CN115145302A - Flight control method and device, cloud platform and storage medium - Google Patents
Flight control method and device, cloud platform and storage medium Download PDFInfo
- Publication number
- CN115145302A CN115145302A CN202110686698.7A CN202110686698A CN115145302A CN 115145302 A CN115145302 A CN 115145302A CN 202110686698 A CN202110686698 A CN 202110686698A CN 115145302 A CN115145302 A CN 115145302A
- Authority
- CN
- China
- Prior art keywords
- flight
- data
- module
- management module
- control
- 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
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 title claims abstract description 166
- 238000000034 method Methods 0.000 title claims abstract description 95
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 151
- 238000012545 processing Methods 0.000 claims abstract description 134
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 95
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 58
- 230000001413 cellular effect Effects 0.000 claims abstract description 47
- 238000007726 management method Methods 0.000 claims description 204
- 238000013439 planning Methods 0.000 claims description 50
- 230000008569 process Effects 0.000 claims description 45
- 238000001514 detection method Methods 0.000 claims description 36
- 230000005540 biological transmission Effects 0.000 claims description 32
- 230000000007 visual effect Effects 0.000 claims description 25
- 230000002265 prevention Effects 0.000 claims description 23
- 230000007613 environmental effect Effects 0.000 claims description 20
- 238000005259 measurement Methods 0.000 claims description 19
- 238000011217 control strategy Methods 0.000 claims description 17
- 238000013500 data storage Methods 0.000 claims description 11
- 230000010267 cellular communication Effects 0.000 claims description 6
- 230000015607 signal release Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims 1
- 230000008447 perception Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 3
- 239000003208 petroleum Substances 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 239000012855 volatile organic compound Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000002341 toxic gas Substances 0.000 description 2
- 101100172132 Mus musculus Eif3a gene Proteins 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000003416 augmentation Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Images
Classifications
-
- 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
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a flight control method and device, a cloud platform and a storage medium, which can reduce deployment cost and flexibly plan a waypoint, and the device can comprise: the system comprises an artificial intelligence data processing control module, a data acquisition module, a flight management module and a data communication management module; the data communication management module is used for selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on a target communication network; the flight management module is used for controlling the unmanned aerial vehicle to execute a flight task according to the target flight track; the data acquisition module is used for acquiring flight data; the artificial intelligence data processing control module is used for processing the flight data by using an artificial intelligence operation algorithm to obtain a control result; and the flight management module is also used for carrying out flight control on the unmanned aerial vehicle by utilizing the control result.
Description
Technical Field
The invention relates to the field of communication control, in particular to a flight control method and device, a cloud platform and a storage medium.
Background
At present, an unmanned aerial vehicle mainly comprises multiple rotors and fixed wings, uses batteries, fuel oil or hybrid power, has a flying height below 1000 meters, and adopts a satellite-based navigation system. During operation, the control of line-of-sight flying and flying hands is mainly used, and each unmanned aerial vehicle is provided with a professional flying hand to carry out whole-course remote control operation on the whole flying, flying and landing and operation of the unmanned aerial vehicle.
In the operation process of the unmanned aerial vehicle, the existing image transmission and data transmission links of the unmanned aerial vehicle adopt point-to-point communication, generally in an ISM (Industrial Scientific Medical) frequency band, the communication distance is short, the remote control distance is within 2km, and the image transmission distance is within 1km, so that the unmanned aerial vehicle is easily interfered. If the flying with beyond visual range and large voyage is required; if the flight is more than 10km, a ground station needs to be deployed on a reserved airline to carry out relay of a communication link, and the deployment cost is high and the waypoint planning is not flexible; and the existing flight depends on the control level of a flyer, and particularly after the visual range is exceeded, the probability of flight accidents is increased.
Disclosure of Invention
In order to solve the technical problem, embodiments of the present invention desirably provide a flight control method and apparatus, a cloud platform, and a storage medium, which can reduce deployment cost and probability of a flight accident, and flexibly plan a waypoint.
The technical scheme of the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a flight control apparatus, where the apparatus includes: the system comprises an artificial intelligence data processing control module, a data acquisition module, a flight management module and a data communication management module;
the data communication management module is used for selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on the target communication network;
the flight management module is used for controlling the unmanned aerial vehicle to execute a flight task according to the target flight track;
the data acquisition module is used for acquiring flight data;
the artificial intelligence data processing control module is used for processing the flight data by using an artificial intelligence operation algorithm to obtain a control result;
the flight management module is also used for carrying out flight control on the unmanned aerial vehicle by utilizing the control result.
In a second aspect, an embodiment of the present invention provides a cloud platform, where the cloud platform includes: the system comprises a track planning management module, a base station position database module, a map information database module and a data communication management module;
the flight path planning management module is used for receiving a flight task and planning an initial flight path according to the flight task;
the base station position database module and the map information database module are used for identifying whether the initial flight path approaches a no-fly zone or a cellular coverage blind spot, and returning an identification result to the flight path planning management module;
the flight path planning management module is further configured to adjust the initial flight path based on the identification result to obtain the target flight path;
and the data communication management module is used for sending the target flight path to a flight control device so that the flight control device can control the unmanned aerial vehicle to fly according to the target flight path.
In a third aspect, an embodiment of the present invention provides a flight control method, which is applied to a flight control device, and the method includes:
selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on the target communication network;
controlling the unmanned aerial vehicle to execute a flight task according to the target flight track;
acquiring flight data, and processing the flight data by using an artificial intelligence operation algorithm to obtain a control result;
and utilizing the control result to carry out flight control on the unmanned aerial vehicle.
In a fourth aspect, an embodiment of the present invention provides a flight control method, which is applied to a cloud platform, and the method includes:
receiving a flight task, and planning an initial flight path according to the flight task;
identifying whether the initial flight path is in a no-fly zone or a honeycomb coverage blind spot, and adjusting the initial flight path based on the identification result to obtain the target flight path;
and sending the target flight path to a flight control device so that the flight control device can control the unmanned aerial vehicle to fly according to the target flight path.
In a fifth aspect, an embodiment of the present invention provides a flight control apparatus, including: the first processor is used for executing an operating program stored in the memory so as to realize the following steps:
selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on the target communication network; controlling the unmanned aerial vehicle to execute a flight task according to the target flight track; acquiring flight data, and processing the flight data by using an artificial intelligence operation algorithm to obtain a control result; and utilizing the control result to carry out flight control on the unmanned aerial vehicle.
In a sixth aspect, an embodiment of the present invention provides a cloud platform, where the cloud platform includes: the second processor is used for executing the running program stored in the second memory so as to realize the following steps:
receiving a flight task, and planning an initial flight path according to the flight task; identifying whether the initial flight path is in a no-fly zone or a honeycomb coverage blind spot, and adjusting the initial flight path based on the identification result to obtain the target flight path; and sending the target flight path to a flight control device so that the flight control device can control the unmanned aerial vehicle to fly according to the target flight path.
In a seventh aspect, an embodiment of the present invention provides a storage medium, on which a computer program is stored, and is applied to a flight control device or a cloud platform, where the computer program is executed by a processor to implement the method according to any one of the above items.
The embodiment of the invention provides a flight control method and device, a cloud platform and a storage medium, wherein the device comprises: the system comprises an artificial intelligence data processing control module, a data acquisition module, a flight management module and a data communication management module; the data communication management module is used for selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on a target communication network; the flight management module is used for controlling the unmanned aerial vehicle to execute a flight task according to the target flight track; the data acquisition module is used for acquiring flight data; the artificial intelligence data processing control module is used for processing the flight data by using an artificial intelligence operation algorithm to obtain a control result; and the flight management module is also used for carrying out flight control on the unmanned aerial vehicle by utilizing the control result. By adopting the method implementation scheme, the scheme adopts a data communication transmission management method which mainly adopts a honeycomb and combines an ad hoc network and a satellite, before the unmanned aerial vehicle takes off, the distribution and the network condition of the honeycomb base station of the operation route are confirmed through a cloud platform, and then the operation is implemented, so that the route planning is flexible without depending on a ground relay station; and the artificial intelligence operation algorithm is arranged on the unmanned aerial vehicle in front, so that the obstacle avoidance and real-time response capabilities of the unmanned aerial vehicle are improved, the autonomous flight control capability of the unmanned aerial vehicle is improved, the flight pressure is reduced, and the accident risk is reduced.
Drawings
Fig. 1 is a first schematic structural diagram of a flight control apparatus according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a flight control device according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of an exemplary method for selecting a target network according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of an exemplary process for determining whether positioning is incorrect and selecting positioning navigation according to an embodiment of the present invention;
fig. 5 is a first schematic structural diagram of a cloud platform according to an embodiment of the present invention;
FIG. 6 is a first flowchart of a flight control method according to an embodiment of the present invention;
FIG. 7 is a second flowchart of a flight control method according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a flight control apparatus according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a cloud platform according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or technical solutions in the prior art, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
At present, the remote control and data transmission of domestic unmanned aerial vehicles and consumer unmanned aerial vehicles mainly use ISM frequency bands, the radio remote control and data transmission adopt 2.4GHz and 5.8GHz ISM frequency bands, and some use Wi-Fi (wireless communication technology) directly.
Because the communication of ISM frequency channel can receive more interference, also receives monitoring and attack easily, can restrict unmanned aerial vehicle's communication distance in the in-service use, generally do not exceed 2km, consequently present beyond the horizon unmanned aerial vehicle need build ground satellite station or relay communication station and guarantee the transmission of data, lays with high costs, predetermines the route and can not adjust at any time, the flight route is limited.
However, in practical applications, there are many demands for over-the-horizon tasks of industrial unmanned aerial vehicles, such as performing operations of aerial surveying and mapping, power transmission and transformation inspection, petroleum pipeline inspection, high-speed inspection, geological exploration, disaster investigation, agriculture and forestry plant protection, aerial photography, emergency fire rescue, material express delivery and the like in a mountainous (tunnel) environment or in an environment shielded by large buildings, roads and bridges and the like, and fire operations in the buildings and the like. Besides over-the-horizon flight, there is an increasing demand for applications for long-range drones. In addition, after the beyond-the-horizon, long-range flight and control capabilities of the industrial unmanned aerial vehicle are enabled, the industrial application scene of the industrial unmanned aerial vehicle must be greatly expanded.
The unmanned aerial vehicle in the prior industry faces the following problems in the application of beyond visual range and large voyage:
1. the existing unmanned aerial vehicle image transmission and data transmission link adopts point-to-point communication, generally adopts an ISM frequency band, has short communication distance, and is easy to be interfered when the remote control distance is within 2km and the image transmission distance is within 1 km. If the flight with beyond visual range and large range is required, a ground station is deployed on a reserved air route to carry out relay of a communication link, and the method is high in deployment cost, inflexible in air point planning and not suitable for large-batch industrial application.
2. The existing unmanned aerial vehicle remote control and operation mainly control the flying hand, particularly after the visual range is exceeded, due to the time delay of a communication link or intermittent interruption of communication, wrong information feedback input is easily caused to the flying hand, so that the flying hand outputs wrong control instructions and crashes are caused, the flying hand is always nervous, and the flying hand is used for quickly judging which of various observed information is useful for next operation according to experience. Currently 40% of accidents are caused by improper operation of the flying hands. The beyond visual range unmanned aerial vehicle is a great challenge to unmanned aerial vehicle flyers due to long flight time and complex loading tasks.
3. In the flying process of the unmanned aerial vehicle based on the remote control of the flying hand, the flying hand observes the surrounding environment and the parameters of the unmanned aerial vehicle such as position, height and fuel and the like by various methods at any moment, and estimates the return time and plans the return route. In beyond-the-horizon flight, the test of the flyer by the factors is multiplied. After the visual range is beyond the visual range, the control and air route judgment capability of the flyer on the unmanned aerial vehicle is weakened, and in addition, the communication time delay is added, whether the airplane enters a no-fly area or not is avoided, and the flyer is difficult to judge in real time; in addition, when the flight distance is greater than 10km, the front environment such as weather, route obstacles and the like temporarily changes, and the flyer cannot sense the change in real time.
4. Beyond the visual range, unmanned aerial vehicle's communication link at present has in essence unable the safety of guaranteeing the aircraft. At present, aiming at the attack of an unmanned aerial vehicle, except for violent means such as direct hitting (rarely adopted) and the like, the main attacking means is navigation deception and interference and hijacking of control signals, the control signals of the common unmanned aerial vehicle are generally 2.4GHz, graphic transmission is in a 5.8Ghz frequency band, the frequency band is the same as that of Wi-Fi, in addition, in order to facilitate interaction with a mobile phone, some unmanned aerial vehicles can even directly use Wi-Fi, and the Wi-Fi is mostly password-free or weak, and one directional antenna can be remotely accessed to the unmanned aerial vehicle or a remote controller to hijack the unmanned aerial vehicle.
5. In the beyond-the-horizon flight, the requirements on the reliability and the safety of a data link are very high, and the anti-interference and anti-eavesdropping capabilities are weak unless a private data link is adopted in the traditional beyond-the-horizon flight control; but like the encrypted data chain for military applications, deployment costs are very high.
To solve the above problem, an embodiment of the present invention provides a flight control device 1, as shown in fig. 1, the device including: the system comprises an artificial intelligence data processing control module 10, a data acquisition module 11, a flight management module 12 and a data communication management module 13;
the data communication management module 13 is configured to select a target communication network according to a selection order of the cellular network, the ad hoc network, and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by the cloud platform 2 based on the target communication network;
the flight management module 12 is configured to control the unmanned aerial vehicle to execute a flight task according to the target flight track;
the data acquisition module 11 is used for acquiring flight data;
the artificial intelligence data processing control module 10 is configured to process the flight data by using an artificial intelligence operation algorithm to obtain a control result;
the flight management module 12 is further configured to perform flight control on the unmanned aerial vehicle by using the control result.
The flight control device provided by the embodiment of the invention can control the unmanned aerial vehicle to carry out flight operation in scenes such as aerial photography and mapping, agricultural plant protection, environmental detection, express transportation, disaster relief, news reporting, electric power petroleum inspection and the like.
In the embodiment of the invention, the flight control device can be a device which is carried on the unmanned aerial vehicle and is used for controlling the flight operation of the unmanned aerial vehicle.
In the embodiment of the invention, a reliable communication link is a necessary condition for the unmanned aerial vehicle to carry out beyond visual range flight, the data communication management module comprises various types of communication networks, and the communication networks can be subjected to priority division in advance according to the reliability of the communication link to obtain the selection sequence of a cellular network, an ad hoc network and a satellite network; the data communication management module selects a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network, a communication link provided by the target communication network is a communication link with the highest reliability in the data communication management module, at the moment, the data communication management module performs data interaction with the cloud platform based on the target communication network, and before executing a flight task, the data communication management module can receive a target flight path and an artificial intelligence operation algorithm sent by the cloud platform based on the target communication network.
Optionally, the communication network may include a cellular network, an ad hoc network, a satellite network, and the like, wherein the cellular network may include a fifth Generation mobile communication technology (5 th-Generation, 5G), a Long Term Evolution (Long Term Evolution, LTE), a third Generation mobile communication technology (3 rd-Generation, 3G), a second Generation mobile communication technology (2-Generation, 2G), and the like, which are specifically selected according to actual situations, and embodiments of the present invention are not limited specifically.
In the embodiment of the invention, in the process of data interaction between the data communication management module and the cloud platform based on the target communication network, the artificial intelligence data processing module can acquire the operation type, determine the real-time requirement and the data transmission quantity according to the operation type, finally determine the data transmission strategy according to the real-time requirement, the data transmission quantity and the network parameters of the target communication network, and realize the data interaction between the data communication management module and the cloud platform based on the data transmission strategy.
In the embodiment of the invention, the definition of the data transmission priority can be carried out according to the operation type; specifically, type 1: the data volume is small (the data production rate is below 100 KB/s), but the real-time performance requires high and important data, such as unmanned aerial vehicle flight control related data and fire alarm geographic position coordinate data; type 2: the data volume is large (the data production rate is more than 1 MB/s), the real-time performance requirement is high and important, such as image data (such as a remote operation scene) in the process of remotely controlling other equipment; type 3: the data volume is large (the data production rate is more than 1 MB/s), but the real-time requirement is not high, and the data can be locally stored, such as image data in measurement and control operation; type 4: the amount of data is small (data production rate below 100 KB/s), but the real-time requirements are not too high, such as drone operation LOG. The data transmission priority is as follows from high to low in sequence: type 1, type 2, type 3, type 4.
In the embodiment of the present invention, the network parameters of the target communication network may include network bandwidth, data transmission delay, and the like, which are specifically selected according to actual situations, and the embodiment of the present invention is not specifically limited.
For example, for a 5G network, if the measured uplink and downlink bandwidths of the 5G network are both greater than 5Mbps and the data transmission delay is less than 300ms, the bandwidth and the delay are considered to meet the flight control requirement of the unmanned aerial vehicle, otherwise, the bandwidth and the delay cannot be used for real-time control of the unmanned aerial vehicle, but can be used for other data transmission applications and unmanned aerial vehicle flight control assistance; when a communication network exists but the real-time performance cannot meet the requirement, the artificial intelligence data processing control module carries out intelligent processing and transmission of data, and the unmanned aerial vehicle enters a local control strategy for flight control.
Specifically, the artificial intelligence data processing control module firstly judges data transmission delay and network bandwidth, preferentially transmits the flight control data if the transmission requirement of the flight control data of the transmission type 1 is met, ensures the real-time performance of the flight control data, caches the type 2 data to the local storage module, transmits the type 2 data under the residual bandwidth of the transmission flight control data, and sequentially analogizes to transmit the type 3 and the type 4.
In the embodiment of the invention, in the process of executing the flight task by the unmanned aerial vehicle, the data acquisition module also acquires flight data in real time, and the artificial intelligence data processing control module processes the flight data by using an artificial intelligence operation algorithm to obtain a control result, so that the flight management module can perform flight control on the unmanned aerial vehicle by using the control result, wherein the artificial intelligence operation algorithm in the artificial intelligence data processing control module can be sent by a cloud platform and can also be subsequently updated on line.
It can be understood that the scheme adopts a preposed AI calculation scheme, namely the AI calculation capability is preposed on the unmanned aerial vehicle, and the front-end AI algorithm library can be updated in real time according to the set strategy, so that the real-time response capability of the unmanned aerial vehicle is improved, the occupation of the air interface data bandwidth is reduced, and the AI algorithm is rich and can be updated in real time.
Optionally, referring to fig. 2, the data communication management module 13 includes: a cellular communication sub-module 130, an ad hoc network communication sub-module 131, and a satellite communication sub-module 132;
the data communication management module 13 is configured to provide a communication link using the cellular communication sub-module 130 if it is determined that a cellular network exists; if the ad hoc network exists, the ad hoc network communication sub-module 131 is used for providing a communication link; if the cellular network and the ad hoc network do not exist, judging whether a satellite network exists, if so, providing a communication link by using the satellite communication submodule 132, and if not, entering a local control strategy.
In the embodiment of the invention, the cellular communication sub-module supports the corresponding national standard and global roaming of networks such as 5G (SA/NSA), 4G (LTE TDD/FDD), 3G (TD-SCDMA, WCDMA, EVDO), 2G (GSM, CDMA) and the like; the ad-hoc network communication module realizes the ad-hoc network communication of the local cluster, selects ALOHA and CSMA/CD protocols according to the cluster capacity, and provides data support for the anti-cheating and anti-hijacking module to increase the anti-attack capability; the satellite communication module is a satellite communication module supporting voice communication and data message transmission and provides a communication link for the unmanned aerial vehicle under emergency.
It should be noted that, because the communication channels of cellular, military and aviation are legally protected, and the 5G network has the characteristics of large bandwidth and low time delay; the data communication management method is cellular priority and 5G priority, and meanwhile, the unmanned aerial vehicle is connected with the ad hoc network; when neither the ad hoc network nor the cellular network exists, the flight control apparatus 1 inquires whether a satellite network exists, if so, connects the satellite network, otherwise, enters a local control strategy.
It should be noted that, if a cellular network and an ad hoc network coexist, the cellular network or the ad hoc network is used simultaneously for communication, or one of the networks is used for communication, which is specifically selected according to the actual situation, and the embodiment of the present invention is not limited in particular.
For example, as shown in fig. 3, it is first determined whether there is a 5G network, and if it is determined that there is a 5G network, the 5G network is preferentially selected; if no 5G network exists, judging whether a 4G network exists, and if the 4G network exists, preferentially selecting the 4G network; if no 4G network exists, judging whether a 3G network exists, and if the 3G network exists, preferentially selecting the 3G network; if no 3G network exists, judging whether a 2G network exists, and if the 2G network exists, preferentially selecting the 2G network; meanwhile, judging whether an ad hoc network exists or not, if the ad hoc network exists, connecting the ad hoc network, and if the ad hoc network and the cellular network do not exist, judging whether a satellite network exists or not; if the satellite network exists, the satellite network is linked, otherwise, the unmanned aerial vehicle enters local control.
It should be noted that, when the bandwidth and delay requirements of the cellular network meet the requirement of remote control, the cloud platform can perform remote control operation according to the selection of the user; when the bandwidth and delay requirements of the cellular network do not meet the requirements of remote control but the communication link is reliable (such as an LTE or 3G network), the unmanned aerial vehicle flight control can be performed in a remote monitoring mode with a local AI policy as a main policy.
Optionally, referring to fig. 2, the data acquisition module 11 includes: a visual inspection processing module 110;
the visual inspection processing module 110 is configured to acquire image video data in a flight process;
the artificial intelligence data processing control module 10 is configured to perform artificial intelligence identification on the image video data to obtain an identification result; and sending the recognition result to the cloud platform 2 to perform flight control based on the recognition result.
In the embodiment of the invention, the visual detection processing module supports binocular image/video acquisition (including but not limited to a tripod head and a camera of the unmanned aerial vehicle), finishes the acquisition of images/videos (including operation targets, geographic environments, foreign matters and the like) in the up/down/left/right/front/back direction of the flight of the unmanned aerial vehicle, and transmits the images/videos to the artificial intelligent data processing control module for identification processing.
It should be noted that, the identification result may be to identify an operation target, such as crack defect detection processing of an oil pipe; or identifying the surrounding environment, and the specific identification type may be selected according to the actual situation, which is not specifically limited in the embodiments of the present invention.
In the embodiment of the invention, the visual detection processing module can also send the identification result to the cloud platform, and the flight control can be carried out based on the identification result in the process of carrying out the remote flight control on the cloud platform.
Optionally, referring to fig. 2, the data acquisition module 11 further includes: a radar scanning early warning module 111;
the radar scanning early warning module 111 is configured to perform distance measurement and speed measurement on a target object in a preset position in a flying process according to the target flight path to obtain a measurement result;
the artificial intelligence data processing control module 10 is configured to perform recognition processing on the image video data and the measurement result to obtain a distance, a speed, and a movement direction of the target object.
In the embodiment of the invention, the radar scanning early warning module detects the targets in the advancing direction of the unmanned aerial vehicle, and performs distance measurement and speed measurement, and the artificial intelligence data processing control module identifies the size, the speed and the moving direction of the obstacle by matching with the data acquired by the visual detection processing module.
Optionally, referring to fig. 2, the flight management module 12 includes: a foreign object detection and obstacle avoidance management module 120 and a flight control management module 121;
the foreign matter detection and obstacle avoidance management module is used for processing the distance, the speed and the movement direction of the target object to obtain an avoidance control result;
and the flight control management module is used for controlling the flight control device to carry out obstacle avoidance operation by utilizing the avoidance control result.
In the embodiment of the invention, the artificial intelligent data processing control module outputs the distance, the speed and the movement direction of the obstacle to the foreign object detection and obstacle avoidance management module, the foreign object detection and obstacle avoidance management module processes the obstacle and outputs the avoidance and control result to the flight control management module, and the unmanned aerial vehicle is controlled to carry out obstacle avoidance operation, so that the occurrence of crashes or crashes is avoided.
Further, after the distance, the speed and the moving direction of the target object are obtained, an early warning signal is generated and the cloud platform is informed, at the moment, in the process of remote flight control of the cloud platform, the unmanned aerial vehicle can be subjected to flight control, and the purposes of avoiding obstacles and protecting the unmanned aerial vehicle are achieved.
It should be noted that, the flight control management module provides a field flight control strategy for the unmanned aerial vehicle, and according to the cloud platform, the networking compliance management module (not shown in fig. 2, used for performing compliance check on the device networking process), the data communication management module, the visual detection processing module, the radar scanning early warning module, the positioning early warning management module, the map management module, the scene identification and operation management module, the cheating prevention module, the hijack prevention module, the safety management module, the environment perception and processing module, the foreign object detection and obstacle avoidance management module, the data storage module, the flight track memory and planning management module and other functional modules, the artificial intelligent data processing module performs preset AI processing, and then the flight control management module performs the field flight control of the unmanned aerial vehicle.
Optionally, referring to fig. 2, the flight management module 12 includes: a map management module 122; the map management module stores three-dimensional map data;
the artificial intelligence data processing control module 10 is configured to perform three-dimensional reconstruction on the image video data and the measurement result to obtain reconstructed map data; comparing the three-dimensional map data with the reconstructed map data to obtain a comparison result; if the comparison result meets the preset deviation, informing the anti-fraud and anti-hijack module to alarm, and sending the comparison result to the cloud platform; and updating the three-dimensional map data according to the instruction returned by the cloud platform.
In the embodiment of the invention, the map management module manages the map data of the unmanned aerial vehicle (the map data comprises a three-dimensional map model of flight tracks), and also provides flight control support, anti-cheating/anti-hijacking support and unmanned aerial vehicle localized control strategy support for the unmanned aerial vehicle.
Specifically, the map management module compares the three-dimensional map model reconstructed by combining the locally stored three-dimensional map data with the current artificial intelligent data processing control module and the data collected by the vision detection processing module and the radar scanning early warning module, if the three-dimensional map model differs, the three-dimensional map model informs the fraud prevention and anti-hijacking module to give an alarm, submits the alarm to the cloud platform for processing, and performs online upgrade or local update reconstruction of the three-dimensional map data according to the instruction of the cloud platform.
Illustratively, the fraud prevention and hijack prevention module sets a preset difference threshold value to be 30%, and generates an early warning signal if the difference between the locally stored three-dimensional map data and the reconstructed three-dimensional map model is greater than 30%.
It should be noted that the reconstruction algorithm for the artificial intelligence data processing control module to perform three-dimensional reconstruction includes, but is not limited to, an SLAM algorithm, which may be specifically selected according to an actual situation, and the embodiment of the present invention is not specifically limited.
Optionally, referring to fig. 2, the data acquisition module 11 includes: a scene recognition and job management module 112;
the scene recognition and operation management module 112 is configured to determine a current operation scene according to the recognition result; carrying out similarity matching on the current operation scene and a preset operation scene; and performing job management according to the similarity matching result.
In the embodiment of the invention, the scene recognition and operation management module determines the current operation scene according to the recognition result, compares the current operation scene with the operation instruction before the takeoff of the unmanned aerial vehicle, and performs production operation and monitoring and management on the operation flow if the matching degree of the preset operation scene corresponding to the operation instruction is more than 90%; if the matching degree with the preset operation scene is less than 50%, for example, the operation instruction before take-off is power patrol, but the field operation detection is a petroleum pipeline, stopping the current operation and early warning and reporting to the cloud platform; and if the matching degree is more than 50% and less than 90%, stopping the operation, reporting to the cloud platform, and manually confirming whether the local AI algorithm library needs to be upgraded.
It should be noted that the scene recognition and operation management module is only responsible for the management of the operation, and does not provide tools for the operation, such as a machine for agricultural pesticide spraying, and is not included in the scene recognition and operation management module.
It should be noted that the matching degree threshold 90% and the matching degree threshold 50% are exemplary two matching degree thresholds, and are not limited to the two matching degree thresholds, and a specific threshold setting may be selected according to an actual situation, and the embodiment of the present invention is not limited in particular.
Optionally, referring to fig. 2, the data acquisition module 11 includes: a positioning early warning management module 113 and a track memory and planning management module 114; the flight management module 12 comprises: a fraud prevention, hijack prevention module 123;
the positioning early warning management module 113 is configured to acquire current real-time positioning data during a flight process according to the target flight track;
the artificial intelligence data processing control module 10 and the flight path memory and planning management module 114 are configured to fit the current predicted positioning data according to the target flight path;
the artificial intelligence data processing control module 10 is further configured to notify the fraud prevention and anti-hijack module to alarm when a difference between the current real-time positioning data and the current predicted positioning data is greater than a preset threshold; and when the difference is smaller than the preset threshold, determining target positioning navigation from the positioning early warning management module according to a preset navigation sequence to perform subsequent flight positioning.
Optionally, the artificial intelligence data processing control module 10 is further configured to notify the fraud prevention and hijack prevention module to alarm if the target positioning navigation is not determined from the positioning early warning management module and the navigation signal is determined to be lost; connecting the cloud platform, and performing remote flight control by the cloud platform; and if the cloud platform is not connected, entering a local control strategy.
In the embodiment of the invention, the positioning early warning management module comprises a GNSS satellite positioning system, a base station (LBS) positioning system and an ad hoc network auxiliary positioning system. GNSS satellite positioning systems include, but are not limited to, beidou, GPS, GLONASS, galileo, and ground/satellite based augmentation.
In the embodiment of the invention, civil Beidou, GPS and other navigation positioning can reach centimeter level under the condition of foundation enhancement (RTK); and in the case of non-RTK, the accuracy can typically reach 10 meters. The positioning accuracy of the LBS base station can reach 100 meter grade below 4G, the accuracy is higher under the condition of 5G, and the positioning accuracy of 3GPP R16 can reach 5 meter; the ad hoc network assisted positioning does not adopt a TOMA method, but the cluster shares the current 3D coordinate, course and speed of the machine, and the coordinate, course and speed are used as the basis for judging whether the current positioning information is deceived by a deception-preventing and hijack-preventing module.
It should be noted that, the current real-time positioning data is processed by the positioning early warning management module, the anti-cheating module, the anti-hijack module and the artificial intelligence data processing control module to provide accurate positioning information for the unmanned aerial vehicle, and then the flight control management module controls the flight of the unmanned aerial vehicle.
Specifically, the current real-time positioning data is determined according to the GNSS positioning data, the base station LBS positioning data, and the cluster unmanned aerial vehicle positioning information, the course and the speed shared by the ad hoc network cluster; then, current predicted positioning data is fitted by a track memory and planning management module and an artificial intelligence data processing control module, a difference value between the current predicted positioning data and the current predicted positioning data is determined, and if the difference value is larger than a preset threshold value, the fraud prevention and hijack prevention module is informed to give an alarm; and if the difference is smaller than the preset threshold, determining target positioning navigation from the positioning early warning management module according to preset navigation sequencing for subsequent flight positioning.
Specifically, in the embodiment of the present invention, the time is in seconds, and as shown in fig. 4, a difference 1 between the current GNSS geographic position and the current position of the unmanned aerial vehicle and the current position calculated at the last time of positioning, speed and heading is calculated; if the difference value 1 is greater than 100 meters, informing the anti-fraud and anti-hijack module to alarm; if the difference value 1 is not more than 100 meters, calculating a difference value 2 between the difference value of the distances between the unmanned aerial vehicle and the ad hoc network cluster at the current moment and the difference value of the distances between the unmanned aerial vehicle and the ad hoc network cluster in the last second; if the difference value 2 is more than 100 meters, informing the anti-fraud and anti-hijack module to alarm; if the difference value 2 is not more than 100 meters, calculating a difference value 3 between the current GNSS geographical position and the current LBS geographical position, and if the difference value 3 is more than 100 meters, informing an anti-fraud and anti-hijack module to alarm; if the difference value 3 is not greater than 100 meters, determining target positioning navigation from the positioning early warning management module according to a preset navigation sequence for subsequent flight positioning, specifically, judging whether a satellite positioning navigation signal exists or not; if the satellite positioning navigation signal exists, the unmanned aerial vehicle adopts GNSS positioning navigation; if the satellite positioning navigation signal does not exist, judging whether an LBS positioning signal exists or not and the positioning accuracy meets the requirement, and if the LBS positioning signal exists and the accuracy meets the requirement, adopting LBS positioning navigation by the unmanned aerial vehicle; if the LBS positioning signal does not exist and/or the positioning accuracy does not meet the requirement, the connection of the cloud platform is tried, if the connection of the cloud platform is successful, the cloud platform takes over the unmanned aerial vehicle in a long-distance mode and carries out remote control flight, and otherwise, the unmanned aerial vehicle enters a local control strategy to execute forced landing or return voyage.
It should be noted that, according to radio management planning, the working frequency bands of the current unmanned aerial vehicle navigation deception or interference devices are mainly 915 MHz-928 MHz, 2400-2500 MHz, 1550 MHz-1625 MHz, 5725 MHz-5825 MHz and the adjacent frequency bands, the cellular network (the working frequency band of the cellular network is wide and protected, and the current unmanned aerial vehicle anti-braking devices are all required to avoid the cellular frequency band, so that the interference is not easy), LBS location and ad hoc network location auxiliary strategies are preferentially adopted in the invention, so that the unmanned aerial vehicle can be effectively prevented from being deceived and hijacked.
In the embodiment of the invention, the track memory and planning management module finishes the planning updating and saving of the track of the unmanned aerial vehicle before takeoff, memorizes the actual flight track of the unmanned aerial vehicle, compares the actual flight track with the track of the cloud platform, and warns in real time if the actual flight track deviates. In the flight of the unmanned aerial vehicle, the track memory and planning management module can fit the three-dimensional geographic position information at the current moment according to the factors such as the course, the speed and the wind speed of the aircraft at the previous moment, and compares the three-dimensional geographic position information with the real-time information provided by the positioning early warning management module and the elevation information provided by the environment perception and processing module, so as to provide decision support for the anti-cheating and anti-hijack module. The flight path memory and planning management module can also memorize current flight position information and flight path information and combines a three-dimensional map which is reconstructed in real time by the map management module, the visual detection processing module and the radar scanning early warning module, and early warning information which is output by foreign matter detection and obstacle avoidance management.
In the embodiment of the invention, when a navigation signal is lost or a fault occurs, new flight control data is generated under the support of a visual detection processing module, a radar scanning early warning module, a foreign matter detection and obstacle avoidance management module, a track memory and planning management module and an anti-cheating and anti-hijacking module according to the position of a standby airport and local three-dimensional data stored in a local machine, and the hovering, forced landing or return of the unmanned aerial vehicle is managed by the flight control management module.
Optionally, the artificial intelligence data processing control module 10 is further configured to control the hovering preset duration through the flight control management module if it is determined that the communication of the data communication management module is interrupted; when an early warning signal release instruction is not received within the preset time, generating new flight control data according to the positioning data acquired by the data acquisition module; performing flight control according to the new flight control data through the flight control management module; judging whether the early warning signal is released or not every other preset flight time interval;
the track memory and planning management module 114 is configured to reconstruct a local three-dimensional map model if a warning signal cancellation instruction is not received yet;
the artificial intelligence data processing control module 10 is further configured to control forced landing or return voyage based on the local three-dimensional map model and the three-dimensional map data; and when the early warning signal release instruction is received, continuing flying based on the navigation signal.
In the embodiment of the present invention, if the data communication management module is interrupted in communication (including satellite signals), it should be noted that the flight policy of the present invention is as follows: the cloud platform can compare the distribution of cellular base stations and the communication quality condition of a track path before flight, cellular network full coverage is defaulted on the formulated flight path, and communication interruption refers in particular to the condition of being attacked or interfered, and then the artificial intelligence data processing control module corrects and records the positioning information according to LBS positioning signals, ad hoc network positioning signals, a map management module and a track memory and planning management module, and carries out a localization control strategy. At the moment, local AI flight control is taken as a main part, and an artificial intelligence data processing control module is taken as a control core of the flight control device.
In an optional embodiment, the preset time is set to be 20 seconds, the new flight control data is the deceleration flight, the preset flight time period is 100 meters, at this time, if the communication terminal of the data communication management module is detected, the unmanned aerial vehicle is controlled to hover for 20 seconds, and if the early warning signal is removed, the normal flight is performed; otherwise, with LBS positioning as a main and track fitting as an auxiliary, with the help of a visual detection processing module, a radar scanning early warning module, foreign object detection and obstacle avoidance management, a flight control management module controls the airplane to slow down and fly according to a set strategy (for example, continuously along the original route), after flying for 100 m, cheating prevention and hijack prevention early warning confirmation is carried out, and if the early warning is released, the airplane normally flies; otherwise, after flying at the reduced speed for 100 m, performing early warning confirmation, and if the early warning is released, normally flying; otherwise, reconstructing a local three-dimensional map model by means of a visual detection processing module, a radar scanning early warning module, foreign matter detection and obstacle avoidance management, and executing a forced landing/return journey algorithm by combining data of a map management module to avoid a navigation deception trap falling into an attacker.
In the embodiment of the invention, the track memory and planning management module also updates the estimated flight, air route management and forced landing and return strategies of the unmanned aerial vehicle in real time according to the fuel of the unmanned aerial vehicle, the flight environment sensed by the environment sensing and processing module, the track forced landing airport and other information. The method enables the unmanned aerial vehicle to automatically carry out flight compliance management in the processes of air route planning, take-off, flight, operation and landing, achieves the effect that the unmanned aerial vehicle can be managed and controlled in flight operation, and improves the automation of unmanned aerial vehicle compliance management.
The scheme adopts the beyond visual range internet unmanned aerial vehicle flight control strategy and method based on AI-based cloud integrated map management and track planning management, gives consideration to multiple flexible modes such as cloud platform remote control and unmanned aerial vehicle local AI autonomous control, achieves the unmanned aerial vehicle supporting local autonomous AI flight control capability, improves the unmanned aerial vehicle obstacle avoidance and safety protection capability, and can effectively avoid the effects of collision, crash and accidents caused by other human factors.
Optionally, the data acquisition module 11 includes: a context awareness and processing module 115;
the environment sensing and processing module 115 is used for acquiring environment parameters of an operation environment in the flying process according to the target flying track;
the artificial intelligence data processing control module 10 is configured to determine an operation judgment result based on the environmental parameter and the current operation scene; performing light control management on the data acquisition module based on the environmental parameters; determining elevation information based on the environment parameters, and correcting the current real-time positioning data by utilizing the elevation information; and providing flight decision support for the unmanned aerial vehicle in the current working environment based on the environment parameters.
In the embodiment of the invention, the environment sensing and processing module is a nose, eyes and ears of an unmanned aerial vehicle, can be used for collecting the environment parameters such as illumination, temperature and humidity (including infrared temperature measurement), wind speed, acceleration, angular velocity, magnetic sensing data, air pressure (elevation), rain and snow weather, VOC (volatile organic compound) toxic gas and sound of a field operation environment for the flight control device, and provides information input for the scene identification and operation management module, the vision detection and processing module, the radar scanning early warning module and the foreign matter detection and obstacle avoidance management module. The application of the environment sensing and processing module to the unmanned aerial vehicle is critical, for example, the location of the cloud platform operation center is clear and empty, the location of the unmanned aerial vehicle outside 100km is large in rain, and the current weather forecast precision cannot be updated in real time, which affects the operation implementation of the unmanned aerial vehicle on the front site. Just need environment perception and processing module to gather unmanned aerial vehicle's real-time environment parameter this moment.
In an optional embodiment, the environment sensing and processing module detects a weather environment of a place where the current operation is located, compares the weather environment with the operation type in the scene recognition and operation management module, obtains a conclusion whether the operation can be performed, and sends the conclusion to the artificial intelligence data processing control module and the cloud platform for processing.
In an optional embodiment, the environmental sensing and processing module collects the illumination data and provides the illumination data to the visual inspection processing module for exposure/compensation control management in the image video collection process.
In an optional embodiment, the environment sensing and processing module collects wind speed, acceleration, angular velocity and magnetic force sensing data, provides the data to the track memory and planning management module for track fitting calculation to obtain a fitting result, and transmits the fitting result to the anti-cheating and anti-hijacking module.
Furthermore, the track memory and planning management module also updates data such as endurance mileage and the like in real time according to the wind speed, the acceleration, the angular velocity and the magnetic sensing data, and provides early warning support for forced landing and return voyage of the unmanned aerial vehicle, for example, the endurance mileage of the unmanned aerial vehicle flying against the wind and flying along the wind is greatly different.
In an optional embodiment, the environment sensing and processing module acquires air pressure data, obtains elevation information by using the air pressure data, and can accurately correct the current operation height by combining the current real-time positioning data of the positioning early warning management module. And comparing the height data with the height data of the positioning early warning management module, when the difference is more than 5 meters, determining that the GNSS is possible to be hijacked or deceived, reporting the cloud platform for early warning, and executing a deception-prevention and hijack-prevention strategy.
In an optional embodiment, environmental perception and processing module gather humiture data, and humiture data can provide the protection for the unmanned aerial vehicle of some special operations, combines visual detection processing module, artificial intelligence data processing control module's recognition result, can prevent that unmanned aerial vehicle from being burnt or the crash in the detection of fire control ignition.
It can be understood that this scheme has adopted leading environmental perception equipment of an unmanned aerial vehicle and method, provides scene type support and safety precaution for long-range unmanned aerial vehicle field work, reaches to avoid unmanned aerial vehicle to meet "different days in ten in the application of unmanned aerial vehicle adaptation over-the-horizon, and there is the condition of this type of environmental parameter sudden change in four seasons" in a mountain, promotes unmanned aerial vehicle environmental suitability and operation safety's effect.
In an alternative embodiment, the environmental sensing and processing module performs toxic gas (VOC) detection, and can provide local environmental data support for monitoring rescue and avoiding personal injury during environmental detection or fire fighting operation.
In an optional embodiment, the environment sensing and processing module collects the sound of the operation environment, the sound is subjected to accurate identification by the artificial intelligent data processing and controlling module, for example, in a rescue task, keywords such as 'life saving' and the like can be identified, and a more detailed operation strategy is provided for the site by combining the processing of the cloud platform; for another example, some dangerous explosion sound, brake sound can be monitored to fix a position through artificial intelligence data processing control module, control visual detection processing module and unmanned aerial vehicle from cloud platform, the camera of taking track the discernment and handle.
It can be understood that the scheme adopts a multi-dimensional unmanned aerial vehicle anti-cheating and anti-hijacking method, a coping processing strategy and a coping processing method, so that the navigation cheating resistance and anti-interference attack resistance of the unmanned aerial vehicle during over-the-horizon flight control are improved, and the unmanned aerial vehicle is prevented from being hijacked by an attacker.
Optionally, the apparatus 1 further comprises: a data storage module 13 and a security management module 14;
the data storage module is used for storing the target flight path, flight control data, operation data and system log data;
and the safety management module is used for carrying out hardware encryption on the data in the data storage module.
In the embodiment of the invention, the data storage module stores the data transmitted in the data communication management module and the locally stored data. The data storage module manages a map management module, a scene recognition and operation management module, a networking compliance management module, a data communication management module, a visual detection processing module, a radar scanning early warning module, a positioning early warning management module, cheating prevention, a hijack prevention module, an environment perception and processing module, foreign matter detection and obstacle avoidance management, service data in a flight path memory and planning management module, including target flight path, flight control data, operation data and the like, system log data in the flight of the unmanned aerial vehicle are also stored, and the black box function of the over-the-horizon internet unmanned aerial vehicle is realized.
In the embodiment of the invention, the security management module adopts a high-speed hardware encryption and decryption chip and an end-to-end security guarantee method to carry out hardware encryption and decryption on data in the data storage module, so that the data is prevented from being monitored or stolen by an attacker, and the effect of guaranteeing the data security of a local communication link and the whole communication link is achieved.
It can be understood that the scheme adopts a data communication transmission management method which mainly adopts a honeycomb and combines an ad hoc network and a satellite, before the unmanned aerial vehicle takes off, the distribution and the network condition of a honeycomb base station of an operation route are confirmed through a cloud platform, and then the operation is implemented, so that the route planning is flexible without depending on a ground relay station; and the artificial intelligence operation algorithm is prepositioned to the unmanned aerial vehicle, so that the obstacle avoidance and real-time response capability of the unmanned aerial vehicle are improved, the autonomous flight control capability of the unmanned aerial vehicle is improved, the flight pressure is reduced, and the accident risk is reduced.
Based on the embodiment, an embodiment of the present invention further provides a cloud platform 2, and as shown in fig. 5, the cloud platform 2 includes: the system comprises a track planning management module 20, a base station position database module 21, a map information database module 22 and a data communication management module 23;
the flight path planning management module 20 is configured to receive a flight task and plan an initial flight path according to the flight task;
the base station position database module 21 and the map information database module 22 are used for identifying whether the initial flight path is in a no-fly zone or a cellular coverage blind spot, and returning an identification result to the flight path planning management module;
the flight path planning management module 20 is further configured to adjust the initial flight path based on the identification result to obtain the target flight path;
and the data communication management module 23 is configured to send the target flight path to a flight control device, so that the flight control device controls the unmanned aerial vehicle to fly according to the target flight path.
In the embodiment of the invention, before the unmanned aerial vehicle starts a flight task, the cloud platform receives the flight task submitted by the user, plans the flight path according to the flight task, and then sends the target flight path to the flight control device through the data communication management module, and the flight control device can fly according to the target flight path.
In the embodiment of the invention, a cloud platform starts a flight path planning management module, queries a base station position database module and a geographic information database module, checks whether a task flight path has complete wireless cellular network coverage and checks network coverage conditions (2G/3G/LTE/5G and each Band), evaluates whether a planned flight path has continuous 5G cellular network coverage (including network system requirements), a forced landing/standby landing airport and whether a no-fly zone exists, evaluates the feasibility of the task according to information of fuel, flight path and the like of an unmanned aerial vehicle, and optimizes the flight path and confirms a user.
Optionally, referring to fig. 5, the cloud platform further includes: an artificial intelligence algorithm library management module 24 and a flight control module 25; wherein, the first and the second end of the pipe are connected with each other,
the artificial intelligence algorithm library management module 24 is used for storing artificial intelligence operation algorithms and synchronizing the artificial intelligence operation algorithms to the flight control device;
the map information database module 22 is further configured to generate three-dimensional map data corresponding to the target flight path, and transmit the three-dimensional map data to the flight control device, so that the flight control device performs localized control and operation;
the flight control module 25 is configured to perform remote flight control on the unmanned aerial vehicle.
In the embodiment of the invention, if a no-fly zone or a 5G coverage blind spot exists, flight path modification and user confirmation are carried out; after the flight mission track planning is confirmed, a flight compliance management module submits flight plan preparation and permission application to each airspace management department passing through the flight mission, and after the flight approval is obtained, an AI algorithm library management module updates an AI operation algorithm library to a flight control device; meanwhile, the geographic information database module updates three-dimensional map data (including path base station position data) of the flight path to the flight control device, and the unmanned aerial vehicle local control and operation capacity are enabled; after the above steps are completed, the operating drone of the flight control device is allowed to take off and operate as planned.
In the embodiment of the invention, in the flight process of the unmanned aerial vehicle, if the network bandwidth and the time delay meet the requirements, the cloud platform also remotely controls the unmanned aerial vehicle to carry out remote flight control. Specifically, the cloud platform can receive the flight data that flight control device gathered to handle the flight data, obtain the flight control result, later flight control module carries out long-range flight control to unmanned aerial vehicle based on the flight control result.
It can be understood that the scheme adopts a data communication transmission management method which mainly adopts a honeycomb and combines an ad hoc network and a satellite, before the unmanned aerial vehicle takes off, the distribution and the network condition of a honeycomb base station of an operation route are confirmed through a cloud platform, and then the operation is implemented, so that the route planning is flexible without depending on a ground relay station; and the artificial intelligence operation algorithm is prepositioned to the unmanned aerial vehicle, so that the obstacle avoidance and real-time response capability of the unmanned aerial vehicle are improved, the autonomous flight control capability of the unmanned aerial vehicle is improved, the flight pressure is reduced, and the accident risk is reduced.
Based on the above embodiments, an embodiment of the present invention provides a flight control method, which is applied to a flight control device 1, and as shown in fig. 6, the method includes:
s101, selecting a target communication network according to the selection sequence of a cellular network, an ad hoc network and a satellite network; and receiving a target flight path and an artificial intelligence operation algorithm sent by the cloud platform based on the target communication network.
And S102, controlling the unmanned aerial vehicle to execute a flight task according to the target flight track.
S103, collecting flight data, and processing the flight data by using an artificial intelligence operation algorithm to obtain a control result.
And S104, carrying out flight control on the unmanned aerial vehicle by using the control result.
Specifically, the process of selecting the target communication network according to the selection order of the cellular network, the ad hoc network, and the satellite network includes: if the cellular network exists, connecting the cellular network for communication; if the self-networking network exists, connecting the self-networking network for communication; if the cellular network and the ad hoc network do not exist, connecting and judging whether a satellite network exists or not; if the satellite network exists, connecting the satellite network for communication; and if the satellite network does not exist, entering a local control strategy.
Specifically, the process of acquiring flight data includes: collecting image video data in the flight process, a measurement result of a target object with a preset position, current real-time positioning data and environmental operation of an operation environment.
Specifically, the process of processing the flight data by using an artificial intelligence operation algorithm to obtain a control result comprises the following steps: identifying and processing image video data and a measurement result by using an artificial intelligence operation algorithm to obtain the distance, the speed and the direction of a target object; and processing the distance, the speed and the moving direction of the target object to obtain an avoidance control result.
Specifically, the process of processing the flight data by using an artificial intelligence operation algorithm to obtain a control result comprises the following steps: performing three-dimensional reconstruction on the image video data and the measurement result to obtain reconstructed map data; comparing the pre-stored three-dimensional map data with the reconstructed map data to obtain a comparison result; if the comparison result meets the preset deviation, performing alarm processing, and sending the comparison result to the cloud platform; and updating the three-dimensional map data according to the instruction returned by the cloud platform.
Specifically, the process of processing the flight data by using an artificial intelligence operation algorithm to obtain a control result comprises the following steps: identifying image video data to obtain an identification result; determining a current operation scene according to the identification result; carrying out similarity matching on the current operation scene and a preset operation scene to obtain a similarity matching result; and performing operation management according to the similarity matching result.
Specifically, the process of processing the flight data by using an artificial intelligence operation algorithm to obtain a control result comprises the following steps: fitting the current predicted positioning data according to the target flight path; when the difference value between the current real-time positioning data and the current prediction positioning data is larger than a preset threshold value, carrying out alarm processing; and when the difference value is smaller than the preset threshold value, determining target positioning navigation for subsequent flight positioning according to the preset navigation sequence.
Specifically, the process after determining the target positioning navigation for subsequent flight positioning according to the preset navigation sequence further includes: if the target positioning navigation is not determined, judging that the navigation signal is lost, and performing alarm processing; the system is connected with a cloud platform, and the cloud platform is used for carrying out remote flight control; and if the cloud platform is not connected, entering a local control strategy.
Specifically, the process of processing the flight data by using an artificial intelligence operation algorithm to obtain a control result comprises the following steps: determining a job judgment result based on the environmental parameters and the current job scene; performing light control management for the process of acquiring image video data based on the environmental parameters; determining elevation information based on the environment parameters, and correcting the current real-time positioning data by utilizing the elevation information; and providing flight decision support for the unmanned aerial vehicle in the current working environment based on the environment parameters.
Specifically, if the communication interruption of the data communication management module is judged, the hovering preset time is controlled; when the early warning signal removing instruction is not received within a preset time length, generating new flight control data according to the acquired positioning data; and performing flight control according to the new flight control data; judging whether the early warning signal is released or not every other preset flight time interval; if the early warning signal removing instruction is not received, reconstructing a local three-dimensional map model; controlling forced landing or return voyage based on the local three-dimensional map model and the three-dimensional map data; and when the early warning signal release instruction is received, continuing flying based on the navigation signal.
It should be noted that, the specific implementation process of the flight control device for performing flight control on the unmanned aerial vehicle refers to the description of the embodiment of the flight control device, and is not described herein again.
Based on the above embodiments, an embodiment of the present invention provides a flight control method, which is applied to a cloud platform 2, and as shown in fig. 7, the method includes:
s201, receiving a flight task, and planning an initial flight path according to the flight task.
S202, identifying whether the initial flight path is in a no-fly zone or a honeycomb coverage blind spot, and adjusting the initial flight path based on the identification result to obtain a target flight path.
And S203, sending the target flight path to a flight control device so that the flight control device can control the unmanned aerial vehicle to fly according to the target flight path.
It should be noted that, the specific implementation process of the unmanned aerial vehicle for performing flight control on the unmanned aerial vehicle refers to the description of the embodiment of the unmanned aerial vehicle, and is not described herein again.
Based on the above embodiment, the embodiment of the present invention further provides a flight control device 1, and in practical applications, based on the same disclosure concept of the above embodiment, as shown in fig. 8, the device 1 includes: a first processor 15, a first memory 16 and a first communication bus 17.
In the process of the Specific embodiment, the data collection module 11, the visual detection Processing module 110, the radar scanning warning module 111, the flight management module 12, the foreign object detection and obstacle avoidance management module 120, the flight control management module 121, the map management module 122, the scene recognition and operation management module 112, the fraud prevention and hijacking prevention module 123, the positioning warning management module 113, the track memory and plan management module 114, the data communication management module 13, the cellular communication sub-module 130, the ad hoc network communication sub-module 131, the satellite communication sub-module 132, the environment sensing and Processing module 115, and the safety management module 14 may be implemented by a first Processor 15 located on the flight control Device 1, the data storage module 13 may be implemented by a first memory 16 located on the flight control Device 1, and the first Processor 15 may be an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP, digital Signal Processor), a Digital Signal Processing Device (DSPD), a Field Programmable Gate Array (FPGA), a Field Programmable Logic Processor (FPGA). It is understood that the electronic device for implementing the above-mentioned processor function may be other devices, and the embodiment is not limited in particular.
In the embodiment of the present application, the first communication bus 17 is used to implement connection communication between the first processor 15 and the first memory 16; the first processor 15 implements the following flight control method when executing the operating program stored in the first memory 16:
selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on the target communication network; controlling the unmanned aerial vehicle to execute a flight task according to the target flight track; acquiring flight data, and processing the flight data by using an artificial intelligence operation algorithm to obtain a control result; and utilizing the control result to carry out flight control on the unmanned aerial vehicle.
Further, the first processor 15 is further configured to connect to a cellular network for communication if it is determined that the cellular network exists; if the self-networking network exists, connecting the self-networking network for communication; if the cellular network and the ad hoc network do not exist, connecting and judging whether a satellite network exists or not; if the satellite network exists, connecting the satellite network for communication; and if the satellite network does not exist, entering a local control strategy.
Further, the first processor 15 is further configured to collect image and video data during a flight process, a measurement result of a target object at a preset position, current real-time positioning data, and an environmental operation of an operation environment.
Further, the first processor 15 is further configured to perform recognition processing on the image video data and the measurement result by using the artificial intelligence operation algorithm, so as to obtain a distance, a speed, and a direction of a target object; and processing the distance, the speed and the movement direction of the target object to obtain an avoidance control result.
Further, the first processor 15 is further configured to perform three-dimensional reconstruction on the image video data and the measurement result, so as to obtain reconstructed map data; comparing pre-stored three-dimensional map data with the reconstructed map data to obtain a comparison result; if the comparison result meets the preset deviation, performing alarm processing, and sending the comparison result to the cloud platform; and updating the three-dimensional map data according to the instruction returned by the cloud platform.
Further, the first processor 15 is further configured to identify the image video data to obtain an identification result; determining a current operation scene according to the identification result; carrying out similarity matching on the current operation scene and a preset operation scene to obtain a similarity matching result; and performing operation management according to the similarity matching result.
Further, the first processor 15 is further configured to fit the current predicted positioning data according to the target flight path; when the difference value between the current real-time positioning data and the current prediction positioning data is larger than a preset threshold value, carrying out alarm processing; and when the difference value is smaller than the preset threshold value, determining target positioning navigation for subsequent flight positioning according to preset navigation sequencing.
Further, the first processor 15 is further configured to perform an alarm process if the target positioning navigation is not determined and the navigation signal is determined to be lost; the system is connected with the cloud platform, and the cloud platform is used for carrying out remote flight control; and if the cloud platform is not connected, entering a local control strategy.
Further, the first processor 15 is further configured to determine a job determination result based on the environmental parameter and the current job scenario; performing light control management for the process of acquiring image video data based on the environmental parameters; determining elevation information based on the environment parameters, and correcting the current real-time positioning data by utilizing the elevation information; and providing flight decision support for the unmanned aerial vehicle in the current working environment based on the environment parameters.
Further, the first processor 15 is further configured to control the hovering preset time length if it is determined that the communication of the data communication management module is interrupted; when the early warning signal removing instruction is not received within the preset time, generating new flight control data according to the acquired positioning data; and performing flight control according to the new flight control data; judging whether the early warning signal is released every other preset flight period; if the early warning signal release instruction is not received yet, reconstructing a local three-dimensional map model; controlling forced landing or return voyage based on the local three-dimensional map model and the three-dimensional map data; and when the early warning signal removing instruction is received, continuing flying based on the navigation signal.
Based on the foregoing embodiment, an embodiment of the present invention further provides a cloud platform 2, and as shown in fig. 9, the cloud platform 2 includes: a second processor 26, a second memory 27, and a second communication bus 28.
In the process of a Specific embodiment, the track planning management module 20, the flight control module 25, the data communication management module 23, the base station location database module 21, the artificial intelligence algorithm library management module 24, and the map information database module 22 may be implemented by a second Processor 26 located on the cloud platform 2, and the second Processor 26 may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic image Processing Device (PLD), a Field Programmable Gate Array (FPGA), a CPU, a controller, a microcontroller, and a microprocessor. It is understood that the electronic device for implementing the above-mentioned processor function may be other devices, and the embodiment is not limited in particular.
In the embodiment of the present application, the second communication bus 28 is used for realizing connection communication between the second processor 26 and the second memory 27; the second processor 26 implements the following flight control method when executing the operating program stored in the second memory 27:
receiving a flight task, and planning an initial flight path according to the flight task; identifying whether the initial flight path is in a no-fly zone or a honeycomb coverage blind spot, and adjusting the initial flight path based on the identification result to obtain the target flight path; and sending the target flight path to a flight control device, so that the flight control device controls the unmanned aerial vehicle to fly according to the target flight path.
The embodiment of the invention provides a storage medium, wherein one or more programs are stored in the storage medium, the one or more programs can be executed by one or more processors and are applied to a flight control device or a cloud platform, and the flight control method is realized when the programs are executed by the processors.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The sequence numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a network function deployment server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are also within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (29)
1. The utility model provides a flight control device, flight control device carries on unmanned aerial vehicle, its characterized in that, the device includes: the system comprises an artificial intelligence data processing control module, a data acquisition module, a flight management module and a data communication management module;
the data communication management module is used for selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on the target communication network;
the flight management module is used for controlling the unmanned aerial vehicle to execute a flight task according to the target flight track;
the data acquisition module is used for acquiring flight data;
the artificial intelligence data processing control module is used for processing the flight data by using an artificial intelligence operation algorithm to obtain a control result;
the flight management module is also used for carrying out flight control on the unmanned aerial vehicle by utilizing the control result.
2. The apparatus of claim 1, wherein the data communication management module comprises: the system comprises a cellular communication sub-module, an ad hoc network communication sub-module and a satellite communication sub-module;
the data communication management module is used for providing a communication link by using the cellular communication sub-module if the cellular network is judged to exist; if the self-organizing network exists, the self-organizing network communication sub-module is used for providing a communication link; if the cellular network and the ad hoc network do not exist, judging whether a satellite network exists, if so, providing a communication link by using a satellite communication sub-module, and if not, entering a local control strategy.
3. The apparatus of claim 1, wherein the data acquisition module comprises: a visual detection processing module;
the visual detection processing module is used for acquiring image video data in the flight process;
the artificial intelligence data processing control module is used for carrying out artificial intelligence recognition on the image video data to obtain a recognition result; and sending the identification result to the cloud platform so as to carry out flight control based on the identification result.
4. The apparatus of claim 3, wherein the data acquisition module further comprises: a radar scanning early warning module;
the radar scanning early warning module is used for measuring the distance and the speed of a target object in a preset direction in the flying process according to the target flying track to obtain a measuring result;
and the artificial intelligence data processing control module is used for identifying the image video data and the measurement result to obtain the distance, the speed and the movement direction of the target object.
5. The apparatus of claim 4, wherein the flight management module comprises: the foreign matter detection and obstacle avoidance management module and the flight control management module;
the foreign matter detection and obstacle avoidance management module is used for processing the distance, the speed and the movement direction of the target object to obtain an avoidance control result;
and the flight control management module is used for controlling the flight control device to carry out obstacle avoidance operation by utilizing the avoidance control result.
6. The apparatus of claim 4, wherein the flight management module comprises: a map management module; the map management module stores three-dimensional map data;
the artificial intelligence data processing control module is used for carrying out three-dimensional reconstruction on the image video data and the measurement result to obtain reconstructed map data; comparing the three-dimensional map data with the reconstructed map data to obtain a comparison result; if the comparison result meets the preset deviation, informing the anti-fraud and anti-hijack module to alarm, and sending the comparison result to the cloud platform; and updating the three-dimensional map data according to the instruction returned by the cloud platform.
7. The apparatus of claim 3, wherein the data acquisition module comprises: a scene recognition and operation management module;
the scene recognition and operation management module is used for determining the current operation scene according to the recognition result; carrying out similarity matching on the current operation scene and a preset operation scene; and performing job management according to the similarity matching result.
8. The apparatus of claim 1, wherein the data acquisition module comprises: a positioning early warning management module and a track memory and planning management module; the flight management module includes: a fraud prevention and hijack prevention module;
the positioning early warning management module is used for acquiring current real-time positioning data in the flying process according to the target flying track;
the artificial intelligence data processing control module and the track memory and planning management module are used for fitting the current predicted positioning data according to the target flight track;
the artificial intelligence data processing control module is also used for informing the fraud prevention and hijack prevention module to give an alarm when the difference value between the current real-time positioning data and the current predicted positioning data is greater than a preset threshold value; and when the difference is smaller than the preset threshold, determining target positioning navigation from the positioning early warning management module according to a preset navigation sequence to perform subsequent flight positioning.
9. The apparatus of claim 8,
the artificial intelligence data processing control module is also used for informing the fraud prevention and anti-hijack module to give an alarm if the target positioning navigation is not determined from the positioning early warning management module and the navigation signal is judged to be lost; the system is connected with the cloud platform, and the cloud platform is used for performing remote flight control; and if the cloud platform is not connected, entering a local control strategy.
10. The apparatus of claim 1, wherein the data acquisition module comprises: track memory and planning management module, flight management module includes: a flight control management module;
the artificial intelligence data processing control module is also used for controlling a preset hovering duration through the flight control management module if the communication interruption of the data communication management module is judged; when an early warning signal removing instruction is not received within the preset time, generating new flight control data according to the positioning data acquired by the data acquisition module; performing flight control according to the new flight control data through the flight control management module; judging whether the early warning signal is released or not every other preset flight time interval;
the track memory and planning management module is used for reconstructing a local three-dimensional map model if an early warning signal removing instruction is not received yet;
the artificial intelligence data processing control module is also used for controlling forced landing or return voyage based on the local three-dimensional map model and the three-dimensional map data; and when the early warning signal release instruction is received, continuing flying based on the navigation signal.
11. The apparatus of claim 1, wherein the data acquisition module comprises: an environment sensing and processing module;
the environment sensing and processing module is used for acquiring environment parameters of an operation environment in the flying process according to the target flying track;
the artificial intelligence data processing control module is used for determining an operation judgment result based on the environment parameters and the current operation scene; performing light control management on the data acquisition module based on the environmental parameters; determining elevation information based on the environment parameters, and correcting the current real-time positioning data by utilizing the elevation information; and providing flight decision support for the unmanned aerial vehicle in the current working environment based on the environment parameters.
12. The apparatus of claim 1,
the artificial intelligence data processing control module is used for acquiring the operation type and determining the real-time requirement and the data transmission quantity according to the operation type; and determining a data transmission strategy according to the real-time requirement, the data transmission quantity and the network parameters of the target communication network.
13. The apparatus of claim 1, further comprising: the system comprises a data storage module and a safety management module;
the data storage module is used for storing the target flight path, flight control data, operation data and system log data;
and the safety management module is used for carrying out hardware encryption on the data in the data storage module.
14. A cloud platform, the cloud platform comprising: the system comprises a track planning management module, a base station position database module, a map information database module and a data communication management module;
the flight path planning management module is used for receiving a flight task and planning an initial flight path according to the flight task;
the base station position database module and the map information database module are used for identifying whether the initial flight track is in a no-fly zone or a honeycomb coverage blind spot, and returning an identification result to the flight track planning management module;
the flight path planning management module is further used for adjusting the initial flight path based on the identification result to obtain a target flight path;
and the data communication management module is used for sending the target flight path to a flight control device so that the flight control device can control the unmanned aerial vehicle to fly according to the target flight path.
15. The cloud platform of claim 14, wherein the cloud platform further comprises: the system comprises an artificial intelligence algorithm library management module and a flight control module; wherein the content of the first and second substances,
the artificial intelligence algorithm library management module is used for storing artificial intelligence operation algorithms and synchronizing the artificial intelligence operation algorithms to the flight control device;
the map information database module is also used for generating three-dimensional map data corresponding to the target flight path and transmitting the three-dimensional map data to the flight control device so that the flight control device can carry out local control and operation;
the flight control module is used for controlling the unmanned aerial vehicle to carry out remote flight.
16. A flight control method is characterized by being applied to a flight control device, and the method comprises the following steps:
selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on the target communication network;
controlling the unmanned aerial vehicle to execute a flight task according to the target flight track;
collecting flight data, and processing the flight data by using an artificial intelligence operation algorithm to obtain a control result;
and utilizing the control result to carry out flight control on the unmanned aerial vehicle.
17. The method of claim 16, wherein selecting the target communication network in the order of selection of the cellular network, the ad hoc network, and the satellite network comprises:
if the cellular network exists, connecting the cellular network for communication;
if the self-networking network exists, connecting the self-networking network for communication;
if the cellular network and the ad hoc network do not exist, connecting and judging whether a satellite network exists or not;
if the satellite network exists, connecting the satellite network for communication;
and if the satellite network does not exist, entering a local control strategy.
18. The method of claim 16, wherein the acquiring flight data comprises:
collecting image video data in the flight process, a measurement result of a target object with a preset position, current real-time positioning data and environmental operation of an operation environment.
19. The method of claim 18, wherein processing the flight data using an artificial intelligence operation algorithm to obtain a control result comprises:
identifying and processing the image video data and the measurement result by using the artificial intelligence operation algorithm to obtain the distance, the speed and the direction of a target object;
and processing the distance, the speed and the movement direction of the target object to obtain an avoidance control result.
20. The method of claim 18, wherein processing the flight data using an artificial intelligence operation algorithm to obtain a control result comprises:
performing three-dimensional reconstruction on the image video data and the measurement result to obtain reconstructed map data;
comparing pre-stored three-dimensional map data with the reconstructed map data to obtain a comparison result;
if the comparison result meets the preset deviation, performing alarm processing, and sending the comparison result to the cloud platform;
and updating the three-dimensional map data according to the instruction returned by the cloud platform.
21. The method of claim 18, wherein processing the flight data using an artificial intelligence operation algorithm to obtain a control result comprises:
identifying the image video data to obtain an identification result;
determining a current operation scene according to the identification result; carrying out similarity matching on the current operation scene and a preset operation scene to obtain a similarity matching result;
and performing operation management according to the similarity matching result.
22. The method of claim 18, wherein processing the flight data using an artificial intelligence operation algorithm to obtain a control result comprises:
fitting the current predicted positioning data according to the target flight path;
when the difference value between the current real-time positioning data and the current prediction positioning data is larger than a preset threshold value, carrying out alarm processing;
and when the difference value is smaller than the preset threshold value, determining target positioning navigation for subsequent flight positioning according to preset navigation sequencing.
23. The method of claim 22, wherein after determining the target position fix navigation for subsequent flight position fixes according to the preset navigation sequence, the method further comprises:
if the target positioning navigation is not determined, judging that the navigation signal is lost, and performing alarm processing;
the system is connected with the cloud platform, and the cloud platform is used for carrying out remote flight control;
and if the cloud platform is not connected, entering a local control strategy.
24. The method of claim 18, wherein processing the flight data using an artificial intelligence operation algorithm to obtain a control result comprises:
determining an operation judgment result based on the environment parameter and the current operation scene;
performing light control management for the process of acquiring image video data based on the environmental parameters;
determining elevation information based on the environment parameters, and correcting the current real-time positioning data by utilizing the elevation information;
and providing flight decision support for the unmanned aerial vehicle in the current working environment based on the environment parameters.
25. The method of claim 17, further comprising:
if the communication interruption of the data communication management module is judged, controlling the preset hovering duration;
when the early warning signal removing instruction is not received within the preset time, generating new flight control data according to the collected positioning data; and performing flight control according to the new flight control data;
judging whether the early warning signal is released every other preset flight period;
if the early warning signal removing instruction is not received, reconstructing a local three-dimensional map model;
controlling forced landing or return voyage based on the local three-dimensional map model and the three-dimensional map data;
and when the early warning signal removing instruction is received, continuing flying based on the navigation signal.
26. A flight control method is applied to a cloud platform, and comprises the following steps:
receiving a flight task, and planning an initial flight path according to the flight task;
identifying whether the initial flight path is in a no-fly zone or a honeycomb coverage blind spot, and adjusting the initial flight path based on the identification result to obtain a target flight path;
and sending the target flight path to a flight control device, so that the flight control device controls the unmanned aerial vehicle to fly according to the target flight path.
27. A flight control apparatus, the apparatus comprising: the first processor is used for executing an operating program stored in the memory so as to realize the following steps:
selecting a target communication network according to the selection sequence of the cellular network, the ad hoc network and the satellite network; receiving a target flight path and an artificial intelligence operation algorithm sent by a cloud platform based on the target communication network; controlling the unmanned aerial vehicle to execute a flight task according to the target flight track; acquiring flight data, and processing the flight data by using an artificial intelligence operation algorithm to obtain a control result; and utilizing the control result to carry out flight control on the unmanned aerial vehicle.
28. A cloud platform, the cloud platform comprising: the second processor is used for executing the running program stored in the second memory so as to realize the following steps:
receiving a flight task, and planning an initial flight path according to the flight task; identifying whether the initial flight path is in a no-fly zone or a honeycomb coverage blind spot, and adjusting the initial flight path based on the identification result to obtain a target flight path; and sending the target flight path to a flight control device so that the flight control device can control the unmanned aerial vehicle to fly according to the target flight path.
29. A storage medium on which a computer program is stored, for use in a flight control device or a cloud platform, which computer program, when executed by a processor, implements a method according to any one of claims 16-25 or 26.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110686698.7A CN115145302A (en) | 2021-06-21 | 2021-06-21 | Flight control method and device, cloud platform and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110686698.7A CN115145302A (en) | 2021-06-21 | 2021-06-21 | Flight control method and device, cloud platform and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115145302A true CN115145302A (en) | 2022-10-04 |
Family
ID=83404973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110686698.7A Pending CN115145302A (en) | 2021-06-21 | 2021-06-21 | Flight control method and device, cloud platform and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115145302A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115438063A (en) * | 2022-11-07 | 2022-12-06 | 深圳市道通智能航空技术股份有限公司 | Data processing method, data processing device and electronic equipment of cluster system |
| CN116193507A (en) * | 2023-04-26 | 2023-05-30 | 深圳市安信达存储技术有限公司 | Unmanned aerial vehicle storage control method and control system |
| CN117991757A (en) * | 2024-04-01 | 2024-05-07 | 成都纺织高等专科学校 | Unmanned aerial vehicle control method and system for heterogeneous airborne radar signals |
| CN117991757B (en) * | 2024-04-01 | 2024-06-07 | 成都纺织高等专科学校 | Unmanned aerial vehicle control method and system for heterogeneous airborne radar signals |
-
2021
- 2021-06-21 CN CN202110686698.7A patent/CN115145302A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115438063A (en) * | 2022-11-07 | 2022-12-06 | 深圳市道通智能航空技术股份有限公司 | Data processing method, data processing device and electronic equipment of cluster system |
| CN116193507A (en) * | 2023-04-26 | 2023-05-30 | 深圳市安信达存储技术有限公司 | Unmanned aerial vehicle storage control method and control system |
| CN116193507B (en) * | 2023-04-26 | 2023-11-03 | 深圳市安信达存储技术有限公司 | Unmanned aerial vehicle storage control method and control system |
| CN117991757A (en) * | 2024-04-01 | 2024-05-07 | 成都纺织高等专科学校 | Unmanned aerial vehicle control method and system for heterogeneous airborne radar signals |
| CN117991757B (en) * | 2024-04-01 | 2024-06-07 | 成都纺织高等专科学校 | Unmanned aerial vehicle control method and system for heterogeneous airborne radar signals |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11693402B2 (en) | Flight management system for UAVs | |
| US9959771B1 (en) | Unmanned aerial vehicle routing using real-time weather data | |
| EP3100127B1 (en) | A computer implemented system and method for providing robust communication links to unmanned aerial vehicles | |
| CN103592948B (en) | Unmanned plane flight collision avoidance method | |
| US20210407303A1 (en) | Systems and methods for managing energy use in automated vehicles | |
| US20190031346A1 (en) | System and method for controlling an unmanned vehicle and releasing a payload from the same | |
| EP2511888B1 (en) | Fire management system | |
| CN115145302A (en) | Flight control method and device, cloud platform and storage medium | |
| CN109417712A (en) | The parameter of unmanned automated spacecraft is managed based on manned aeronautical data | |
| CN111508281B (en) | Method for classifying and guiding ADS-B target by satellite-borne platform | |
| CN114253283A (en) | Control method of movable platform and movable platform | |
| US20220017221A1 (en) | Communication management device, communication management system, communication management method, and communication management program | |
| WO2018103716A1 (en) | Composite flight control method and system, aircraft | |
| Glaab et al. | Small unmanned aerial system (UAS) flight testing of enabling vehicle technologies for the UAS traffic management project | |
| CN112650271A (en) | Unmanned aerial vehicle over-the-horizon flight system and method based on star chain and 5G technology | |
| CN107839691A (en) | Control method for vehicle and device | |
| KR102475866B1 (en) | Surveillance method for unmanned aerial vehicle, and surveillance apparatus for the same | |
| RU2666091C1 (en) | Method for automated control of operation of an unmanned aircraft for flights in common airspace, combining all stages of the life cycle | |
| Radišić et al. | Challenges and solutions for urban UAV operations | |
| EP4152289A1 (en) | Computer system and method for providing wildfire evacuation support | |
| US11955020B2 (en) | Systems and methods for operating drone flights over public roadways | |
| Ivanytskyi et al. | UAS Flight Trajectory Optimization Algorithm Based on Operative Meteorological Information. | |
| Vidal-Franco et al. | Robust uas communications and loss of link operational impact | |
| CN106155089A (en) | A kind of unmanned aerial vehicle ground control system based on wireless telecommunications | |
| RU2789896C1 (en) | Intelligent system for automatic remote monitoring of the state of power transmission lines |
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 |