任务规划》", 30 September 2014 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108716919A (en) * | 2018-05-25 | 2018-10-30 | 南京航空航天大学 | Plant protection drone path planning method based on arbitrary polygon clear area |
| CN109033966A (en) * | 2018-06-25 | 2018-12-18 | 北京嘀嘀无限科技发展有限公司 | Detour detection model training method and device, and detour detection method and device |
| CN109033966B (en) * | 2018-06-25 | 2019-07-23 | 北京嘀嘀无限科技发展有限公司 | Detour detection model training method and device, and detour detection method and device |
| CN109634284B (en) * | 2019-01-15 | 2021-07-23 | 安徽工程大学 | Robot execution end obstacle avoidance path planning method based on nested three-division algorithm |
| CN109634284A (en) * | 2019-01-15 | 2019-04-16 | 安徽工程大学 | The paths planning method of robot actuating station avoidance based on nested three points of algorithms |
| CN109828607A (en) * | 2019-04-03 | 2019-05-31 | 南京航空航天大学 | A kind of unmanned plane paths planning method and system towards irregular slalom object |
| CN109828607B (en) * | 2019-04-03 | 2020-07-07 | 南京航空航天大学 | Unmanned aerial vehicle path planning method and system for irregular obstacles |
| CN111830983A (en) * | 2019-08-06 | 2020-10-27 | 清华大学 | Multi-agent group system navigation and obstacle avoidance method and device in dynamic environment |
| CN110849373A (en) * | 2019-11-28 | 2020-02-28 | 中国航空工业集团公司沈阳飞机设计研究所 | Man-machine real-time airway re-planning method |
| CN110849373B (en) * | 2019-11-28 | 2023-07-21 | 中国航空工业集团公司沈阳飞机设计研究所 | Real-time route re-planning method for man-machine |
| CN112148033A (en) * | 2020-10-22 | 2020-12-29 | 广州极飞科技有限公司 | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium |
| CN112379692B (en) * | 2020-11-23 | 2022-06-21 | 广州极飞科技股份有限公司 | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium |
| CN112379692A (en) * | 2020-11-23 | 2021-02-19 | 广州极飞科技有限公司 | Method, device and equipment for determining unmanned aerial vehicle air route and storage medium |
| CN113190031A (en) * | 2021-04-30 | 2021-07-30 | 成都思晗科技股份有限公司 | Forest fire automatic photographing and tracking method, device and system based on unmanned aerial vehicle |
| CN113220027A (en) * | 2021-05-08 | 2021-08-06 | 北京大学 | Concave polygon area unmanned aerial vehicle flight path planning based on remote sensing task |
| CN114637305A (en) * | 2022-02-15 | 2022-06-17 | 山东省计算中心（国家超级计算济南中心） | Unmanned aerial vehicle shortest path planning method and device |
| CN114637305B (en) * | 2022-02-15 | 2023-08-15 | 山东省计算中心（国家超级计算济南中心） | Unmanned aerial vehicle shortest path planning method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107478231A (en) | Unmanned plane Route Planning Algorithm based on polygon obstacle detection | |
| US20190156507A1 (en) | Method and apparatus for processing point cloud data and storage medium | |
| US10861183B2 (en) | Method and device for short-term path planning of autonomous driving through information fusion by using V2X communication and image processing | |
| CN108345822B (en) | Point cloud data processing method and device | |
| EP3686779B1 (en) | Method and device for attention-based lane detection without post-processing by using lane mask and testing method and testing device using the same | |
| KR102337362B1 (en) | Method and device for generating deceivable composite image by using gan including generating neural network and discriminating neural network to allow surveillance system to recognize surroundings and detect rare event more accurately | |
| CN106980657A (en) | A kind of track level electronic map construction method based on information fusion | |
| CN110823240B (en) | Following robot path planning method and system with course constraint | |
| CN107223261A (en) | Man-machine hybrid decision method and device | |
| CN108268483A (en) | The method for the grid map that generation controls for unmanned vehicle navigation | |
| CN110132291A (en) | Grating map generation method, system, equipment and storage medium for harbour | |
| CN108334080A (en) | A kind of virtual wall automatic generation method for robot navigation | |
| CN109657614B (en) | Automatic road identification method in aerial photography road traffic accident scene investigation | |
| CN108268518A (en) | The device for the grid map that generation controls for unmanned vehicle navigation | |
| CN110244716A (en) | A method of the robot based on wave front algorithm is explored | |
| CN111507373A (en) | Method and apparatus for performing seamless parameter change | |
| CN109839112B (en) | Underground operation equipment positioning method, device and system and storage medium | |
| US11645775B1 (en) | Methods and apparatus for depth estimation on a non-flat road with stereo-assisted monocular camera in a vehicle | |
| CN111507161B (en) | Method and device for heterogeneous sensor fusion by utilizing merging network | |
| CN110411454A (en) | A kind of method for planning path for mobile robot improving random walk figure method | |
| Yao et al. | Semantic labelling of ultra dense MLS point clouds in urban road corridors based on fusing CRF with shape priors | |
| Zhang et al. | Real time obstacle detection method based on lidar and wireless sensor | |
| Zheng et al. | BRR-DQN: UAV path planning method for urban remote sensing images | |
| CN113807305A (en) | Road destructive prediction automatic driving method based on naive Bayes classification algorithm | |
| CN115861186A (en) | Electric power tower detection method and device based on deep learning and unmanned aerial vehicle equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171215 |
|
| RJ01 | Rejection of invention patent application after publication |