CN109901580A - A kind of unmanned plane cooperates with unmanned ground robot follows diameter obstacle avoidance system and its method - Google Patents
A kind of unmanned plane cooperates with unmanned ground robot follows diameter obstacle avoidance system and its method Download PDFInfo
- Publication number
- CN109901580A CN109901580A CN201910188193.0A CN201910188193A CN109901580A CN 109901580 A CN109901580 A CN 109901580A CN 201910188193 A CN201910188193 A CN 201910188193A CN 109901580 A CN109901580 A CN 109901580A
- Authority
- CN
- China
- Prior art keywords
- unmanned
- ground robot
- module
- unmanned ground
- unmanned plane
- 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
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
It cooperates the invention discloses a kind of unmanned plane with unmanned ground robot and follows diameter obstacle avoidance system and its method, the system includes the unmanned plane and unmanned ground robot for being equipped with wireless communication module, GPS module and power plant module, and unmanned plane further includes flight control units, airborne calculation processing unit, Multi-sensor Fusion inertial navigation module and video camera；Unmanned ground robot further includes airborne control unit, detection of obstacles module and navigation module；The barrier-avoiding method are as follows: video camera is by the image transmitting of shooting to airborne calculation processing unit, identify road barrier after generate can pass and to unmanned ground robot be accurately positioned, the advance avoidance route that planning obtains is transmitted to wireless ground robot and carries out Navigation Control, simultaneously, Obstacle Position and azimuth information are back to airborne calculation processing unit more variation route by detection of obstacles module, enable unmanned ground robot independent navigation in complex environment, improves the success rate and stability for following diameter avoidance.
Description
Technical field
The present invention relates to unmanned planes, robot autonomous localization technical field, and in particular to a kind of unmanned plane and unmanned ground
It is robot cooperated to follow diameter obstacle avoidance system and its method.
Background technique
The fast development of unmanned plane and unmanned ground robot technology, makes it widely apply disaster assistance field.For
Earthquake, nuclear pollution etc. have safely scene after the calamity of potential threat to human life, can be quick using the high maneuverability of unmanned plane
Arrival scene carries out investigations, searches and rescues and Disaster Assessment, grasps the condition of a disaster rapidly by the open high-altitude visual field and mentions for rescue work
For advantageous information；Disaster scene is arrived at using the relief goods that ground robot can carry urgent need, realizes the search and rescue of the wounded.
However, there may be the factors such as house and tree falls, barrier obstruction for devastated, task is searched and rescued to unmanned ground robot
Avoidance airmanship propose new challenge.Existing airmanship combines the cartographic information that has measured mostly, using being based on
The path point of GPS (global positioning system) is navigated, and passes through the avoiding barriers such as installation laser radar, ultrasonic wave.But it is this kind of to lead
Boat technology disaster assistance application in there are some problems and defect, specific manifestations are as follows: (1) at present civilian GPS precision only
It is 10 meters or so, signal, which is easy to be covered by building and trees, to be influenced and lost, can in narrow landform or complex environment
Navigation can be made to deviate.Economy is insufficient if using professional high-precision GPS.(2) cartographic information prestored can not provide edge
The distribution of obstacles situation of way road, devastateds especially numerous in barrier can be to the nothing advanced according to preset path point
People's ground robot will cause very big puzzlement.(3) existing barrier perception means can not be planned by the active of optimal path
And achievees the purpose that obstacle avoidance and advance.
The prior art is applied to disaster assistance field using a kind of air-ground integration and cooperation search and rescue system, by unmanned plane, several
Crawler type search and rescue robot and electric energy supply robot composition.The function mode of the system are as follows: 1. server schedulings control nothing
It is man-machine to fly along search and rescue route, it determines search and rescue region and caterpillar type robot is sent to by server；2. caterpillar type robot
It forms into columns and sets out along search and rescue route, suspicious region is searched for respectively.If not finding to search and rescue target, leaves a robot and waited in region
Life, remaining robot advance to next region of search；3. if electric energy feeds robot from original place find target in subsequent region
It sets out, supply stays caterpillar type robot electric energy and rushes for target position together.
There are the following problems for the air-ground integration and cooperation search and rescue system: 1. unmanned planes are with caterpillar type robot dependent on existing
Wireless communication means and server communication obtain the information such as advance route and search and rescue region.In devastated, underlying wireless communication
Facility is probably destroyed and which is no longer applicable in.2. caterpillar type robot is formed into columns to advance along preset path and be executed
Search and rescue task only obtains real-time position information by GPS in complex environment, lacks sensing capability to road barrier, pole has
May because barrier obstruct can not be by causing damaged in collision.
Summary of the invention
In order to overcome the drawbacks of the prior art, the present invention, which provides a kind of unmanned plane and cooperates with unmanned ground robot, follows diameter and keeps away
Hinder system and method, by cooperating for unmanned plane and unmanned ground robot, enables unmanned ground robot multiple
Independent navigation in miscellaneous circumstances not known, and improve the success rate and stability for following diameter avoidance.
In order to achieve the above object, the invention adopts the following technical scheme:
The present invention, which provides a kind of unmanned plane and cooperates with unmanned ground robot, follows diameter obstacle avoidance system, including unmanned plane and nobody
Ground robot,
The unmanned plane includes: flight control units, unmanned plane terminal load calculation processing unit, Multi-sensor Fusion inertia
Navigation module, video camera, unmanned generator terminal wireless communication module, unmanned generator terminal GPS module and unmanned generator terminal power plant module,
The flight control units are communicated with Multi-sensor Fusion inertial navigation module, acquire drone status information, are led to
The state of flight of unmanned generator terminal power plant module control unmanned plane is crossed,
The unmanned plane terminal carry calculation processing unit receive flight control units transmitting drone status information, nobody
The location information of generator terminal GPS module acquisition and the image information of video camera acquisition, plan unmanned ground robot advance route, lead to
It crosses unmanned generator terminal wireless communication module and is transmitted to unmanned ground robot；
The unmanned ground robot includes: unmanned ground robot end power plant module, unmanned ground robot terminal load
Control unit, detection of obstacles module, navigation module, unmanned ground robot end wireless communication module and unmanned ground robot
GPS module is held,
The unmanned ground robot terminal carry control unit respectively with navigation module, unmanned ground robot end GPS mould
Block, the communication of detection of obstacles module, for acquiring the status information of unmanned ground robot, location information and the barrier of direction of advance
Hinder object location information, updates the advance route that unmanned ground robot end wireless communication module receives, and pass through unmanned ground
Robotic end power plant module controls unmanned ground robot and advances.
The unmanned plane is also equipped with cradle head of two degrees of freedom, the flight control units control as a preferred technical solution,
Cradle head of two degrees of freedom processed adjusts the angle, and the video camera is mounted on cradle head of two degrees of freedom.
The Multi-sensor Fusion inertial navigation module includes gyro module, unmanned plane as a preferred technical solution,
Acceleration sensing module, unmanned generator terminal electrical compass module, gas pressure sensor module and unmanned generator terminal posture fused filtering device are held,
The gyro module is used to measure the triaxial attitude angle angular speed of unmanned plane, the unmanned generator terminal acceleration sensing
Module is for measuring three axis linear accelerations, and the unmanned generator terminal electrical compass module is for measuring yaw angle, the air pressure
Sensor module for measuring cruising altitude, the unmanned generator terminal posture fused filtering device for merge gyro module, nobody
The data of generator terminal acceleration sensor module, unmanned generator terminal electrical compass module and gas pressure sensor module, obtain unmanned plane
Status information.
The navigation module includes unmanned ground robot end electrical compass module, wheel speed as a preferred technical solution,
Sensing module, unmanned ground robot end acceleration sensing module, inclination angle sensing module and unmanned ground robot end posture are melted
Filter is closed,
The unmanned ground robot end electrical compass module is used to measure the yaw angle of unmanned ground robot, described
Wheel speed sensing module is used to measure the speed of unmanned ground robot, and the unmanned ground robot end acceleration sensing module is used
In the acceleration for measuring unmanned ground robot, the inclination angle sensing module is used to measure the attitude angle of unmanned ground robot,
The unmanned ground robot end posture fused filtering device is for merging unmanned ground robot end electrical compass module, wheel speed biography
Feel module, unmanned ground robot end acceleration sensing module, the data of inclination angle sensing module, obtains unmanned ground robot
Status information,
It cooperates the present invention also provides a kind of unmanned plane with unmanned ground robot and follows diameter barrier-avoiding method, include the following steps:
S1: unmanned ground robot carries unmanned plane and arrives at task starting point W0, unmanned plane takes off, and unmanned ground robot stops
Stay in task starting point W0It awaits orders, unmanned plane flies to preset task road sign point W1；
S2: image sequence, unmanned plane terminal carry calculation processing unit to collected image over the ground over the ground for video camera acquisition
Sequence is split processing using rigid dividing method, carries out tagsort to segmentation result, is marked using classifier different
Terrain category, extract can advance road image block composition can travel path region, while to the image sequence over the ground of acquisition into
Row target identification marks unmanned ground robot and all kinds of barriers area size in the picture and coordinate position, can lead to
Where row passage zone subtracts barrier, formed it is new can pass region, extraction can pass p；
S3: air pressure is acquired according to Multi-sensor Fusion inertial navigation module, obtains the current flying altitude h of unmanned plane；
S4: using the model parameter of video camera, in conjunction with the reality of the current flying altitude h of unmanned plane, unmanned ground robot
Area size in border size, coordinate position and image in the picture carries calculation processing unit by unmanned plane terminal and calculates
Unmanned ground robot and can real standard deviation between pass p, and result is passed through into unmanned generator terminal radio communication mold
Block is sent to unmanned ground robot end wireless communication module；
S5: unmanned ground robot terminal carries control unit and calculates kinematic parameter according to deviation, controls unmanned ground machine
Device people along can pass p advance, while immediately ahead of the unmanned ground robot of detection of obstacles module scans within fan angle σ
Barrier；If barrier exists, unmanned ground machine is obtained according to navigation module and unmanned ground robot end GPS module
The relative distance information of the current location information of device people, yaw angle and barrier, calculates the physical location of barrier, by nobody
Ground robot end wireless communication module sends this information to unmanned generator terminal wireless communication module, is carried and is calculated by unmanned plane terminal
Processing unit update can pass p '；
S6: judge whether unmanned ground robot has arrived at task road sign point Wn, it is that unmanned plane flies to next road sign point
Wn+1, go to step S7, and otherwise go to step S2；
S7: if road sign point is task terminal Wf, then unmanned ground robot is arriving at WfAfterwards, unmanned plane is in unmanned ground machine
The landing recycling of device people top, task terminate, and the S2 that otherwise gos to step continues task until task terminates.
That specific step is as follows is described for tagsort described in step S2 as a preferred technical solution:
The image sequence over the ground is divided into M × N number of image after unmanned plane terminal carries calculation processing unit dividing processing
Fritter extracts special each image fritter using Local textural feature operator LBP, in conjunction with the color space HSV of image fritter
Simultaneously composition characteristic vector is levied, the LBP+HSV feature of extraction is made at classification using the support vector machine classifier SVM of pre-training
Reason, label can traffic areas and impassabitity region, by labeled as can the image fritter of traffic areas connect, obtain it is final can
Pass result.
That specific step is as follows is described for target identification described in step S2 as a preferred technical solution:
Make target identification using the original image that end-to-end convolutional neural networks model exports video camera, by minimum outside
It connects rectangle frame and marks unmanned ground robot and all kinds of barriers position in the picture, the top left corner apex for obtaining rectangle frame is sat
Mark, the width of rectangle frame and height, if barrier be present in can in traffic areas, can traffic areas subtract barrier
Minimum circumscribed rectangle frame region, formed it is new can pass region；At the same time, the center line conduct for extracting the region can lead to
Walking along the street diameter p.
The unmanned ground robot of calculating described in step S4 and can be between pass p as a preferred technical solution,
Real standard deviation, specific calculation are as follows:
The lens distortion of the inner parameter and correcting camera of video camera is obtained using Zhang Shi chessboard calibration method；According to pin hole
Camera model, it is assumed that unmanned plane imaging plane of video camera in flight course is parallel with level ground, can by geometrical relationship
Obtain real standard distance d representated by the flying height h of unmanned plane, the unit pixel of camera outputhThere are inverse ratios
Relationship, calculation formula are as follows:
Wherein, c is proportionality constant.The figure between unmanned ground robot and pass p is being calculated in camera review
As number of pixels n, the horizontal distance which represents is obtained as nd according to calculation formulah, substitution can pass p calculate
Unmanned ground robot and can real standard deviation between pass p.
Unmanned ground robot is controlled along the road that can pass through using pure track algorithm in step S5 as a preferred technical solution,
Diameter p advances, and after the actual position coordinate for calculating barrier, using actual position coordinate as the center of circle, radius r is set as to lead to
Row region, carrying calculation processing unit update by unmanned plane terminal can pass p '.
Judge whether unmanned ground robot has arrived at task road sign point described in step S6 as a preferred technical solution,
WnJudgment method use: calculate unmanned ground robot and video camera output picture centre real standard distance s, if s
Then think that unmanned ground robot has arrived at road sign point Wn less than given threshold ε, execution accordingly jumps.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) present invention realizes determining for unmanned ground robot by handling the technological means of unmanned plane field of view information over the ground
The identification of position, surface road and barrier, compared with the conventional navigation means that vehicle, ground robot are installed, unmanned plane high-altitude
The accessible visual field can more effectively guide unmanned ground robot to follow diameter navigation and avoiding barrier over the ground.
(2) present invention is solved by combining visual identification algorithm, camera model parameter and Multi-sensor Fusion data
The location estimation problem of unmanned ground robot compared with traditional GPS positioning mode improves positioning accuracy.
(3) unmanned plane proposed by the present invention cooperates with unmanned ground robot follows diameter obstacle avoidance system and belongs to self-sustaining formula system,
The interaction of information, data and control instruction is only produced between unmanned plane and unmanned ground robot by small scale wireless network
It is raw, it needs not move through basic network communications facility and external system (such as earth station) carries out information exchange, so that this system
It is remained under the extreme externals environmental condition such as scene after the calamity for causing basic network communications facility impaired after disaster generation normal complete
At information exchange task and realize set function.
(4) present invention is utilized using low cost, the unmanned plane of high maneuverability and unmanned ground robot as task carrier
Visual identification algorithm, which realizes, follows diameter navigation and avoiding barrier function, is especially suitable for rapid deployment to be unfavorable for the mankind close
Appointed task is completed in particular surroundings (after such as calamity in scene), substantially reduces the risk of casualties.
(5) present invention employs the segmented path policy based on road sign point, unmanned plane can be made to hold during task
It is continuous that control instruction is positioned and sent to unmanned ground robot, achieve the effect that the two collaboration is advanced.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the present embodiment UAV system；
Fig. 2 is the structural schematic diagram of the Multi-sensor Fusion inertial navigation module of the present embodiment UAV system；
Fig. 3 is the structural schematic diagram of the unmanned ground robot system of the present embodiment；
Fig. 4 is the structural schematic diagram of the navigation module of the unmanned ground robot system of the present embodiment；
Fig. 5 is that the present embodiment unmanned plane cooperates with unmanned ground robot and follows the flow chart of diameter barrier-avoiding method.
Wherein, 1- unmanned aerial vehicle body frame, 2- flight control units, 3- unmanned plane terminal load calculation processing unit, 4- are more
Sensor merge inertial navigation module, 5- cradle head of two degrees of freedom, 6- video camera, the unmanned generator terminal wireless communication module of 7-, 8- nobody
The unmanned generator terminal battery component of generator terminal GPS module, 9-, the unmanned generator terminal power plant module of 10-, 11- gyro module, the unmanned generator terminal of 12-
The unmanned generator terminal posture fusion of the unmanned generator terminal electrical compass module of acceleration sensing module, 13-, 14- gas pressure sensor module, 15-
The unmanned ground robot terminal of the unmanned ground robot fuselage ring of filter, 16-, 17- carries control unit, 18- obstacle quality testing
Survey module, 19- navigation module, the unmanned ground robot end wireless communication module of 20-, the unmanned ground robot end GPS mould of 21-
The unmanned ground robot end battery component of block, 22-, the unmanned ground robot end power plant module of 23-, the unmanned ground robot of 24-
Hold electrical compass module, 25- wheel speed sensing module, the unmanned ground robot end acceleration sensing module of 26-, the inclination angle 27- sensing
The unmanned ground robot end posture fused filtering device of module, 28-.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
Embodiment 1:
Diameter obstacle avoidance system is followed as shown in Figure 1, providing a kind of unmanned plane in the present embodiment and cooperating with unmanned ground robot, is wrapped
Unmanned plane and unmanned ground robot are included,
The unmanned plane includes: unmanned aerial vehicle body frame 1, flight control units 2, airborne calculation processing unit 3, more sensings
Device merges inertial navigation module 4, cradle head of two degrees of freedom 5, video camera 6, unmanned generator terminal wireless communication module 7, unmanned generator terminal GPS mould
Block 8, unmanned generator terminal battery component 9 and unmanned generator terminal power plant module 10,
The flight control units 2 carry calculation processing unit 3, Multi-sensor Fusion inertial navigation module with unmanned plane terminal
4, cradle head of two degrees of freedom 5 is connected with unmanned generator terminal power plant module 10, and the unmanned plane terminal carries calculation processing unit 3 and unmanned plane
End wireless communication module 7 is connected with unmanned generator terminal GPS module 8, and the video camera 6 is mounted on cradle head of two degrees of freedom 5, the nothing
Man-machine end battery component 9 carries calculation processing unit 3 and unmanned generator terminal power plant module 10 to flight control units 2, unmanned plane terminal
Power supply, the flight control units acquire drone status information, control the flight path of unmanned plane,
Its working principle is that: unmanned plane during the work time, flight control units 2 and Multi-sensor Fusion inertial navigation mould
Block 4 communicate, update the status informations such as UAV Attitude angle, linear acceleration and the flying height of current sample time, using than
Example integral-derivative controller is by the state of flight of unmanned generator terminal power plant module 10 control unmanned plane, and in synchronization by state
Information is transmitted to unmanned plane terminal and carries calculation processing unit 3；At the same time, flight control units 2 calculate separately current unmanned plane
The angle of pitch angle, roll angle and horizontal plane is poor, and control cradle head of two degrees of freedom 5 compensates the included angle, makes video camera 6 at nobody
Vertically downward state is always maintained in machine flight course, angle is constant；Video camera 6 captures image over the ground, coding with certain frame per second
After be transmitted to unmanned plane terminal carry calculation processing unit 3 handle；Unmanned plane terminal carries the processing of calculation processing unit 3 and is controlled by flight
It drone status information that unit 2 transmits, the location information that is obtained by unmanned generator terminal GPS module 8 and is obtained by video camera 6
Image calculates the kinematic parameter of unmanned plane itself and controls the flight path of unmanned plane by flight control units 2, and calculates
It plans the progress path of unmanned ground robot and result is transmitted to unmanned ground machine by unmanned generator terminal wireless communication module 7
People；
As shown in Fig. 2, Multi-sensor Fusion inertial navigation module 4 includes gyro module 11, unmanned generator terminal acceleration biography
Feel module 12, unmanned generator terminal electrical compass module 13, gas pressure sensor module 14 and unmanned generator terminal posture fused filtering device 15, institute
State gyro module 11, unmanned generator terminal acceleration sensor module 12, unmanned generator terminal electrical compass module 13 and baroceptor
Module 14 is connect with unmanned generator terminal posture fused filtering device 15 respectively.
In the present embodiment, the gyro module 11 is used to measure the triaxial attitude angle angular speed of unmanned plane, the nothing
Man-machine end acceleration sensing module 12 is for measuring three axis linear accelerations, and unmanned 13 module of generator terminal electronic compass is for surveying
Yaw angle is measured, the gas pressure sensor module 14 is for measuring cruising altitude, the unmanned generator terminal posture fused filtering device 15
For merging the data of each sensor module and calculating the linear velocity and yaw angle of unmanned ground robot, in the present embodiment
In, data are carried out by fusion Denoising disposal using linear kalman filter, obtain the status information of unmanned plane；
As shown in figure 3, unmanned ground robot include: unmanned ground robot fuselage ring 16, airborne control unit 17,
Detection of obstacles module 18, navigation module 19, unmanned ground robot end wireless communication module 20, unmanned ground robot end
GPS module 21, unmanned ground robot end battery component 22 and unmanned ground robot end power plant module 23,
In the present embodiment, the airborne control unit 17 and detection of obstacles module 18, navigation module 19, unmanned ground
Robotic end wireless communication module 20, unmanned ground robot end GPS module 21 and unmanned ground robot end power plant module 23
It is connected, the unmanned ground robot end battery component 22 gives airborne control unit 17 and unmanned ground robot end power plant module
23 power supplies.
In the present embodiment, during the work time, unmanned ground robot terminal carries control unit to unmanned ground robot
17 communicate with navigation module 19, unmanned ground robot end GPS module 21 respectively, update the unmanned ground machine of current sample time
The posture informations such as position, speed and the yaw angle of people, and before the detection module 18 that breaks the barriers obtains unmanned ground robot
Into the obstacle position information in direction；At the same time, unmanned ground robot terminal load control unit 17 passes through unmanned ground machine
Device people end wireless communication module 20 monitors the wireless signal that unmanned generator terminal wireless communication module 7 is sent, and acquisition is calculated by unmanned plane
The progress path of the unmanned ground robot obtained；If barrier is not present in direction of advance, unmanned ground machine is controlled
People end power plant module 23 is advanced according to given route；Otherwise, new progress path, same time control are calculated according to obstacle position information
Unmanned ground robot end power plant module 23 is made to advance according to new route；
As shown in figure 4, navigation module 19 includes unmanned ground robot end electrical compass module 24, wheel speed sensing module
25, unmanned ground robot end acceleration sensing module 26, inclination angle sensing module 27 and the fusion of unmanned ground robot end posture
Filter 28,
In the present embodiment, the unmanned ground robot end electrical compass module 24 is for measuring unmanned ground robot
Yaw angle, the wheel speed sensing module 25 is used to measure the speed of unmanned ground robot, the unmanned ground robot
End acceleration sensing module 26 is used to measure the acceleration of unmanned ground robot, and the inclination angle sensing module 27 is for measuring nothing
The attitude angle (tilt angle) of people's ground robot, the unmanned ground robot end posture fused filtering device 28 are used for each sensing
The data fusion of device module and the linear velocity and yaw angle for calculating unmanned ground robot, in the present embodiment, using linear
Data are carried out fusion Denoising disposal by Kalman filter, obtain the status information of unmanned ground robot.
In the present embodiment, the unmanned ground robot end electrical compass module 24, wheel speed sensing module 25, unmanned ground
Face robotic end acceleration sensing module 26, inclination angle sensing module 27 respectively with unmanned ground robot end posture fused filtering device
28 connections.
It cooperates with unmanned ground robot as shown in figure 5, the present embodiment also provides a kind of unmanned plane and follows diameter barrier-avoiding method,
Work step includes:
S1: unmanned ground robot carries unmanned plane and arrives at task starting point W0, unmanned plane takes off, and unmanned ground robot stops
Stay in task starting point W0It awaits orders, unmanned plane flies to preset task road sign point W1；
Specifically, unmanned ground robot carries unmanned plane and arrives at task starting point in the task incipient stage, unmanned plane is opened
Unmanned generator terminal GPS module 8 positions, and task starting point is recorded as road sign point W0, take off to preset height and preset task road of flying to
Punctuate W1；
Image sequence, unmanned plane terminal carry calculation processing unit 3 to collected to map over the ground for S2, the acquisition of video camera 6
As sequence is split processing using rigid dividing method, tagsort is carried out to segmentation result, utilizes classifier label difference
Terrain category, extract the road image block composition that can advance can travel path region, while to the image sequence over the ground of acquisition
Target identification is carried out, unmanned ground robot and all kinds of barriers area size in the picture and coordinate position are marked, can
Where pass region subtracts barrier, formed it is new can pass region, extraction can travel path p；
Specifically, unmanned plane is according to the location information of unmanned generator terminal GPS module 8 by road sign point W0Navigate to W1And hover, it takes the photograph
Camera 6 starts to work and captures image over the ground by certain frame per second, and each frame image transmitting to unmanned plane terminal carries calculation processing list
Member 3 makees rigid dividing processing, is divided into M × N number of image fritter, to each image fritter, utilizes Local textural feature operator
LBP, color space HSV extraction feature and composition characteristic vector in conjunction with image fritter, utilize the SVM support vector machines of pre-training
Classifier makees classification processing to the LBP+HSV feature of extraction, label can traffic areas and impassabitity region, by image fritter
Classification results merge after obtain it is final can pass result；Meanwhile utilizing end-to-end convolutional neural networks model
The original image that YOLOv3 exports video camera 6 makees target identification, remembers unmanned ground robot by minimum circumscribed rectangle collimation mark
With all kinds of barriers position in the picture, the top left corner apex (x of rectangle frame is obtainedn,yn) coordinate, rectangle frame width w and height
Spend h, if barrier be present in can in traffic areas, can traffic areas subtract the minimum circumscribed rectangle frame region of barrier,
Formed it is new can pass region；At the same time, the center line conduct for extracting the region can pass p；
S3, according to Multi-sensor Fusion inertial navigation module 4, obtain the current flying altitude h of unmanned plane；
S4, using the model parameter of video camera 6, in conjunction with the reality of the current flying altitude h of unmanned plane, unmanned ground robot
Area size in border size, coordinate position and image in the picture carries calculation processing unit 3 by unmanned plane terminal and calculates
Unmanned ground robot and can real standard deviation between pass p, and result is passed through into unmanned generator terminal radio communication mold
Block 7 is sent to unmanned ground robot end wireless communication module 20；
Specifically, by Zhang Shi chessboard calibration method, the inner parameter of available video camera 6 and the camera lens of correcting camera
Distortion；According to pinhole camera modeling, it is assumed that the unmanned plane imaging plane of video camera 6 and level ground in flight course is flat
Row can show that the flying height h of unmanned plane, video camera 6 export practical water representated by the unit pixel of image as geometrical relationship
Flat distance dhThere are inverse relation, calculation formula is as follows:
Wherein c is proportionality constant；Again because size is equal in the actual size of unmanned ground robot, coordinate position and image
It is known that therefore can according to unmanned ground robot in the proportionality constant c of above-mentioned formula, camera review and pass p it
Between image pixel number n, calculate the n pixel representative horizontal distance ndh, and then substituting into can pass p calculating nothing
People's ground robot and can real standard deviation between pass p；The calculated result will be by unmanned generator terminal radio communication mold
Block 7 is sent to unmanned ground robot end wireless communication module 20；
S5, unmanned ground robot terminal carry control unit 17 and calculate kinematic parameter according to deviation, control unmanned ground
Robot travelling route p advances, at the same detection of obstacles module 18 scan immediately ahead of unmanned ground robot fan angle σ it
Interior barrier；If barrier exists, nobody is obtained according to navigation module 19 and unmanned ground robot end GPS module 21
The relative distance information of the current location information of ground robot, yaw angle and barrier, calculates the physical location of barrier,
Unmanned generator terminal wireless communication module 7 is sent this information to by unmanned ground robot end wireless communication module 20, passes through unmanned plane
Terminal carries the update of calculation processing unit 3 can pass p '；
Specifically, can be used pure after unmanned ground robot terminal load control unit 17 obtains real standard deviation
It tracks (Pure Pursuit) algorithm and controls unmanned ground robot along route p advance, and the detection module 18 that breaks the barriers is real
When scanning front fan angle σ region in barrier；If barrier exists, can be according to GPS coordinate, yaw angle, barrier
With the actual range between unmanned ground robot, the actual coordinate of barrier is calculated by geometrical relationship, informs unmanned plane
Afterwards, it is set as impassabitity region by the radius r in the center of circle of the coordinate, unmanned plane terminal carries 3 reference of calculation processing unit
Method update in step S2 can pass p '；
S6, judge whether unmanned ground robot has arrived at task road sign point Wn, it is that unmanned plane flies to next road sign point
Wn+1, go to step S7, and otherwise go to step S2；
Specifically, calculating the reality for the picture centre (i.e. unmanned plane center) that unmanned ground robot and video camera 6 export
Horizontal distance s, calculation method think that unmanned ground robot has arrived at road sign point if the small Mr. Yu's threshold epsilon of s referring to step S4
Wn, execute and accordingly jump.
If S7, road sign point are task terminal Wf, then unmanned ground robot is arriving at WfAfterwards, unmanned plane is in unmanned ground machine
The landing recycling of device people top, task terminate, and otherwise jump to S2 and continue task until task terminates.
In the present embodiment, preferred embodiment are as follows:
As shown in connection with fig. 1, DJI M100 type quadrotor drone can be selected in unmanned plane, in the unmanned aerial vehicle body frame 1 in
Set flight control units 2, Multi-sensor Fusion inertial navigation module 4, unmanned generator terminal GPS module 8 and unmanned generator terminal power mould
DJI TB48D type poly-lithium battery can be selected in block 10, unmanned generator terminal battery component 9, and unmanned plane terminal carries calculation processing unit 3
NVidia TX2 type can be selected, cradle head of two degrees of freedom 5 can be selected to be closed by BGC3.0 type control panel, 2208 type hollow shaft motors, aluminium
The combinations such as golden bracket are constituted, and UI-1221-LE type can be selected in video camera 6, and TP-LINK can be selected in unmanned generator terminal wireless communication module 7
WN823N type；
As shown in connection with fig. 3, Autolabor Pro type crawler type ground robot, the nothing can be selected in unmanned ground robot
Built-in navigation module 19, unmanned ground robot end battery component 22 and unmanned ground machine in people's ground robot fuselage ring 16
Device people end power plant module 23, unmanned ground robot terminal, which carries control unit 17, can be selected 3 type of Raspberry Pi, barrier
Hukuyo URG-04LX-UG1 type can be selected in detection module 18, and TP- can be selected in unmanned ground robot end wireless communication module 20
NEO-7N type can be selected in LINK WN823N type, unmanned ground robot end GPS module 21；
As shown in connection with fig. 5, image resolution ratio may be configured as 1152 × 864, M=32, N=24, ε=5 meter.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (10)
1. a kind of unmanned plane cooperates with unmanned ground robot and follows diameter obstacle avoidance system, which is characterized in that including unmanned plane and nobody
Ground robot,
The unmanned plane includes: flight control units, unmanned plane terminal load calculation processing unit, Multi-sensor Fusion inertial navigation
Module, video camera, unmanned generator terminal wireless communication module, unmanned generator terminal GPS module and unmanned generator terminal power plant module,
The flight control units are communicated with Multi-sensor Fusion inertial navigation module, are acquired drone status information, are passed through nothing
The state of flight of man-machine end power plant module control unmanned plane,
The unmanned plane terminal carries calculation processing unit and receives the drone status information of flight control units transmitting, unmanned generator terminal
The location information of GPS module acquisition and the image information of video camera acquisition, plan unmanned ground robot advance route, pass through nothing
Man-machine end wireless communication module is transmitted to unmanned ground robot；
The unmanned ground robot includes: unmanned ground robot end power plant module, the load control of unmanned ground robot terminal
Unit, detection of obstacles module, navigation module, unmanned ground robot end wireless communication module and unmanned ground robot end
GPS module,
The unmanned ground robot terminal carry control unit respectively with navigation module, unmanned ground robot end GPS module, barrier
Analyte detection module is hindered to communicate, for acquiring the status information of unmanned ground robot, location information and the barrier of direction of advance
Location information updates the advance route that unmanned ground robot end wireless communication module receives, and passes through unmanned ground machine
People end power plant module controls unmanned ground robot and advances.
2. unmanned plane according to claim 1 cooperates with unmanned ground robot and follows diameter obstacle avoidance system, which is characterized in that institute
It states unmanned plane and is also equipped with cradle head of two degrees of freedom, the flight control units control cradle head of two degrees of freedom adjusts the angle, described to take the photograph
Camera is mounted on cradle head of two degrees of freedom.
3. unmanned plane according to claim 1 cooperates with unmanned ground robot and follows diameter obstacle avoidance system, which is characterized in that institute
Stating Multi-sensor Fusion inertial navigation module includes gyro module, unmanned generator terminal acceleration sensing module, unmanned generator terminal electronics
Compass module, gas pressure sensor module and unmanned generator terminal posture fused filtering device,
The gyro module is used to measure the triaxial attitude angle angular speed of unmanned plane, the unmanned generator terminal acceleration sensing module
For measuring three axis linear accelerations, the unmanned generator terminal electrical compass module is for measuring yaw angle, the air pressure sensing
Device module is for measuring cruising altitude, and the unmanned generator terminal posture fused filtering device is for merging gyro module, unmanned generator terminal
The data of acceleration sensor module, unmanned generator terminal electrical compass module and gas pressure sensor module, obtain the state of unmanned plane
Information.
4. unmanned plane according to claim 1 cooperates with unmanned ground robot and follows diameter obstacle avoidance system, which is characterized in that institute
Stating navigation module includes unmanned ground robot end electrical compass module, wheel speed sensing module, the acceleration of unmanned ground robot end
Sensing module, inclination angle sensing module and unmanned ground robot end posture fused filtering device are spent,
The unmanned ground robot end electrical compass module is used to measure the yaw angle of unmanned ground robot, the wheel speed
Sensing module is used to measure the speed of unmanned ground robot, and the unmanned ground robot end acceleration sensing module is for surveying
The acceleration of unmanned ground robot is measured, the inclination angle sensing module is used to measure the attitude angle of unmanned ground robot, described
Unmanned ground robot end posture fused filtering device is for merging unmanned ground robot end electrical compass module, wheel speed sensing mould
Block, unmanned ground robot end acceleration sensing module, the data of inclination angle sensing module, obtain the state of unmanned ground robot
Information.
5. a kind of unmanned plane cooperates with unmanned ground robot and follows diameter barrier-avoiding method, which is characterized in that include the following steps:
S1: unmanned ground robot carries unmanned plane and arrives at task starting point W0, unmanned plane takes off, and unmanned ground robot rests on
Task starting point W0It awaits orders, unmanned plane flies to preset task road sign point W1；
S2: image sequence, unmanned plane terminal carry calculation processing unit to collected image sequence over the ground over the ground for video camera acquisition
Processing is split using rigid dividing method, tagsort is carried out to segmentation result, different landform is marked using classifier
Classification, extract can advance road image block composition can travel path region, while to the image sequence over the ground of acquisition carry out mesh
The area size not marked unmanned ground robot and all kinds of barriers in the picture and coordinate position are identified, on the road that can pass through
Where diameter region subtracts barrier, formed it is new can pass region, extraction can pass p；
S3: air pressure is acquired according to Multi-sensor Fusion inertial navigation module, obtains the current flying altitude h of unmanned plane；
S4: using the model parameter of video camera, in conjunction with the current flying altitude h of unmanned plane, the practical ruler of unmanned ground robot
Area size in coordinate position and image very little, in the picture carries calculation processing unit by unmanned plane terminal and calculates nobody
Ground robot and can real standard deviation between pass p, and result is sent out by unmanned generator terminal wireless communication module
It send to unmanned ground robot end wireless communication module；
S5: unmanned ground robot terminal carries control unit and calculates kinematic parameter according to deviation, controls unmanned ground robot
Along can pass p advance, while the barrier immediately ahead of the unmanned ground robot of detection of obstacles module scans within fan angle σ
Hinder object；If barrier exists, unmanned ground robot is obtained according to navigation module and unmanned ground robot end GPS module
The relative distance information of current location information, yaw angle and barrier, calculates the physical location of barrier, by unmanned ground
Robotic end wireless communication module sends this information to unmanned generator terminal wireless communication module, carries calculation processing by unmanned plane terminal
Unit update can pass p '；
S6: judge whether unmanned ground robot has arrived at task road sign point Wn, it is that unmanned plane flies to next road sign point Wn+1, jump
Step S7 is gone to, otherwise go to step S2；
S7: if road sign point is task terminal Wf, then unmanned ground robot is arriving at WfAfterwards, unmanned plane is in unmanned ground robot
Top landing recycling, task terminate, and the S2 that otherwise gos to step continues task until task terminates.
6. unmanned plane according to claim 5 cooperates with unmanned ground robot and follows diameter barrier-avoiding method, which is characterized in that step
That specific step is as follows is described for tagsort described in rapid S2:
It is small to be divided into M × N number of image after unmanned plane terminal carries calculation processing unit dividing processing for the image sequence over the ground
Block extracts feature using Local textural feature operator LBP, in conjunction with the color space HSV of image fritter to each image fritter
And composition characteristic vector, classification processing is made to the LBP+HSV feature of extraction using the support vector machine classifier SVM of pre-training,
Label can traffic areas and impassabitity region, by labeled as can traffic areas image fritter connect, obtain final lead to
Row route result.
7. unmanned plane according to claim 5 cooperates with unmanned ground robot and follows diameter barrier-avoiding method, which is characterized in that step
That specific step is as follows is described for target identification described in rapid S2:
Make target identification using the original image that end-to-end convolutional neural networks model exports video camera, passes through minimum external square
Shape collimation mark remembers unmanned ground robot and all kinds of barriers position in the picture, obtains top left corner apex coordinate, the square of rectangle frame
The width and height of shape frame, if barrier be present in can in traffic areas, can traffic areas subtract the minimum of barrier
Boundary rectangle frame region, formed it is new can pass region；At the same time, the center line in the region is extracted as the road that can pass through
Diameter p.
8. unmanned plane according to claim 5 cooperates with unmanned ground robot and follows diameter barrier-avoiding method, which is characterized in that step
Calculated described in rapid S4 unmanned ground robot and can real standard deviation between pass p, specific calculation are as follows:
The lens distortion of the inner parameter and correcting camera of video camera is obtained using Zhang Shi chessboard calibration method；It is imaged according to pin hole
Machine model, it is assumed that unmanned plane imaging plane of video camera in flight course is parallel with level ground, can be obtained by geometrical relationship
Real standard distance d representated by the flying height h of unmanned plane, the unit pixel of camera outputhThere are inverse relation,
Calculation formula is as follows:
Wherein, c is proportionality constant, and the image slices between unmanned ground robot and pass p are being calculated in camera review
Plain number n obtains the horizontal distance that the pixel represents according to calculation formula as ndh, substitution can pass p calculate nobody
Ground robot and can real standard deviation between pass p.
9. unmanned plane according to claim 5 cooperates with unmanned ground robot and follows diameter barrier-avoiding method, which is characterized in that step
In rapid S5 using pure track algorithm control unmanned ground robot along can pass p advance, calculate the physical location of barrier
After coordinate, using actual position coordinate as the center of circle, radius r is set as impassabitity region, is carried and is calculated by unmanned plane terminal
Processing unit update can pass p '.
10. unmanned plane according to claim 5 cooperates with unmanned ground robot and follows diameter barrier-avoiding method, which is characterized in that
Judge whether unmanned ground robot has arrived at task road sign point W described in step S6nJudgment method use: calculate unmanned ground
The real standard distance s of face robot and the picture centre of video camera output thinks unmanned ground if s is less than given threshold ε
Robot has arrived at road sign point Wn, and execution accordingly jumps.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910188193.0A CN109901580A (en) | 2019-03-13 | 2019-03-13 | A kind of unmanned plane cooperates with unmanned ground robot follows diameter obstacle avoidance system and its method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910188193.0A CN109901580A (en) | 2019-03-13 | 2019-03-13 | A kind of unmanned plane cooperates with unmanned ground robot follows diameter obstacle avoidance system and its method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109901580A true CN109901580A (en) | 2019-06-18 |
Family
ID=66952182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910188193.0A Pending CN109901580A (en) | 2019-03-13 | 2019-03-13 | A kind of unmanned plane cooperates with unmanned ground robot follows diameter obstacle avoidance system and its method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109901580A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209176A (en) * | 2019-06-28 | 2019-09-06 | 北京史河科技有限公司 | A kind of robot |
| CN110262567A (en) * | 2019-06-27 | 2019-09-20 | 深圳市道通智能航空技术有限公司 | A kind of path relaying space of points generation method, device and unmanned plane |
| CN110399807A (en) * | 2019-07-04 | 2019-11-01 | 深圳前海达闼云端智能科技有限公司 | Detect method, apparatus, readable storage medium storing program for executing and the electronic equipment of ground obstacle |
| CN110989505A (en) * | 2019-10-28 | 2020-04-10 | 中国人民解放军96782部队 | Unmanned command and dispatch system based on ground equipment machine vision |
| CN110989672A (en) * | 2019-12-12 | 2020-04-10 | 国网黑龙江省电力有限公司七台河供电公司 | Unmanned aerial vehicle-based real-time power transmission line fault detection system and routing inspection method thereof |
| CN111008949A (en) * | 2019-08-16 | 2020-04-14 | 苏州喆安医疗科技有限公司 | Soft and hard tissue detection method for tooth image |
| CN111352426A (en) * | 2020-03-17 | 2020-06-30 | 广西柳工机械股份有限公司 | Vehicle obstacle avoidance method, vehicle obstacle avoidance device, vehicle obstacle avoidance system and vehicle |
| CN111427353A (en) * | 2020-04-01 | 2020-07-17 | 无锡格物智能科技有限公司 | Roadblock navigation optimization method, device, terminal, system and storage medium |
| CN111427352A (en) * | 2020-04-01 | 2020-07-17 | 无锡格物智能科技有限公司 | Interaction method for laying mobile roadblocks, terminal, unmanned aerial vehicle and storage medium |
| CN111830995A (en) * | 2020-08-06 | 2020-10-27 | 中国科学院自动化研究所 | Group intelligent cooperation method and system based on hybrid architecture |
| CN112020981A (en) * | 2020-09-14 | 2020-12-04 | 皖西学院 | Intelligent weeding robot system based on machine vision |
| 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 |
| WO2021078203A1 (en) * | 2019-10-22 | 2021-04-29 | 深圳市道通智能航空技术有限公司 | Obstacle avoidance method for aircraft, and aircraft, flight system, and storage medium |
| CN112926371A (en) * | 2019-12-06 | 2021-06-08 | 中国移动通信集团设计院有限公司 | Road surveying method and system |
| CN112923928A (en) * | 2021-01-29 | 2021-06-08 | 江苏提米智能科技有限公司 | Photovoltaic panel navigation method and device based on image recognition, electronic equipment and storage medium |
| CN113002774A (en) * | 2021-02-19 | 2021-06-22 | 北京玄马知能科技有限公司 | Robot inspection system based on ground-air integrated cooperative work |
| CN113295156A (en) * | 2021-05-08 | 2021-08-24 | 西安达升科技股份有限公司 | AGV fusion navigation system and method |
| WO2021179293A1 (en) * | 2020-03-13 | 2021-09-16 | 深圳市大疆创新科技有限公司 | Gimbal control method and apparatus, unmanned aerial vehicle, and storage medium |
| CN113515132A (en) * | 2021-09-13 | 2021-10-19 | 深圳市普渡科技有限公司 | Robot path planning method, robot, and computer-readable storage medium |
| CN113781676A (en) * | 2021-09-15 | 2021-12-10 | 北京顺造科技有限公司 | Security protection system of patrolling and examining based on four-footed robot and unmanned aerial vehicle |
| CN113938924A (en) * | 2021-09-30 | 2022-01-14 | 中国联合网络通信集团有限公司 | Network measurement method and device |
| CN114296480A (en) * | 2021-12-31 | 2022-04-08 | 上海洛轲智能科技有限公司 | Obstacle detection method, traffic determination method, device, aircraft and vehicle |
| CN114879732A (en) * | 2022-05-23 | 2022-08-09 | 北京航空航天大学 | Unknown environment-oriented ground-air collaborative unmanned cluster search platform |
| CN114906326A (en) * | 2022-05-06 | 2022-08-16 | 大连理工大学 | Closed living area intelligent material distribution robot based on unmanned aerial vehicle and mobile ground platform |
| CN114993261A (en) * | 2021-02-26 | 2022-09-02 | 中国科学院宁波材料技术与工程研究所 | Unmanned autonomous obstacle avoidance space detection system and method |
| CN115104432A (en) * | 2022-07-08 | 2022-09-27 | 中山大学 | Picking robot system and method with cooperation of unmanned aerial vehicle and mechanical vehicle |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365297A (en) * | 2013-06-29 | 2013-10-23 | 天津大学 | Optical flow-based four-rotor unmanned aerial vehicle flight control method |
| CN104134222A (en) * | 2014-07-09 | 2014-11-05 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
| CN105222760A (en) * | 2015-10-22 | 2016-01-06 | 一飞智控(天津)科技有限公司 | The autonomous obstacle detection system of a kind of unmanned plane based on binocular vision and method |
| CN205281183U (en) * | 2015-12-30 | 2016-06-01 | 南京信息工程大学 | Low latitude environmental monitoring unmanned aerial vehicle system |
| CN106403900A (en) * | 2016-08-29 | 2017-02-15 | 上海交通大学 | Flyer tracking and locating system and method |
| CN107194339A (en) * | 2017-05-15 | 2017-09-22 | 武汉星巡智能科技有限公司 | Obstacle recognition method, equipment and unmanned vehicle |
| CN107490803A (en) * | 2017-06-14 | 2017-12-19 | 合肥中导机器人科技有限公司 | Using GPS and inertial navigation system to robot localization orientation method |
| CN108062108A (en) * | 2017-12-11 | 2018-05-22 | 郑宏远 | A kind of intelligent multi-rotor unmanned aerial vehicle and its implementation based on airborne computer |
| CN108197569A (en) * | 2017-12-29 | 2018-06-22 | 驭势科技（北京）有限公司 | Obstacle recognition method, device, computer storage media and electronic equipment |
| CN109002053A (en) * | 2018-08-17 | 2018-12-14 | 河南科技大学 | Unmanned equipment Intellectualized space positioning and environmental perception device and method |
| CN109000664A (en) * | 2018-09-25 | 2018-12-14 | 宁夏大学 | A kind of the robot search and rescue system and rescue method of air-ground coordination |
-
2019
- 2019-03-13 CN CN201910188193.0A patent/CN109901580A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103365297A (en) * | 2013-06-29 | 2013-10-23 | 天津大学 | Optical flow-based four-rotor unmanned aerial vehicle flight control method |
| CN104134222A (en) * | 2014-07-09 | 2014-11-05 | 郑州大学 | Traffic flow monitoring image detecting and tracking system and method based on multi-feature fusion |
| CN105222760A (en) * | 2015-10-22 | 2016-01-06 | 一飞智控(天津)科技有限公司 | The autonomous obstacle detection system of a kind of unmanned plane based on binocular vision and method |
| CN205281183U (en) * | 2015-12-30 | 2016-06-01 | 南京信息工程大学 | Low latitude environmental monitoring unmanned aerial vehicle system |
| CN106403900A (en) * | 2016-08-29 | 2017-02-15 | 上海交通大学 | Flyer tracking and locating system and method |
| CN107194339A (en) * | 2017-05-15 | 2017-09-22 | 武汉星巡智能科技有限公司 | Obstacle recognition method, equipment and unmanned vehicle |
| CN107490803A (en) * | 2017-06-14 | 2017-12-19 | 合肥中导机器人科技有限公司 | Using GPS and inertial navigation system to robot localization orientation method |
| CN108062108A (en) * | 2017-12-11 | 2018-05-22 | 郑宏远 | A kind of intelligent multi-rotor unmanned aerial vehicle and its implementation based on airborne computer |
| CN108197569A (en) * | 2017-12-29 | 2018-06-22 | 驭势科技（北京）有限公司 | Obstacle recognition method, device, computer storage media and electronic equipment |
| CN109002053A (en) * | 2018-08-17 | 2018-12-14 | 河南科技大学 | Unmanned equipment Intellectualized space positioning and environmental perception device and method |
| CN109000664A (en) * | 2018-09-25 | 2018-12-14 | 宁夏大学 | A kind of the robot search and rescue system and rescue method of air-ground coordination |
Non-Patent Citations (1)
| Title |
|---|
| 王焱春等: "多传感器信息融合的四旋翼姿态解算研究", 《单片机与嵌入式系统应用》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110262567A (en) * | 2019-06-27 | 2019-09-20 | 深圳市道通智能航空技术有限公司 | A kind of path relaying space of points generation method, device and unmanned plane |
| CN110262567B (en) * | 2019-06-27 | 2022-04-15 | 深圳市道通智能航空技术股份有限公司 | Path relay point space generation method and device and unmanned aerial vehicle |
| CN110209176A (en) * | 2019-06-28 | 2019-09-06 | 北京史河科技有限公司 | A kind of robot |
| CN110399807A (en) * | 2019-07-04 | 2019-11-01 | 深圳前海达闼云端智能科技有限公司 | Detect method, apparatus, readable storage medium storing program for executing and the electronic equipment of ground obstacle |
| CN110399807B (en) * | 2019-07-04 | 2021-07-16 | 达闼机器人有限公司 | Method and device for detecting ground obstacle, readable storage medium and electronic equipment |
| CN111008949B (en) * | 2019-08-16 | 2021-09-14 | 苏州喆安医疗科技有限公司 | Soft and hard tissue detection method for tooth image |
| CN111008949A (en) * | 2019-08-16 | 2020-04-14 | 苏州喆安医疗科技有限公司 | Soft and hard tissue detection method for tooth image |
| WO2021078203A1 (en) * | 2019-10-22 | 2021-04-29 | 深圳市道通智能航空技术有限公司 | Obstacle avoidance method for aircraft, and aircraft, flight system, and storage medium |
| CN110989505A (en) * | 2019-10-28 | 2020-04-10 | 中国人民解放军96782部队 | Unmanned command and dispatch system based on ground equipment machine vision |
| CN112926371A (en) * | 2019-12-06 | 2021-06-08 | 中国移动通信集团设计院有限公司 | Road surveying method and system |
| CN112926371B (en) * | 2019-12-06 | 2023-11-03 | 中国移动通信集团设计院有限公司 | Road survey method and system |
| CN110989672A (en) * | 2019-12-12 | 2020-04-10 | 国网黑龙江省电力有限公司七台河供电公司 | Unmanned aerial vehicle-based real-time power transmission line fault detection system and routing inspection method thereof |
| WO2021179293A1 (en) * | 2020-03-13 | 2021-09-16 | 深圳市大疆创新科技有限公司 | Gimbal control method and apparatus, unmanned aerial vehicle, and storage medium |
| CN111352426B (en) * | 2020-03-17 | 2021-03-02 | 广西柳工机械股份有限公司 | Vehicle obstacle avoidance method, vehicle obstacle avoidance device, vehicle obstacle avoidance system and vehicle |
| CN111352426A (en) * | 2020-03-17 | 2020-06-30 | 广西柳工机械股份有限公司 | Vehicle obstacle avoidance method, vehicle obstacle avoidance device, vehicle obstacle avoidance system and vehicle |
| CN111427352A (en) * | 2020-04-01 | 2020-07-17 | 无锡格物智能科技有限公司 | Interaction method for laying mobile roadblocks, terminal, unmanned aerial vehicle and storage medium |
| CN111427353A (en) * | 2020-04-01 | 2020-07-17 | 无锡格物智能科技有限公司 | Roadblock navigation optimization method, device, terminal, system and storage medium |
| CN111830995A (en) * | 2020-08-06 | 2020-10-27 | 中国科学院自动化研究所 | Group intelligent cooperation method and system based on hybrid architecture |
| CN111830995B (en) * | 2020-08-06 | 2021-05-11 | 中国科学院自动化研究所 | Group intelligent cooperation method and system based on hybrid architecture |
| CN112020981A (en) * | 2020-09-14 | 2020-12-04 | 皖西学院 | Intelligent weeding robot system based on machine vision |
| CN112020981B (en) * | 2020-09-14 | 2022-04-01 | 皖西学院 | Intelligent weeding robot system based on machine vision |
| 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 |
| CN112923928A (en) * | 2021-01-29 | 2021-06-08 | 江苏提米智能科技有限公司 | Photovoltaic panel navigation method and device based on image recognition, electronic equipment and storage medium |
| CN113002774A (en) * | 2021-02-19 | 2021-06-22 | 北京玄马知能科技有限公司 | Robot inspection system based on ground-air integrated cooperative work |
| CN114993261A (en) * | 2021-02-26 | 2022-09-02 | 中国科学院宁波材料技术与工程研究所 | Unmanned autonomous obstacle avoidance space detection system and method |
| CN113295156A (en) * | 2021-05-08 | 2021-08-24 | 西安达升科技股份有限公司 | AGV fusion navigation system and method |
| CN113295156B (en) * | 2021-05-08 | 2024-05-03 | 西安达升科技股份有限公司 | AGV fusion navigation system and method |
| CN113515132B (en) * | 2021-09-13 | 2021-12-28 | 深圳市普渡科技有限公司 | Robot path planning method, robot, and computer-readable storage medium |
| CN113515132A (en) * | 2021-09-13 | 2021-10-19 | 深圳市普渡科技有限公司 | Robot path planning method, robot, and computer-readable storage medium |
| CN113781676A (en) * | 2021-09-15 | 2021-12-10 | 北京顺造科技有限公司 | Security protection system of patrolling and examining based on four-footed robot and unmanned aerial vehicle |
| CN113938924A (en) * | 2021-09-30 | 2022-01-14 | 中国联合网络通信集团有限公司 | Network measurement method and device |
| CN114296480A (en) * | 2021-12-31 | 2022-04-08 | 上海洛轲智能科技有限公司 | Obstacle detection method, traffic determination method, device, aircraft and vehicle |
| CN114906326A (en) * | 2022-05-06 | 2022-08-16 | 大连理工大学 | Closed living area intelligent material distribution robot based on unmanned aerial vehicle and mobile ground platform |
| CN114879732A (en) * | 2022-05-23 | 2022-08-09 | 北京航空航天大学 | Unknown environment-oriented ground-air collaborative unmanned cluster search platform |
| CN115104432A (en) * | 2022-07-08 | 2022-09-27 | 中山大学 | Picking robot system and method with cooperation of unmanned aerial vehicle and mechanical vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109901580A (en) | A kind of unmanned plane cooperates with unmanned ground robot follows diameter obstacle avoidance system and its method | |
| CN110446159B (en) | System and method for accurate positioning and autonomous navigation of indoor unmanned aerial vehicle | |
| CN110262546B (en) | Tunnel intelligent unmanned aerial vehicle inspection method | |
| US20210247764A1 (en) | Multi-sensor environmental mapping | |
| CN104298248B (en) | Rotor wing unmanned aerial vehicle accurate vision positioning and orienting method | |
| CN109683629B (en) | Unmanned aerial vehicle electric power overhead line system based on combination navigation and computer vision | |
| CN206691107U (en) | Pilotless automobile system and automobile | |
| CN104843176B (en) | Unmanned-gyroplane system used for automatic-inspection of bridges and tunnels and navigation method | |
| CN103822635B (en) | The unmanned plane during flying spatial location real-time computing technique of view-based access control model information | |
| CN112130579A (en) | Tunnel unmanned aerial vehicle inspection method and system | |
| CN108571971A (en) | A kind of AGV vision positioning systems and method | |
| CN111966114A (en) | Drop-off location planning for delivery vehicles | |
| CN109911188A (en) | The bridge machinery UAV system of non-satellite navigator fix environment | |
| CN106647814A (en) | System and method of unmanned aerial vehicle visual sense assistant position and flight control based on two-dimensional landmark identification | |
| CN110333735B (en) | System and method for realizing unmanned aerial vehicle water and land secondary positioning | |
| CN102190081B (en) | Vision-based fixed point robust control method for airship | |
| CN106444837A (en) | Obstacle avoiding method and obstacle avoiding system for unmanned aerial vehicle | |
| Chen et al. | An auto-landing strategy based on pan-tilt based visual servoing for unmanned aerial vehicle in GNSS-denied environments | |
| CN113156998B (en) | Control method of unmanned aerial vehicle flight control system | |
| CN109521781A (en) | Unmanned plane positioning system, unmanned plane and unmanned plane localization method | |
| CN107783119A (en) | Apply the Decision fusion method in obstacle avoidance system | |
| JP2020149640A (en) | Flight system and landing control method | |
| CN114923477A (en) | Multi-dimensional space-ground collaborative map building system and method based on vision and laser SLAM technology | |
| CN114371725A (en) | System suitable for automatic inspection of wind turbine generator | |
| CN112859923B (en) | Unmanned aerial vehicle vision formation flight control system |
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: 20190618 |
|
| RJ01 | Rejection of invention patent application after publication |