CN207182100U - A kind of binocular vision obstacle avoidance system for fixed-wing unmanned plane - Google Patents
A kind of binocular vision obstacle avoidance system for fixed-wing unmanned plane Download PDFInfo
- Publication number
- CN207182100U CN207182100U CN201720572391.3U CN201720572391U CN207182100U CN 207182100 U CN207182100 U CN 207182100U CN 201720572391 U CN201720572391 U CN 201720572391U CN 207182100 U CN207182100 U CN 207182100U
- Authority
- CN
- China
- Prior art keywords
- instruction
- unmanned aerial
- aerial vehicle
- flight
- angle
- 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
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 6
- 230000004888 barrier function Effects 0.000 abstract description 9
- 238000000034 method Methods 0.000 abstract description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000001228 spectrum 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
The utility model discloses a kind of binocular vision obstacle avoidance system for fixed-wing unmanned plane, including be sequentially connected image capture module, vision processing module, guidance command computing module and flight control modules, image capture module includes left and right two cameras, for gathering vision signal;Vision processing module, for receiving the vision signal of two cameras collection, and calculate according to the intrinsic parameter of two cameras the angle and distance parameter with front obstacle;Computing module is guidanceed command, guidanceing command for control unmanned plane next step flight is calculated for the angle and distance parameter according to barrier and using Artificial Potential Field algorithm, is guidanceed command including the angle of pitch or yaw angle instruction;Flight control modules, the avoiding barrier flight of control unmanned plane is guidanceed command for basis.The utility model is guidanceed command due to taking Artificial Potential Field Method calculating, when there is barrier in front, without making unmanned plane hover, also makes the flight path during unmanned plane avoidance more smooth.
Description
Technical Field
The utility model relates to an unmanned aerial vehicle guidance and control technology field, concretely relates to two mesh vision keep away barrier system for fixed wing unmanned aerial vehicle.
Background
At present, a known unmanned aerial vehicle obstacle avoidance system detects whether an obstacle exists in a certain distance around by using distance measuring devices such as ultrasonic waves, infrared and binocular cameras, so that the unmanned aerial vehicle is hovered or vertically ascended when the distance between the unmanned aerial vehicle and the obstacle is smaller than a certain set value, and the obstacle is prevented from being collided. However, the obstacle avoidance system is only suitable for helicopters and multi-rotor aircrafts capable of hovering, and cannot be used for fixed-wing drones.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to provide an unmanned aerial vehicle keep away barrier system for make fixed wing unmanned aerial vehicle can avoid the place ahead barrier effectively.
In order to achieve the above purpose, the utility model provides a binocular vision obstacle avoidance system for a fixed wing unmanned aerial vehicle, which comprises an image acquisition device, an instruction device and a fixed wing unmanned aerial vehicle flight controller which are connected in sequence, wherein,
the image acquisition equipment comprises a left camera and a right camera and is used for acquiring video signals and sending the video signals to the instruction equipment;
the command subsystem is used for generating a corresponding flight guidance command according to the received video signal;
and the fixed wing unmanned aerial vehicle flight controller is used for receiving the flight guidance instruction and controlling the flight direction according to the flight guidance instruction.
Further, the instruction subsystem comprises a vision processor and a guidance instruction calculator, wherein,
the vision processor is used for receiving the video signals collected by the two cameras and calculating the angle and distance parameters between the vision processor and the front obstacle according to the internal parameters of the two cameras;
and the guidance instruction calculator is used for calculating a guidance instruction for controlling the unmanned aerial vehicle to fly next step by utilizing an artificial potential field algorithm according to the angle and distance parameters of the obstacle, and the guidance instruction comprises a pitch angle instruction or a yaw angle instruction.
Further, the distance between the left camera and the right camera is 6-12 cm.
In the technical solution provided by the utility model, the guidance instruction is calculated owing to having taken artifical potential field method, consequently, when the barrier appears in the front, need not to make unmanned aerial vehicle hover, is applicable to fixed wing unmanned aerial vehicle. In addition, compare with the current perpendicular ascending obstacle avoidance mode of hovering back, the utility model provides a continuous guidance instruction output also can make unmanned aerial vehicle keep away the flight orbit of obstacle in-process more level and smooth.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings can be obtained by those skilled in the art according to these drawings.
Fig. 1 is a structural schematic diagram of an embodiment of a binocular vision obstacle avoidance system for a fixed wing unmanned aerial vehicle.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings.
The utility model provides a two mesh vision keep away barrier systems for fixed wing unmanned aerial vehicle, as shown in fig. 1, including image acquisition equipment 4, instruction subsystem 5, fixed wing unmanned aerial vehicle flight control ware 6 that connect gradually.
Wherein,
the image acquisition equipment 4 comprises a left camera and a right camera and is used for acquiring the video signal 41 and sending the video signal to the instruction equipment;
an instruction subsystem 5 for generating a corresponding flight guidance instruction 51 according to the received video signal;
and the fixed wing unmanned aerial vehicle flight controller 6 is used for receiving the flight guidance instruction and controlling the flight direction according to the flight guidance instruction.
During concrete implementation, image acquisition equipment and instruction subsystem all install on fixed wing unmanned aerial vehicle, and image acquisition equipment is optional to be connected with the instruction subsystem like the CAN line through the serial port line, the instruction subsystem is connected to on the fixed wing unmanned aerial vehicle flight controller, realize that fixed wing unmanned aerial vehicle flight controller installs on fixed wing unmanned aerial vehicle 7, realized that fixed wing unmanned aerial vehicle flight controller receives control flight course behind the guidance instruction to cross the barrier, safe flight.
Further, the instruction subsystem comprises a vision processor and a guidance instruction calculator, wherein,
the vision processor is used for receiving the video signals collected by the two cameras and calculating the angle and distance parameters between the vision processor and the front obstacle according to the internal parameters of the two cameras; in particular, the visual processor is model number Nvidia TegraK 1.
And the guidance instruction calculator is used for calculating a guidance instruction for controlling the unmanned aerial vehicle to fly next step by utilizing an artificial potential field algorithm according to the angle and distance parameters of the obstacle, and the guidance instruction comprises a pitch angle instruction or a yaw angle instruction.
The artificial potential field method is a virtual force method proposed by Khatib. The guiding instruction calculator is implemented by optionally using a processor with the model of TegraK1 to operate an artificial potential field method to realize the calculation of the guiding instruction of the unmanned aerial vehicle. The principle is as follows: the motion of the unmanned aerial vehicle in the environment is regarded as the motion of the robot in a virtual artificial stress field. The obstacle generates repulsion to the unmanned aerial vehicle, the target point generates attraction to the unmanned aerial vehicle, and the resultant force of the attraction and the repulsion is used as the acceleration force of the robot to control the motion direction of the robot and calculate the position of the robot. When the unmanned aerial vehicle is located at the position of the obstacle, the maximum value is generated, and the maximum value monotonically decreases along with the increase of the distance between the unmanned aerial vehicle and the obstacle, and the direction points to the direction away from the obstacle. And (4) optionally editing by Matlab by using an artificial potential field method operated in the instruction calculator. Specific procedures are optionally referenced as follows:
clear clc
xo ═ 00 ]; % starting position
k is 15; % gain factor required to calculate gravity
m is 4; % calculated gain factor for repulsion is self-setting.
Po ═ 2.5; % obstacle affects the distance, and when the distance between the obstacle and the vehicle is greater than this distance, the repulsive force is 0, i.e., is not affected by the obstacle. And is also self-setting. n is 7; % obstacle number l is 0.2; % step size
J is 600; % number of loop iterations
% may also be associated with an inappropriate setting of the initial gain factor, Po, if the desired objective cannot be achieved. % end
% gives obstacle and target information
Xsum ═ 1010; 11.5; 32.2; 44.5; 36; 62, a first step of mixing; 5.56; 88.2 ]; % of this vector is (n +1) × 2 dimensions, where [1010] is the target location and the rest are the locations of obstacles.
Xj is Xo; cycle initial,% j 1, assigning the start coordinate of the vehicle to Xj
This is done by initializing, starting the main cycle, and starting the J% cycle
Goul (j,1) ═ Xj (1); % Goal is the coordinates of each point the car was kept walking through. The start point is initially placed into the vector. Goul (j,2) ═ Xj (2);
% calling calculation angle module
Theta ═ computer _ angle (Xj, Xsum, n); theta is the calculated angle between the vehicle and obstacle and the target to the X-axis, and is calculated by this module with the angle uniformly specified as counterclockwise. % call calculation gravitation module
Angle Theta (1); theta (1) is the angle between the vehicle and the target, which is the gravitational force on the vehicle.
angle _ at ═ Theta (1); % is assigned to the component of the repulsive force in the direction of attraction for subsequent calculations
angle_at
(xxj, Xsum, k, Angle) is set to "computer _ attribute (Xj, Xsum, k, Angle); % calculates two component values of the attraction of the object to the vehicle in the x and y directions.
for i=1:n
angle _ re (i) ═ Theta (i + 1); % calculation the angle for repulsion is a vector, since there are n obstacles, there are n angles.
End。
Specifically, the processor can be selectively integrated or connected with at least one of a positioning chip, a storage chip, a data transmission radio station, a picture transmission radio station, a Beidou chip and the like. So that the unmanned aerial vehicle can remotely transmit the acquired data. Specifically, a flight circuit diagram is prestored through a memory chip. And can optionally adopt the special frequency channel to carry out image transmission when specifically utilizing unmanned aerial vehicle transmission data, reach the image transmission's that improves distance, do not influence image quality's purpose again. The data transmission radio station is consistent with the image circuit principle and optionally comprises a transmitting end, a receiving end and a display end. Specifically, the unmanned aerial vehicle can be provided with a data transmission radio antenna to receive the flight data of the unmanned aerial vehicle sent by the unmanned aerial vehicle. Specifically, the available frequency band of the unmanned aerial vehicle is 902-928 MHZ optionally. And the frequency bands of 840.5-845MHz, 1430-1444MHz or 2408-2440MHz can be used for notifying the use of the spectrum of the unmanned aerial vehicle according to the Ministry of industry and communications.
Further, the distance between the left camera and the right camera is 6-12 cm.
While certain exemplary embodiments of the present invention have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that the described embodiments may be modified in various different ways without departing from the spirit and scope of the present invention. Accordingly, the drawings and description are illustrative in nature and should not be construed as limiting the scope of the invention.
Claims (3)
1. A binocular vision obstacle avoidance system for a fixed wing unmanned aerial vehicle is characterized by comprising an image acquisition device, an instruction device and a fixed wing unmanned aerial vehicle flight controller which are connected in sequence, wherein,
the image acquisition equipment comprises a left camera and a right camera and is used for acquiring video signals and sending the video signals to the instruction subsystem;
the command subsystem is used for generating a corresponding flight control command according to the received video signal;
and the fixed-wing unmanned aerial vehicle flight controller is used for receiving the flight control command and controlling the flight direction according to the flight control command.
2. The binocular vision obstacle avoidance system for a fixed wing drone of claim 1, wherein the command subsystem includes a vision processor and a guidance command calculator, wherein,
the vision processor is used for receiving the video signals collected by the two cameras and calculating the angle and distance parameters between the vision processor and the front obstacle according to the internal parameters of the two cameras;
and the guidance instruction calculator is used for calculating a guidance instruction for controlling the unmanned aerial vehicle to fly next step by utilizing an artificial potential field algorithm according to the angle and distance parameters, and the guidance instruction comprises a pitch angle instruction or a yaw angle instruction.
3. The binocular vision obstacle avoidance system for the fixed wing drone of claim 1, wherein the distance between the left and right cameras is 6-12 cm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720572391.3U CN207182100U (en) | 2017-05-22 | 2017-05-22 | A kind of binocular vision obstacle avoidance system for fixed-wing unmanned plane |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720572391.3U CN207182100U (en) | 2017-05-22 | 2017-05-22 | A kind of binocular vision obstacle avoidance system for fixed-wing unmanned plane |
Publications (1)
Publication Number | Publication Date |
---|---|
CN207182100U true CN207182100U (en) | 2018-04-03 |
Family
ID=61732649
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201720572391.3U Active CN207182100U (en) | 2017-05-22 | 2017-05-22 | A kind of binocular vision obstacle avoidance system for fixed-wing unmanned plane |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN207182100U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110720023A (en) * | 2018-09-25 | 2020-01-21 | 深圳市大疆创新科技有限公司 | Method and device for processing parameters of camera and image processing equipment |
US20220075394A1 (en) * | 2019-05-22 | 2022-03-10 | Autel Robotics Co., Ltd | Autonomous orbiting method and device and uav |
-
2017
- 2017-05-22 CN CN201720572391.3U patent/CN207182100U/en active Active
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110720023A (en) * | 2018-09-25 | 2020-01-21 | 深圳市大疆创新科技有限公司 | Method and device for processing parameters of camera and image processing equipment |
CN110720023B (en) * | 2018-09-25 | 2022-04-29 | 深圳市大疆创新科技有限公司 | Method and device for processing parameters of camera and image processing equipment |
US20220075394A1 (en) * | 2019-05-22 | 2022-03-10 | Autel Robotics Co., Ltd | Autonomous orbiting method and device and uav |
US11755042B2 (en) * | 2019-05-22 | 2023-09-12 | Autel Robotics Co., Ltd. | Autonomous orbiting method and device and UAV |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11460844B2 (en) | Unmanned aerial image capture platform | |
EP3540550B1 (en) | Method for acquiring images from arbitrary perspectives with uavs equipped with fixed imagers | |
WO2018086130A1 (en) | Flight trajectory generation method, control device, and unmanned aerial vehicle | |
CN105843251B (en) | Method, device and system for controlling aircraft | |
CN202600486U (en) | Aerial remote sensing platform airborne operation control system | |
CN104808686A (en) | System and method enabling aircraft to be flied along with terminal | |
CN105620731B (en) | A kind of unmanned aerial vehicle (UAV) control method and unmanned aerial vehicle control system | |
CN106603970A (en) | Video shooting method and system and unmanned aerial vehicle | |
CN110716579B (en) | Target tracking method and unmanned aerial vehicle | |
CN106843275B (en) | Fixed-point flying method, device and system for unmanned aerial vehicle | |
CN109660721B (en) | Unmanned aerial vehicle flight shooting quality optimization method, system, equipment and storage medium | |
WO2018059398A1 (en) | Method, apparatus, and system for controlling multi-rotor aircraft | |
CN207182100U (en) | A kind of binocular vision obstacle avoidance system for fixed-wing unmanned plane | |
CN113228103A (en) | Target tracking method, device, unmanned aerial vehicle, system and readable storage medium | |
CN105867400A (en) | Flying control method and device for unmanned aerial vehicle | |
WO2023036260A1 (en) | Image acquisition method and apparatus, and aerial vehicle and storage medium | |
CN110139038A (en) | It is a kind of independently to surround image pickup method, device and unmanned plane | |
CN204287973U (en) | flight camera | |
CN113776503B (en) | Depth map processing method and device and unmanned aerial vehicle | |
WO2021238743A1 (en) | Flight control method and apparatus for unmanned aerial vehicle, and unmanned aerial vehicle | |
WO2022126397A1 (en) | Data fusion method and device for sensor, and storage medium | |
CN107783542A (en) | The control method and control system of unmanned plane | |
CN111830939A (en) | Unmanned aerial vehicle monitoring method, device, system, medium and electronic equipment | |
KR101876829B1 (en) | Induction control system for indoor flight control of small drones | |
RU2735196C1 (en) | Control method of landing of small unmanned aerial vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |