CN105892467A - Visual navigation method and system of glass curtain wall cleaning robot - Google Patents
Visual navigation method and system of glass curtain wall cleaning robot Download PDFInfo
- Publication number
- CN105892467A CN105892467A CN201610339803.9A CN201610339803A CN105892467A CN 105892467 A CN105892467 A CN 105892467A CN 201610339803 A CN201610339803 A CN 201610339803A CN 105892467 A CN105892467 A CN 105892467A
- Authority
- CN
- China
- Prior art keywords
- image information
- planning
- overall
- curtain wall
- glass curtain
- 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
- 239000011521 glass Substances 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004140 cleaning Methods 0.000 title claims abstract description 20
- 230000000007 visual effect Effects 0.000 title abstract description 9
- 230000033001 locomotion Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000012937 correction Methods 0.000 claims description 14
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000005549 size reduction Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 230000008878 coupling Effects 0.000 claims description 2
- 238000010168 coupling process Methods 0.000 claims description 2
- 238000005859 coupling reaction Methods 0.000 claims description 2
- 238000010191 image analysis Methods 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 25
- 230000008901 benefit Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
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
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (AREA)
Abstract
The present invention provides a visual navigation method and system of a glass curtain wall cleaning robot. The method includes the following steps that: overall wall surface image information and regional image information of a glass curtain wall to be cleaned are obtained; pre-processing and image analysis are performed on the overall wall surface image information and the regional image information, and overall regional planning is carried out; the regional image information is matched with the overall wall surface image information, and inter-region obstacle crossing planning is carried out; and the robot moves under control according to paths of the inter-region obstacle crossing planning. The system comprises a first image acquisition module, an image processing module, a second image acquisition module and a robot movement control module. According to the visual navigation method and system of the glass curtain wall cleaning robot of the invention, the overall wall surface image information and the regional image information of the glass curtain wall to be cleaned are acquired under different angles and modes, and the overall wall surface image information and the regional image information are analyzed and processed, and therefore, intra-region path planning and inter-region obstacle crossing planning can be realized, and therefore, the movement trajectories of the robot can be controlled according to the intra-region path planning and the inter-region obstacle crossing planning, and finally, the robot can continuously work on a plurality of glass surfaces.
Description
Technical field
The present invention relates to robot navigation's technical field, particularly relate to a kind of glass curtain wall cleaning machine device people's
Vision navigation method and system.
Background technology
Glass curtain wall is the construction wall trailing of a kind of novelty attractive in appearance, when being modernism skyscraper
The marked feature in generation, glass curtain wall also brings for us while bringing visual enjoyment for us
Trouble, such as its cleaning.For our research and development that people are freed from dangerous work high above the ground environment
A curtain cleaning robot, this robot needs to be operated in vertical glass curtain wall surface.Machine
People has certain similarity in the motion of vertical wall with the motion on ground, but is different more.
Generally glass curtain wall can be divided into bright frame glass curtain wall and concealed frame glass curtain wall two class, is particularly having frame glass
The surface of curtain wall, how safety and precise ground leaping over obstacles becomes restriction robot on glass curtain wall surface even
The bottleneck of continuous large area work.
Traditional area navigation mode uses GPS/ inertial navigation system to merge location, wherein, GPS mostly
Of many uses, precision is high, but affected by environment greatly, inertial navigation system then can entirely autonomous and frequency
Rate is high, but influence of noise is big.Although if both merge can effectively utilize respective advantage, taking length
Mend short, but, in actual applications, under a lot of occasions, gps signal can be blocked and cannot use,
And then cause system entirety positioning precision to decline quickly, this point and area navigation and the navigation of vertical plane
There is similarity.The most such navigation system can only realize avoidance mostly, say, that robot can only
Constantly spin at one piece of glass surface, thus be difficult to the continuous work to multiple pieces of glass face.
Summary of the invention
It is an object of the invention to provide the vision navigation method of a kind of glass curtain wall cleaning machine device people and be
System, is difficult on multiple pieces of glass face asking of work continuously in order to solve glass curtain wall robot in prior art
Topic.
To achieve these goals, the first aspect of the invention is to provide a kind of glass curtain wall cleaning machine device
The vision navigation method of people, comprises the steps:
Obtain the overall metope image information of glass curtain wall to be cleaned;
Overall metope image information is carried out pretreatment and graphical analysis, and carries out overall region planning;
Pickup area image information is planned according to overall region;
Regional image information is carried out pretreatment and graphical analysis, and mates with overall metope image information,
Carry out interregional obstacle detouring planning;
The path clustering robot motion planned according to interregional obstacle detouring.
Further, overall metope image information is carried out pretreatment and graphical analysis, and carries out entirety
Regional planning specifically includes:
Overall metope image information is carried out successively the pre-of noise reduction, filtering, distortion correction and size reduction
Process;
Carry out again scheming splicing, edge segmentation, object reconstruction and the graphical analysis of human assistance correction more;
Finally carry out overall region planning.
Further, regional image information is carried out pretreatment and graphical analysis, and with overall metope figure
As information matches, carry out the planning of interregional obstacle detouring and specifically include:
Regional image information is carried out successively noise reduction, filtering, distortion correction and the pretreatment of size reduction;
Carry out edge segmentation, object reconstruction again, and mate with overall metope image information;
Finally carry out path planning and the planning of interregional obstacle detouring in region.
Another aspect of the present invention is to provide the vision navigation system of a kind of glass curtain wall cleaning machine device people,
Including:
First image capture module, for obtaining the overall metope image information of glass curtain wall to be cleaned;
Image processing module, for overall metope image information is carried out pretreatment and graphical analysis, and
Carry out overall region planning;
Second image capture module, for planning pickup area image information according to overall region;
Image processing module is additionally operable to carry out regional image information pretreatment and graphical analysis, and with whole
Body metope image information is mated, and carries out interregional obstacle detouring planning;
Motion planning and robot control module, for the path clustering robot fortune planned according to interregional obstacle detouring
Dynamic.
Further, image processing module specifically includes:
Image pre-processing unit, for carrying out noise reduction, filtering, abnormal successively to overall metope image information
Become and correct and the pretreatment of size reduction;
Image analyzing unit, is used for carrying out scheming splicing, edge segmentation, object reconstruction and human assistance more
The graphical analysis of correction;
Regional planning unit, is used for carrying out overall region planning.
Further, image pre-processing unit is additionally operable to, regional image information is carried out successively noise reduction,
Filtering, distortion correction and the pretreatment of size reduction;
Image analyzing unit is additionally operable to, and carries out edge segmentation, object reconstruction, and with overall metope image
Information is mated;
Regional planning unit is additionally operable to, and carries out path planning and the planning of interregional obstacle detouring in region.
The invention described above technical scheme is used to provide the benefit that: to be gathered respectively by different angles and pattern
The overall metope image information of glass curtain wall to be cleaned is with regional image information, and it is analyzed place
Reason, thus path planning and the planning of interregional obstacle detouring in formation zone, control the fortune of robot with this
Dynamic track, finally realizing robot can work on multiple pieces of glass face continuously.
Accompanying drawing explanation
Fig. 1 is the structural representation of the vision navigation system of glass curtain wall cleaning machine device people of the present invention;
Fig. 2 is the flow chart of the vision navigation method of glass curtain wall cleaning machine device people of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in inventive embodiments, clearly and completely retouches the technical scheme in the embodiment of the present invention
State, it is clear that described embodiment is a part of embodiment of the present invention rather than whole embodiments.
The invention discloses the vision navigation system of a kind of glass curtain wall cleaning machine device people, as it is shown in figure 1,
This system can include first image capture module the 10, second image capture module 20, image procossing mould
Block 30 and motion planning and robot control module 40, wherein:
First image capture module 10, for obtaining the overall metope image letter of glass curtain wall to be cleaned
Breath;
Image processing module 30, for overall metope image information is carried out pretreatment and graphical analysis,
And carry out overall region planning;
Second image capture module 20, for planning pickup area image information according to overall region;
Image processing module 30 is additionally operable to regional image information is carried out pretreatment and graphical analysis, and
Mate with overall metope image information, carry out interregional obstacle detouring planning;
Motion planning and robot control module 40, for the path clustering robot planned according to interregional obstacle detouring
Motion.
In the present embodiment, image processing module 30 specifically can also include:
Image pre-processing unit 31, for overall metope image information and regional image information successively
Carry out noise reduction, filtering, distortion correction and the pretreatment of size reduction;
Image analyzing unit 32, for carry out overall metope image information scheming more splicing, edge segmentation,
Object reconstruction and the graphical analysis of human assistance correction;It is additionally operable to that regional image information is carried out edge divide
Cut, object reconstruction, and mate with overall metope image information;
Regional planning unit 33, in being used for carrying out overall region planning and carrying out region path planning with
And the planning of interregional obstacle detouring.
Concrete, in embodiments of the present invention, the first image capture module is ground image acquisition module,
It can include camera frame, visual servo device and high speed camera etc..Second image capture module is machine
Carrying image capture module, it is arranged in airborne device, can include airborne visual servo device and height
Speed camera etc..Image processing module can be arranged on ground and control in terminal, control on ground terminal with
Data communication module it is additionally provided with between airborne device.In the present embodiment, ground image acquisition module
Controlling terminal with ground to be connected, ground controls terminal and is connected with data communication module, data communication module
Being connected with the airborne data communication unit in airborne device, control information is sent out by airborne data communication unit
Deliver to motion planning and robot control module.Onboard image acquisition module is connected with airborne data communication unit,
The image information of collection is sent to data communication module, data communication module by airborne data communication unit
Controlling terminal with ground to be connected, the information that process is completed by ground control terminal passes through data communication module
Being sent to airborne data communication unit, the information received is sent to machine by airborne data communication unit
People's motion-control module, motion planning and robot control module receiver carries data communication units and transmits the number of coming
According to, thus control the movement locus of robot.
In the present embodiment, concrete, ground controls terminal and incoming image is carried out Image semantic classification
With image intelligent analysis, and by process gained information carry out intelligence path planning, plan road the most at last
Footpath information is sent to data communication module;Data communication module receives ground and controls the data of terminal, and
It is transferred to airborne data communication unit or receives the image information transmission of airborne data communication units
Terminal is controlled to ground;Airborne data communication unit then receives the number from ground data communication module
According to, and pass it to motion planning and robot control module, or reception is adopted from onboard image acquisition module
The image information of collection, and pass it to data communication module.
The invention also discloses the vision navigation method of a kind of glass curtain wall cleaning machine device people, as in figure 2 it is shown,
The method may include steps of:
Step S201, obtains the overall metope image information of glass curtain wall to be cleaned;
In the embodiment of the present invention, before starting working, ground visual servo device control ground surface high speed phase
Machine, collects complete building metope image information clearly, can multi collect.
Step S202, carries out pretreatment and graphical analysis, and carries out overall district overall metope image information
Territory is planned;
Concrete, in the present embodiment, the image of collection being sent to ground and controls in terminal, ground is controlled
Image processing module in terminal processed carries out Image semantic classification to it, it include noise reduction, filter, distort strong
Just, size reduction etc.;And carry out image intelligent analysis, including scheming splicing, edge segmentation, object weight more
Build and human assistance correction etc.;Carry out overall region planning the most again, district overall region first planned
Territory routing information is sent to ground data communication module, as the reference information of subsequent treatment.
Step S203, plans pickup area image information according to overall region;
Robot airborne visual servo device controls onboard high-speed collected by camera area image clearly, will adopt
Collect to area image be sent to airborne data communication unit, by airborne data communication unit by image information
Being sent to ground data communication module, image information is sent to ground and controls eventually by ground data communication module
End.
Step S204, carries out pretreatment and graphical analysis to regional image information, and with overall metope image
Information matches, carries out interregional obstacle detouring planning;
Concrete, in the present embodiment, ground control the district to gathering of the image processing module in terminal
Area image information carries out Image semantic classification, specifically includes noise reduction, filtering, distortion correction and size reduction etc.;
And carry out image intelligent analysis, including edge segmentation, object reconstruction, and enter with overall metope image information
Row coupling;Finally carry out path planning and the planning of interregional obstacle detouring in region.
Step S205, the path clustering robot motion planned according to interregional obstacle detouring.
In embodiments of the present invention, ground visual servo device in normal work, control ground surface high speed camera
Following the trail of robot, and timing acquiring image, the image of collection is sent to ground and controls terminal to carry out image pre-
Process the reference information for mating as overall, area image, and combine and divided by regional image information
Analysis processes path planning and the planning of interregional obstacle detouring in the region obtained, thus by robot control module
Control robot motion, it is achieved robot can work on multiple pieces of glass face continuously.
The overall metope image that the present invention gathers glass curtain wall to be cleaned respectively by different angles and pattern is believed
Breath with regional image information, and to its be analyzed process, thus in formation zone path planning and
Interregional obstacle detouring is planned, controlling the movement locus of robot with this, finally realizing robot can be many
Work continuously on block glass surface.
One of ordinary skill in the art will appreciate that: realize all or part of of above-mentioned each method embodiment
Step can be completed by the hardware that programmed instruction is relevant.Aforesaid program can be stored in a calculating
In machine read/write memory medium.This program upon execution, performs to include the step of above-mentioned each method embodiment
Suddenly;And aforesaid storage medium includes: ROM, RAM, magnetic disc or CD etc. are various can store journey
The medium of sequence code.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, rather than
It is limited;Although the present invention being described in detail with reference to foregoing embodiments, this area
Those of ordinary skill is it is understood that the technical scheme described in foregoing embodiments still can be entered by it
Row amendment, or the most some or all of technical characteristic is carried out equivalent;And these amendment or
Person replaces, and does not make the essence of appropriate technical solution depart from the model of various embodiments of the present invention technical scheme
Enclose.
Claims (6)
1. the vision navigation method of a glass curtain wall cleaning machine device people, it is characterised in that include walking as follows
Rapid:
Obtain the overall metope image information of glass curtain wall to be cleaned;
Described overall metope image information is carried out pretreatment and graphical analysis, and carries out overall region planning;
Pickup area image information is planned according to described overall region;
Described regional image information is carried out pretreatment and graphical analysis, and believes with described overall metope image
Breath coupling, carries out interregional obstacle detouring planning;
Path clustering robot motion according to the planning of described interregional obstacle detouring.
The vision navigation method of glass curtain wall cleaning machine device people the most according to claim 1, its feature
It is, described described overall metope image information is carried out pretreatment and graphical analysis, and carry out overall district
Territory planning specifically includes:
Described overall metope image information is carried out noise reduction, filtering, distortion correction and size reduction successively
Pretreatment;
Carry out again scheming splicing, edge segmentation, object reconstruction and the graphical analysis of human assistance correction more;
Finally carry out overall region planning.
The vision navigation method of glass curtain wall cleaning machine device people the most according to claim 1 and 2, its
Be characterised by, described described regional image information carried out pretreatment and graphical analysis, and with described entirety
Metope image information is mated, and carries out the planning of interregional obstacle detouring and specifically includes:
Described regional image information is carried out successively noise reduction, filtering, distortion correction and the pre-place of size reduction
Reason;
Carry out edge segmentation, object reconstruction again, and mate with described overall metope image information;
Finally carry out path planning and the planning of interregional obstacle detouring in region.
4. the vision navigation system of a glass curtain wall cleaning machine device people, it is characterised in that including:
First image capture module, for obtaining the overall metope image information of glass curtain wall to be cleaned;
Image processing module, for described overall metope image information is carried out pretreatment and graphical analysis,
And carry out overall region planning;
Second image capture module, for planning pickup area image information according to described overall region;
Described image processing module is additionally operable to described regional image information is carried out pretreatment and graphical analysis,
And mate with described overall metope image information, carry out interregional obstacle detouring planning;
Motion planning and robot control module, for the path clustering robot according to the planning of described interregional obstacle detouring
Motion.
The vision navigation system of glass curtain wall cleaning machine device people the most according to claim 4, its feature
Being, described image processing module specifically includes:
Image pre-processing unit, for described overall metope image information is carried out successively noise reduction, filtering,
Distortion correction and the pretreatment of size reduction;
Image analyzing unit, is used for carrying out scheming splicing, edge segmentation, object reconstruction and human assistance school more
Positive graphical analysis;
Regional planning unit, is used for carrying out overall region planning.
The vision navigation system of glass curtain wall cleaning machine device people the most according to claim 5, its feature
It is,
Described image pre-processing unit is additionally operable to, described regional image information is carried out successively noise reduction, filtering,
Distortion correction and the pretreatment of size reduction;
Described image analyzing unit is additionally operable to, then carries out edge segmentation, object reconstruction, and with described entirety
Metope image information is mated;
Described regional planning unit is additionally operable to, and carries out path planning and the planning of interregional obstacle detouring in region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610339803.9A CN105892467A (en) | 2016-05-22 | 2016-05-22 | Visual navigation method and system of glass curtain wall cleaning robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610339803.9A CN105892467A (en) | 2016-05-22 | 2016-05-22 | Visual navigation method and system of glass curtain wall cleaning robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105892467A true CN105892467A (en) | 2016-08-24 |
Family
ID=56717550
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610339803.9A Pending CN105892467A (en) | 2016-05-22 | 2016-05-22 | Visual navigation method and system of glass curtain wall cleaning robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105892467A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106325299A (en) * | 2016-09-13 | 2017-01-11 | 上海顺砾智能科技有限公司 | Unmanned plane return flight landing method based on visual sense |
CN106725081A (en) * | 2017-02-06 | 2017-05-31 | 赵东来 | The control method of glass-cleaning robot and its obstacle detouring pattern |
WO2018195767A1 (en) * | 2017-04-25 | 2018-11-01 | 深圳市元征科技股份有限公司 | Glass cleaning method and device based on automated driving, and computer readable storage medium |
CN109008841A (en) * | 2017-06-09 | 2018-12-18 | 河北卓达建材研究院有限公司 | A kind of metope repair robot by different level |
CN109213177A (en) * | 2018-11-09 | 2019-01-15 | 苏州瑞得恩光能科技有限公司 | Algorithms of Robots Navigation System and air navigation aid |
CN109298715A (en) * | 2018-11-09 | 2019-02-01 | 苏州瑞得恩光能科技有限公司 | Robot traveling control system and traveling control method |
CN109782772A (en) * | 2019-03-05 | 2019-05-21 | 浙江国自机器人技术有限公司 | A kind of air navigation aid, system and cleaning robot |
CN113741465A (en) * | 2021-09-07 | 2021-12-03 | 深圳大方智能科技有限公司 | Ceiling wall construction method, path planning device and construction robot |
CN117464694A (en) * | 2023-12-28 | 2024-01-30 | 汉狮光动科技(广东)有限公司 | Path planning method for automatic hollow glass cleaning device |
-
2016
- 2016-05-22 CN CN201610339803.9A patent/CN105892467A/en active Pending
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106325299A (en) * | 2016-09-13 | 2017-01-11 | 上海顺砾智能科技有限公司 | Unmanned plane return flight landing method based on visual sense |
CN106725081A (en) * | 2017-02-06 | 2017-05-31 | 赵东来 | The control method of glass-cleaning robot and its obstacle detouring pattern |
CN110418594A (en) * | 2017-04-25 | 2019-11-05 | 深圳市元征科技股份有限公司 | Automatic Pilot cleans glass process, device and computer readable storage medium |
WO2018195767A1 (en) * | 2017-04-25 | 2018-11-01 | 深圳市元征科技股份有限公司 | Glass cleaning method and device based on automated driving, and computer readable storage medium |
CN109008841A (en) * | 2017-06-09 | 2018-12-18 | 河北卓达建材研究院有限公司 | A kind of metope repair robot by different level |
CN109298715B (en) * | 2018-11-09 | 2021-12-07 | 苏州瑞得恩光能科技有限公司 | Robot traveling control system and traveling control method |
CN109298715A (en) * | 2018-11-09 | 2019-02-01 | 苏州瑞得恩光能科技有限公司 | Robot traveling control system and traveling control method |
CN109213177A (en) * | 2018-11-09 | 2019-01-15 | 苏州瑞得恩光能科技有限公司 | Algorithms of Robots Navigation System and air navigation aid |
CN109213177B (en) * | 2018-11-09 | 2022-01-11 | 苏州瑞得恩光能科技有限公司 | Robot navigation system and navigation method |
CN109782772A (en) * | 2019-03-05 | 2019-05-21 | 浙江国自机器人技术有限公司 | A kind of air navigation aid, system and cleaning robot |
CN113741465A (en) * | 2021-09-07 | 2021-12-03 | 深圳大方智能科技有限公司 | Ceiling wall construction method, path planning device and construction robot |
CN113741465B (en) * | 2021-09-07 | 2024-05-03 | 深圳大方智能科技有限公司 | Ceiling wall construction method, path planning device and construction robot |
CN117464694A (en) * | 2023-12-28 | 2024-01-30 | 汉狮光动科技(广东)有限公司 | Path planning method for automatic hollow glass cleaning device |
CN117464694B (en) * | 2023-12-28 | 2024-03-05 | 汉狮光动科技(广东)有限公司 | Path planning method for automatic hollow glass cleaning device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105892467A (en) | Visual navigation method and system of glass curtain wall cleaning robot | |
Müller et al. | Driving policy transfer via modularity and abstraction | |
Smolyanskiy et al. | Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness | |
Máthé et al. | Vision and control for UAVs: A survey of general methods and of inexpensive platforms for infrastructure inspection | |
Lee et al. | Deep learning-based monocular obstacle avoidance for unmanned aerial vehicle navigation in tree plantations: Faster region-based convolutional neural network approach | |
Dickmanns et al. | An integrated spatio-temporal approach to automatic visual guidance of autonomous vehicles | |
Pérez et al. | Ground vehicle detection through aerial images taken by a UAV | |
Ishihara et al. | Multi-task learning with attention for end-to-end autonomous driving | |
CN103279949A (en) | Operation method of self-positioning robot-based multi-camera parameter automatic calibration system | |
CN111291697B (en) | Method and device for detecting obstacles | |
CN110924340A (en) | Mobile robot system for intelligently picking up garbage and implementation method | |
CN110398720A (en) | A kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method | |
CN106197452A (en) | A kind of visual pattern processing equipment and system | |
DE112008001884T5 (en) | Path planning device, path planning method and moving body | |
CN111768489B (en) | Indoor navigation map construction method and system | |
CN106162144A (en) | A kind of visual pattern processing equipment, system and intelligent machine for overnight sight | |
CN106092123B (en) | A kind of video navigation method and device | |
CN106127788A (en) | A kind of vision barrier-avoiding method and device | |
CN103116279A (en) | Vague discrete event shared control method of brain-controlled robotic system | |
CN107766930B (en) | Equivalent ROM distance calculation method based on DTW cluster fuzzy clustering SOM neurons | |
Zeng et al. | Deep reinforcement learning for next-best-view planning in agricultural applications | |
CN111161325A (en) | Three-dimensional multi-target tracking method based on Kalman filtering and LSTM | |
CN113515536A (en) | Map updating method, device, equipment, server and storage medium | |
Grewe et al. | Seeing eye drone: a deep learning, vision-based UAV for assisting the visually impaired with mobility | |
CN106155082A (en) | A kind of unmanned plane bionic intelligence barrier-avoiding method based on light stream |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160824 |
|
WD01 | Invention patent application deemed withdrawn after publication |