CN110262568A - A kind of unmanned plane barrier-avoiding method, device and unmanned plane based on target following - Google Patents
A kind of unmanned plane barrier-avoiding method, device and unmanned plane based on target following Download PDFInfo
- Publication number
- CN110262568A CN110262568A CN201910655674.8A CN201910655674A CN110262568A CN 110262568 A CN110262568 A CN 110262568A CN 201910655674 A CN201910655674 A CN 201910655674A CN 110262568 A CN110262568 A CN 110262568A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- forward speed
- optimal
- barrier
- heading
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 230000004888 barrier function Effects 0.000 claims abstract description 136
- 238000001514 detection method Methods 0.000 claims description 133
- 230000006870 function Effects 0.000 claims description 41
- 230000015654 memory Effects 0.000 claims description 26
- 238000005070 sampling Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000012491 analyte Substances 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 12
- 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 57
- 238000010586 diagram Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012372 quality testing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
- G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present embodiments relate to unmanned plane automatic obstacle avoiding technical fields, more particularly to a kind of unmanned plane barrier-avoiding method, device and unmanned plane based on target following.Wherein, the unmanned plane barrier-avoiding method based on target following comprises determining that the expection forward speed of unmanned plane, it is contemplated that forward speed is for making unmanned plane and target keep initial level distance;The depth map of environment in front of unmanned plane is obtained, and according to depth map, determines the grating map centered on unmanned plane;According to grating map, the optimal heading of unmanned plane and the minimum range of unmanned plane and barrier are determined;According to minimum range, expected forward speed and optimal heading, the optimal flying speed of unmanned plane is determined;Control unmanned plane is flown with optimal flying speed along optimal heading, to hide the barrier of environment in front of unmanned plane.By the above-mentioned means, the embodiment of the present invention can carry out path planning to entire flight space, the accuracy of automatic obstacle avoiding in object tracking process is improved.
Description
Technical field
The present embodiments relate to unmanned plane automatic obstacle avoiding technical fields, more particularly to a kind of nothing based on target following
Man-machine barrier-avoiding method, device and unmanned plane.
Background technique
Unmanned plane is a kind of unmanned vehicle manipulated by radio robot or itself presetting apparatus.With
The development of unmanned plane the relevant technologies and its complicated variation of application scenarios, unmanned plane automatic sensing ability and path planning are calculated
The requirement of method is higher and higher, especially in the automatic obstacle avoiding technology of unmanned plane, unmanned plane is needed to pass through the movement shape of perception itself
The environment of state and surrounding, and path planning algorithm is combined, it flies, avoids safely, without collision in the environment for having barrier
It collides with barrier.
Currently, when unmanned plane is based on target following progress automatic obstacle avoiding, the main flight rail by being set in the library of track
The flying speed at each moment set on mark and flight path is flown, but flight path set by this kind of mode without
Method covers entire flight space, so that unmanned plane can not carry out path planning to the region outside flight path, if in flight space
There are dynamic changes, then unmanned plane can not carry out accurate avoidance.
Summary of the invention
The embodiment of the present invention is intended to provide a kind of unmanned plane barrier-avoiding method, device and unmanned plane based on target following, energy
It is enough that path planning is carried out to entire flight space, improve the accuracy of automatic obstacle avoiding in object tracking process.
In order to solve the above technical problems, a technical solution used in the embodiment of the present invention is: providing a kind of based on target
The unmanned plane barrier-avoiding method of tracking, which comprises
Determine the expection forward speed of unmanned plane, the expected forward speed is for keeping the unmanned plane and target just
Beginning horizontal distance;
The depth map of environment in front of the unmanned plane is obtained, and according to the depth map, determines with the unmanned plane and be
The grating map of the heart;
According to the grating map, the optimal heading and the unmanned plane and barrier of the unmanned plane are determined
Minimum range;
According to the minimum range, the expected forward speed and the optimal heading, the unmanned plane is determined
Optimal flying speed;
The unmanned plane is controlled to fly with the optimal flying speed along the optimal heading, with hide it is described nobody
The barrier of environment in front of machine.
Optionally, the expection forward speed of the determining unmanned plane, comprising:
Obtain the initial level distance of the unmanned plane Yu the target;
Determine the present level distance of the unmanned plane Yu the target;
Based on the initial level distance, P I D is carried out to the present level distance and is adjusted, with the determination unmanned plane
The expected forward speed.
Optionally, the unmanned plane includes holder, the method also includes:
The center for controlling the holder is directed at the target;Then,
The present level distance of the determination unmanned plane and the target, comprising:
Obtain the holder current distance away the ground and current pitch angle;
The current of the unmanned plane and the target is determined according to the current distance away the ground and the current pitch angle
Horizontal distance.
Optionally, the method also includes:
Determine the current forward speed of the unmanned plane;Then,
It is described according to the grating map, determine the optimal heading and the unmanned plane and obstacle of the unmanned plane
The minimum range of object, comprising:
According to the current forward speed and the expected forward speed, detection of obstacles is determined in the grating map
Region;
In the detection of obstacles region, determine the unmanned plane optimal heading and the unmanned plane and barrier
Hinder the minimum range of object.
Optionally, described according to the current forward speed and the expected forward speed, in the grating map really
Determine detection of obstacles region, comprising:
Compare the current forward speed and the expected forward speed;
If the current forward speed is less than the expected forward speed, according to the expected forward speed in the grid
The detection of obstacles region is determined in lattice map;
If the current forward speed is greater than the expected forward speed, according to the current forward speed in the grid
True the detection of obstacles region in lattice map.
Optionally, when determining detection of obstacles region in the grating map according to the expected forward speed, institute
It is bigger to state expected forward speed, the detection of obstacles region is bigger;
When determining detection of obstacles region in the grating map according to the current forward speed, it is described it is current before
Bigger to speed, the detection of obstacles region is bigger.
Optionally, described in the detection of obstacles region, determine the optimal heading of the unmanned plane, comprising:
In the detection of obstacles region, determine the unmanned plane can traffic areas, wherein it is described can traffic areas
For there is no the regions of barrier;
According to it is described can traffic areas, determine the candidate heading of the unmanned plane;
The cost function value of candidate's heading according to cost function calculation;
The smallest candidate heading of the cost function value is determined as to the optimal heading of the unmanned plane.
Optionally, described in the detection of obstacles region, determine the unmanned plane can traffic areas, comprising:
Centered on the unmanned plane, predetermined angle is interval, is divided to the detection of obstacles region, by institute
Stating detection of obstacles region division is multiple regions;
Sample the coordinate of barrier;
Determine that the region that the coordinate is not fallen within can traffic areas for described in.
Optionally, the coordinate of the sampling barrier, comprising:
Sample the center point coordinate of the grid occupied in the detection of obstacles region by the barrier and/or described
The angular coordinate for the grid that barrier occupies.
Optionally, the cost function are as follows:
F=k1×g(direcgoal,direccur)+k2×g(direcpre,direccur)-k3×sum
Wherein, g (direcgoal,direccur) indicate one of candidate heading in the candidate heading
With the consistency in the direction of the target, g (direcpre,direccur) indicate the candidate heading and a preceding decision
The consistency of optimal heading, sum expression described in can traffic areas quantity, k1、k2、k3For weight coefficient.
Optionally, described in the detection of obstacles region, it determines the minimum range of the unmanned plane and barrier, wraps
It includes:
It determines in the detection of obstacles region with the unmanned plane apart from the smallest barrier as target obstacle;
The target obstacle is determined as the minimum range at a distance from the unmanned plane.
Optionally, the optimal flying speed includes optimal forward speed and optimal side velocity;Then,
It is described according to the minimum range, the expected forward speed and the optimal heading, determine the nothing
Man-machine optimal flying speed, comprising:
According to the minimum range, the maximum forward speed of the unmanned plane is calculated;
According to the maximum forward speed and the expected forward speed, the optimal forward speed is determined;
According to the optimal forward speed and the optimal heading, the optimal side velocity is determined.
Optionally, described according to the maximum forward speed and the expected forward speed, determine the optimal forward direction speed
Degree, comprising:
Compare the maximum forward speed and the expected forward speed;
If the maximum forward speed is greater than the expected forward speed, it is determined that the expected forward speed be it is described most
Excellent forward speed;
If the maximum forward speed is not more than the expected forward speed, it is determined that the maximum forward speed is described
Optimal forward speed.
Optionally, the optimal heading corresponds to optimal flight angle;Then,
It is described according to the optimal forward speed and the optimal heading, determine the optimal side velocity, comprising:
It is determined according to the product of the tangent value of the optimal flight angle and the optimal forward speed described optimal lateral
Speed.
Optionally, the depth map for obtaining environment in front of the unmanned plane, comprising:
The depth map of environment in front of the unmanned plane is obtained by the depth transducer of the unmanned plane.
Optionally, described before determining the grating map centered on the unmanned plane described according to the depth map
Method further include:
Judge the depth transducer with the presence or absence of pitch angle;
If so, carrying out depth compensation to the depth map.
Optionally, the depth transducer is depth camera;Then,
If there are pitch angles for the depth transducer, described to carry out depth compensation to the depth map, comprising:
Calculate the number of lines of pixels of the depth compensation, the number of lines of pixels of the depth compensation are as follows:
Row_see=tan θ2× f, wherein θ2For the pitch angle of the depth camera, f is the focal length of the depth camera;
The row rope as plane on the depth map of the unmanned plane is determined according to the number of lines of pixels of the depth compensation
Draw, the line index row_horizon as plane on the depth map of the unmanned plane are as follows:
Row_horizon=row_half+row_see, wherein row_half is the half of the depth map line number.
In order to solve the above technical problems, another technical solution used in the embodiment of the present invention is: providing a kind of based on mesh
The unmanned plane obstacle avoidance apparatus of tracking is marked, described device includes:
First determining module, for determining that the expection forward speed of unmanned plane, the expected forward speed are described for making
Unmanned plane and target keep initial level distance;
Module is obtained, for obtaining the depth map of environment in front of the unmanned plane, and according to the depth map, is determined with institute
State the grating map centered on unmanned plane;
Second determining module, for determining optimal heading and the institute of the unmanned plane according to the grating map
State the minimum range of unmanned plane and barrier;And
For determining the nothing according to the minimum range, the expected forward speed and the optimal heading
Man-machine optimal flying speed;
Control module is flown with the optimal flying speed along the optimal heading for controlling the unmanned plane,
To hide the barrier of environment in front of the unmanned plane.
Optionally, first determining module is specifically used for:
Obtain the initial level distance of the unmanned plane Yu the target;
Determine the present level distance of the unmanned plane Yu the target;
Based on the initial level distance, P I D is carried out to the present level distance and is adjusted, with the determination unmanned plane
The expected forward speed.
Optionally, the unmanned plane includes holder, and the control module is also used to:
The center for controlling the holder is directed at the target;Then,
First determining module is specifically used for:
Obtain the holder current distance away the ground and current pitch angle;
The current of the unmanned plane and the target is determined according to the current distance away the ground and the current pitch angle
Horizontal distance.
Optionally, first determining module is also used to:
Determine the current forward speed of the unmanned plane;Then,
Second determining module is specifically used for:
According to the current forward speed and the expected forward speed, detection of obstacles is determined in the grating map
Region;
In the detection of obstacles region, determine the unmanned plane optimal heading and the unmanned plane and barrier
Hinder the minimum range of object.
Optionally, second determining module is specifically used for:
Compare the current forward speed and the expected forward speed;
If the current forward speed is less than the expected forward speed, according to the expected forward speed in the grid
The detection of obstacles region is determined in lattice map;
If the current forward speed is greater than the expected forward speed, according to the current forward speed in the grid
True the detection of obstacles region in lattice map.
Optionally, when determining detection of obstacles region in the grating map according to the expected forward speed, institute
It is bigger to state expected forward speed, the detection of obstacles region is bigger;
When determining detection of obstacles region in the grating map according to the current forward speed, it is described it is current before
Bigger to speed, the detection of obstacles region is bigger.
Optionally, second determining module is specifically used for:
In the detection of obstacles region, determine the unmanned plane can traffic areas, wherein it is described can traffic areas
For there is no the regions of barrier;
According to it is described can traffic areas, determine the candidate heading of the unmanned plane;
The cost function value of candidate's heading according to cost function calculation;
The smallest candidate heading of the cost function value is determined as to the optimal heading of the unmanned plane.
Optionally, second determining module is specifically used for:
Centered on the unmanned plane, predetermined angle is interval, is divided to the detection of obstacles region, by institute
Stating detection of obstacles region division is multiple regions;
Sample the coordinate of barrier;
Determine that the region that the coordinate is not fallen within can traffic areas for described in.
Optionally, second determining module is specifically used for:
Sample the center point coordinate of the grid occupied in the detection of obstacles region by the barrier and/or described
The angular coordinate for the grid that barrier occupies.
Optionally, the cost function are as follows:
F=k1×g(direcgoal,direccur)+k2×g(direcpre,direccur)-k3×sum
Wherein, g (direcgoal,direccur) indicate one of candidate heading in the candidate heading
With the consistency in the direction of the target, g (direcpre,direccur) indicate the candidate heading and a preceding decision
The consistency of optimal heading, sum expression described in can traffic areas quantity, k1、k2、k3For weight coefficient.
Optionally, second determining module is specifically used for:
It determines in the detection of obstacles region with the unmanned plane apart from the smallest barrier as target obstacle;
The target obstacle is determined as the minimum range at a distance from the unmanned plane.
Optionally, the optimal flying speed includes optimal forward speed and optimal side velocity;Then,
Second determining module is specifically used for:
According to the minimum range, the maximum forward speed of the unmanned plane is calculated;
According to the maximum forward speed and the expected forward speed, the optimal forward speed is determined;
According to the optimal forward speed and the optimal heading, the optimal side velocity is determined.
Optionally, second determining module is specifically used for:
Compare the maximum forward speed and the expected forward speed;
If the maximum forward speed is greater than the expected forward speed, it is determined that the expected forward speed be it is described most
Excellent forward speed;
If the maximum forward speed is not more than the expected forward speed, it is determined that the maximum forward speed is described
Optimal forward speed.
Optionally, the optimal heading corresponds to optimal flight angle;Then,
Second determining module is specifically used for:
It is determined according to the product of the tangent value of the optimal flight angle and the optimal forward speed described optimal lateral
Speed.
Optionally, the acquisition module is specifically used for:
The depth map of environment in front of the unmanned plane is obtained by the depth transducer of the unmanned plane.
Optionally, described before determining the grating map centered on the unmanned plane described according to the depth map
Module is obtained to be also used to:
Judge the depth transducer with the presence or absence of pitch angle;
If so, carrying out depth compensation to the depth map.
Optionally, the depth transducer is depth camera;Then,
The acquisition module is specifically used for:
Calculate the number of lines of pixels of the depth compensation, the number of lines of pixels of the depth compensation are as follows:
Row_see=tan θ2× f, wherein θ2For the pitch angle of the depth camera, f is the focal length of the depth camera;
The row rope as plane on the depth map of the unmanned plane is determined according to the number of lines of pixels of the depth compensation
Draw, the line index row_horizon as plane on the depth map of the unmanned plane are as follows:
Row_horizon=row_half+row_see, wherein row_half is the half of the depth map line number.
In order to solve the above technical problems, another technical solution used in the embodiment of the present invention is: a kind of unmanned plane is provided,
Include:
Fuselage;
Horn is connected with the fuselage;
Power device is set to the horn;
Holder is connected with the fuselage;
Depth camera is connected with the fuselage;
At least one processor is set in the fuselage;And
The memory being connect at least one described processor communication;Wherein, the memory be stored with can by it is described extremely
The instruction that a few processor executes, described instruction are executed by least one described processor, so that at least one described processing
Device can be used in the above-described unmanned plane barrier-avoiding method based on target following.
In order to solve the above technical problems, another technical solution used in the embodiment of the present invention is: providing a kind of non-volatile
Property computer readable storage medium, which is characterized in that the non-volatile computer readable storage medium storing program for executing is stored with computer can
It executes instruction, the computer executable instructions are kept away for making unmanned plane execute the above-described unmanned plane based on target following
Barrier method.
The beneficial effect of the embodiment of the present invention is: being in contrast to the prior art down, the embodiment of the present invention provides one kind
Unmanned plane barrier-avoiding method, device and unmanned plane based on target following, in the unmanned plane barrier-avoiding method based on target following, really
Determine for making unmanned plane and target keep the expection forward speed of initial level distance, and according to the depth of environment in front of unmanned plane
After figure determines grating map centered on unmanned plane, according to grating map determine unmanned plane optimal heading and nobody
The minimum range of machine and barrier, and determined according to identified minimum range, expected forward speed and optimal heading
Then the optimal flying speed of unmanned plane is controlled unmanned plane and is flown with optimal flying speed along optimal heading, before hiding
The barrier of square environment.In the above method, since the depth map of environment in front of unmanned plane can be with the flight of unmanned plane
Journey reflects the environmental aspect on unmanned plane during flying path in real time, therefore, the grid determined according to the depth map of environment in front of unmanned plane
Lattice map determines the optimal heading of unmanned plane, enables the unmanned plane to carry out path planning to entire flight space, real
When strain flight space in dynamic change;Meanwhile according to identified minimum range, expected forward speed and optimal flight
Direction determines optimal flying speed of the unmanned plane on optimal heading, enables unmanned plane according to actual environment situation
It plans optimal flying speed, prevents unmanned plane because of the too fast collision obstacle of speed, improve automatic obstacle avoiding in object tracking process
Accuracy.
Detailed description of the invention
One or more embodiments are illustrated by the picture in corresponding attached drawing, these exemplary theorys
The bright restriction not constituted to embodiment, the element in attached drawing with same reference numbers label are expressed as similar element, remove
Non- to have special statement, composition does not limit the figure in attached drawing.
Fig. 1 is a kind of structural schematic diagram of unmanned plane provided in an embodiment of the present invention;
Fig. 2 is to work as depth transducer in a kind of unmanned plane barrier-avoiding method based on target following provided in an embodiment of the present invention
There are pitch angles, and the schematic illustration of depth compensation is carried out to depth map;
Fig. 3 is the structural schematic diagram of grating map;
Fig. 4 is a kind of flow diagram of unmanned plane barrier-avoiding method based on target following provided in an embodiment of the present invention;
Fig. 5 is a kind of structural schematic diagram of unmanned plane obstacle avoidance apparatus based on target following provided in an embodiment of the present invention;
Fig. 6 is a kind of hardware structural diagram of unmanned plane provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.It should be appreciated that specific embodiment described herein is only to solve
The present invention is released, is not intended to limit the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not making
Every other embodiment obtained, shall fall within the protection scope of the present invention under the premise of creative work.
It should be noted that be expressed " being fixed on " another element when element, it can directly on the other element,
Or there may be one or more elements placed in the middle therebetween.When an element is expressed " connection " another element, it can be with
It is directly to another element or there may be one or more elements placed in the middle therebetween.Used in this specification
Term "vertical", "horizontal", "left" and "right" and similar statement are for illustrative purposes only.
As long as in addition, technical characteristic involved in each embodiment of invention described below non-structure each other
It can be combined with each other at conflict.
The present invention provides a kind of unmanned plane barrier-avoiding method and device based on target following, this method and device are applied to
Unmanned plane is cooked up so that the unmanned plane can carry out path planning in entire flight space according to real flight conditions
Optimal heading and optimal flying speed, and flown with optimal flying speed along optimal heading, before accurately hiding
The barrier of square environment.Wherein, optimal heading refers to the direction there is no barrier.
Unmanned plane in the present invention can be the High Altitude UAV or low latitude unmanned plane of any suitable type, including fixation
Wing unmanned plane, rotor wing unmanned aerial vehicle, umbrella wing unmanned plane or flapping wing unmanned plane etc..
In the following, the present invention will be specifically addressed by specific embodiment.
Embodiment one
Referring to Fig. 1, being a kind of present invention unmanned plane 100 that wherein an embodiment provides, which is quadrotor
Unmanned plane, comprising: fuselage 10, horn 20, power device 30, holder 40, filming apparatus 50, depth transducer (not shown),
One gyroscope (not shown), the second gyroscope (not shown), undercarriage 60, intelligent battery (not shown) and flight control system (figure
Do not show).Horn 20, holder 40, depth transducer and undercarriage 60 are connect with fuselage 10, and power device 30 is set to horn
On 20, filming apparatus 50 and the first gyroscope are installed on holder 40, and the second gyroscope, intelligent battery and flight control system are then set
It is placed in fuselage 10.Wherein, power device 30, holder 40, filming apparatus 50, depth transducer, the first gyroscope, the second gyro
Instrument and undercarriage 60 are communicated to connect with flight control system, and flight control system is enabled to control unmanned plane by power device 30
100 flight obtains the ambient conditions in front of 100 flight path of unmanned plane by depth transducer, additionally it is possible to control holder 40
Rotation, control filming apparatus 50 are taken photo by plane and are controlled undercarriage 60 and open and pack up, additionally it is possible to receive the first gyroscope, the second top
The measurement data of spiral shell instrument.
Preferably, 20 quantity of horn is 4, is uniformly distributed in 10 surrounding of fuselage, is fixedly connected with fuselage 10, dynamic for carrying
Power device 30.Wherein, horn 20 and fuselage 10 are integrally formed.
Power device 30 includes motor and the propeller with motor axis connection, and motor is able to drive propeller rotation and thinks
Unmanned plane 100 provides lift or thrust, realizes flight;Motor can also change nothing by changing revolving speed and the direction of propeller
Man-machine 100 heading.When power device 30 and flight control system communicate to connect, flight control system can by control motor come
Control the flight of unmanned plane 100.
The power device 30 is set to one end that horn 20 is not connect with fuselage 10, and connects horn 20 by motor.
Preferably, it is provided with power device 30 on 4 horns of unmanned plane 100, so that unmanned plane 100 can be steady
Flight.
Holder 40 is then set to 10 bottom of fuselage, for carrying filming apparatus 50.Preferably, which is electronic cloud
Platform can be rotated under the control of flight control system, to realize the tracking to target.Wherein, flight control system controls holder 40
When rotation, the center alignment target of holder 40 is controlled.
The electric platform includes but is not limited to rotate horizontally holder, all-directional tripod head etc..
When holder 40 is to rotate horizontally holder, flight control system can control the holder 40 left-right rotation in the horizontal direction;
When holder 40 is all-directional tripod head, flight control system can control the holder 40 left-right rotation in the horizontal direction, and, control should
The lower rotation in the vertical direction of holder 40.
Preferably, in embodiments of the present invention, holder 40 be all-directional tripod head, with can it is comprehensive to target carry out with
Track.
Filming apparatus 50 can shoot the electronic equipment of video image then for camera, video camera etc., for flying
It takes photo by plane under the control of control system.
The filming apparatus 50 is fixed on holder 40, can rotate with the rotation of holder 40;Also, the filming apparatus 50
Taking lens be located on the center line of holder 40, when the center alignment target of holder 40, the taking lens of filming apparatus 50
Also alignment target, at this point, target is located at video image captured by filming apparatus 50 if filming apparatus 50 shoots video image
Center.
First gyroscope is then installed on holder 40, for measuring the posture information of holder 40, the posture information of the holder 40
Pitch angle including holder.Wherein, when the pitch angle of holder 40 is 0, the centerline parallel of holder 40 is in horizontal direction.
After the first gyroscope and flight control system communicate to connect, flight control system can obtain holder 40 from the first gyroscope
Posture information.
Depth transducer is then fixed on fuselage 10, and posture and the posture of fuselage 10 are consistent.The depth transducer is used
In the depth map (Depth Map) of acquisition 100 front environment of unmanned plane, which is comprising the table with the scenario objects of viewpoint
Image or image channel of the identity distance from related information, in depth map, each of which pixel value indicates depth transducer apart from object
The actual range of body, thus depth transducer sampling depth figure namely sampling depth sensor and front environmental objects it is practical away from
From.When depth transducer and flight control system communicate to connect, flight control system can obtain ring in front of unmanned plane from depth transducer
The depth map in border, namely the actual range of depth transducer and front environmental objects is obtained, to obtain 100 flight path of unmanned plane
The ambient conditions in front.
The depth transducer is depth camera, including but not limited to: binocular camera, TOF (Time of Flight, flight
Time) camera etc..
Second gyroscope is then installed in fuselage 10, for measuring the posture information of fuselage 10, also that is, the sensing that fathoms
The posture information of the posture information of device, the depth transducer includes the pitch angle of depth transducer.Wherein, when depth transducer
When pitch angle is 0, the detection direction of depth transducer is horizontal direction.
After the second gyroscope and flight control system communicate to connect, flight control system can obtain depth sensing from the second gyroscope
The posture information of device.
Further, when the first gyroscope and the second gyroscope do not generate attitudes vibration, the center line court of holder 40
To consistent with the detection direction of depth transducer.
Undercarriage 60 is then set to 10 bottom opposite sides of fuselage, is connected via drive in fuselage 10, undercarriage 60
It is able to carry out opening under the drive of the drive and packs up.Unmanned plane 100 when being contacted with ground, driving device control rise and fall
Frame 60 is opened, so that unmanned plane 100 can pass through undercarriage 60 and ground face contact;In 100 flight course of unmanned plane, driving dress
It sets control undercarriage 60 to pack up, influences unmanned plane 100 to avoid undercarriage 60 and fly.When undercarriage 60 and flight control system communication link
When connecing, flight control system can be controlled the opening of undercarriage 60 by control driving device and be packed up.
Intelligent battery is then used to power for unmanned plane 100, so that the power device 30 of unmanned plane 100, holder 40, shooting dress
Setting 50, depth transducer, the first gyroscope, the second gyroscope, undercarriage 60 and flight control system can be powered operation.Wherein,
Intelligent battery includes but is not limited to: dry cell, lead storage battery and lithium battery etc..
Flight control system then with power device 30, holder 40, filming apparatus 50, depth transducer, the first gyroscope, the second top
Spiral shell instrument and undercarriage 60 are communicatively coupled by way of wired connection or wireless connection.Wherein, wireless connection includes
But it is not limited to: WiFi, bluetooth, ZigBee etc..
The flight control system is empty with the entire flight to unmanned plane for executing the unmanned plane barrier-avoiding method based on target following
Between carry out path planning, improve the accuracy of automatic obstacle avoiding in object tracking process.
Specifically, in 100 flight course of unmanned plane, flight control system controls the center alignment target of holder 40, to realize
Tracking of the unmanned plane 100 to target.
Wherein, target is the object of tracking during unmanned plane during flying, which is located at ground, can be in ground moving.
When flight control system controls the center alignment target of holder 40, the direction of target is obtained in real time, then, according to target
Direction, control holder 40 is rotated, until the target-bound direction in center of holder 40, with target alignment.
During unmanned plane 100 tracks target, flight control system determines Xiang Su before the expection of unmanned plane 100
Degree, the expection forward speed is for making unmanned plane 100 and target keep initial level distance, the i.e. forward speed of unmanned plane 100
When to be expected forward speed, unmanned plane 100 could keep initial level distance with target.
Then, when determining the expection forward speed of unmanned plane 100, firstly, obtaining the initial level of unmanned plane 100 and target
Distance;Then, it is determined that the present level distance of unmanned plane 100 and target;Finally, based on acquired initial level distance, it is right
Identified present level distance carries out PID adjusting, to determine the expection forward speed of unmanned plane 100.
Wherein, initial level distance be unmanned plane 100 initialize when position and target position in the horizontal direction
On relative distance, which stores after capable of being set by user to memory, also can be by flight control system
It stores after being calculated when unmanned plane 100 initializes to memory.
Therefore, the initial level distance of unmanned plane 100 Yu target can be obtained in memory.
Present level distance then for 100 present position of unmanned plane and target present position in the horizontal direction
Relative distance.
Ground is located at due to target and is aligned with the center of holder 40, can by the pitch angle of holder 40 and
The distance away the ground of holder 40 calculates unmanned plane 100 and the relative distance of target in the horizontal direction, also that is, unmanned plane 100 with
Horizontal distance between target.Specifically, the horizontal distance between unmanned plane 100 and targetH is pair of holder 40
Ground height, θ1For the pitch angle of holder 40.
Then, flight control system determine the present level of unmanned plane and target apart from when, obtain the current high over the ground of holder 40
After the current pitch angle of degree and holder 40, unmanned plane 100 is calculated according to acquired current distance away the ground and current pitch angle
With the present level distance of target.
Similarly, flight control system can according to unmanned plane 100 initialize when holder 40 pitch angle and holder 40 over the ground
Highly, it calculates the initial level distance of unmanned plane 100 and target and stores to memory.
Based on acquired initial level distance, PID adjusting is carried out to identified present level distance, to determine nothing
In the step of man-machine 100 expection forward speed, then closed-loop control is carried out with PID controller.
In PID controller, initial level distance is the desired value of controlled variable, and present level distance is controlled variable
Actual value, and it is expected forward speed then and is the response output of PID controller.When present level distance and initial level distance exist
When deviation, then adjusting expected forward speed enables present level distance to reach initial level distance.
Further, after flight control system determines the expection forward speed of unmanned plane 100, nobody is obtained by depth transducer
The depth map of 100 front environment of machine, and according to depth map, determine the grating map centered on unmanned plane 100.
Wherein, grating map is then the planar grid by being mapped to the depth information in depth map centered on body
It is formed in figure, each grid gives a probable value, indicates the probability that the grid is occupied by barrier.When in environment depth map
There are when barrier, barrier occupies grid in grating map, can know barrier by being occupied the coordinate of grid
Position.
The grid of grating map is arranged in matrix, for example, the grid of grating map is arranged in the matrix of 10*10.
In some other embodiment of the present invention, if unmanned plane 100 generates pitch angle in flight course, nobody can be made
100 forward sight of machine is no longer horizontal, at this point, the depth map of depth transducer acquisition is no longer the depth in the horizontal front of unmanned plane 100
Degree figure, so that error occurs in the depth information that depth map is reflected, causes the inaccuracy of grating map.Then, flight control system exists
Before determining the grating map centered on unmanned plane 100 according to depth map, also need to judge depth transducer with the presence or absence of pitching
Angle, if depth transducer there are pitch angle, after flight control system carries out after depth compensation further according to depth compensation depth map
Depth map determines the grating map centered on unmanned plane 100.
Wherein, flight control system can measure the triaxial attitude angle of unmanned plane 100 by the second gyroscope, according to three axis appearances
State angle judges depth transducer with the presence or absence of pitch angle.
Flight control system carries out depth compensation to depth map and specifically includes: flight control system calculates the number of lines of pixels of depth compensation,
And after the number of lines of pixels of depth compensation is calculated, the picture plane of unmanned plane is determined according to the number of lines of pixels of the depth compensation
Line index on depth map.
Specifically, referring to Fig. 2, when depth transducer is depth camera, the number of lines of pixels row_see of the depth compensation
Are as follows:
Row_see=tan θ2× f, wherein θ2For the pitch angle of depth camera, f is the focal length of depth camera;
The line index row_horizon as plane on depth map of the unmanned plane are as follows:
Row_horizon=row_half+row_see, wherein row_half is the half of depth map line number.
Further, after flight control system determines the grating map centered on unmanned plane 100, according to identified grid
Figure, determines the optimal heading of unmanned plane 100 and the minimum range of unmanned plane 100 and barrier.
Wherein, during due to unmanned plane during flying, the forward speed of unmanned plane 100 is bigger, the probability with barrier collision
It is bigger, need to consider earlier the distribution of obstacles situation of 100 front environment of unmanned plane;And the forward speed of unmanned plane 100 is got over
Small, with regard to smaller, the distribution of obstacles situation of too early consideration 100 front environment of unmanned plane is easy the probability with barrier collision
Unnecessary barrier is taken into account, the judgement inaccuracy of optimal heading is caused.
Then, according to identified grating map, the optimal heading and unmanned plane 100 of unmanned plane 100 are determined
Before the minimum range of barrier, flight control system is also it needs to be determined that the current forward speed of unmanned plane 100, then, according to working as
Preceding forward speed and expected forward speed, after determining detection of obstacles region in grating map, then in detection of obstacles region
In, determine the optimal heading of unmanned plane 100 and the minimum range of unmanned plane 100 and barrier.That is, by unmanned plane 100
Forward speed in conjunction with the detection range of barrier, a suitable barrier is determined according to the forward speed of unmanned plane 100
Detection range, to increase the accuracy of detection of obstacles.
Wherein, detection of obstacles region is in grating map for detecting the region of barrier, the detection of obstacles region
Positioned at the top half (i.e. 100 front of unmanned plane) of grating map, the columns in the detection of obstacles region and the column of grating map
The half that identical, line number is less than or equal to the line number of grating map is counted, i.e. the detection of obstacles region is less than or equal to grid
The half of lattice map.For example, referring to Fig. 3, solid line region P1 is detection of obstacles region.
The optimal heading of unmanned plane 100 is that there is no the directions of barrier;The most narrow spacing of unmanned plane 100 and barrier
From i.e. unmanned plane 100 at a distance from nearest barrier within sweep of the eye.
Specifically, according to current forward speed and expected forward speed, detection of obstacles region is determined in grating map,
It include: the current forward speed of comparison and expected forward speed, if current forward speed is less than expected forward speed, according to expection
Forward speed determines detection of obstacles region in grating map, at this time, it is contemplated that forward speed is bigger, identified obstacle quality testing
It is bigger to survey region;If current forward speed is greater than expected forward speed, determined in grating map according to current forward speed
Detection of obstacles region, at this point, current forward speed is bigger, identified detection of obstacles region is bigger.
In identified detection of obstacles region, the optimal heading of unmanned plane 100 is determined, comprising: firstly, in institute
In determining detection of obstacles region, determine unmanned plane 100 can traffic areas.
Wherein, can traffic areas be detection of obstacles region in be not present barrier region.
Flight control system in identified detection of obstacles region, determine unmanned plane 100 can traffic areas, it is specific to wrap
Include: centered on unmanned plane 100, predetermined angle is interval, is divided to detection of obstacles region, by detection of obstacles area
Domain is divided into multiple regions, then, samples the coordinate of barrier, and whether the obstacle article coordinate for judging that sampling obtains falls into obstacle
In the region of analyte detection region division, the region that obstacle article coordinate is not fallen within is determined as can traffic areas.For example, please referring to figure
3, centered on unmanned plane 100, predetermined angle θ3For interval, multiple fan-shaped regions, institute are divided in the P1 of detection of obstacles region
The fan-shaped region of division is respectively B1 to B11 from left to right;Then, the coordinate for sampling barrier Z1, Z2 and Z3, determines barrier
The coordinate of Z1 falls into the region B2 and B3, and the coordinate of barrier Z2 falls into B6 to the region B9, and the coordinate of barrier Z3 does not fall within barrier
Hinder in the P1 of analyte detection region, accordingly, it is determined that region B1, B4, B5, B10 and B11 that barrier is not fallen within are can traffic areas.
Wherein, each region that flight control system marks off in detection of obstacles region is fan-shaped region.
When dividing to detection of obstacles region, predetermined angle is bigger, and the region of division is bigger, the region marked off
Quantity is then fewer;Predetermined angle is smaller, and the region of division is smaller, and the region quantity marked off is then more.
The coordinate of flight control system sampling barrier, comprising: the grid occupied in sampling detection of obstacles region by barrier
Center point coordinate and/or the grid occupied by barrier angular coordinate.
Flight control system is by the center point coordinate of the grid occupied by barrier and/or the angle point of the grid occupied by barrier
The region that coordinate is not fallen within is determined as can traffic areas.Based on this, if the region division of grating map is too small, it is easy
The case where existing region is covered by barrier, but the coordinate sampled does not fall within region, at this point, be mistaken for can in impassabitity region
Traffic areas;And if the region division of grating map is excessive, will lead to that heading is very few, is unfavorable for optimal heading
Determine.Then, in order to guarantee that the reliability of flight control system path planning, flight control system can adjust default according to practical flight effect
The size of angle.
Flight control system adjusts predetermined angle according to the robustness of depth map data and the accuracy in planning direction.
Secondly, can determine the candidate heading of unmanned plane 100 in traffic areas identified.
Based on can the candidate heading that determines of traffic areas be there is no the direction of barrier, flight control system by it is all can
The corresponding direction in traffic areas is determined as candidate heading.
Then, according to the cost function value of cost function calculation candidate's heading, by the smallest candidate of cost function value
Heading is determined as the optimal heading of unmanned plane 100.
Above-mentioned least cost function value is the minimum flight cost gone out by cost function calculation, that is, determines flight cost most
Small candidate heading is the optimal heading of unmanned plane 100.
Wherein, cost function are as follows:
F=k1×g(direcgoal,direccur)+k2×g(direcpre,direccur)-k3× sum,
Wherein, g (direcgoal,direccur) indicate one of candidate heading and mesh in candidate heading
The consistency in target direction, g (direcpre,direccur) indicate the optimal heading of candidate heading and a preceding decision
Consistency, sum indicate can traffic areas quantity, k1、k2、k3For weight coefficient.
It is higher, higher with the consistency of the optimal heading of a preceding decision and can with the consistency in the direction of target
The cost of the more candidate heading of the quantity of traffic areas is smaller.
k1、k2、k3Relative size determine the priority orders of three kinds of factors.To make determining candidate heading
It is consistent as far as possible with the direction of target, then makes k1>k2、k3;To make determining candidate heading and a preceding decision
Optimal heading be consistent as far as possible, then make k2>k1、k3;To guarantee determining candidate heading safe enough,
Then make k3>k2、k1。
In identified detection of obstacles region, the minimum range of unmanned plane 100 Yu barrier is determined, comprising: determine
In detection of obstacles region with unmanned plane 100 apart from the smallest barrier as target obstacle, then, by target obstacle with
The distance of unmanned plane 100 is determined as minimum range.For example, referring to Fig. 3, flight control system determines barrier Z1 and unmanned plane 100
Distance it is minimum, therefore flight control system determines that barrier Z1 is target obstacle, then, by barrier Z1 and unmanned plane 100 away from
From being determined as minimum range.
Further, the optimal heading and unmanned plane 100 and barrier that flight control system determines unmanned plane 100 are most
After small distance, according to identified minimum range, expected forward speed and optimal heading, unmanned plane 100 is determined most
Excellent flying speed.
Wherein, optimal flying speed includes optimal forward speed and optimal side velocity.
Unmanned plane is determined according to identified minimum range, expected forward speed and optimal heading based on this
100 optimal flying speed, specifically includes: according to minimum range, the maximum forward speed of unmanned plane 100 is calculated, then, according to
Maximum forward speed and expected forward speed, determine optimal forward speed, then, according to optimal forward speed and optimal flight side
To determining optimal side velocity.
Wherein, the maximum forward speed of unmanned plane 100 is to guarantee that unmanned plane 100 will not collide the forward direction of nearest barrier
Speed, if the forward speed of unmanned plane 100 is greater than maximum forward speed, unmanned plane 100 may collide nearest barrier.
According to maximum forward speed and expected forward speed, determines optimal forward speed, specifically include: comparing maximum forward
Speed and expected forward speed, if maximum forward speed is greater than expected forward speed, it is determined that it is expected that before forward speed is optimal
To speed, at this point, optimal forward speed not only can guarantee that unmanned plane 100 will not collide nearest barrier, but also unmanned plane can guarantee
100 keep initial level distance with target;If maximum forward speed is not more than expected forward speed, it is determined that maximum forward speed
For optimal forward speed, at this point, since expected forward speed is greater than maximum forward speed, if to be expected forward speed as optimal
Forward speed, although can guarantee that unmanned plane 100 and target keep initial level distance, unmanned plane 100 may be collided recently
Barrier, therefore determine that maximum forward speed is optimal forward speed, to guarantee that unmanned plane 100 will not collide nearest barrier.
It is from by pre- when determining the optimal heading of unmanned plane 100 in detection of obstacles region due to flight control system
If angular divisions can determine optimal heading in the corresponding candidate heading in traffic areas, therefore optimal heading
Corresponding optimal flight angle.
Based on this, according to optimal forward speed and optimal heading, when determining optimal side velocity, according to optimal flight
The product of the tangent value of angle and optimal forward speed determines optimal side velocity.
Optimal forward speed and optimal side velocity determined by flight control system, which collectively constitute, instructs the flight of unmanned plane 100
Optimal flying speed.
Further, it after flight control system determines the optimal flying speed of unmanned plane 100, controls unmanned plane 100 and is flown with optimal
Scanning frequency degree flies along optimal heading, to hide the barrier of 100 front environment of unmanned plane.
When the optimal forward speed in optimal flying speed is maximum forward speed, flight control system controls unmanned plane 100
When with optimal flying speed along optimal heading flight, unmanned plane 100 being capable of accurate avoidance;When in optimal flying speed most
When excellent forward speed is expected forward speed, flight control system controls unmanned plane 100 with optimal flying speed along optimal heading
When flight, unmanned plane 100 can accurate avoidance while, with target keep initial level distance.
In embodiments of the present invention, unmanned plane, which passes through, executes the unmanned plane barrier-avoiding method based on target following, and being capable of root
Grating map is determined according to the depth map of acquired front environment, and then optimal heading, and root are determined according to grating map
According to identified minimum range, expected forward speed and optimal heading, the optimal flight on optimal heading is determined
Speed is realized and carries out path planning to entire flight space, to strain the dynamic change of flight space in real time, improves target following
The accuracy of automatic obstacle avoiding in the process.
Embodiment two
Referring to Fig. 4, being a kind of present invention unmanned plane barrier-avoiding method based on target following that wherein an embodiment provides
Flow diagram, be applied to unmanned plane, the unmanned plane be above-described embodiment described in unmanned plane 100, and the present invention implement
The method that example provides is executed by above-mentioned flight control system, is carried out path planning for the entire flight space to unmanned plane, is improved mesh
The accuracy of automatic obstacle avoiding during mark tracking, being somebody's turn to do the unmanned plane barrier-avoiding method based on target following includes:
S100: the expection forward speed of unmanned plane is determined.
Above-mentioned " it is expected that forward speed " is for making unmanned plane and target keep initial level distance, i.e. the forward direction speed of unmanned plane
When degree is is expected forward speed, unmanned plane could keep initial level distance with target.Wherein, target is unmanned plane during flying process
The object of middle tracking, the target are located at ground, can be in ground moving.
Then, when determining the expection forward speed of unmanned plane, firstly, obtaining the initial level distance of unmanned plane and target;
Then, it is determined that the present level distance of unmanned plane and target;Finally, based on acquired initial level distance, to identified
Present level distance carries out P I D and adjusts, to determine the expection forward speed of unmanned plane.
Wherein, position and target position be in the horizontal direction when initial level distance is unmanned plane initialization
Relative distance, the initial level distance are stored after capable of being set by user to memory, also can be by flight control system in nothing
It is stored after being calculated when man-machine initialization to memory.
Based on this, the initial level distance of unmanned plane and target can be obtained in memory.
Present level distance is then phase of the unmanned plane present position with target present position in the horizontal direction
It adjusts the distance.
Since expected forward speed is determined based on the object tracking process of unmanned plane, therefore in the expection for determining unmanned plane
Before forward speed, this method further include: control the center alignment target of holder.
Specifically, when controlling the center alignment target of holder, the direction of target is obtained in real time, then, according to the side of target
To control holder is rotated, until the target-bound direction in center of holder realizes unmanned plane to target with target alignment
Tracking.
Based on this, ground is located at due to target and is aligned with the center of holder, can by the pitch angle of holder with
And the distance away the ground of holder, calculate unmanned plane and the relative distance of target in the horizontal direction, also that is, unmanned plane and target it
Between horizontal distance.Specifically, the horizontal distance between unmanned plane and targetH is the distance away the ground of holder, θ1For
The pitch angle of holder.
Then, determine the present level of unmanned plane and target apart from when, obtain the current distance away the ground and holder of holder
After current pitch angle, the present level of unmanned plane and target is calculated according to acquired current distance away the ground and current pitch angle
Distance.
Similarly, the distance away the ground of the pitch angle of holder and holder, calculates nobody when can be initialized according to unmanned plane
Machine and the initial level of target distance are simultaneously stored to memory.
Based on acquired initial level distance, PID adjusting is carried out to identified present level distance, to determine nothing
In the step of man-machine expection forward speed, then closed-loop control is carried out with PID controller.
In PID controller, initial level distance is the desired value of controlled variable, and present level distance is controlled variable
Actual value, and it is expected forward speed then and is the response output of PID controller.When present level distance and initial level distance exist
When deviation, then adjusting expected forward speed enables present level distance to reach initial level distance.
S200: obtaining the depth map of environment in front of the unmanned plane, and according to the depth map, determines with the unmanned plane
Centered on grating map.
Above-mentioned " depth map (Depth Map) " is the figure comprising information related with the surface distance of the scenario objects of viewpoint
Picture or image channel, in depth map, each of which pixel value indicates actual range of the depth transducer apart from object.
In an embodiment of the present invention, the depth map that environment in front of unmanned plane is obtained by depth transducer, passes through depth
Spending sensor to obtain the depth map of environment in front of unmanned plane is the actual range for obtaining depth transducer and front environmental objects.
Above-mentioned " grating map " is then the planar gate by being mapped to the depth information in depth map centered on body
It is formed in trrellis diagram, each grid gives a probable value, indicates the probability that the grid is occupied by barrier.When environment depth map
In there are when barrier, barrier occupies grid in grating map, can know barrier by being occupied the coordinate of grid
Position.
The grid of grating map is arranged in matrix, for example, the grid of grating map is arranged in the matrix of 10*10.
In an embodiment of the present invention, if unmanned plane generates pitch angle in flight course, unmanned plane forward sight can be made not
It is horizontal again, at this point, the depth map of depth transducer acquisition is no longer the depth map in the horizontal front of unmanned plane, so that depth map
There is error in the depth information reflected, causes the inaccuracy of grating map.Then, it is with unmanned plane determining according to depth map
Before the grating map at center, also need to judge depth transducer with the presence or absence of pitch angle, if depth transducer there are pitch angle,
To the grating map determined after depth map progress depth compensation further according to the depth map after depth compensation centered on unmanned plane.
Wherein, the triaxial attitude angle of unmanned plane can be measured by the second gyroscope, it is deep to be judged according to triaxial attitude angle
Spending sensor whether there is pitch angle.
Depth compensation is carried out to depth map to specifically include: calculating the number of lines of pixels of depth compensation, and depth is being calculated
After the number of lines of pixels of compensation, the row rope as plane on depth map of unmanned plane is determined according to the number of lines of pixels of the depth compensation
Draw.
Specifically, referring to Fig. 2, when depth transducer is depth camera, the number of lines of pixels row_see of the depth compensation
Are as follows:
Row_see=tan θ2× f, wherein θ2For the pitch angle of depth camera, f is the focal length of depth camera;
The line index row_horizon as plane on depth map of the unmanned plane are as follows:
Row_horizon=row_half+row_see, wherein row_half is the half of depth map line number.
S300: according to the grating map, the optimal heading and the unmanned plane and barrier of the unmanned plane are determined
Hinder the minimum range of object.
During unmanned plane during flying, the forward speed of unmanned plane is bigger, bigger with the probability of barrier collision, needs
The distribution of obstacles situation of environment in front of unmanned plane is considered earlier;And the forward speed of unmanned plane is smaller, collides with barrier
Probability with regard to smaller, the too early distribution of obstacles situation for considering environment in front of unmanned plane is easy to examine on unnecessary barrier
Worry is entered, and the judgement inaccuracy of optimal heading is caused.
Then, in an embodiment of the present invention, according to identified grating map, the optimal flight side of unmanned plane is determined
To and the minimum range of unmanned plane and barrier before, it is also necessary to the current forward speed of unmanned plane is determined, then, according to working as
Preceding forward speed and expected forward speed, after determining detection of obstacles region in grating map, then in detection of obstacles region
In, determine the optimal heading of unmanned plane and the minimum range of unmanned plane and barrier.That is, by the forward speed of unmanned plane
In conjunction with the detection range of barrier, a suitable detection of obstacles range is determined according to the forward speed of unmanned plane, to increase
Add the accuracy of detection of obstacles.
Wherein, detection of obstacles region is in grating map for detecting the region of barrier, the detection of obstacles region
Positioned at the top half (i.e. 100 front of unmanned plane) of grating map, the columns in the detection of obstacles region and the column of grating map
The half that identical, line number is less than or equal to the line number of grating map is counted, i.e. the detection of obstacles region is less than or equal to grid
The half of lattice map.For example, referring to Fig. 3, solid line region P1 is detection of obstacles region.
The optimal heading of unmanned plane is that there is no the directions of barrier;Minimum range, that is, nothing of unmanned plane and barrier
It is man-machine at a distance from nearest barrier within sweep of the eye.
Further, in an embodiment of the present invention, according to current forward speed and expected forward speed, in grating map
Middle determining detection of obstacles region, comprising: more current forward speed and expected forward speed, if current forward speed is less than in advance
Phase forward speed then determines detection of obstacles region according to expected forward speed, at this time, it is contemplated that forward speed in grating map
Bigger, identified detection of obstacles region is bigger;If current forward speed is greater than expected forward speed, according to current forward direction
Speed determines detection of obstacles region in grating map, at this point, current forward speed is bigger, identified detection of obstacles area
Domain is bigger.
Further, in an embodiment of the present invention, in identified detection of obstacles region, determine unmanned plane most
Excellent heading, comprising: firstly, in identified detection of obstacles region, determine unmanned plane can traffic areas.
Wherein, can traffic areas be detection of obstacles region in be not present barrier region.
In identified detection of obstacles region, determine unmanned plane can traffic areas, specifically include: being with unmanned plane
Center, predetermined angle are interval, are divided to detection of obstacles region, are multiple areas by detection of obstacles region division
Then domain samples the coordinate of barrier, and whether the obstacle article coordinate for judging that sampling obtains falls into detection of obstacles region division
Region in, the region that obstacle article coordinate is not fallen within is determined as can traffic areas.For example, referring to Fig. 3, with unmanned plane 100
Centered on, predetermined angle θ3For interval, multiple fan-shaped regions are divided in the P1 of detection of obstacles region, the fan-shaped region divided
It is from left to right respectively B1 to B11;Then, the coordinate for sampling barrier Z1, Z2 and Z3, determines that the coordinate of barrier Z1 falls into B2
With the region B3, the coordinate of barrier Z2 falls into B6 to the region B9, and the coordinate of barrier Z3 does not fall within detection of obstacles region P1
In, accordingly, it is determined that region B1, B4, B5, B10 and B11 that barrier is not fallen within are can traffic areas.
Wherein, each region marked off in detection of obstacles region is fan-shaped region.
When dividing to detection of obstacles region, predetermined angle is bigger, and the region of division is bigger, the region marked off
Quantity is then fewer;Predetermined angle is smaller, and the region of division is smaller, and the region quantity marked off is then more.
Sample the coordinate of barrier, comprising: the central point of the grid occupied in sampling detection of obstacles region by barrier
The angular coordinate of coordinate and/or the grid occupied by barrier.
Not by the angular coordinate of the center point coordinate of the grid occupied by barrier and/or the grid occupied by barrier
The region fallen into is determined as can traffic areas.Based on this, if the region division of grating map is too small, it is easy to appear region quilt
Barrier covering, but the coordinate the case where not falling within region sampled, at this point, be mistaken for can FOH in impassabitity region
Domain;And if the region division of grating map is excessive, will lead to that heading is very few, is unfavorable for the judgement of optimal heading.
Then, in order to guarantee the reliability of path planning, the size of predetermined angle can be adjusted according to practical flight effect.
Predetermined angle is adjusted according to the robustness of depth map data and the accuracy in planning direction.
Secondly, can determine the candidate heading of unmanned plane in traffic areas identified.
Based on can the candidate heading that determines of traffic areas be there is no the direction of barrier, by it is all can traffic areas
Corresponding direction is determined as candidate heading.
Then, according to the cost function value of cost function calculation candidate's heading, by the smallest candidate of cost function value
Heading is determined as the optimal heading of unmanned plane.
Above-mentioned least cost function value is the minimum flight cost gone out by cost function calculation, that is, determines flight cost most
Small candidate heading is the optimal heading of unmanned plane.
Wherein, cost function are as follows:
F=k1×g(direcgoal,direccur)+k2×g(direcpre,direccur)-k3× sum,
Wherein, g (direcgoal,direccur) indicate one of candidate heading and mesh in candidate heading
The consistency in target direction, g (direcpre,direccur) indicate the optimal heading of candidate heading and a preceding decision
Consistency, sum indicate can traffic areas quantity, k1、k2、k3For weight coefficient.
It is higher, higher with the consistency of the optimal heading of a preceding decision and can with the consistency in the direction of target
The cost of the more candidate heading of the quantity of traffic areas is smaller.
k1、k2、k3Relative size determine the priority orders of three kinds of factors.To make determining candidate heading
It is consistent as far as possible with the direction of target, then makes k1>k2、k3;To make determining candidate heading and a preceding decision
Optimal heading be consistent as far as possible, then make k2>k1、k3;To guarantee determining candidate heading safe enough,
Then make k3>k2、k1。
Further, in an embodiment of the present invention, in identified detection of obstacles region, unmanned plane and barrier are determined
Hinder the minimum range of object, comprising: determine in detection of obstacles region with unmanned plane apart from the smallest barrier as target disorders
Then target obstacle is determined as minimum range by object at a distance from unmanned plane.For example, referring to Fig. 3, determining barrier Z1
With it is minimum at a distance from unmanned plane 100, therefore determine that barrier Z1 is target obstacle, then, by barrier Z1 and unmanned plane 100
Distance is determined as minimum range.
S400: according to the minimum range, the expected forward speed and the optimal heading, the nothing is determined
Man-machine optimal flying speed.
In an embodiment of the present invention, optimal flying speed includes optimal forward speed and optimal side velocity.
Unmanned plane is determined according to identified minimum range, expected forward speed and optimal heading based on this
Optimal flying speed, specifically includes: according to minimum range, the maximum forward speed of unmanned plane is calculated, then, according to maximum forward
Speed and expected forward speed, determine optimal forward speed, then, according to optimal forward speed and optimal heading, determine
Optimal side velocity.
Wherein, the maximum forward speed of unmanned plane is to guarantee that unmanned plane will not collide the forward speed of nearest barrier,
If nobody forward speed is greater than maximum forward speed, unmanned plane may collide nearest barrier.
In an embodiment of the present invention, it according to maximum forward speed and expected forward speed, determines optimal forward speed, has
Body includes: to compare maximum forward speed and expected forward speed, if maximum forward speed is greater than expected forward speed, it is determined that pre-
Phase forward speed is optimal forward speed, at this point, optimal forward speed both can guarantee that unmanned plane will not collide nearest barrier,
It can guarantee that unmanned plane and target keep initial level distance again;If maximum forward speed is not more than expected forward speed, it is determined that
Maximum forward speed is optimal forward speed, at this point, since expected forward speed is greater than maximum forward speed, if with before expected to
Speed is as optimal forward speed, although can guarantee that unmanned plane and target keep initial level distance, unmanned plane may be collided
To nearest barrier, therefore determine that maximum forward speed is optimal forward speed, to guarantee that unmanned plane will not collide nearest obstacle
Object.
When in an embodiment of the present invention, due to the optimal heading of unmanned plane determining in detection of obstacles region,
It is that can determine optimal heading in the corresponding candidate heading in traffic areas from what is divided by predetermined angle, therefore it is optimal
Heading corresponds to optimal flight angle.
Based on this, according to optimal forward speed and optimal heading, when determining optimal side velocity, according to optimal flight
The product of the tangent value of angle and optimal forward speed determines optimal side velocity.
Identified optimal forward speed and optimal side velocity collectively constitute the optimal flight speed for instructing unmanned plane during flying
Degree.
S500: it controls the unmanned plane and is flown with the optimal flying speed along the optimal heading, to hide
State the barrier of environment in front of unmanned plane.
When the optimal forward speed in optimal flying speed is maximum forward speed, unmanned plane is controlled with optimal flight speed
When degree is along optimal heading flight, unmanned plane being capable of accurate avoidance;When the optimal forward speed in optimal flying speed is pre-
When phase forward speed, control unmanned plane with optimal flying speed along optimal heading flight when, unmanned plane being capable of accurate avoidance
While, initial level distance is kept with target.
In embodiments of the present invention, nothing is determined by obtaining the grating map that the depth map of environment in front of unmanned plane determines
Man-machine optimal heading enables unmanned plane to carry out path planning to entire flight space, strains flight space in real time
Dynamic change, meanwhile, according to identified minimum range, expected forward speed and optimal heading, determine unmanned plane
Optimal flying speed on optimal heading enables unmanned plane to plan optimal flight speed according to actual environment situation
Degree improves the accuracy of automatic obstacle avoiding in object tracking process.
Embodiment three
Term " module " used below is the combination that the software and/or hardware of predetermined function may be implemented.Although with
Device described in lower embodiment can be realized with software, but the combined realization of hardware or software and hardware is also
It may be contemplated.
Referring to Fig. 5, be a kind of present invention unmanned plane obstacle avoidance apparatus based on target following that wherein an embodiment provides,
The device is applied to unmanned plane, which is unmanned plane 100 described in above-described embodiment, and provided in an embodiment of the present invention
The function of device modules is executed by above-mentioned flight control system, carries out path planning for the entire flight space to unmanned plane,
The accuracy of automatic obstacle avoiding in object tracking process is improved, being somebody's turn to do the unmanned plane obstacle avoidance apparatus based on target following includes:
First determining module 200, for determining the expection forward speed of unmanned plane, the expected forward speed is for making institute
It states unmanned plane and target keeps initial level distance;
Module 300 is obtained, for obtaining the depth map of environment in front of the unmanned plane, and according to the depth map, is determined
Grating map centered on the unmanned plane;
Second determining module 400, for according to the grating map, determine the unmanned plane optimal heading and
The minimum range of the unmanned plane and barrier;And
For determining the nothing according to the minimum range, the expected forward speed and the optimal heading
Man-machine optimal flying speed;
Control module 500 is flown with the optimal flying speed along the optimal heading for controlling the unmanned plane
Row, to hide the barrier of environment in front of the unmanned plane.
In some other embodiment, first determining module 200 is specifically used for:
Obtain the initial level distance of the unmanned plane Yu the target;
Determine the present level distance of the unmanned plane Yu the target;
Based on the initial level distance, PID adjusting is carried out to the present level distance, with the determination unmanned plane
The expected forward speed.
In some other embodiment, the unmanned plane includes holder, and the control module 500 is also used to:
The center for controlling the holder is directed at the target;Then,
First determining module 200 is specifically used for:
Obtain the holder current distance away the ground and current pitch angle;
The current of the unmanned plane and the target is determined according to the current distance away the ground and the current pitch angle
Horizontal distance.
In some other embodiment, first determining module 200 is also used to:
Determine the current forward speed of the unmanned plane;Then,
Second determining module 400 is specifically used for:
According to the current forward speed and the expected forward speed, detection of obstacles is determined in the grating map
Region;
In the detection of obstacles region, determine the unmanned plane optimal heading and the unmanned plane and barrier
Hinder the minimum range of object.
In some other embodiment, second determining module 400 is specifically used for:
Compare the current forward speed and the expected forward speed;
If the current forward speed is less than the expected forward speed, according to the expected forward speed in the grid
The detection of obstacles region is determined in lattice map;
If the current forward speed is greater than the expected forward speed, according to the current forward speed in the grid
True the detection of obstacles region in lattice map.
In some other embodiment, when according to the expected forward speed in the grating map determine obstacle quality testing
When surveying region, the expected forward speed is bigger, and the detection of obstacles region is bigger;
When determining detection of obstacles region in the grating map according to the current forward speed, it is described it is current before
Bigger to speed, the detection of obstacles region is bigger.
In some other embodiment, second determining module 400 is specifically used for:
In the detection of obstacles region, determine the unmanned plane can traffic areas, wherein it is described can traffic areas
For there is no the regions of barrier;
According to it is described can traffic areas, determine the candidate heading of the unmanned plane;
The cost function value of candidate's heading according to cost function calculation;
The smallest candidate heading of the cost function value is determined as to the optimal heading of the unmanned plane.
In some other embodiment, second determining module 400 is specifically used for:
Centered on the unmanned plane, predetermined angle is interval, is divided to the detection of obstacles region, by institute
Stating detection of obstacles region division is multiple regions;
Sample the coordinate of barrier;
Determine that the region that the coordinate is not fallen within can traffic areas for described in.
In some other embodiment, second determining module 400 is specifically used for:
Sample the center point coordinate of the grid occupied in the detection of obstacles region by the barrier and/or described
The angular coordinate for the grid that barrier occupies.
In some other embodiment, the cost function are as follows:
F=k1×g(direcgoal,direccur)+k2×g(direcpre,direccur)-k3×sum
Wherein, g (direcgoal,direccur) indicate one of candidate heading in the candidate heading
With the consistency in the direction of the target, g (direcpre,direccur) indicate the candidate heading and a preceding decision
The consistency of optimal heading, sum expression described in can traffic areas quantity, k1、k2、k3For weight coefficient.
In some other embodiment, second determining module 400 is specifically used for:
It determines in the detection of obstacles region with the unmanned plane apart from the smallest barrier as target obstacle;
The target obstacle is determined as the minimum range at a distance from the unmanned plane.
In some other embodiment, the optimal flying speed includes optimal forward speed and optimal side velocity;Then,
Second determining module 400 is specifically used for:
According to the minimum range, the maximum forward speed of the unmanned plane is calculated;
According to the maximum forward speed and the expected forward speed, the optimal forward speed is determined;
According to the optimal forward speed and the optimal heading, the optimal side velocity is determined.
In some other embodiment, second determining module 400 is specifically used for:
Compare the maximum forward speed and the expected forward speed;
If the maximum forward speed is greater than the expected forward speed, it is determined that the expected forward speed be it is described most
Excellent forward speed;
If the maximum forward speed is not more than the expected forward speed, it is determined that the maximum forward speed is described
Optimal forward speed.
In some other embodiment, the optimal heading corresponds to optimal flight angle;Then,
Second determining module 400 is specifically used for:
It is determined according to the product of the tangent value of the optimal flight angle and the optimal forward speed described optimal lateral
Speed.
In some other embodiment, the acquisition module 300 is specifically used for:
The depth map of environment in front of the unmanned plane is obtained by the depth transducer of the unmanned plane.
In some other embodiment, described according to the depth map, the grid centered on the unmanned plane is determined
Before map, the acquisition module 300 is also used to:
Judge the depth transducer with the presence or absence of pitch angle;
If so, carrying out depth compensation to the depth map.
In some other embodiment, the depth transducer is depth camera;Then,
The acquisition module 300 is specifically used for:
Calculate the number of lines of pixels of the depth compensation, the number of lines of pixels of the depth compensation are as follows:
Row_see=tan θ2× f, wherein θ2For the pitch angle of the depth camera, f is the focal length of the depth camera;
The row rope as plane on the depth map of the unmanned plane is determined according to the number of lines of pixels of the depth compensation
Draw, the line index row_horizon as plane on the depth map of the unmanned plane are as follows:
Row_horizon=row_half+row_see, wherein row_half is the half of the depth map line number.
Certainly, in some other alternate embodiments, above-mentioned first determining module 200 obtains module 300, second really
Cover half block 400 and control module 500 can be the winged control chip in flight control system.
Since Installation practice and embodiment of the method under the premise of content does not conflict mutually, are filled based on same design
The content for setting embodiment can be with quoting method embodiment, and this is no longer going to repeat them.
In embodiments of the present invention, nothing is determined by obtaining the grating map that the depth map of environment in front of unmanned plane determines
Man-machine optimal heading enables unmanned plane to carry out path planning to entire flight space, strains flight space in real time
Dynamic change, meanwhile, according to identified minimum range, expected forward speed and optimal heading, determine unmanned plane
Optimal flying speed on optimal heading enables unmanned plane to plan optimal flight speed according to actual environment situation
Degree improves the accuracy of automatic obstacle avoiding in object tracking process.
Example IV
Referring to Fig. 6, being a kind of hardware structural diagram of present invention unmanned plane that wherein an embodiment provides, the present invention
The hardware module that embodiment provides can be integrated in flight control system described in above-described embodiment, also can be directly as flight control system
It is set in fuselage 10, so that unmanned plane 100 is able to carry out a kind of unmanned plane based on target following described in above embodiments
Barrier-avoiding method, moreover it is possible to realize a kind of modules of the unmanned plane obstacle avoidance apparatus based on target following described in above embodiments
Function.The unmanned plane 100 includes:
One or more processors 110 and memory 120.Wherein, in Fig. 6 by taking a processor 110 as an example.
Processor 110 can be connected with memory 120 by bus or other modes, to be connected by bus in Fig. 6
For.
Memory 120 is used as a kind of non-volatile computer readable storage medium storing program for executing, can be used for storing non-volatile software journey
Sequence, non-volatile computer executable program and module, such as one of the above embodiment of the present invention based on target following
The corresponding program instruction of unmanned plane barrier-avoiding method and a kind of corresponding module (example of unmanned plane obstacle avoidance apparatus based on target following
Such as, the first determining module 200, acquisition module 300, the second determining module 400 and control module 500 etc.).Processor 110 passes through
Non-volatile software program, instruction and the module being stored in memory 120 are run, is based on target following thereby executing one kind
Unmanned plane barrier-avoiding method various function application and data processing, i.e. realization one of above method embodiment is based on mesh
Mark the function of the unmanned plane barrier-avoiding method of tracking and the modules of above-mentioned apparatus embodiment.
Memory 120 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function;Storage data area can be stored according to a kind of unmanned plane based on target following
Obstacle avoidance apparatus uses created data etc..
The storage data area is also stored with preset data, including initial level distance, predetermined angle etc..
In addition, memory 120 may include high-speed random access memory, it can also include nonvolatile memory, example
Such as at least one disk memory, flush memory device or other non-volatile solid state memory parts.In some embodiments, it deposits
Optional reservoir 120 includes the memory remotely located relative to processor 110, these remote memories can pass through network connection
To processor 110.The example of above-mentioned network include but is not limited to internet, intranet, local area network, mobile radio communication and its
Combination.
Described program instruction and one or more module are stored in the memory 120, when by one or
When multiple processors 110 execute, unmanned plane avoidance side of one of the above-mentioned any means embodiment based on target following is executed
Each step of method, alternatively, realizing unmanned plane obstacle avoidance apparatus of one of the above-mentioned any device embodiment based on target following
Modules function.
Method provided by the above embodiment of the present invention can be performed in the said goods, has the corresponding functional module of execution method
And beneficial effect.The not technical detail of detailed description in the present embodiment, reference can be made to side provided by the above embodiment of the present invention
Method.
The embodiment of the invention also provides a kind of non-volatile computer readable storage medium storing program for executing, the computer-readable storage
Media storage has computer executable instructions, which is executed by one or more processors, such as in Fig. 6
A processor 110, may make computer to execute nobody based on target following of one of above-mentioned any means embodiment
Each step of machine barrier-avoiding method, alternatively, realizing unmanned plane of one of the above-mentioned any device embodiment based on target following
The function of the modules of obstacle avoidance apparatus.
The embodiment of the invention also provides a kind of computer program product, the computer program product is non-including being stored in
Computer program on volatile computer readable storage medium storing program for executing, the computer program include program instruction, work as described program
Instruction is executed by one or more processors, such as in Fig. 6 a processor 110, and it is above-mentioned any to may make that computer executes
Each step of unmanned plane barrier-avoiding method of one of the embodiment of the method based on target following, alternatively, realizing above-mentioned any dress
Set the function of the modules of unmanned plane obstacle avoidance apparatus of one of the embodiment based on target following.
The apparatus embodiments described above are merely exemplary, wherein described, module can as illustrated by the separation member
It is physically separated with being or may not be, the component shown as module may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.
By the description of above embodiment, those of ordinary skill in the art can be understood that each embodiment can borrow
Help software that the mode of general hardware platform is added to realize, naturally it is also possible to pass through hardware.Those of ordinary skill in the art can manage
All or part of the process in solution realization above-described embodiment method is can be by the relevant hardware of computer program instructions come complete
At the program can be stored in a computer-readable storage medium, and the program is when being executed, it may include such as above-mentioned each side
The process of the implementation method of method.Wherein, the storage medium can be magnetic disk, CD, read-only memory (Read-Only
Memory, ROM) or random access memory (RandomAccessMemory, RAM) etc..
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;At this
It under the thinking of invention, can also be combined between the technical characteristic in above embodiments or different embodiment, step can be with
It is realized with random order, and there are many other variations of different aspect present invention as described above, for simplicity, they do not have
Have and is provided in details;Although the present invention is described in detail referring to the foregoing embodiments, the ordinary skill people of this field
Member is it is understood that it is still possible to modify the technical solutions described in the foregoing embodiments, or to part of skill
Art feature is equivalently replaced;And these are modified or replaceed, each reality of the application that it does not separate the essence of the corresponding technical solution
Apply the range of a technical solution.
Claims (36)
1. a kind of unmanned plane barrier-avoiding method based on target following, which is characterized in that the described method includes:
Determine the expection forward speed of unmanned plane, the expected forward speed is for making the unmanned plane and target keep initial water
Flat distance;
The depth map of environment in front of the unmanned plane is obtained, and according to the depth map, is determined centered on the unmanned plane
Grating map;
According to the grating map, the optimal heading of the unmanned plane and the minimum of the unmanned plane and barrier are determined
Distance;
According to the minimum range, the expected forward speed and the optimal heading, the unmanned plane is determined most
Excellent flying speed;
It controls the unmanned plane to fly with the optimal flying speed along the optimal heading, before hiding the unmanned plane
The barrier of square environment.
2. the method according to claim 1, wherein the expection forward speed of the determining unmanned plane, comprising:
Obtain the initial level distance of the unmanned plane Yu the target;
Determine the present level distance of the unmanned plane Yu the target;
Based on the initial level distance, PID adjusting is carried out to the present level distance, described in the determination unmanned plane
It is expected that forward speed.
3. according to the method described in claim 2, it is characterized in that, the unmanned plane includes holder, the method also includes:
The center for controlling the holder is directed at the target;Then,
The present level distance of the determination unmanned plane and the target, comprising:
Obtain the holder current distance away the ground and current pitch angle;
The present level of the unmanned plane Yu the target is determined according to the current distance away the ground and the current pitch angle
Distance.
4. according to the method in any one of claims 1 to 3, which is characterized in that the method also includes:
Determine the current forward speed of the unmanned plane;Then,
It is described according to the grating map, determine the optimal heading and the unmanned plane and barrier of the unmanned plane
Minimum range, comprising:
According to the current forward speed and the expected forward speed, detection of obstacles area is determined in the grating map
Domain;
In the detection of obstacles region, the optimal heading and the unmanned plane and barrier of the unmanned plane are determined
Minimum range.
5. according to the method described in claim 4, it is characterized in that, it is described according to the current forward speed and the expection before
To speed, detection of obstacles region is determined in the grating map, comprising:
Compare the current forward speed and the expected forward speed;
If the current forward speed is less than the expected forward speed, in the grid according to the expected forward speed
The detection of obstacles region is determined in figure;
If the current forward speed is greater than the expected forward speed, in the grid according to the current forward speed
True the detection of obstacles region in figure.
6. according to the method described in claim 5, it is characterized in that,
When determining detection of obstacles region in the grating map according to the expected forward speed, Xiang Su before the expection
Degree is bigger, and the detection of obstacles region is bigger;
When determining detection of obstacles region in the grating map according to the current forward speed, the current forward direction speed
Degree is bigger, and the detection of obstacles region is bigger.
7. the method according to any one of claim 4 to 6, which is characterized in that described in the detection of obstacles region
In, determine the optimal heading of the unmanned plane, comprising:
In the detection of obstacles region, determine the unmanned plane can traffic areas, wherein it is described can traffic areas be not
There are the regions of barrier;
According to it is described can traffic areas, determine the candidate heading of the unmanned plane;
The cost function value of candidate's heading according to cost function calculation;
The smallest candidate heading of the cost function value is determined as to the optimal heading of the unmanned plane.
8. the method according to the description of claim 7 is characterized in that described in the detection of obstacles region, determine described in
Unmanned plane can traffic areas, comprising:
Centered on the unmanned plane, predetermined angle is interval, is divided to the detection of obstacles region, by the barrier
Hindering analyte detection region division is multiple regions;
Sample the coordinate of barrier;
Determine that the region that the coordinate is not fallen within can traffic areas for described in.
9. according to the method described in claim 8, it is characterized in that, the coordinate of the sampling barrier, comprising:
Sample the center point coordinate of the grid occupied in the detection of obstacles region by the barrier and/or by the obstacle
The angular coordinate for the grid that object occupies.
10. method according to any one of claims 7 to 9, which is characterized in that the cost function are as follows:
F=k1×g(direcgoal,direccur)+k2×g(direcpre,direccur)-k3×sum
Wherein, g (direcgoal,direccur) indicate one of candidate heading in the candidate heading with it is described
The consistency in the direction of target, g (direcpre,direccur) indicate that the candidate heading and the optimal of a preceding decision fly
The consistency of line direction, sum expression described in can traffic areas quantity, k1、k2、k3For weight coefficient.
11. the method according to any one of claim 4 to 10, which is characterized in that described in the detection of obstacles area
In domain, the minimum range of the unmanned plane and barrier is determined, comprising:
It determines in the detection of obstacles region with the unmanned plane apart from the smallest barrier as target obstacle;
The target obstacle is determined as the minimum range at a distance from the unmanned plane.
12. method according to any one of claim 1 to 11, which is characterized in that the optimal flying speed includes most
Excellent forward speed and optimal side velocity;Then,
It is described according to the minimum range, the expected forward speed and the optimal heading, determine the unmanned plane
Optimal flying speed, comprising:
According to the minimum range, the maximum forward speed of the unmanned plane is calculated;
According to the maximum forward speed and the expected forward speed, the optimal forward speed is determined;
According to the optimal forward speed and the optimal heading, the optimal side velocity is determined.
13. according to the method for claim 12, which is characterized in that described according to the maximum forward speed and the expection
Forward speed determines the optimal forward speed, comprising:
Compare the maximum forward speed and the expected forward speed;
If the maximum forward speed be greater than the expected forward speed, it is determined that the expected forward speed be it is described it is optimal before
To speed;
If the maximum forward speed is not more than the expected forward speed, it is determined that the maximum forward speed is described optimal
Forward speed.
14. method according to claim 12 or 13, which is characterized in that the optimal heading corresponds to optimal flying angle
Degree;Then,
It is described according to the optimal forward speed and the optimal heading, determine the optimal side velocity, comprising:
The optimal side velocity is determined according to the product of the tangent value of the optimal flight angle and the optimal forward speed.
15. according to claim 1 to method described in any one of 14, which is characterized in that described to obtain in front of the unmanned plane
The depth map of environment, comprising:
The depth map of environment in front of the unmanned plane is obtained by the depth transducer of the unmanned plane.
16. according to the method for claim 15, which is characterized in that described according to the depth map, determine with the nothing
Before grating map centered on man-machine, the method also includes:
Judge the depth transducer with the presence or absence of pitch angle;
If so, carrying out depth compensation to the depth map.
17. according to the method for claim 16, which is characterized in that the depth transducer is depth camera;Then,
If there are pitch angles for the depth transducer, described to carry out depth compensation to the depth map, comprising:
Calculate the number of lines of pixels of the depth compensation, the number of lines of pixels of the depth compensation are as follows:
Row_see=tan θ2× f, wherein θ2For the pitch angle of the depth camera, f is the focal length of the depth camera;
The line index as plane on the depth map of the unmanned plane, institute are determined according to the number of lines of pixels of the depth compensation
State the line index row_horizon as plane on the depth map of unmanned plane are as follows:
Row_horizon=row_half+row_see, wherein row_half is the half of the depth map line number.
18. a kind of unmanned plane obstacle avoidance apparatus based on target following, which is characterized in that described device includes:
First determining module, for determining the expection forward speed of unmanned plane, the expected forward speed for make it is described nobody
Machine and target keep initial level distance;
Module is obtained, for obtaining the depth map of environment in front of the unmanned plane, and according to the depth map, is determined with the nothing
Grating map centered on man-machine;
Second determining module, for according to the grating map, determine the unmanned plane optimal heading and the nothing
The man-machine minimum range with barrier;And
For determining the unmanned plane according to the minimum range, the expected forward speed and the optimal heading
Optimal flying speed;
Control module is flown for controlling the unmanned plane with the optimal flying speed along the optimal heading, to hide
Refuge states the barrier of environment in front of unmanned plane.
19. device according to claim 18, which is characterized in that first determining module is specifically used for:
Obtain the initial level distance of the unmanned plane Yu the target;
Determine the present level distance of the unmanned plane Yu the target;
Based on the initial level distance, PID adjusting is carried out to the present level distance, described in the determination unmanned plane
It is expected that forward speed.
20. device according to claim 19, which is characterized in that the unmanned plane includes holder, and the control module is also
For:
The center for controlling the holder is directed at the target;Then,
First determining module is specifically used for:
Obtain the holder current distance away the ground and current pitch angle;
The present level of the unmanned plane Yu the target is determined according to the current distance away the ground and the current pitch angle
Distance.
21. device described in any one of 8 to 20 according to claim 1, which is characterized in that first determining module is also used
In:
Determine the current forward speed of the unmanned plane;Then,
Second determining module is specifically used for:
According to the current forward speed and the expected forward speed, detection of obstacles area is determined in the grating map
Domain;
In the detection of obstacles region, the optimal heading and the unmanned plane and barrier of the unmanned plane are determined
Minimum range.
22. device according to claim 21, which is characterized in that second determining module is specifically used for:
Compare the current forward speed and the expected forward speed;
If the current forward speed is less than the expected forward speed, in the grid according to the expected forward speed
The detection of obstacles region is determined in figure;
If the current forward speed is greater than the expected forward speed, in the grid according to the current forward speed
True the detection of obstacles region in figure.
23. device according to claim 22, which is characterized in that
When determining detection of obstacles region in the grating map according to the expected forward speed, Xiang Su before the expection
Degree is bigger, and the detection of obstacles region is bigger;
When determining detection of obstacles region in the grating map according to the current forward speed, the current forward direction speed
Degree is bigger, and the detection of obstacles region is bigger.
24. the device according to any one of claim 21 to 23, which is characterized in that second determining module is specifically used
In:
In the detection of obstacles region, determine the unmanned plane can traffic areas, wherein it is described can traffic areas be not
There are the regions of barrier;
According to it is described can traffic areas, determine the candidate heading of the unmanned plane;
The cost function value of candidate's heading according to cost function calculation;
The smallest candidate heading of the cost function value is determined as to the optimal heading of the unmanned plane.
25. device according to claim 24, which is characterized in that second determining module is specifically used for:
Centered on the unmanned plane, predetermined angle is interval, is divided to the detection of obstacles region, by the barrier
Hindering analyte detection region division is multiple regions;
Sample the coordinate of barrier;
Determine that the region that the coordinate is not fallen within can traffic areas for described in.
26. device according to claim 25, which is characterized in that second determining module is specifically used for:
Sample the center point coordinate of the grid occupied in the detection of obstacles region by the barrier and/or by the obstacle
The angular coordinate for the grid that object occupies.
27. the device according to any one of claim 24 to 26, which is characterized in that the cost function are as follows:
F=k1×g(direcgoal,direccur)+k2×g(direcpre,direccur)-k3×sum
Wherein, g (direcgoal,direccur) indicate one of candidate heading in the candidate heading with it is described
The consistency in the direction of target, g (direcpre,direccur) indicate that the candidate heading and the optimal of a preceding decision fly
The consistency of line direction, sum expression described in can traffic areas quantity, k1、k2、k3For weight coefficient.
28. the device according to any one of claim 21 to 27, which is characterized in that second determining module is specifically used
In:
It determines in the detection of obstacles region with the unmanned plane apart from the smallest barrier as target obstacle;
The target obstacle is determined as the minimum range at a distance from the unmanned plane.
29. device described in any one of 8 to 28 according to claim 1, which is characterized in that the optimal flying speed includes most
Excellent forward speed and optimal side velocity;Then,
Second determining module is specifically used for:
According to the minimum range, the maximum forward speed of the unmanned plane is calculated;
According to the maximum forward speed and the expected forward speed, the optimal forward speed is determined;
According to the optimal forward speed and the optimal heading, the optimal side velocity is determined.
30. device according to claim 29, which is characterized in that second determining module is specifically used for:
Compare the maximum forward speed and the expected forward speed;
If the maximum forward speed be greater than the expected forward speed, it is determined that the expected forward speed be it is described it is optimal before
To speed;
If the maximum forward speed is not more than the expected forward speed, it is determined that the maximum forward speed is described optimal
Forward speed.
31. the device according to claim 29 or 30, which is characterized in that the optimal heading corresponds to optimal flying angle
Degree;Then,
Second determining module is specifically used for:
The optimal side velocity is determined according to the product of the tangent value of the optimal flight angle and the optimal forward speed.
32. device described in any one of 8 to 31 according to claim 1, which is characterized in that the acquisition module is specifically used for:
The depth map of environment in front of the unmanned plane is obtained by the depth transducer of the unmanned plane.
33. device according to claim 32, which is characterized in that described according to the depth map, determine with the nothing
Before grating map centered on man-machine, the acquisition module is also used to:
Judge the depth transducer with the presence or absence of pitch angle;
If so, carrying out depth compensation to the depth map.
34. device according to claim 33, which is characterized in that the depth transducer is depth camera;Then,
The acquisition module is specifically used for:
Calculate the number of lines of pixels of the depth compensation, the number of lines of pixels of the depth compensation are as follows:
Row_see=tan θ2× f, wherein θ2For the pitch angle of the depth camera, f is the focal length of the depth camera;
The line index as plane on the depth map of the unmanned plane, institute are determined according to the number of lines of pixels of the depth compensation
State the line index row_horizon as plane on the depth map of unmanned plane are as follows:
Row_horizon=row_half+row_see, wherein row_half is the half of the depth map line number.
35. a kind of unmanned plane characterized by comprising
Fuselage;
Horn is connected with the fuselage;
Power device is set to the horn;
Holder is connected with the fuselage;
Depth camera is connected with the fuselage;
At least one processor is set in the fuselage;And
The memory being connect at least one described processor communication;Wherein, be stored with can be by described at least one for the memory
The instruction that a processor executes, described instruction is executed by least one described processor, so that at least one described processor energy
It is enough in the unmanned plane barrier-avoiding method based on target following executed as described in any one of claim 1-17.
36. a kind of non-volatile computer readable storage medium storing program for executing, which is characterized in that the non-volatile computer readable storage medium
Matter is stored with computer executable instructions, and the computer executable instructions are for executing unmanned plane as in claim 1-17
Described in any item unmanned plane barrier-avoiding methods based on target following.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910655674.8A CN110262568B (en) | 2019-07-19 | 2019-07-19 | Unmanned aerial vehicle obstacle avoidance method and device based on target tracking and unmanned aerial vehicle |
PCT/CN2020/102878 WO2021013110A1 (en) | 2019-07-19 | 2020-07-18 | Target tracking-based unmanned aerial vehicle obstacle avoidance method and apparatus, and unmanned aerial vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910655674.8A CN110262568B (en) | 2019-07-19 | 2019-07-19 | Unmanned aerial vehicle obstacle avoidance method and device based on target tracking and unmanned aerial vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110262568A true CN110262568A (en) | 2019-09-20 |
CN110262568B CN110262568B (en) | 2021-10-22 |
Family
ID=67927214
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910655674.8A Active CN110262568B (en) | 2019-07-19 | 2019-07-19 | Unmanned aerial vehicle obstacle avoidance method and device based on target tracking and unmanned aerial vehicle |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110262568B (en) |
WO (1) | WO2021013110A1 (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110597293A (en) * | 2019-10-12 | 2019-12-20 | 上海复亚智能科技有限公司 | Unmanned aerial vehicle autonomous flight method, device, equipment and storage medium |
CN112068592A (en) * | 2020-08-31 | 2020-12-11 | 南京航空航天大学 | Dispatching method for realizing fence coverage based on rechargeable unmanned aerial vehicle |
CN112180977A (en) * | 2020-09-30 | 2021-01-05 | 苏州臻迪智能科技有限公司 | Trajectory planning method and device, storage medium and aircraft |
WO2021013110A1 (en) * | 2019-07-19 | 2021-01-28 | 深圳市道通智能航空技术有限公司 | Target tracking-based unmanned aerial vehicle obstacle avoidance method and apparatus, and unmanned aerial vehicle |
CN112666984A (en) * | 2020-12-29 | 2021-04-16 | 北京电子工程总体研究所 | Aircraft pursuit and escape game method and system |
CN112698659A (en) * | 2020-12-29 | 2021-04-23 | 北京电子工程总体研究所 | Formation obstacle avoidance method for static scene |
CN112731939A (en) * | 2020-12-29 | 2021-04-30 | 北京电子工程总体研究所 | Formation obstacle avoidance method for dynamic targets |
CN113050691A (en) * | 2021-03-25 | 2021-06-29 | 成都纵横自动化技术股份有限公司 | Unmanned aerial vehicle obstacle avoidance method, device, equipment and computer readable storage medium |
CN113310493A (en) * | 2021-05-28 | 2021-08-27 | 广东工业大学 | Unmanned aerial vehicle real-time navigation method based on event trigger mechanism |
CN113612920A (en) * | 2021-06-23 | 2021-11-05 | 广西电网有限责任公司电力科学研究院 | Method and device for shooting power equipment image by unmanned aerial vehicle |
CN114371720A (en) * | 2021-12-29 | 2022-04-19 | 国家电投集团贵州金元威宁能源股份有限公司 | Control method and control device for unmanned aerial vehicle to track target |
CN115512292A (en) * | 2022-09-07 | 2022-12-23 | 湖北国际物流机场有限公司 | Aircraft landing gear tracking and observing method |
WO2023173330A1 (en) * | 2022-03-16 | 2023-09-21 | 深圳市大疆创新科技有限公司 | Flight control method and apparatus for unmanned aerial vehicle, unmanned aerial vehicle, and storage medium |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112947570B (en) * | 2021-03-10 | 2022-11-11 | 苏州臻迪智能科技有限公司 | Unmanned aerial vehicle obstacle avoidance method and device and storage medium |
CN113110594B (en) * | 2021-05-08 | 2022-05-17 | 北京三快在线科技有限公司 | Method and device for controlling unmanned aerial vehicle to avoid obstacle, storage medium and unmanned aerial vehicle |
CN113759985A (en) * | 2021-08-03 | 2021-12-07 | 华南理工大学 | Unmanned aerial vehicle flight control method, system, device and storage medium |
CN113867341B (en) * | 2021-09-18 | 2023-12-22 | 盐城中科高通量计算研究院有限公司 | Patrol car path planning and tracking method with high-precision tracking and control |
CN114123021A (en) * | 2021-11-05 | 2022-03-01 | 国网辽宁省电力有限公司铁岭供电公司 | Mountain area electric power facility flight inspection monitoring system and device based on power line |
CN114323051B (en) * | 2022-01-07 | 2024-02-02 | 苏州挚途科技有限公司 | Intersection driving track planning method and device and electronic equipment |
CN114268964B (en) * | 2022-02-28 | 2022-05-20 | 汕头大学 | Base station autonomous cooperative deployment method based on unmanned aerial vehicle cluster in unknown indoor environment |
CN115661204B (en) * | 2022-11-01 | 2023-11-10 | 中国人民解放军军事科学院国防科技创新研究院 | Collaborative searching and tracking positioning method for moving target by unmanned aerial vehicle cluster |
CN116820136B (en) * | 2023-08-25 | 2023-12-05 | 雄安国创中心科技有限公司 | Unmanned aerial vehicle path optimization method and device based on RRT algorithm |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107223219A (en) * | 2016-09-26 | 2017-09-29 | 深圳市大疆创新科技有限公司 | Control method, control device and delivery system |
CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
CN107703951A (en) * | 2017-07-27 | 2018-02-16 | 上海拓攻机器人有限公司 | A kind of unmanned plane barrier-avoiding method and system based on binocular vision |
CN108351649A (en) * | 2015-09-15 | 2018-07-31 | 深圳市大疆创新科技有限公司 | System and method for UAV interactive instructions and control |
CN108444482A (en) * | 2018-06-15 | 2018-08-24 | 东北大学 | A kind of autonomous pathfinding barrier-avoiding method of unmanned plane and system |
CN108701362A (en) * | 2016-02-29 | 2018-10-23 | 深圳市大疆创新科技有限公司 | Obstacle during target following avoids |
CN109358638A (en) * | 2018-09-10 | 2019-02-19 | 南京航空航天大学 | Unmanned plane vision barrier-avoiding method based on distributed maps |
CN109634304A (en) * | 2018-12-13 | 2019-04-16 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Unmanned plane during flying paths planning method, device and storage medium |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8366054B2 (en) * | 2009-12-17 | 2013-02-05 | The United States Of America As Represented By The Secretary Of The Navy | Hand launchable unmanned aerial vehicle |
US10337835B2 (en) * | 2016-05-11 | 2019-07-02 | Rivada Research LLC | Method and system for using enhanced location-based information to guide munitions |
CN105910604A (en) * | 2016-05-25 | 2016-08-31 | 武汉卓拔科技有限公司 | Multi-sensor-based autonomous obstacle avoidance navigation system |
CN109960269B (en) * | 2019-04-04 | 2021-05-04 | 武汉大学 | Simplified environment modeling method serving autonomous navigation of unmanned aerial vehicle |
CN110262568B (en) * | 2019-07-19 | 2021-10-22 | 深圳市道通智能航空技术股份有限公司 | Unmanned aerial vehicle obstacle avoidance method and device based on target tracking and unmanned aerial vehicle |
-
2019
- 2019-07-19 CN CN201910655674.8A patent/CN110262568B/en active Active
-
2020
- 2020-07-18 WO PCT/CN2020/102878 patent/WO2021013110A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108351649A (en) * | 2015-09-15 | 2018-07-31 | 深圳市大疆创新科技有限公司 | System and method for UAV interactive instructions and control |
CN108701362A (en) * | 2016-02-29 | 2018-10-23 | 深圳市大疆创新科技有限公司 | Obstacle during target following avoids |
CN107223219A (en) * | 2016-09-26 | 2017-09-29 | 深圳市大疆创新科技有限公司 | Control method, control device and delivery system |
CN107703951A (en) * | 2017-07-27 | 2018-02-16 | 上海拓攻机器人有限公司 | A kind of unmanned plane barrier-avoiding method and system based on binocular vision |
CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
CN108444482A (en) * | 2018-06-15 | 2018-08-24 | 东北大学 | A kind of autonomous pathfinding barrier-avoiding method of unmanned plane and system |
CN109358638A (en) * | 2018-09-10 | 2019-02-19 | 南京航空航天大学 | Unmanned plane vision barrier-avoiding method based on distributed maps |
CN109634304A (en) * | 2018-12-13 | 2019-04-16 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Unmanned plane during flying paths planning method, device and storage medium |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021013110A1 (en) * | 2019-07-19 | 2021-01-28 | 深圳市道通智能航空技术有限公司 | Target tracking-based unmanned aerial vehicle obstacle avoidance method and apparatus, and unmanned aerial vehicle |
CN110597293A (en) * | 2019-10-12 | 2019-12-20 | 上海复亚智能科技有限公司 | Unmanned aerial vehicle autonomous flight method, device, equipment and storage medium |
CN112068592A (en) * | 2020-08-31 | 2020-12-11 | 南京航空航天大学 | Dispatching method for realizing fence coverage based on rechargeable unmanned aerial vehicle |
CN112068592B (en) * | 2020-08-31 | 2021-10-26 | 南京航空航天大学 | Dispatching method for realizing fence coverage based on rechargeable unmanned aerial vehicle |
CN112180977A (en) * | 2020-09-30 | 2021-01-05 | 苏州臻迪智能科技有限公司 | Trajectory planning method and device, storage medium and aircraft |
CN112666984B (en) * | 2020-12-29 | 2022-11-22 | 北京电子工程总体研究所 | Many-to-one intelligent cooperative pursuit game method and system |
CN112666984A (en) * | 2020-12-29 | 2021-04-16 | 北京电子工程总体研究所 | Aircraft pursuit and escape game method and system |
CN112698659A (en) * | 2020-12-29 | 2021-04-23 | 北京电子工程总体研究所 | Formation obstacle avoidance method for static scene |
CN112731939A (en) * | 2020-12-29 | 2021-04-30 | 北京电子工程总体研究所 | Formation obstacle avoidance method for dynamic targets |
CN113050691A (en) * | 2021-03-25 | 2021-06-29 | 成都纵横自动化技术股份有限公司 | Unmanned aerial vehicle obstacle avoidance method, device, equipment and computer readable storage medium |
CN113310493A (en) * | 2021-05-28 | 2021-08-27 | 广东工业大学 | Unmanned aerial vehicle real-time navigation method based on event trigger mechanism |
CN113310493B (en) * | 2021-05-28 | 2022-08-05 | 广东工业大学 | Unmanned aerial vehicle real-time navigation method based on event trigger mechanism |
CN113612920A (en) * | 2021-06-23 | 2021-11-05 | 广西电网有限责任公司电力科学研究院 | Method and device for shooting power equipment image by unmanned aerial vehicle |
CN114371720A (en) * | 2021-12-29 | 2022-04-19 | 国家电投集团贵州金元威宁能源股份有限公司 | Control method and control device for unmanned aerial vehicle to track target |
CN114371720B (en) * | 2021-12-29 | 2023-09-29 | 国家电投集团贵州金元威宁能源股份有限公司 | Control method and control device for realizing tracking target of unmanned aerial vehicle |
WO2023173330A1 (en) * | 2022-03-16 | 2023-09-21 | 深圳市大疆创新科技有限公司 | Flight control method and apparatus for unmanned aerial vehicle, unmanned aerial vehicle, and storage medium |
CN115512292A (en) * | 2022-09-07 | 2022-12-23 | 湖北国际物流机场有限公司 | Aircraft landing gear tracking and observing method |
CN115512292B (en) * | 2022-09-07 | 2024-01-05 | 湖北国际物流机场有限公司 | Aircraft landing gear tracking and observing method |
Also Published As
Publication number | Publication date |
---|---|
CN110262568B (en) | 2021-10-22 |
WO2021013110A1 (en) | 2021-01-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110262568A (en) | A kind of unmanned plane barrier-avoiding method, device and unmanned plane based on target following | |
WO2020103034A1 (en) | Method and device for planning path of unmanned aerial vehicle, and unmanned aerial vehicle | |
US10648809B2 (en) | Adaptive compass calibration based on local field conditions | |
EP3420428B1 (en) | Systems and methods for visual target tracking | |
JP6326237B2 (en) | Measuring system | |
JP6878567B2 (en) | 3D shape estimation methods, flying objects, mobile platforms, programs and recording media | |
CN108062106A (en) | Unmanned vehicle and the method for using unmanned vehicle shooting object | |
US9738399B2 (en) | Unmanned aerial vehicle control method and unmanned aerial vehicle using same | |
CN202600150U (en) | Intelligent low-altitude remote sensing surveying and mapping system | |
WO2022027596A1 (en) | Control method and device for mobile platform, and computer readable storage medium | |
WO2021052334A1 (en) | Return method and device for unmanned aerial vehicle, and unmanned aerial vehicle | |
CN107101636B (en) | A method of more rotor dynamics model parameters are recognized using Kalman filter | |
KR102118157B1 (en) | Sensor mounting device of unmanned aerial vehicle for meteorological observation, unmanned aerial vehicle for meteorological observation and meteorological observation method thereof and sensor mounting device of unmanned aerial vehicle for meteorological observation | |
CN110209202A (en) | A kind of feas ible space generation method, device, aircraft and aerocraft system | |
EP3893078A1 (en) | Relay point generation method and apparatus, and unmanned aerial vehicle | |
CN105468029A (en) | Unmanned aerial vehicle aerial shooting device and unmanned aerial vehicle aerial shooting method | |
CN111142548A (en) | Surveying and mapping unmanned aerial vehicle and surveying and mapping method based on unmanned aerial vehicle | |
CN107820585A (en) | Aircraft landing method, aircraft and computer-readable recording medium | |
JPWO2020105183A1 (en) | Information processing system, information processing method and program | |
JP6577083B2 (en) | Measuring system | |
CN113066120A (en) | Intelligent pole and tower inclination detection method based on machine vision | |
WO2021166845A1 (en) | Information processing device, information processing method, and program | |
CN110366711A (en) | Information processing unit, flight control instructions method and recording medium | |
CN109891188A (en) | Mobile platform, camera paths generation method, program and recording medium | |
CN111615677B (en) | Unmanned aerial vehicle safety landing method and device, unmanned aerial vehicle and medium |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 518055 Guangdong city of Shenzhen province Nanshan District Xili Street Xueyuan Road No. 1001 Chi Yuen Building 9 layer B1 Applicant after: Shenzhen daotong intelligent Aviation Technology Co.,Ltd. Address before: 518055 Guangdong city of Shenzhen province Nanshan District Xili Street Xueyuan Road No. 1001 Chi Yuen Building 9 layer B1 Applicant before: AUTEL ROBOTICS Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |