CN104950695B - A kind of general unmanned plane vision emulation platform - Google Patents
A kind of general unmanned plane vision emulation platform Download PDFInfo
- Publication number
- CN104950695B CN104950695B CN201510415014.4A CN201510415014A CN104950695B CN 104950695 B CN104950695 B CN 104950695B CN 201510415014 A CN201510415014 A CN 201510415014A CN 104950695 B CN104950695 B CN 104950695B
- Authority
- CN
- China
- Prior art keywords
- control
- ros
- general unmanned
- machine connecting
- connecting interface
- 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.)
- Active
Links
- 238000004088 simulation Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000010006 flight Effects 0.000 claims 1
- 238000012360 testing method Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A kind of general unmanned plane vision emulation platform, including simulated environment part and true environment part, the simulated environment part includes robot operating system ROS, the robot simulation console module Gazebo to increase income, vision algorithm storehouse and the information for ROS systems to be transmitted through coming and is converted into the Bu Tong winged general unmanned machine connecting interface for controlling the control information that can be identified, the general unmanned machine connecting interface supports ROS systems, and the robot simulation console module Gazebo to increase income, vision algorithm storehouse and the general unmanned machine connecting interface are connected with robot operating system ROS；The true environment part includes aircraft frame and flight controller, and the general unmanned machine connecting interface is connected with the flight controller.The present invention provides a kind of unmanned plane vision emulation platform with good autgmentability and versatility.
Description
Technical field
It is especially a kind of that emulation can be made to be put down with what prototype was combined the present invention relates to unmanned plane vision automation field
Platform.
Background technology
In recent years either in terms of the research or in terms of business application, the field of unmanned plane is more and more hot, and nothing
The man-machine simulation system field relatively new as one, its demand socially is also more and more higher, and phase is tested with prototype
Than it can be effectively prevented from damage of the aircraft in test process., can be with no consumption, peace by the analogue system of unmanned plane
The algorithm and aircraft of full testing vision automatically control.
But current unmanned plane analogue system is mainly just for the AR.Drone analogue systems of a kind of aircraft, such as TUM,
And it can only test a kind of vision algorithm, without what autgmentability and versatility, other analogue systems even can not with it is true
Machine carries out the docking of test of heuristics, thus loses the final meaning of emulation.
The content of the invention
In order to overcome the shortcomings of that the single object of existing unmanned plane emulation mode, autgmentability and versatility are poor, the present invention
A kind of unmanned plane vision emulation platform with good autgmentability and versatility is provided.
The technical solution adopted for the present invention to solve the technical problems is：
A kind of general unmanned plane vision emulation platform, including simulated environment part and true environment part, the emulation
Environment division includes robot operating system ROS, the robot simulation console module Gazebo to increase income, vision algorithm storehouse and is used for
The information that ROS systems are transmitted through is converted into the different general unmanned machine connecting interfaces for flying the control information that control can identify, it is described
General unmanned machine connecting interface supports ROS systems, the robot simulation console module Gazebo to increase income, vision algorithm storehouse and
General unmanned machine connecting interface is connected with robot operating system ROS；The true environment part include aircraft frame and
Flight controller, the general unmanned machine connecting interface are connected with the flight controller.
Further, in the general unmanned machine connecting interface, input is the incoming logical layer control information of ROS systems,
After getting logical layer control information, need to carry out the pretreatment of data before being ready for sending to the winged control of unmanned plane, to control
Information processed flies to issue flight controller after control is converted for some.
Further, the process of the conversion is as follows：Winged control for AR.Drone is needed the control up and down of logic
System is converted into the control message that AR.Drone drivings can identify, is then transferred to AR.Drone flight controllers reality by WIFI
Now control；The logical control information of interface is equally converted into mavlink message for the winged controls of Pixhawk and issues Pixhawk again
Flight controller；Winged control for ASCTEC is also required to the message that logical control information is converted into ASCTEC drivings and can identified
It is then forwarded to flight controller.
Further, the robot operating system ROS also includes User Interface, for allowing user to go to select needs
The winged control type of connection.
Beneficial effects of the present invention are mainly manifested in：With good autgmentability and versatility.
Brief description of the drawings
Fig. 1 is the theory diagram of general unmanned plane vision emulation platform.
Embodiment
The invention will be further described below in conjunction with the accompanying drawings.
Reference picture 1, a kind of general unmanned plane vision emulation platform, including simulated environment part and true environment part,
Robot simulation console module Gazebo, the vision algorithm that the simulated environment part includes robot operating system ROS, increased income
Storehouse with the information for ROS systems to be transmitted through is converted into the different general unmanned machines for flying the control information that control can identify and connected to connect
Mouthful, the general unmanned machine connecting interface supports ROS systems, the robot simulation console module Gazebo to increase income, vision
Algorithms library and general unmanned machine connecting interface are connected with robot operating system ROS；The true environment part includes flight
Device frame and flight controller, the general unmanned machine connecting interface are connected with the flight controller.
Further, in the general unmanned machine connecting interface, input is the incoming logical layer control information of ROS systems,
After getting logical layer control information, need to carry out the pretreatment of data before being ready for sending to the winged control of unmanned plane, to control
Information processed flies to issue flight controller after control is converted for some.
The platform of the present embodiment can support a variety of unmanned planes to fly control such as AR.Drone 2.0, pixhawk, APM etc..
And it can support that a variety of relatively advanced vision algorithm automatically controls unmanned plane, such as OpenTLD, ORB- in the world at present
SLAM etc..
The emulation platform of the present embodiment is generally formed based on ROS systems and Gazebo, and Gazebo is more popular at present
's
Simulation software increase income for robot simulation design.And ROS systems are also the best work(generally acknowledged in the world at present
Robot operating system of increasing income that can be most complete.
Design the environment of a set of simulation unmanned plane first in Gazebo, include the three-dimensional scenic of multiple analog, nobody
The model of machine aircraft, the kinematics and dynamics of unmanned plane, frictional impact model and various sensor Simulations etc..
Then the image information that simulation unmanned plane obtains in the scene is transferred to ROS systems in Gazebo, vision is calculated
Method module obtains the input of image from ROS systems again, then carries out correspondingly computing, and the result drawn is feeding back to ROS,
Result treatment is converted into control information and issues simulated flight device in Gazebo by ROS, is so achieved that vision algorithm control
The flow of simulated flight device.
General unmanned machine connecting interface, it is necessary to support ROS systems, the aspect being connected in Interface design with analogue system
Only the interface to be communicated with ROS need to be designed, motion model or kinetic model all can be with algorithm layer and analogue system
ROS is communicated.
It is complex, it is necessary to which design a kind of general-purpose interface is transmitted through what is come ROS systems with the connection design in prototype environment
Information is converted into the different control information that flies control and can identify, for example is communicated with pixhawk and need to use mavros to drive, that is,
Mavlink and ROS communication connection.For another example AR.Drone due to official provide ROS versions driving, can directly with
ROS communicates, so need to only be added in general-purpose interface.
Design one is finally needed with the interface of user mutual, the winged control type that user can be allowed to go selection needs to connect,
Once selection finishes Vision control algorithm seamless application can be allowed to fly specific in control, specific unmanned plane is performed some bases
In the task of vision.
The workflow of general unmanned machine connecting interface：
1) input of interface first is the incoming logical layer control information of ROS systems, in logic to different unmanned planes
Control is not different, and is all the change such as rotation up and down all around.
2) followed by after interface gets logical layer control information, needed before being ready for sending to the winged control of unmanned plane into
The pretreatment of row data, control is flown for some to control information and carries out special conversion：Winged control for AR.Drone needs handle to patrol
The control up and down collected is converted into the control message that AR.Drone drivings can identify, is then transferred to by WIFI
AR.Drone flies control and realizes control；Fly control such as Pixhawk again to be equally converted into the logical control information of interface
Mavlink message issues Pixhawk and flies control again；Winged control for ASCTEC is also required to logical control information to be converted into ASCTEC
The message that can be identified is driven, is then issued to flight controller.
Especially, the winged control for pixhawk or APM due to its versatility it is stronger, it is possible to be carried to different chis
In very little unmanned plane frame, the extension in frame is realized.
So that unmanned plane tracks as an example, the model aircraft used is AR.Drone, uses OpenTLD Vision Trackings, sheet
The main flow of the platform in operation of embodiment：
1) it is that emulation module and reality module are relatively independent first.
2) first since emulation module, there are prior designed unmanned plane model, including geometry model in Gazebo
And kinematics model, it can go to control unmanned plane in Gazebo algorithms after these are ready, same can also be in Gazebo
In go to obtain the various attitude informations of current unmanned plane.
3) after Gazebo obtains the view data of aircraft current visual angle, image information, and handle are obtained by ROS systems
Information is transmitted to computer vision processing module, then carries out algorithm process in the module, then the result after processing is transferred to ROS
System, by ROS conversion controling informations to Gazebo, model aerial vehicle is allowed to complete corresponding action in Gazebo.
4) vision algorithm layer carry out algorithm process after, we can also control information it is system converting by ROS be true
The information that can be identified in machine, and this needs the interface of ROS systems and various winged controls, typically more general Fei Kong officials will
The driving of ROS versions, such as AR.Drone etc. are provided.And we do be be connected with ROS systems it is a series of it is winged control into
Row is integrated, and then establishes a general interface, and ROS systems and many kinds can be flown control using this interface is carried out.
5) in the test of true environment, using mavros as ROS systems and the conversion group of mavlink puppy parcs
Part.Carry-on flight control modules are communicated by the ROS systems at mavlink agreements and PC ends.So, in ROS
The vision algorithm can and actual aircraft tested interact.Vision algorithm after emulation testing can be very
The test of practical flight device is advantageously applied to, improves the security and high efficiency of test of heuristics.
Claims (2)
- A kind of 1. general unmanned plane vision emulation platform, it is characterised in that：The emulation platform include simulated environment part and True environment part, the robot simulation console module that the simulated environment part includes robot operating system ROS, increased income Gazebo, vision algorithm storehouse and the information for ROS systems to be transmitted through are converted into Bu Tong flying the control information that control can identify General unmanned machine connecting interface, the general unmanned machine connecting interface support ROS systems, the robot simulation platform increased income Module Gazebo, vision algorithm storehouse and general unmanned machine connecting interface are connected with robot operating system ROS；The true ring Border part includes aircraft frame and flight controller, and the general unmanned machine connecting interface is connected with the flight controller； In the general unmanned machine connecting interface, input is the incoming logical layer control information of ROS systems, gets logical layer control After information, need to carry out the pretreatment of data before being ready for sending to the winged control of unmanned plane, control information is flown for some Control issues flight controller after being converted；The process of the conversion is as follows：Winged control for AR.Drone needs logic to control the control that is converted into AR.Drone drivings and can identify up and down Message processed, AR.Drone flight controllers are then transferred to by WIFI and realize control；The logical control information of interface is equally converted into mavlink message for the winged controls of Pixhawk and issues Pixhawk flights again Controller；Winged control for ASCTEC is also required to the logical control information to be converted into the message that can identify of ASCTEC drivings and retransmited To flight controller.
- A kind of 2. general unmanned plane vision emulation platform as claimed in claim 1, it is characterised in that：The robot manipulation System ROS also includes User Interface, for allowing user to go selection to need the winged control type connected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510415014.4A CN104950695B (en) | 2015-07-15 | 2015-07-15 | A kind of general unmanned plane vision emulation platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510415014.4A CN104950695B (en) | 2015-07-15 | 2015-07-15 | A kind of general unmanned plane vision emulation platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104950695A CN104950695A (en) | 2015-09-30 |
| CN104950695B true CN104950695B (en) | 2018-02-27 |
Family
ID=54165431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510415014.4A Active CN104950695B (en) | 2015-07-15 | 2015-07-15 | A kind of general unmanned plane vision emulation platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104950695B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105843249A (en) * | 2016-03-22 | 2016-08-10 | 安徽大学 | Unmanned aerial vehicle automatic navigation system based on Pixhawk flight control and navigation method thereof |
| CN106326087B (en) * | 2016-08-31 | 2019-04-19 | 北京光年无限科技有限公司 | Web page experience method and system based on robot operating system |
| CN108241354B (en) * | 2016-12-26 | 2022-11-22 | 法法汽车(中国)有限公司 | Test method for automatic driving simulation system |
| CN108268050A (en) * | 2016-12-30 | 2018-07-10 | 昊翔电能运动科技(昆山)有限公司 | Motion control device wears display equipment, unmanned plane and flight system |
| US10332413B2 (en) * | 2017-05-30 | 2019-06-25 | Honeywell International Inc. | System and method for adjusting the correlation between a visual display perspective and a flight path of an aircraft |
| CN108375979A (en) * | 2018-02-10 | 2018-08-07 | 浙江工业大学 | Self-navigation robot general-purpose control system based on ROS |
| CN110333738A (en) * | 2019-07-10 | 2019-10-15 | 华东师范大学 | A kind of unmanned plane cluster verification method based on analogue simulation software |
| CN110887489A (en) * | 2019-11-22 | 2020-03-17 | 深圳晨芯时代科技有限公司 | AR robot-based SLAM algorithm experimental method |
| CN111830845A (en) * | 2020-04-30 | 2020-10-27 | 航天图景（北京）科技有限公司 | Automatic inspection simulation system and method for fan blade of unmanned aerial vehicle |
| CN113759751A (en) * | 2020-10-30 | 2021-12-07 | 北京京东乾石科技有限公司 | Reinforced learning method, device and system based on simulation system |
| CN112562443A (en) * | 2020-12-22 | 2021-03-26 | 北京航空航天大学 | Intelligent detection teaching practice platform and intelligent detection vehicle |
| CN114326438B (en) * | 2021-12-30 | 2023-12-19 | 北京理工大学 | Safety reinforcement learning four-rotor control system and method based on control obstacle function |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339021A (en) * | 2011-07-21 | 2012-02-01 | 成都西麦克虚拟现实电子技术有限公司 | UAV(unmanned aerial vehicle) visual simulation system and simulation method |
| CN102508439A (en) * | 2011-11-18 | 2012-06-20 | 天津大学 | HLA (High Level Architecture)-based multi-unmmaned aerial vehicle distributed simulation method |
| CN203551961U (en) * | 2013-09-24 | 2014-04-16 | 中国兵器工业计算机应用技术研究所 | Avionics hardware-in-the-loop simulation system for unmanned plane |
-
2015
- 2015-07-15 CN CN201510415014.4A patent/CN104950695B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339021A (en) * | 2011-07-21 | 2012-02-01 | 成都西麦克虚拟现实电子技术有限公司 | UAV(unmanned aerial vehicle) visual simulation system and simulation method |
| CN102508439A (en) * | 2011-11-18 | 2012-06-20 | 天津大学 | HLA (High Level Architecture)-based multi-unmmaned aerial vehicle distributed simulation method |
| CN203551961U (en) * | 2013-09-24 | 2014-04-16 | 中国兵器工业计算机应用技术研究所 | Avionics hardware-in-the-loop simulation system for unmanned plane |
Non-Patent Citations (3)
| Title |
|---|
| 三维姿态实时显示的小型无人机飞控仿真系统;张云洲 等;《实验室研究与探索》;20150131;第34卷(第1期);第73-78页 * |
| 中小型无人机建模分析与仿真研究;云超 等;《计算机仿真》;20131130;第30卷(第11期);第32-35页 * |
| 基于嵌入式系统的室内移动机器人定位与导航;胡春旭 等;《华中科技大学学报（自然科学版）》;20131031;第41卷;第254-257页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104950695A (en) | 2015-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104950695B (en) | A kind of general unmanned plane vision emulation platform | |
| CN107589752B (en) | Method and system for realizing cooperative formation of unmanned aerial vehicle and ground robot | |
| CN103093047B (en) | Typical aircraft visual simulation system | |
| CN106773787A (en) | A kind of unmanned plane during flying simulation demo verification platform based on serial communication | |
| CN105182770B (en) | A kind of spacecraft semi-physical simulation experimental system and method based on rotor craft | |
| CN202758243U (en) | Unmanned aerial vehicle flight control system | |
| CN104950902B (en) | The control method and multi-rotor aerocraft of multi-rotor aerocraft | |
| CN206541135U (en) | A kind of unmanned plane Real-time Flight Simulation System | |
| CN103365214A (en) | Single rotor wing unmanned aerial vehicle three-freedom degree semi-physical simulation platform and experimental method | |
| Wang et al. | Research of UAV target detection and flight control based on deep learning | |
| CN106716272A (en) | Systems and methods for flight simulation | |
| CN102854887A (en) | Unmanned plane route planning and remote synchronous control method | |
| CN108473200A (en) | For in multi-rotor unmanned aerial vehicle（UAV）In strong track following general purpose controller | |
| CN110347171A (en) | A kind of flying vehicles control method and aircraft | |
| CN110223565B (en) | Flight simulation method, device, equipment and storage medium | |
| CN102849226A (en) | Scientific research teaching device based on multi-rotor aircraft | |
| WO2019104554A1 (en) | Control method for unmanned aerial vehicle and control terminal | |
| Um et al. | Modular augmented reality platform for smart operator in production environment | |
| CN106127146A (en) | A kind of unmanned aerial vehicle flight path guidance method based on gesture identification | |
| Maher et al. | Realtime human-UAV interaction using deep learning | |
| CN102331778B (en) | Handheld device and method for controlling unmanned vehicle by utilizing same | |
| CN109359629A (en) | Artificial intelligence aircraft and its intelligent control method | |
| CN105676755A (en) | Dual-core flight control computer | |
| Shah | Real-time image processing on low cost embedded computers | |
| Wang et al. | Four-rotor UAV virtual simulation system for agricultural sowing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |