CN108037768A - Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane - Google Patents
Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane Download PDFInfo
- Publication number
- CN108037768A CN108037768A CN201711331013.7A CN201711331013A CN108037768A CN 108037768 A CN108037768 A CN 108037768A CN 201711331013 A CN201711331013 A CN 201711331013A CN 108037768 A CN108037768 A CN 108037768A
- Authority
- CN
- China
- Prior art keywords
- distance
- unmanned plane
- obstacle
- heading
- avoidance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004927 fusion Effects 0.000 claims abstract description 25
- 230000000007 visual effect Effects 0.000 claims abstract description 17
- 238000005259 measurement Methods 0.000 claims description 12
- 238000007500 overflow downdraw method Methods 0.000 claims description 7
- 238000002604 ultrasonography Methods 0.000 claims description 4
- 239000004744 fabric Substances 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000000034 method Methods 0.000 description 3
- 238000002156 mixing Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000002045 lasting Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006011 modification reaction Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Abstract
The present invention relates to a kind of unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane.The unmanned plane obstruction-avoiding control system includes：Embedded monocular vision distance measuring unit；Ultrasonic ranging unit；Fusion treatment device, according to the visual token information on heading and ultrasonic ranging information acquisition corrected range；Flight controller, by corrected range compared with the first secure threshold distance；If corrected range is less than the first secure threshold distance, the visual token information with obstacle is obtained；When with the distance of the obstacle on heading be less than the second secure threshold apart from when, then obtain with heading on and the ultrasonic ranging information with the obstacle on other directions；Avoidance flight is carried out according to the distance of the obstacle on heading and other directions.It while technical scheme can ensure that avoidance can succeed, can ensure during unmanned plane during flying as far as possible along predetermined airline operation, rather than excessive drift off the course.
Description
Technical field
The present invention relates to unmanned vehicle technical field, in particular to a kind of unmanned plane obstruction-avoiding control system, avoidance
Control method and unmanned plane.
Background technology
With the fast development of unmanned air vehicle technique, multi-rotor aerocraft is with its mechanical structure is simple, mobility is good, hovering is solidifying
Depending on, fixed point it is outstanding clap, VTOL the advantages that, oneself becomes the research hotspots of current many countries or scientific research institution, in the military and people
Also all have broad application prospects with multiple fields.However, with the lasting acceleration of unmanned plane civil nature, in face of complicated scene
With cost control requirement, more and more safety problems embody out, and unmanned plane plane collision incident is commonplace, effectively improves nothing
Oneself is extremely urgent for man-machine security.
Unmanned plane automatic obstacle avoiding system effectively can avoid colliding and hurt sb.'s feelings, and reduce loss.So-called unmanned plane automatic obstacle avoiding
Function, be exactly unmanned plane during flying device when barrier is run into during flight, by automatically in advance identify, effectively evade
Barrier, reaches the effect of safe flight, and for now, the multi-rotor unmanned aerial vehicle obstacle avoidance system of mainstream mainly has three kinds, point
It is not ultrasonic wave, TOF and the relatively more complicated complex method being made of a variety of distance measuring methods and visual pattern processing,
But which kind of method all only for specific flight control system, is not knowing about the situation of flight control system software and hardware architecture
Under, in face of sound wave, light wave etc. external interference factor, existing obstacle avoidance system does not possess good suitability, there is certain limitation
Property.
Further, since current unmanned plane is generally powered by the way of battery, therefore power consumption using electricity wisely is reduced so as to carry
The cruising ability of high unmanned plane is most important.
The content of the invention
In view of the above problems, the present invention provide a kind of new unmanned plane obstruction-avoiding control system, avoidance obstacle method and nobody
Machine.
An embodiment of the invention provides a kind of unmanned plane obstruction-avoiding control system, including：
Embedded monocular vision distance measuring unit, for obtaining the visual token information on heading；
Ultrasonic ranging unit is super in the ultrasonic ranging information on the heading and other directions for obtaining
Sound ranging information；
Fusion treatment device, according to the visual token information on heading and the ultrasonic ranging information, profit
Data fusion is carried out with multidimensional information fusion method to obtain the corrected range with the obstacle on the heading；
Flight controller, by the corrected range compared with the first secure threshold distance；
If the corrected range is less than the first secure threshold distance, obtain by the embedded monocular vision ranging list
The distance with the obstacle on the heading that member measures；
When with the distance of the obstacle on the heading be less than the second secure threshold apart from when, then obtain by the ultrasound
The distance with the distance of the obstacle on the heading and with the obstacle on other directions that ripple distance measuring unit measures；
Make unmanned plane according to the distance with the obstacle on the heading and with the distance of the obstacle on other directions
Carry out avoidance flight.
In above-mentioned unmanned plane obstruction-avoiding control system, the embedded monocular vision distance measuring unit includes monocular cam
With field programmable gate array vision processor.
In above-mentioned unmanned plane obstruction-avoiding control system, the ultrasonic ranging unit includes being used to measure unmanned plane surrounding
Distance four ultrasonic sensors and a ultrasonic sensor for being used to measure distance below unmanned plane, the use
It is uniformly distributed in the horizontal plane in four ultrasonic sensors of the distance of measurement unmanned plane surrounding, and the monocular cam
Shooting direction and four ultrasonic sensors for the distance for measuring unmanned plane surrounding in the measurement direction of one
Unanimously.
In above-mentioned unmanned plane obstruction-avoiding control system, it is less than the first secure threshold distance in the corrected range
When, the flight controller reduces the speed of the unmanned plane.
In above-mentioned unmanned plane obstruction-avoiding control system, measuring with the flight side by the ultrasonic ranging unit
The distance of upward obstacle be less than the 3rd secure threshold apart from when, the flight controller according to the obstacle on other directions
Distance makes unmanned plane carry out avoidance flight.
Another embodiment of the present invention provides a kind of unmanned plane avoidance obstacle method, including：
According to the monocular vision ranging information and ultrasonic ranging information on heading received, believed using multidimensional
Breath fusion method carries out data fusion to obtain the corrected range with the obstacle on the heading, the monocular vision ranging letter
Breath is obtained by embedded monocular vision distance measuring unit；
By the corrected range compared with the first secure threshold distance；
If the corrected range is less than the first secure threshold distance, obtain by the embedded monocular vision ranging list
The distance with the obstacle on the heading that member measures；
When with the distance of the obstacle on the heading be less than the second secure threshold apart from when, then obtain by the ultrasound
The distance with the distance of the obstacle on the heading and with the obstacle on other directions that ripple distance measuring unit measures；
Make unmanned plane according to the distance with the obstacle on the heading and with the distance of the obstacle on other directions
Carry out avoidance flight.
In above-mentioned unmanned plane avoidance obstacle method, the embedded monocular vision distance measuring unit ranging is by using fortune
Dynamic parallax obtains different angle image sequence and obtains depth information.
In above-mentioned unmanned plane avoidance obstacle method, it is less than the first secure threshold distance in the corrected range
When, make the speed of the unmanned plane reduce.
In above-mentioned unmanned plane avoidance obstacle method, further include：
It is safe less than the 3rd with the distance of the obstacle on the heading being measured by the ultrasonic ranging unit
During threshold distance, unmanned plane is set to carry out avoidance flight according to the distance with the obstacle on other directions.
Another embodiment of the invention provides a kind of unmanned plane, including above-mentioned unmanned plane obstruction-avoiding control system.
Technical scheme carries out obstacle using the hierarchical control of embedded single item stereo vision and ultrasonic system
The detection of thing, mainly merges the closest detection of obstacles between unmanned plane on two kinds of sensors progress headings.
The processing intent of fusion is so that the depth information that the depth information and the ultrasonic wave that obtain vision obtain is simultaneous during avoidance
Care for and consider, can either on the direction of unmanned plane during flying apart from itself farther out under conditions of barrier existing for detection, and can
Ensure that barrier is carrying out avoidance again close to limiting safe distance.In this way, on the one hand can ensure that avoidance can succeed, the opposing party
Face can also be ensured during unmanned plane during flying as far as possible along predetermined airline operation, rather than excessive drifted off the course.
The configuration of the present invention is simple, can reduce the power consumption of obstacle avoidance system, this has for the cruising ability for improving unmanned plane
Positive meaning.In addition, system manufacture cost is low, use and maintenance is simple, helps to be generalized to the platform of a variety of unmanned planes
Avoidance obstacle is carried out, solves the problems such as vision system power consumption existing in the prior art is high, obstacle avoidance system is of high cost.
The unmanned plane obstruction-avoiding control system of the present invention can be installed and used on existing unmanned aerial vehicle platform, and need not
Change flight control system framework and parameter.Therefore, the product of all kinds of flight control systems can be effectively matched, there is well general
All over property, it is suitable for being generalized on all kinds of unmanned aerial vehicle platforms.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Brief description of the drawings
In order to illustrate more clearly of technical scheme, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as to the present invention
The restriction of protection domain.In various figures, it is similarly comprised part and uses similar numbering.
Fig. 1 shows the schematic block diagram of the unmanned plane obstruction-avoiding control system of one embodiment of the present of invention.
Fig. 2 shows the indicative flowchart of the unmanned plane avoidance obstacle method of one embodiment of the present of invention.
Fig. 3 shows the schematic diagram of the unmanned plane of the unmanned plane obstacle avoidance system including the embodiment of the present invention.
Fig. 4 shows the schematic partial bottom view of the unmanned plane shown in Fig. 3.
Embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and designed with a variety of configurations herein.Cause
This, the detailed description of the embodiment of the present invention to providing in the accompanying drawings is not intended to limit claimed invention below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Go out all other embodiments obtained on the premise of creative work, belong to the scope of protection of the invention.
Embodiment 1
Fig. 1 shows the unmanned plane obstruction-avoiding control system 100 of one embodiment of the present of invention, including embedded monocular vision
Distance measuring unit 110, ultrasonic ranging unit 120, fusion treatment device 130 and flight controller 140.
Embedded single mesh distance measuring unit 110 is used to obtain the visual token information on heading, it may include monocular images
First 111 and embedded vision processor 112.Embedded single mesh distance measuring unit 110 can obtain three dimensional local information, in ranging
When, monocular timesharing Image Acquisition is carried out first, image procossing and feature point extraction is carried out to the image of collection, after Stereo matching
Carry out real-time deep calculating.Different angle image sequence can be obtained by using motion parallax and obtain depth information, for example, can
Obtain as follows：
1) doubtful barrier region is set；
2) using doubtful barrier region as image process target, according to the region in each frame ask for barrier pose and
Depth with error simultaneously calculates polar curve of the pixel in subsequent image frames in the region；
3) matching is found on polar curve；
4) this Observational depth value and depth is obtained using the matching between present frame and previous frame and by triangulation
Uncertainty；
5) in order to improve precision, the depth data repeatedly measured and variance are merged using image sequence；
6) on the basis of frames fusion obtains depth map, it is carried out smoothly, so that " noise depth " is removed, with
This obtains high-precision real-time range, i.e. depth information between unmanned plane and barrier.
Monocular cam 111 is low-power consumption camera preferably using monocular CMOS camera, CMOS camera, can reduce nothing
Man-machine power consumption.Monocular cam 111 can be fixed facing one direction, or can be rotated on holder, thus may be used
With the barrier on other directions of vision-based detection, such as the barrier of direction of advance left side, right side, rear side or lower section is detected, from
And the flexibility of ranging can be improved.
Embedded vision processor 112 preferably uses field programmable gate array (FPGA) processor, and FPGA is as a kind of
High performance programmable logic device, can utilize programming modification internal logic function, have the operational capability of high-speed parallel, fit
Optimize for performances such as the high speed of embedded system, parallelization, low-power consumption.In addition, present inventor has found FPGA insertions
Formula vision system power consumption is well below the vision system based on universal cpu and GPU (power consumption of FPGA less than 1W, and high-performance CPU
With the power consumption of GPU usually in more than 100W), optimize suitable for the low power capabilities of embedded system.
Ultrasonic ranging unit 120 it is of low cost, the cost of obstacle avoidance system can be significantly reduced.Ultrasonic range finder sensor
Emitting head send ultrasonic signal, after this signal is reflected by barrier, received by reception head, according to launching and receive signal
Time difference and the velocity of sound, you can obtain the range information of barrier.
Ultrasonic ranging unit 120 can include multiple ultrasonic sensors.For example, it can include being used to measure unmanned plane
Four ultrasonic sensors of the distance of surrounding and a ultrasonic sensor for being used to measure the distance below unmanned plane, are used
It is uniformly distributed in the horizontal plane in four ultrasonic sensors of distance of measurement unmanned plane surrounding, that is, is used to measure and the side of advance
To the distance of the barrier at left and right sides of side, rear side, direction of advance.The supersonic sensing of the distance of four measurement unmanned plane surroundings
Device can be distributed in below rotor.The shooting direction of monocular cam can be with four of the distance for being used to measure unmanned plane surrounding
The measurement direction of one in ultrasonic sensor is consistent.
Certainly, the quantity of ultrasonic sensor can also be other quantity, such as can include 6, the other quantities such as 8
For measuring the distance around unmanned plane.From the perspective of meeting practicality and reducing cost, preferably it is in the horizontal direction
Four equally distributed ultrasonic sensors.Ultrasonic sensor for measuring the distance below unmanned plane can be used for detecting
The height of unmanned plane, it may also be used for the obstacle for detecting lower section is used for avoidance, it is therefore possible to use the ultrasonic wave than horizontal direction passes
The more preferable ultrasonic sensor of sensor performance.In addition, it can include measurement unmanned plane above whether there are obstacles and with
The ultrasonic sensor of the obstacle distance.
Fusion treatment device 130, for according to the ultrasonic wave in the visual token information and heading on heading
Ranging information, using multidimensional information fusion method carry out data fusion with obtain with the amendment of the obstacle on the heading away from
From.Such as STF blending algorithms can be used in multidimensional information fusion method.For example, the barrier that two kinds of sensors can be obtained first
Range information carries out Kalman filtering, reduces the influence of clutter in environment, then, according to STF blending algorithms, is obtained using after filtering
The estimate and covariance matrix of the two groups of state vectors arrived carry out fusion treatment.The estimate curve of filtered range information
Actual value curve has been tracked well, and Kalman filtering algorithm can play good filter action.Compared with before fusion, after fusion
The variance of range information estimate be obviously reduced, therefore, the obstacle position information after fusion is more accurate.
When camera is installed on holder, data can also be carried out using visual token information and ultrasonic ranging information
Merge to obtain the corrected range with the obstacle on other directions.
Flight controller 140, flight control is carried out according to the range information received from fusion treatment 130 to unmanned plane
System.Although not shown in the drawings, still, flight controller 140 also can be from embedded single mesh distance measuring unit 110 and ultrasonic ranging list
Member 140, which directly acquires information and it is acted, to be controlled.For example, flight controller 140 pacifies the corrected range and first
Full threshold distance is compared, if the corrected range is less than the first secure threshold distance, carries out following avoidance control
System：Embedded 110 ranging of monocular vision distance measuring unit is set to obtain the distance with the obstacle on the heading；When with it is described
The distance of obstacle on heading be less than the second secure threshold apart from when, then make ultrasonic ranging unit 120 measurement with it is described
The distance of obstacle on heading, and make the measurement of ultrasonic ranging unit 120 and the distance of the obstacle on other directions；Root
According to the distance with the obstacle on the heading and make unmanned plane carry out avoidance with the distance of the obstacle on other directions to fly
OK.
In example more than, by flight controller 120 to corrected range compared with the first secure threshold distance, but
It is that above-mentioned comparison can also be carried out by fusion treatment device 130.
Using the embedded vision system of low-power consumption, when realizing the related algorithm of image procossing using FPGA, compare
Other vision systems such as DSP, GPU etc., FPGA has the advantages that parallel processing and low-power consumption.In addition, ultrasonic sensor is also
The cost-effective product of low-power consumption.Obstacle avoidance system integrally uses low power dissipation design, so unmanned function is in equal power supply and complete
Into the cruising ability that unmanned plane is significantly improved on the premise of avoidance task.
Embodiment 2
Fig. 2 shows the indicative flowchart of the unmanned plane avoidance obstacle method of embodiment 2.Unmanned plane shown in Fig. 2 is kept away
Barrier control method includes：
In step S210, according to the monocular vision ranging information and ultrasonic ranging letter on heading received
Breath, data fusion is carried out to obtain the corrected range with the obstacle on the heading using multidimensional information fusion method, described
Monocular vision ranging information is obtained by embedded monocular vision distance measuring unit.For example, fusion treatment device 130 is from embedded monocular
Visual token unit 110 and ultrasonic ranging unit 120 obtain visual token information and supersonic sounding letter on heading
Breath is being obtained more accurate with barrier positional information due to having carried out data fusion.
For unmanned plane in flight course, monocular vision distance measuring unit 110 and ultrasonic ranging unit 120 can detect nothing in real time
Man-machine operating status, such as the course angle of body and the distance with barrier.Forward direction during due to unmanned plane during flying
Range information in flight course is the most key, and only needs to ensure that clear is i.e. in its safe distance in other direction
Can.In order to improve the precision of ranging on heading, therefore monocular vision and 1 ultrasonic sensor can be installed simultaneously in heading
Visual token information is carried out with the data fusion of ultrasonic ranging information so as to which corrected range is believed using multidimensional information fusion method
Breath.
In step S220, by the corrected range compared with the first secure threshold distance.For example, can be by flying
Controller 120 compared with the first secure threshold distance, can set different corrected range according to different flying speeds
The first secure threshold distance, such as could be provided as 20 meters.When corrected range be less than the first secure threshold apart from when, advance to
Step S230；If corrected range be more than or equal to the first secure threshold apart from when, be back to step S210.In addition, safety away from
When with a distance from less than the first secure threshold, flight controller 120 can reduce the flying speed of unmanned plane to predetermined value.
In step S230, obtain measured by the embedded monocular vision distance measuring unit with the heading
The distance of obstacle.For example, obtain the distance with obstacle in a forward direction from embedded single mesh distance measuring unit 110.
The detection (general detection range is such as more than 10 meters) of long-distance barrier thing is carried out using monocular vision, distance
Estimation uses single eye stereo vision analysis method.The principle of estimation of Depth for motion parallax obtain different angle image sequence so as to
Obtain, be hereinbefore described, be not repeated herein.
In step S240, the visual token information on the heading of acquisition and the second secure threshold distance are compared
Compared with.For example, flight controller 120 pacifies the visual token information obtained from embedded monocular vision distance measuring unit 110 and second
Full threshold distance is compared.Second secure threshold distance is less than the first secure threshold distance, and can be according to unmanned plane
Flying speed is preset, and can also consider that the size of the first secure threshold distance is configured at the same time, such as can set 10
Rice.If the distance of the obstacle on unmanned plane and heading that embedded monocular vision distance measuring unit 110 obtains is less than the second peace
Full threshold distance, then advance to step S250, if being not less than the second secure threshold distance, is back to step S230.
In step s 250, obtain measured by the ultrasonic ranging unit with the obstacle on the heading away from
With a distance from obstacle on other directions.For example, when ultrasonic ranging unit 110 includes 5 ultrasonic sensors,
The distance of consistent with the ranging direction of camera ultrasonic sensor measurement direction of advance and barrier, horizontal direction remaining
Three ultrasonic sensor measurement left and right and rear whether there are obstacles and the distance with barrier.Downward super
Distance below sonic sensor measurement unmanned plane with ground, or lower section whether there are obstacles.
Avoidance (within 10 meters of distance) is carried out using the mode of ultrasonic wave, ultrasonic sensor is mainly responsible for nothing closely
Man-machine avoidance.The ultrasonic sensor group of multiple directions is detected in real time, ensures that unmanned plane can in the range of safe distance
Effectively hovering.Safe distance can rule of thumb or simulation preassign or specified according to specific application scenario, such as
Safe distance can set relatively large when outdoor, and indoors when safe distance can set relatively smaller.
In step S260, according to the distance with the obstacle on the heading and with the obstacle on other directions
Distance makes unmanned plane carry out avoidance flight.It is less than the second secure threshold distance in distance of the unmanned plane with obstacle on heading
When, flight controller 120 according to the distance of the obstacle on the heading and with the distance of the obstacle on other directions into
Row avoidance is flown.
For example, flight controller 120 can control unmanned plane to hover, according to the left and right sides with the presence or absence of obstacle and with barrier
Size between hindering, selects never obstacle or the side small with distance of obstacle to detour.If both sides do not have obstacle, Ke Yisui
Machine selects side or predetermined left or right side to detour.In both sides there are during barrier, unmanned plane can be controlled to retreat
To the accessible position in the left and right sides further around row.Alternatively, can also by ultrasonic wave and/or vision-based detection front obstacle size,
Height etc..When barrier is low buildings, the flying height of unmanned plane can be improved, can when barrier is bridge etc.
To control unmanned plane to reduce flying height, fly through bridge opening.
In addition, flight controller 120 can also according to factors such as the size of the second secure threshold distance and flying speeds, into
One step reduces flying speed to predetermined value.Measured by ultrasonic ranging unit 110 and obstacle on the heading
Distance be less than the 3rd secure threshold apart from when, according to the distance with the obstacle on other directions make unmanned plane carry out avoidance flight.
For example, measured by ultrasonic ranging unit 110 be less than about 2 meters with the distance of the obstacle on heading when, according to other
Fly on direction with the presence or absence of obstacle and with the distance of obstacle around barrier.For example, unmanned plane can be controlled to pacifying on other directions
Full distance is more than or equal to a direction avoidance flight of the 3rd secure threshold distance.
After the barrier in initial planning path has been bypassed, recalculate shortest path between target point or
Continue to hold winged course line before returning to according to initial planning path, whole avoidance process terminates.Initial planning path is returned in unmanned plane
After flight, continue step S210.
The present invention devises the obstacle avoidance system that a kind of general unmanned plane monocular vision is merged with ultrasonic sensor,
The embedded vision system based on FPGA can be used in single camera vision system.By the single camera vision system and such as 4 ultrasounds
Wave sensor group is merged, and the detection information of barrier and relevant control signal are sent into avoidance obstacle device, final to realize
The automatic obstacle avoiding of unmanned plane.
The present invention carries out the detection of barrier using the hierarchical control of embedded single item stereo vision and ultrasonic system, main
If two kinds of sensors of fusion carry out the closest detection of obstacles on heading between unmanned plane.The fusion of the present invention
Processing causes the depth information that the depth information for obtaining vision and ultrasonic wave obtain to take into account consideration during avoidance, can either
On the direction of unmanned plane during flying apart from itself farther out under conditions of barrier existing for detection, and be able to ensure that barrier is connecing
Near limit safe distance carries out avoidance again.In this way, on the one hand can ensure that avoidance can succeed, nothing on the other hand can also be ensured
As far as possible along predetermined airline operation in man-machine flight course, rather than excessive drift off the course.
Embodiment 3
Fig. 3 shows the schematic diagram of the unmanned plane of the unmanned plane obstruction-avoiding control system including the embodiment of the present invention.Fig. 4 is shown
The schematic partial bottom view of unmanned plane shown in Fig. 3.
Include in the unmanned plane shown in Fig. 3 and 4：The ultrasonic sensor 2,3,4 and 5 being distributed in below rotor, is bowing
Depending under state, ultrasonic sensor 2,3,4 and 5 is located between the angle of adjacent rotor composition；And it is arranged on below unmanned plane
Ultrasonic sensor 6 (have detection height and barrier avoiding function)；Monocular cam 1 is further included, its ranging direction and ultrasonic wave
The ranging direction of sensor 5 is consistent.Certainly, monocular cam 1 may be mounted on holder, when needed, can take the photograph monocular
Turn to other directions and carry out visual token as first 1, and can be by the ultrasonic ranging in visual token and other directions into line number
According to fusion to obtain more accurately distance.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.
Claims (10)
- A kind of 1. unmanned plane obstruction-avoiding control system, it is characterised in that including：Embedded monocular vision distance measuring unit, for obtaining the visual token information on heading；Ultrasonic ranging unit, for obtaining the ultrasonic ranging information on the heading and the ultrasonic wave on other directions Ranging information；Fusion treatment device, according to the visual token information on heading and the ultrasonic ranging information, using more Dimension information fusion method carries out data fusion to obtain the corrected range with the obstacle on the heading；Flight controller, by the corrected range compared with the first secure threshold distance；If the corrected range is less than the first secure threshold distance, obtains and surveyed by the embedded monocular vision distance measuring unit The distance with the obstacle on the heading obtained；When with the distance of the obstacle on the heading be less than the second secure threshold apart from when, then obtain by the ultrasound The distance with the obstacle on heading distance and with the obstacle on other directions that is being measured away from unit；Unmanned plane is carried out according to the distance with the obstacle on the heading and with the distance of the obstacle on other directions Avoidance is flown.
- 2. unmanned plane obstruction-avoiding control system according to claim 1, it is characterised in that the embedded monocular vision ranging Unit includes monocular cam and field programmable gate array vision processor.
- 3. unmanned plane obstruction-avoiding control system according to claim 2, it is characterised in that the ultrasonic ranging unit includes It is used to measure the distance below unmanned plane for four ultrasonic sensors of the distance that measures unmanned plane surrounding and one Ultrasonic sensor, four ultrasonic sensors of the distance for measuring unmanned plane surrounding uniformly divide in the horizontal plane Cloth, and four supersonic sensings of the shooting direction of the monocular cam and the distance for being used to measure unmanned plane surrounding The measurement direction of one in device is consistent.
- 4. unmanned plane obstruction-avoiding control system according to claim 1, it is characterised in that be less than in the corrected range described First secure threshold apart from when, the flight controller reduces the speed of the unmanned plane.
- 5. unmanned plane obstruction-avoiding control system according to claim 1, it is characterised in that by the ultrasonic ranging unit It is measuring be less than with the obstacle on heading distance the 3rd secure threshold apart from when, the flight controller according to The distance of obstacle on other directions makes unmanned plane carry out avoidance flight.
- A kind of 6. unmanned plane avoidance obstacle method, it is characterised in that including：According to the monocular vision ranging information and ultrasonic ranging information on heading received, melted using multidimensional information Legal progress data fusion to obtain the corrected range with the obstacle on the heading, lead to by the monocular vision ranging information Embedded monocular vision distance measuring unit is crossed to obtain；By the corrected range compared with the first secure threshold distance；If the corrected range is less than the first secure threshold distance, obtains and surveyed by the embedded monocular vision distance measuring unit The distance with the obstacle on the heading obtained；When with the distance of the obstacle on the heading be less than the second secure threshold apart from when, then obtain by the ultrasound The distance with the obstacle on heading distance and with the obstacle on other directions that is being measured away from unit；Unmanned plane is carried out according to the distance with the obstacle on the heading and with the distance of the obstacle on other directions Avoidance is flown.
- 7. unmanned plane avoidance obstacle method according to claim 6, it is characterised in that the embedded monocular vision ranging Unit ranging obtains different angle image sequence by using motion parallax and obtains depth information.
- 8. unmanned plane avoidance obstacle method according to claim 6, it is characterised in that be less than in the corrected range described First secure threshold apart from when, make the speed of the unmanned plane reduce.
- 9. unmanned plane avoidance obstacle method according to claim 6, it is characterised in that further include：It is less than the 3rd secure threshold with the distance of the obstacle on the heading being measured by the ultrasonic ranging unit Apart from when, according to the distance with the obstacle on other directions make unmanned plane carry out avoidance flight.
- 10. a kind of unmanned plane, it is characterised in that including the unmanned plane obstruction-avoiding control system any one of claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711331013.7A CN108037768A (en) | 2017-12-13 | 2017-12-13 | Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711331013.7A CN108037768A (en) | 2017-12-13 | 2017-12-13 | Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108037768A true CN108037768A (en) | 2018-05-15 |
Family
ID=62102772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711331013.7A Pending CN108037768A (en) | 2017-12-13 | 2017-12-13 | Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108037768A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684994A (en) * | 2018-12-21 | 2019-04-26 | 宁波如意股份有限公司 | The fork truck barrier-avoiding method and system of view-based access control model |
| CN110618674A (en) * | 2018-06-19 | 2019-12-27 | 广州极飞科技有限公司 | Obstacle avoidance method and device for movable equipment, movable equipment and storage medium |
| CN110799801A (en) * | 2018-09-28 | 2020-02-14 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle-based distance measurement method and device and unmanned aerial vehicle |
| CN110824127A (en) * | 2019-10-23 | 2020-02-21 | 军事科学院军事医学研究院环境医学与作业医学研究所 | Intelligent unmanned aerial vehicle water quality monitoring cruise operation monitoring and alarm control method |
| CN112817325A (en) * | 2020-12-18 | 2021-05-18 | 易瓦特科技股份公司 | Method, device, equipment and storage medium for fusing data of multiple sensors |
| CN112904889A (en) * | 2021-01-15 | 2021-06-04 | 安徽工业大学 | Obstacle avoidance device and obstacle avoidance method for flying robot |
| CN113391642A (en) * | 2021-05-28 | 2021-09-14 | 西南交通大学 | Unmanned aerial vehicle autonomous obstacle avoidance method and system based on monocular vision |
| WO2021195886A1 (en) * | 2020-03-30 | 2021-10-07 | 深圳市大疆创新科技有限公司 | Distance determination method, mobile platform, and computer-readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPWO2010137596A1 (en) * | 2009-05-26 | 2012-11-15 | 国立大学法人 千葉大学 | MOBILE BODY CONTROL DEVICE AND MOBILE BODY HAVING MOBILE BODY CONTROL DEVICE |
| CN104820429A (en) * | 2015-04-28 | 2015-08-05 | 南京航空航天大学 | Ultrasonic distance detection-based unmanned aerial vehicle obstacle avoidance system and control method thereof |
| CN105892489A (en) * | 2016-05-24 | 2016-08-24 | 国网山东省电力公司电力科学研究院 | Multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and control method |
| CN106527480A (en) * | 2016-12-02 | 2017-03-22 | 南京航空航天大学 | Multi-sensor fusion obstacle avoiding system of unmanned aerial vehicle and method |
| CN107466384A (en) * | 2016-05-25 | 2017-12-12 | 深圳市大疆创新科技有限公司 | A kind of method and device for following the trail of target |
-
2017
- 2017-12-13 CN CN201711331013.7A patent/CN108037768A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPWO2010137596A1 (en) * | 2009-05-26 | 2012-11-15 | 国立大学法人 千葉大学 | MOBILE BODY CONTROL DEVICE AND MOBILE BODY HAVING MOBILE BODY CONTROL DEVICE |
| CN104820429A (en) * | 2015-04-28 | 2015-08-05 | 南京航空航天大学 | Ultrasonic distance detection-based unmanned aerial vehicle obstacle avoidance system and control method thereof |
| CN105892489A (en) * | 2016-05-24 | 2016-08-24 | 国网山东省电力公司电力科学研究院 | Multi-sensor fusion-based autonomous obstacle avoidance unmanned aerial vehicle system and control method |
| CN107466384A (en) * | 2016-05-25 | 2017-12-12 | 深圳市大疆创新科技有限公司 | A kind of method and device for following the trail of target |
| CN106527480A (en) * | 2016-12-02 | 2017-03-22 | 南京航空航天大学 | Multi-sensor fusion obstacle avoiding system of unmanned aerial vehicle and method |
Non-Patent Citations (5)
| Title |
|---|
| MARIUS S.VASSILIOU: "《指挥控制的新构想 企业的未来》", 31 March 2016 * |
| SUBRAMANIANRAMASAMY，ETC: "LIDAR obstacle warning and avoidance system for unmanned aerial vehicle sense-and-avoid", 《AEROSPACE SCIENCE AND TECHNOLOGY》 * |
| 汪明磊，等: "智能车辆车道保持系统中避障路径规划", 《合肥工业大学学报(自然科学版)》 * |
| 理查德•布赖斯: "《多媒体与虚拟现实工程》", 30 April 2000 * |
| 陈小桥，等: "基于双目视觉的无人机定位与控制系统", 《武汉大学学报(工学版)》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110618674A (en) * | 2018-06-19 | 2019-12-27 | 广州极飞科技有限公司 | Obstacle avoidance method and device for movable equipment, movable equipment and storage medium |
| CN110799801A (en) * | 2018-09-28 | 2020-02-14 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle-based distance measurement method and device and unmanned aerial vehicle |
| WO2020062024A1 (en) * | 2018-09-28 | 2020-04-02 | 深圳市大疆创新科技有限公司 | Distance measurement method and device based on unmanned aerial vehicle and unmanned aerial vehicle |
| CN109684994A (en) * | 2018-12-21 | 2019-04-26 | 宁波如意股份有限公司 | The fork truck barrier-avoiding method and system of view-based access control model |
| CN110824127A (en) * | 2019-10-23 | 2020-02-21 | 军事科学院军事医学研究院环境医学与作业医学研究所 | Intelligent unmanned aerial vehicle water quality monitoring cruise operation monitoring and alarm control method |
| WO2021195886A1 (en) * | 2020-03-30 | 2021-10-07 | 深圳市大疆创新科技有限公司 | Distance determination method, mobile platform, and computer-readable storage medium |
| CN112817325A (en) * | 2020-12-18 | 2021-05-18 | 易瓦特科技股份公司 | Method, device, equipment and storage medium for fusing data of multiple sensors |
| CN112904889A (en) * | 2021-01-15 | 2021-06-04 | 安徽工业大学 | Obstacle avoidance device and obstacle avoidance method for flying robot |
| CN112904889B (en) * | 2021-01-15 | 2022-03-01 | 安徽工业大学 | Obstacle avoidance device and obstacle avoidance method for flying robot |
| CN113391642A (en) * | 2021-05-28 | 2021-09-14 | 西南交通大学 | Unmanned aerial vehicle autonomous obstacle avoidance method and system based on monocular vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037768A (en) | Unmanned plane obstruction-avoiding control system, avoidance obstacle method and unmanned plane | |
| US11295458B2 (en) | Object tracking by an unmanned aerial vehicle using visual sensors | |
| CN106681353B (en) | The unmanned plane barrier-avoiding method and system merged based on binocular vision with light stream | |
| US10599161B2 (en) | Image space motion planning of an autonomous vehicle | |
| CN103984357B (en) | Unmanned aerial vehicle automatic obstacle avoidance flight system based on panoramic stereo imaging device | |
| CN106595631B (en) | A kind of method and electronic equipment of avoiding barrier | |
| KR102226350B1 (en) | Autonomous visual navigation | |
| CN106802668B (en) | Unmanned aerial vehicle three-dimensional collision avoidance method and system based on binocular and ultrasonic fusion | |
| US11242144B2 (en) | Aerial vehicle smart landing | |
| US20190378423A1 (en) | User interaction with an autonomous unmanned aerial vehicle | |
| WO2018090250A1 (en) | Three-dimensional point cloud generation method, device, computer system, and mobile apparatus | |
| WO2018058442A1 (en) | Method and device for panning route, flight control system, omnidirectional obstacle avoidance system, and unmanned aerial vehicle | |
| JP2014119828A (en) | Autonomous aviation flight robot | |
| CN109767452A (en) | A kind of object localization method and device, unmanned plane | |
| JP6599143B2 (en) | Autonomous mobile robot | |
| JP6527726B2 (en) | Autonomous mobile robot | |
| JP6140458B2 (en) | Autonomous mobile robot | |
| CN109214348A (en) | A kind of obstacle detection method, device, equipment and storage medium | |
| Hu et al. | Obstacle avoidance methods for rotor UAVs using RealSense camera | |
| Laflamme et al. | Driving datasets literature review | |
| CN113467500A (en) | Unmanned aerial vehicle non-cooperative target tracking system based on binocular vision | |
| Ha et al. | Vision-based Obstacle Avoidance Based on Monocular SLAM and Image Segmentation for UAVs. | |
| JP6595284B2 (en) | Autonomous mobile robot | |
| CN110764531A (en) | Unmanned aerial vehicle formation flying obstacle avoidance method based on laser radar and artificial potential field method | |
| CN208314856U (en) | A kind of system for the detection of monocular airborne target |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180515 |