WO2022047709A1 - 更新限制区域数据的方法、装置、可移动平台和计算机存储介质 - Google Patents

更新限制区域数据的方法、装置、可移动平台和计算机存储介质 Download PDF

Info

Publication number
WO2022047709A1
WO2022047709A1 PCT/CN2020/113312 CN2020113312W WO2022047709A1 WO 2022047709 A1 WO2022047709 A1 WO 2022047709A1 CN 2020113312 W CN2020113312 W CN 2020113312W WO 2022047709 A1 WO2022047709 A1 WO 2022047709A1
Authority
WO
WIPO (PCT)
Prior art keywords
restricted area
data
movable platform
update
information
Prior art date
Application number
PCT/CN2020/113312
Other languages
English (en)
French (fr)
Inventor
邸健
李子健
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to CN202080031236.5A priority Critical patent/CN113853596A/zh
Priority to PCT/CN2020/113312 priority patent/WO2022047709A1/zh
Publication of WO2022047709A1 publication Critical patent/WO2022047709A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]

Definitions

  • the present invention generally relates to the technical field of data processing, and more particularly to a method, apparatus, removable platform and computer storage medium for updating restricted area data.
  • the selection of the update threshold of the flight restriction database is a fixed value set by experience, which is inflexible. Therefore, how to optimize the update threshold of the flight restriction database is a technical problem that needs to be solved at present.
  • one aspect of the present application provides a method for updating restricted area data, the method is applied to a mobile platform, and the method includes:
  • the update threshold of the current restricted area data is obtained, and the current state information includes one or more of the following information: the current moving speed of the movable platform, the current processing of the movable platform load, the restricted area query radius currently used by the mobile platform, the country where the mobile platform is currently located, the restricted area density in the area where the mobile platform is currently located, or the current onboard computing unit temperature of the mobile platform ;
  • movable platform includes:
  • processors for executing the program instructions stored in the memory, causing the processors to perform the following actions:
  • the update threshold value of the current restricted area data is obtained, and the current state information includes at least one of the following information: the current moving speed of the movable platform, the current processor load of the movable platform , the query radius of the restricted area currently used by the mobile platform, the country where the mobile platform is currently located, the restricted area density of the area where the mobile platform is currently located, or the current temperature of the onboard computing unit of the mobile platform;
  • Another aspect of the present application also provides a method for updating restricted area data, the method comprising:
  • the update threshold of the restricted area data of the movable platform is adjusted, and the state information includes one or more of the following information: the current moving speed of the movable platform, The current processor load of the mobile platform, the restricted area query radius currently used by the mobile platform, the country where the mobile platform is currently located, the restricted area density in the area where the mobile platform is currently located, or the mobile platform the current onboard compute unit temperature of the platform;
  • the restricted area data of the movable platform is updated.
  • Yet another aspect of the present application also provides an apparatus for updating restricted area data, the apparatus comprising:
  • a processor configured to execute the program instructions stored in the memory, so that the processor performs the following actions:
  • the update threshold of the restricted area data of the movable platform is adjusted, and the state information includes one or more of the following information: the current moving speed of the movable platform, The current processor load of the mobile platform, the restricted area query radius currently used by the mobile platform, the country where the mobile platform is currently located, the restricted area density in the area where the mobile platform is currently located, or the mobile platform the current onboard compute unit temperature of the platform;
  • the restricted area data of the movable platform is updated.
  • Yet another aspect of the present application provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the aforementioned method for updating restricted area data.
  • the method for updating restricted area data and the movable platform in the embodiments of the present application obtain the update threshold value of the current restricted area data based on the current state information of the movable platform, so as to adjust the update threshold value of the restricted area data in real time, so as to ensure the function of the restricted area. At the same time, it saves on-board computing power, and effectively avoids the problem of the mobile platform accidentally entering restricted movement areas (such as restricted flight areas).
  • FIG. 1 shows a schematic diagram of an aircraft in an embodiment of the present application
  • FIG. 2 shows a flowchart of a method for updating restricted area data in an embodiment of the present application
  • FIG. 3 shows a flowchart of a method for updating restricted area data in another embodiment of the present application
  • FIG. 4 shows a schematic diagram of an aircraft searching for a restricted flight area in another embodiment of the present application
  • FIG. 5 shows a schematic diagram of obtaining an update threshold based on a trained neural network in an embodiment of the present application
  • Fig. 6 shows the structure diagram of the recurrent RBF neural network in one embodiment of the present application
  • FIG. 7 shows a flowchart of a method for updating restricted area data in still another embodiment of the present application.
  • FIG. 8 shows a schematic block diagram of an apparatus for updating restricted area data in an embodiment of the present application.
  • the method for updating the database of restricted areas can be applied to movable platforms and any other applications involving restricted areas (such as restricted areas)
  • the movable platform may include an aircraft (eg, an unmanned aerial vehicle), a robot, an unmanned vehicle, and an unmanned boat, and the embodiment of the present application does not limit the specific application scenario.
  • the restricted area may be a restricted flying area, a no-flying area, or a restricted height area.
  • the restricted area may be a restricted activity area, a restricted activity area, or an area such as a restricted activity height.
  • the restricted area may be a restricted area, a restricted area, or an area such as a restricted driving height.
  • the restricted area can be a restricted area, a restricted area, and the like.
  • the method for updating the database of the restricted area in this embodiment of the present application may also be applied to the restricted area (for example, the restricted area) between two devices.
  • the update of the database includes updating the restricted area data through other devices such as terminals or servers, and the mobile platform obtains the updated restricted area data and stores the data, for example, the terminal updates the restricted area (for example, the restricted area) data through the server , and the movable platform obtains the updated restricted area (such as the restricted area) data through the terminal and stores it in the memory, or the aircraft updates the data of the restricted area (such as the restricted area) through the terminal, or the movable platform updates the restricted area through the server area (for example, restricted area) data, and the movable platform directly drives the server to obtain the updated restricted area data.
  • the terminal updates the restricted area (for example, the restricted area) data through the server
  • the movable platform obtains the updated restricted area (such as the restricted area) data through the terminal and stores it in the memory
  • the aircraft updates the data of the restricted area (such as the restricted area) through the terminal
  • the movable platform updates the restricted area through the server area (for example, restricted area) data
  • the movable platform directly
  • the restricted areas may include at least one of the following: (1) large civil aviation airports; (2) fixed-wing airports for general aviation; (3) heliports; (4) restricted areas in special areas (for example, restricted areas), such as Washington, Beijing, commercial areas, military areas, office areas, etc.; (5) other restricted areas (for example, restricted areas), such as temporary restricted areas (for example, restricted areas).
  • the case where the movable platform is an aircraft is mainly used as an example to describe the solution of the present application, but it can be understood that this is not intended to limit the application scenario of the present application.
  • FIG. 1 shows a schematic diagram of an aircraft 100 in one embodiment of the present application.
  • the aircraft 100 includes a carrier (ie, a frame) 102 and a load 104 .
  • a carrier ie, a frame
  • a load 104 e.g., unmanned aerial vehicles, also known as drones.
  • the load 104 may be located directly on the aircraft 100 without the need for the carrier 102 .
  • Aircraft 100 may include processor 101 , memory 102 , powertrain 106 , sensing system 108 , and communication system 110 . These components are interconnected by a bus system and/or other form of connection mechanism (not shown).
  • the powertrain 106 may include one or more rotating bodies, propellers, blades, engines, motors, wheels, bearings, magnets, nozzles.
  • the rotating body of the power mechanism may be a self-tightening rotating body, a rotating body assembly, or other rotating body power unit.
  • An aircraft may have one or more power mechanisms. All powertrains can be of the same type. Alternatively, one or more of the power mechanisms may be of a different type.
  • Powertrain 106 may be mounted on the aircraft by suitable means, such as by support elements (eg, drive shafts). The powertrain 106 may be installed in any suitable location on the aircraft 100, such as the top end, the lower end, the front end, the rear end, the side, or any combination thereof.
  • the powertrain 106 enables the aircraft to take off vertically from a surface, or land vertically on a surface, without requiring any horizontal movement of the aircraft 100 (eg, without taxiing on a runway).
  • powertrain 106 may allow aircraft 100 to preset positions and/or steering wheel in the air.
  • One or more of the power mechanisms 106 may be controlled independently of the other power mechanisms.
  • one or more power mechanisms 106 may be controlled simultaneously.
  • the aircraft 100 may have multiple horizontal rotations to track the lift and/or push of the target.
  • the horizontally oriented rotator can be actuated to provide the ability of the aircraft 100 to take off vertically, land vertically, and hover.
  • one or more of the horizontal rotating bodies may rotate clockwise, while the other one or more of the horizontal rotating bodies may rotate counterclockwise.
  • the rate of rotation of each horizontal rotator can be varied independently to effect lift and/or push operations caused by each rotator to adjust the spatial orientation, velocity, and/or acceleration of the aircraft 100 (eg, relative to up to three rotation and translation of degrees of freedom).
  • Sensing system 108 may include one or more sensors to sense spatial orientation, velocity, and/or acceleration (eg, rotation and translation with respect to up to three degrees of freedom) of aircraft 100 .
  • the one or more sensors include any of the sensors described above, including GPS sensors, motion sensors, inertial sensors, proximity sensors, or image sensors.
  • Sensing data provided by the sensing system 108 may be used to track the spatial orientation, velocity and/or acceleration of the target 100 (as described below, using a suitable processing unit and/or control unit).
  • the sensing system 108 may be used to collect data on the environment of the aircraft, such as climatic conditions, potential obstacles to be approached, locations of geographic features, locations of man-made structures, and the like.
  • the communication system 110 is capable of communicating with the terminal 112 having the communication system 114 via the wireless signal 116 .
  • Communication systems 110, 114 may include any number of transmitters, receivers, and/or transceivers for wireless communication.
  • the communication may be one-way communication, so that data can be sent from one direction.
  • one-way communication may include only aircraft 100 transmitting data to terminal 112, or vice versa.
  • One or more transmitters of communication system 110 may transmit data to one or more receivers of communication system 112, and vice versa.
  • the communication may be two-way communication, so that data may be transmitted between the aircraft 100 and the terminal 112 in both directions. Two-way communication includes that one or more transmitters of communication system 110 can transmit data to one or more receivers of communication system 114, and vice versa.
  • terminal 112 may provide control data to, and receive information from, one or more of aircraft 100 , carrier 102 , and payload 104 (eg position and/or motion information of aircraft, carrier or payload, payload sensing data, such as image data captured by a camera).
  • the terminal's control data may include instructions regarding position, movement, actuation, or control of the aircraft, carrier, and/or payload.
  • the control data may cause changes in the position and/or orientation of the aircraft (eg, by controlling the power mechanism 106 ), or cause movement of the carrier relative to the aircraft (eg, by controlling the carrier 102 ).
  • Terminal control data can lead to load control, such as controlling the operation of a camera or other image capture device (capturing still or moving images, zooming, turning on or off, switching imaging modes, changing image resolution, changing focus, changing depth of field, changing exposure time, changing the viewing angle or field of view).
  • the communication of the aircraft, carrier and/or payload may include information from one or more sensors (eg, sensing system 108 or payload 104).
  • the communication may include sensory information transmitted from one or more different types of sensors, such as GPS sensors, motion sensors, inertial sensors, proximity sensors, or image sensors.
  • the sensed information is about the position (eg, orientation, position), motion, or acceleration of the aircraft, carrier, and/or load.
  • the sensed information transmitted from the load includes the data captured by the load or the status of the load.
  • Terminal 112 transmits provided control data that may be used to track the status of one or more of aircraft 100 , carrier 102 , or payload 104 .
  • carrier 102 and payload 104 may each include a communication module for communicating with terminal 112 so that the terminal may communicate or track aircraft 100 , carrier 102 and payload 104 individually.
  • aircraft 100 may communicate with other remote devices in addition to terminal 112 , and terminal 112 may also communicate with other remote devices in addition to aircraft 100 .
  • the aircraft and/or terminal 112 may be in communication with another aircraft or a carrier or payload of another aircraft.
  • the additional remote device may be a second terminal or other computing device (eg, a computer, desktop, tablet, smartphone, or other mobile device) when desired.
  • the remote device may transmit data to the aircraft 100 , receive data from the aircraft 100 , transmit data to the terminal 112 , and/or receive data from the terminal 112 .
  • the remote device may be connected to the Internet or other telecommunications network to allow data received from aircraft 100 and/or terminal 112 to be uploaded to a website or server.
  • the movement of the aircraft, the movement of the carrier, and the movement of the load relative to a fixed reference (eg, the external environment), and/or relative to each other, may be controlled by the terminal.
  • the terminal may be a remote control terminal located remotely from the aircraft, carrier and/or load.
  • the terminal can be located on or attached to the support platform.
  • the terminal may be handheld or wearable.
  • the terminal may include a smartphone, tablet, desktop, computer, glasses, gloves, helmet, microphone, or any combination thereof.
  • the terminal may include a user interface such as a keyboard, mouse, joystick, touch screen or display. Any suitable user input may interact with the terminal, such as manual input of commands, voice control, gesture control, or position control (eg, through movement, position, or tilt of the terminal).
  • the aircraft 100 may include one or more memories 102 on which are stored a computer program executed by the processor, such as for storing a database for implementing an updated restricted area (eg, restricted area) database according to embodiments of the present application. Corresponding steps and program instructions in the method.
  • One or more computer program products may be included, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the volatile memory may include, for example, random access memory (RAM) and/or cache memory, or the like.
  • the non-volatile memory may include, for example, read only memory (ROM), hard disk, flash memory, and the like.
  • Aircraft 100 may include one or more processors 101, which may be central processing units (CPUs), graphics processing units (GPUs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or have data processing Other forms of processing units capable of and/or instruction execution capabilities, and may control other components in aircraft 100 to perform desired functions.
  • the processor can execute the program instructions stored in the memory, so as to execute the relevant steps in the method for updating the database of restricted areas (eg, restricted areas) according to the embodiments of the present application described below.
  • a processor can include one or more embedded processors, processor cores, microprocessors, logic circuits, hardware finite state machines (FSMs), digital signal processors (DSPs), or combinations thereof.
  • the processor includes a Field Programmable Gate Array (FPGA), or one or more ARM processors.
  • the drone geofencing system is a way to restrict the flight of drones.
  • the geofence system has two forms on some current UAVs: one is the UAV without a high-performance processor (no advanced functions such as forward-looking obstacle avoidance), and currently only the most advanced UAV can be realized.
  • a simple circular restricted area (such as a restricted area), the data storage format of this restricted area (such as a restricted area) is very simple, and the number of databases is also small; the other is a drone with a high-performance processor ( With advanced functions such as visual obstacle avoidance and tracking), complex polygonal restricted areas (such as flying restricted areas) are currently implemented on such products, and there are also a large number of restricted areas (such as flying restricted areas).
  • the function of the restricted area (such as the restricted area) of the UAV without a high-performance processor can only be realized on the microcontroller unit (MCU) where the flight control system (FC) is located.
  • the function of the restricted area (such as the restricted area) of the UAV of the device is mainly implemented on the AP (Application Processor), and only executed on the FC.
  • the airport restricted areas are mostly considered in the horizontal and vertical directions of the UAV.
  • the common forms of airport restricted areas are: There is an expanded area (also called restricted area (such as restricted flight area)) with a fixed height limit outside the no-fly zone that does not allow take-off at all.
  • the drone may enter restricted areas (such as restricted areas) or no-fly areas (hereinafter collectively referred to as restricted areas (e.g. restricted areas)).
  • restricted areas e.g. restricted areas
  • restricted areas e.g. restricted areas
  • the selection of the update threshold of the restricted area (such as the restricted area) database is based on a fixed value set by experience, without real-time optimization and adjustment based on the actual flight dynamics of the UAV. If the update threshold is set too small, it may cause problems. Frequent reading of the database in restricted areas (such as flight-restricted areas) wastes airborne computing power. If the update threshold is set too large, the drone may be close to the previous data boundary, and new restricted areas (such as restricted areas) may occur. Flying zone) data has not been updated, or has not started to be updated, which will cause the drone to enter the no-fly zone by mistake, causing unnecessary risks.
  • an embodiment of the present application provides a method for updating restricted area data, the method is applied to a movable platform, and the method includes: based on the current state information of the movable platform, obtaining the current restricted area data
  • the threshold is updated, and the current state information includes at least one of the following information: the current moving speed of the movable platform, the current processor load of the movable platform, the limited area query radius currently used by the movable platform, the The country where the mobile platform is currently located, the density of the restricted area in the area where the mobile platform is currently located, or the current temperature of the onboard computing unit of the mobile platform (such as an aircraft);
  • the position information of the movable platform and the current position information of the movable platform are used to determine the movement distance of the movable platform; based on the movement distance and the update threshold, it is determined whether to update the restricted area data.
  • the method for updating restricted area data in the embodiment of the present application obtains the update threshold of the current restricted area data based on the current state information of the movable platform, so as to adjust the update threshold of the restricted area data in real time, and moves the movable platform in the guaranteed restricted area. At the same time, it saves the on-board computing power and effectively avoids the problem of the mobile platform entering the forbidden area by mistake.
  • the execution subject may be a movable platform (for example, an aircraft), or a combination of software, hardware, or software and hardware.
  • a computer device implementing a method of updating a restricted area (eg, restricted area) database in a manner.
  • the method 200 for updating restricted area data includes the following steps S201 to S203 .
  • step S201 based on the current state information of the movable platform, the update threshold of the current restricted area data is acquired. Based on the current state information of the mobile platform, the update threshold of the data in the restricted area is adjusted in real time, which saves the on-board computing power while ensuring the function of the restricted area, and effectively avoids the problem of the mobile platform entering the forbidden area by mistake.
  • the current state information includes at least one of the following information: the current movement speed (eg, flight speed) of the movable platform (eg, the aircraft), the movement speed, the current processor load of the movable platform (eg, the aircraft), the The query radius of the restricted area (for example, the restricted area) currently used by the movable platform (for example, the aircraft), the country where the mobile platform (for example, the aircraft) is currently located, and the restricted area of the area where the mobile platform (for example, the aircraft) is currently located (such as restricted fly area) density or the current onboard computing unit temperature of the movable platform (eg aircraft).
  • other information that affects database updates of restricted areas (eg, restricted areas) of movable platforms (eg, aircraft) may also be included.
  • the update threshold for acquiring the current restricted area (such as a restricted area) database can be obtained by any suitable calculation method, for example, the current state information can be indicated by, for example, a table The mapping relationship between the multiple information in and the update threshold value, so as to obtain the update threshold value of the current restricted area (for example, the restricted area) database.
  • various machine learning algorithms can be used to learn to identify the mapping relationship between the current state information of a movable platform (such as an aircraft) and the update threshold. Once trained, the trained machine learning algorithm can be used by the movable platform (such as an aircraft). ) storage for obtaining update thresholds of the current restricted area (e.g.
  • machine learning algorithms may include supervised or unsupervised machine learning algorithms , including regression algorithms (eg, ordinary least squares regression), instance-based algorithms (eg, learning vector quantization), decision tree algorithms (eg, classification and regression trees), Bayesian algorithms (eg, Naive Bayes) , clustering algorithms (eg, k-means clustering), association rule learning algorithms (eg, a priori algorithms), artificial neural network algorithms (eg, perceptrons), deep learning algorithms (eg, deep Boltzmann machines, or deep neural networks), dimensionality reduction algorithms (eg, principal component analysis), ensemble algorithms (eg, stacked generalization), and/or other machine learning algorithms.
  • regression algorithms eg, ordinary least squares regression
  • instance-based algorithms eg, learning vector quantization
  • decision tree algorithms eg, classification and regression trees
  • Bayesian algorithms eg, Naive Bayes
  • clustering algorithms eg, k-means clustering
  • association rule learning algorithms eg, a priori algorithms
  • artificial neural network algorithms
  • the obtaining the update threshold of the current restricted area (for example, flight restricted area) database based on the current state information of the movable platform (for example, the aircraft) includes: The current state information is input into the trained neural network for processing, and the update threshold of the database of the current restricted area (for example, the restricted area) is obtained. For example, as shown in FIG.
  • the query radius of the currently used restricted area (for example, flying restricted area) is input into the trained neural network for processing, so as to obtain the updated threshold X of the current restricted area (for example, flying restricted area) database.
  • one or more pieces of the aforementioned current state information may be used as input, and input into the trained neural network for processing to obtain the update threshold of the current restricted area (eg, restricted flight area) database.
  • the updated threshold of the current restricted area (for example, restricted flight area) database can be obtained faster, more accurately and effectively through the trained neural network.
  • the flight speed of the aircraft may be the flight speed of the aircraft over the ground.
  • the wind speed will affect the speed of the aircraft over the ground. Therefore, in some examples, the flight speed of the aircraft may be the sum of the airspeed of the aircraft and the wind speed.
  • the trained neural network may be any suitable type of neural network, wherein, preferably, the trained neural network comprises a trained recurrent (RBF) neural network.
  • RBF neural network can directly use input and output data to approximate complex nonlinear relationship through simple topology structure.
  • the trained neural network includes a neural network with a feedback structure, such as a neural network with a feedback structure, more for example, a recurrent RBF neural network with a feedback structure, wherein, as shown in FIG.
  • the recurrent RBF neural network includes an input side, a hidden layer, an output layer, and a feedback connection, and the output layer feeds back output information to the hidden layer through the feedback connection to adjust the input information of the hidden layer.
  • the dynamic selection of the update radius has high requirements on the dynamic characteristics of the system.
  • This application adopts a recursive RBF neural network with a feedback structure.
  • the RBF neural network can directly use the input and output data to approximate complex nonlinear relationships through a simple topology structure.
  • the output information is fed back to the hidden layer to adjust the input of the hidden layer, so it has strong feedback, which can improve the dynamic characteristics of the system.
  • the neural network can be trained based on any suitable training method to obtain a trained neural network.
  • the following will describe the training process of the RBF neural network for outputting the database update threshold of restricted areas (eg, restricted areas), the training process is only an example, and other suitable training methods can also be applied to the present application.
  • Figure 6 shows a structure diagram of a recurrent RBF neural network, the network structure includes an input layer, a hidden layer and an output layer.
  • the input layer contains n neurons in total, and the output of each neuron is:
  • o i (t) corresponds to the output of the ith neuron at time t .
  • n is three
  • the three inputs are the current movement speed (eg, flight speed) of the movable platform such as the aircraft, the current movement speed of the CPU, and the search radius of the set restricted area (eg, the restricted area).
  • suitable movement data information eg, aircraft flight data information
  • aircraft flight data information may also be entered.
  • Each neuron of the hidden layer is not only connected to the neuron of the input layer, but also to each neuron of the output.
  • the output of each neuron of the hidden layer is:
  • c j (t) is the coordinate vector of the center point of the Gauss meter function of the jth neuron in the hidden layer at time t
  • b j (t) is the width of the Gauss meter function of the jth neuron in the hidden layer at time t
  • ⁇ ⁇ represents the Euclidean distance
  • ⁇ j (t) represents:
  • p j (t) is the feedback connection weight between the output neuron and the jth neuron in the hidden layer at time t
  • y(t-1) is the output of the output layer neuron at t-1.
  • the output layer has only one neuron, which can be expressed as:
  • ⁇ j (t) is the connection weight between the output neuron and the jth hidden layer neuron.
  • the error indicator of the network approximation is:
  • the gradient descent method is used to adjust the weights of the network.
  • the specific optimization and update methods are as follows:
  • ⁇ (0, 1) is the learning rate
  • the initial weight of the network takes a random value from 0 to 1.
  • the defined error metric is minimized.
  • the trained neural network is trained based on the movement data information (eg, the flight data information of the aircraft) of the movable platform (eg, the aircraft) in at least one historical movement process (eg, the historical flight process of the aircraft) , that is, the movement data information (such as the flight data information of the aircraft) of the movable platform (such as the aircraft) during at least one historical movement process is used as the training data set.
  • Flight data information can reflect the movement (such as flight) state information of a movable platform (such as an aircraft), and training a neural network based on these data can make the output value of the trained neural network more reliable, accurate and effective when in use .
  • the movement data information (such as the flight data information of the aircraft) of the movable platform (such as an aircraft) during at least one historical movement process can be obtained through a log (log) in the actual historical movement, that is, in the actual historical movement process.
  • the mobile data information (for example, the flight data information of the aircraft) is recorded and stored in the memory, and only needs to be retrieved from the memory when needed.
  • the movement data information (eg, the flight data information of the aircraft) includes first movement data information (eg, the first flight data information of the aircraft) and second movement data information (eg, the second flight data information of the aircraft)
  • the first movement data information (for example, the flight data information of the aircraft) includes at least one of the following information: when the movable platform (for example, the aircraft) triggers the database update of the restricted area (for example, the restricted area) during the historical movement process Movement speed (such as flight speed), CPU load when triggering database update of restricted area (such as flight control area), and search radius of restricted area (such as flight control area) when triggering database update of limited area (such as flight control area), The country where the database of the trigger restricted area (such as the restricted area) is updated, the density of the restricted area (e.g.
  • the restricted area in the current area when the database of the restricted area (e.g. the restricted area) is updated, the restricted area (e.g. the restricted area) is triggered.
  • the temperature of the onboard computing unit when the database is updated, the second movement data information (such as the flight data information of the aircraft) includes the movable platform (such as the aircraft) from the start of updating the database in a restricted area (such as a restricted area) to the completion of the update flight distance.
  • the first movement data information (for example, the first flight data information of the aircraft) is used as the input information of the input layer of the neural network, for example, the first movement data information (for example, the flight data information of the aircraft), the moving speed (for example, the flight speed) of the movable platform (for example, the aircraft) when the database of the restricted area (for example, the flight restriction area) is updated during the historical movement, the movement speed, the trigger restriction area ( For example, the CPU load of the restricted area (for example, the restricted area) database update and the search radius of the restricted area (for example, the restricted area) when the database is updated are triggered as the input information of the neural network input layer.
  • the second movement data information (such as the flight data information of the aircraft) is recorded after the database of the restricted area (such as the restricted area) is updated, for example, the record is updated from the beginning to the The completion of updating the moving distance of the movable platform (eg, drone), eg, the flying distance of the drone (ie, the distance flown).
  • the second movement data information (such as the flight data information of the aircraft) is used to correct the output result of the output layer of the neural network, that is, the movable data is based on the update from the restricted area (such as the restricted area) database to the completion of the update.
  • the moving distance of the platform (such as the aircraft), such as the flying distance of the drone, corrects the output result of the output layer of the neural network, and uses the moving distance, such as the flying distance of the drone, to correct the desired update threshold.
  • the desired update threshold should be that when the flight restriction database update of the database update position B is completed, the aircraft just flies to the limit with the database update position A as the circle point and the flight limit area search radius R as the radius.
  • the boundary of the flight data search circle if the position of the aircraft is within the flight limit data search circle of the database update position A when the update of the flight restriction database of database update position B is completed, it means that the output update threshold is smaller than the expected value, which will lead to an increase in the number of updates.
  • the position of the aircraft is outside the flight limit data search circle of database update position A, it means that the output update threshold is greater than the expected value, and the drone may be close to the previous data boundary (such as position Find the boundary of the circle in the flight restriction data at the database update position A), the new flight restriction data has not been updated, or has not started to be updated, which will cause the drone to accidentally enter the no-fly zone and cause unnecessary risks. Therefore, it is necessary to use the database to update the flight limit database of the position B to start updating the flight distance of the aircraft until the update is completed to correct the output value, so as to obtain the desired update threshold.
  • the training of the neural network is completed by using the data stored offline after the mobile platform (such as an aircraft) moves for many times, and the offline trained neural network (that is, the trained neural network) is integrated into the mobile platform (such as It is sufficient to obtain the update threshold in real time according to the current state information of the movable platform (such as the aircraft).
  • step S202 the movable platform is determined based on the position information of the movable platform and the current position information of the movable platform when the restricted area data was updated last time. movement distance.
  • the position information (eg GPS position) of the movable platform (eg aircraft) when the last time the restricted area (eg restricted area) database was started to be updated may be obtained based on sensors such as GPS sensors on the movable platform (eg aircraft) and Current location information (eg GPS position) of the movable platform (eg aircraft). For example, taking an aircraft as an example, the movement distance D of the aircraft is obtained by comparing the latitude and longitude coordinates of the two.
  • step S203 based on the movement distance and the update threshold, it is determined whether to update the restricted area data.
  • the current update threshold X is obtained by the method in the aforementioned step S201.
  • the database of the restricted area for example, the restricted area
  • the database of the restricted area is triggered to be updated, That is, a new restricted area (for example, a restricted area) database is triggered to update, so that the distance from the movable platform (for example, an aircraft) within the radius R of the restricted area (for example, a restricted area) is searched.
  • the restricted area (for example, the restricted area) data of the restricted area (for example, the restricted area) is updated to the database of the restricted area (for example, the restricted area), for example, the restricted area data of the restricted area within R meters around the aircraft is read into the memory medium spare.
  • the update threshold X is acquired in real time according to the method in the foregoing step S201.
  • the position information of the movable platform (such as the aircraft) when the database of the restricted area (such as the restricted area) was updated last time was the database update position A
  • the current position is the database update position B in FIG. 4, the movement distance D between the database update position A and the database update position B, and at the database update position B, the update of the database is obtained based on the current state information of the movable platform (such as an aircraft).
  • Threshold X at this time, the movement distance D is greater than the update threshold X, so a limited area (such as a restricted area) database update is triggered at the database update position B, that is, the database update position B is the center to find the surrounding R meters.
  • the restricted area (for example, the restricted area) data of the restricted area (for example, the restricted area) and update it to the database of the restricted area (for example, the restricted area), such as the restricted area (for example, the restricted area) database stored in the memory medium spare.
  • the movable platform (such as an aircraft) includes a first memory and a second memory, for example, the first memory includes a memory, and the second memory includes a hard disk, wherein the restricted area (for example, the restricted area) database storage
  • the restricted area for example, the restricted area
  • the data of the restricted area is data read from the second memory, for example, read from a structured database stored in the second memory.
  • it can also be the data read from the database of geohash organization, or it can also be the data read from other databases with restricted area (for example, restricted area) data.
  • the data of a restricted area (for example, a restricted area) within a certain range around a movable platform (for example, an aircraft) is read from the physical storage medium into the memory, so that the surrounding restricted area (for example, a restricted area) can be easily and quickly obtained from the memory.
  • the data of the restricted area and then judge the relative positional relationship between the UAV and the restricted area (such as the restricted area) in time, so as to control the moving trajectory, speed, height, etc. of the movable platform (such as the aircraft).
  • the search radius range R of a restricted area may be a preset search radius of a restricted area (eg, a restricted area), which may be reasonably set according to experience.
  • the restricted area (for example, the restricted area) data of the restricted area (for example, the restricted area) in this application may include, for example, the length, width, the restricted area (for example, the restricted area) Fly area) height, center position, shape, type and other data information.
  • the method of the present application also comprises the following steps:
  • the movable platform such as aircraft
  • the updated database of restricted areas such as restricted areas
  • obtain at least one restricted area around the movable platform (such as aircraft) and its surroundings (such as restricted areas) area) location relationship For example, the geometric relationship between a movable platform (eg, an aircraft) and a plurality of surrounding restricted areas (eg, a restricted flight zone) is obtained.
  • a target restricted area for example, a flying restricted area
  • the target restricted area for example, a flying restricted area
  • the closest restricted area e.g. flight restriction area
  • a target restricted area e.g. flight restriction area
  • the target restricted area is determined among multiple restricted areas (e.g. flight restriction area) area), the target restricted area (such as the restricted area) area will first affect the movement of the movable platform (such as the aircraft).
  • the movement parameters (for example, flight parameters) of the mobile platform (for example, the aircraft) are controlled, and the The movement parameters (eg, flight parameters) include at least one of a movement speed (eg, flight speed), a movement height (eg, flight height), and a movement direction (eg, flight direction).
  • the target restricted area for example, the flying restricted area
  • the restricted area for example, the flying restricted area
  • the movable platform for example, the aircraft
  • the aircraft controls the aircraft to perform deceleration logic, change the flight direction, reduce the flight altitude, etc. Therefore, it is avoided that the movable platform (eg, the aircraft) violates the rules of the restricted area (eg, the restricted flying area), resulting in unnecessary risks.
  • the movable platform such as an aircraft
  • the target restricted area such as a flight-restricted area
  • control the movement of the movable platform such as an aircraft. For example, taking the aircraft as an example, If the aircraft is located in the restricted flight area, if the flying height of the aircraft is higher than the restricted flying height in the restricted area, control the aircraft to lower its flying height below the restricted flying height. For another example, if the aircraft is in the restricted area, adjust the The heading (that is, the flight direction) of the aircraft to control the drone to fly outside the restricted flight area.
  • the aircraft is located outside the flight-restricted area and within a preset distance from the flight-restricted area, the aircraft is prevented from taking off or the aircraft is prohibited from flying in the direction of the flight-restricted area. Also for example, if the aircraft is in a no-fly zone, the aircraft is controlled to land on the ground. For another example, if the aircraft is located in a restricted flight zone, the aircraft is controlled to decelerate, or, after deceleration, the course is changed to prevent entering the no-fly zone by mistake.
  • the update threshold will be re-acquired in real time according to the aforementioned method, and a restricted area (eg, a restricted flight area) will be triggered when the aforementioned conditions are met. ) database update, and check the geometric relationship with the surrounding restricted areas (such as flight control areas) in real time according to the database of restricted areas (such as flight control areas), so as to implement reasonable movement strategies (such as flight strategies) and avoid movable platforms ( For example, the problem of straying into restricted areas (eg, restricted areas) arises.
  • the update threshold of the database is updated in real time, it can avoid the problem of affecting the airborne computing power caused by the update threshold being too small and the number of updates being too many, and avoid the mobile movement caused by the update threshold being too large. Platforms (such as aircraft) mistakenly intrude into no-movement areas, creating unnecessary risks. That is, the method of the present application can save on-board computing power while ensuring the normal function of restricted areas (eg, restricted flying areas).
  • restricted areas eg, restricted flying areas
  • the embodiment of the present application also provides a movable platform, the movable platform may include an aircraft (such as an unmanned aerial vehicle), a robot, an unmanned vehicle, and an unmanned ship, and the movable platform may include a power mechanism, and the power mechanism is used for moving the movable platform; a memory for storing executable program instructions; one or more processors for executing the program instructions stored in the memory so that the processors perform the foregoing descriptions Relevant steps of method 200 of updating restricted area data.
  • an aircraft such as an unmanned aerial vehicle
  • the movable platform may include a power mechanism, and the power mechanism is used for moving the movable platform
  • a memory for storing executable program instructions
  • one or more processors for executing the program instructions stored in the memory so that the processors perform the foregoing descriptions Relevant steps of method 200 of updating restricted area data.
  • the aircraft 100 includes one or more processors 101 for executing the program instructions stored in the memory, so that the processors execute the foregoing Relevant steps of the method 200 for updating restricted area data in an embodiment.
  • the movable platform (eg, aircraft) 100 includes one or more processors 101 for executing the program instructions stored in the memory, causing the processors to perform the following actions: based on the movable platform (for example, the current state information of the aircraft), to obtain the update threshold of the current restricted area (such as the restricted area) database, the current state information includes at least one of the following information: the current moving speed of the movable platform (such as the aircraft) (such as flight speed) moving speed, the current processor load of the movable platform (such as the aircraft), the restricted area (such as the aircraft) currently used by the movable platform (such as the aircraft) query radius, the movable platform (such as the aircraft) For example, the country where the mobile platform (such as the aircraft) is currently located, the density of the restricted area (such as the restricted area) in the area where the mobile platform (such as the aircraft) is currently located, or the current temperature of the onboard computing unit of the mobile platform (such as the aircraft); based on the previous The position information of the movable platform
  • the processor 101 is configured to obtain an update threshold of the current restricted area (eg, flight restricted area) data based on the current state information of the movable platform (eg, the aircraft), including:
  • the current state information of the movable platform (eg, aircraft) is input into the trained neural network for processing, and the update threshold of the current restricted area (eg, restricted flight area) data is obtained.
  • the update threshold of the current restricted area eg, restricted flight area
  • the trained neural network includes a trained RBF neural network.
  • the trained neural network includes a neural network with a feedback structure, wherein the neural network includes an input side, a hidden layer, an output layer, and a feedback connection, and the output layer is connected through the feedback The output information is fed back to the hidden layer to adjust the input information of the hidden layer.
  • the trained neural network is trained based on movement data information (eg, flight data information of the aircraft) of the movable platform (eg, aircraft) during at least one historical movement process.
  • movement data information eg, flight data information of the aircraft
  • movable platform eg, aircraft
  • the movement data information includes first movement data information (eg, flight data information of an aircraft) and second movement data information (eg, flight data information of an aircraft), and the first movement data information (eg, flight data information of an aircraft)
  • a movement data information (such as the flight data information of the aircraft) includes at least one of the following information: the movement speed ( Such as flight speed) moving speed, CPU load when triggering restricted area (such as flight control area) data update and triggering limited area (such as flight control area) when data update is restricted area (such as flight control area) area search radius, trigger
  • the first movement data information (for example, the flight data information of the aircraft) is used as the input information of the input layer of the neural network
  • the second movement data information is used as the input information of the input layer of the neural network.
  • the flight data information of the aircraft is used to correct the output results of the output layer of the neural network.
  • the processor 101 is further configured to determine whether to update the data of the restricted area (for example, a restricted area) based on the movement distance and the update threshold, including:
  • a restricted area for example, a restricted area
  • searches for a restricted area for example, a restricted area
  • the restricted area (for example, a restricted area) data is updated to the database of the restricted area (for example, a restricted area).
  • the movable platform (eg, aircraft) includes a first memory and a second memory, eg, the first storage includes a memory and the second storage includes a hard disk, wherein the restricted area (eg, restricted area) database Stored in the first memory, the data of the restricted area (for example, the restricted area) is the data read from the second memory, for example, read from the structured database stored in the second memory
  • the restricted area eg, restricted area
  • the restricted area is the data read from the second memory, for example, read from the structured database stored in the second memory
  • the processor is also used to:
  • the movable platform such as the aircraft
  • the updated data of the restricted area such as a restricted area
  • obtain at least one restricted area such as a restricted area around the movable platform (such as an aircraft) and its surroundings the geometric relationship of the area
  • a target restricted area for example, a flying restricted area
  • the target restricted area for example, a flying restricted area
  • the at least one restricted area for example, a flying restricted area
  • the closest restricted area e.g. restricted area
  • the flight parameters of the movable platform are controlled, and the flight parameters at least include the moving speed ( For example, flight speed) at least one of moving speed, flight altitude and flight direction.
  • the movable platform (eg, an aircraft) of the embodiment of the present application can be used to execute the aforementioned method for updating data of a restricted area (eg, a restricted area), it also has the aforementioned advantages.
  • the movable platform (such as an aircraft) can save on-board computing power while ensuring the function of a restricted area (such as a restricted flight area).
  • the method for updating restricted area data of the present application includes the following steps:
  • step S701 when the state information of the movable platform changes, the update threshold of the restricted area data of the movable platform is adjusted, and the state information includes one or more of the following information: the movable platform The current moving speed of the mobile platform, the current processor load of the mobile platform, the query radius of the restricted area currently used by the mobile platform, the country where the mobile platform is currently located, and the restricted area density of the area where the mobile platform is currently located or the current onboard computing unit temperature of the movable platform.
  • adjusting the update threshold of the restricted area data of the movable platform includes: when at least one state information of the movable platform is detected by a sensor When a change occurs, prompt information is output, wherein the prompt information at least includes data information of the changed state information; the display device of the movable platform acquires the prompt information and displays the prompt information on the display interface.
  • the prompt information may be presented on the display interface in the form of text symbols, and may also be displayed by highlighting, blinking, additional symbols, differentiated shading color display, or differentiated font color display.
  • the prompt information can also be presented in the form of sound, for example. Through the prompt information, the user can be reminded of the type of state information that has changed, and the data information of the changed state information, such as specific values, so that the user can adjust the update threshold according to the change.
  • adjusting the update threshold of the restricted area data of the movable platform includes: acquiring an operation instruction input by the user, where the operation instruction is used to make the setting window Displayed on the display interface of the display device, for example, there is a first button on the display interface of the display device, and the user can use one or more of the keyboard, trackball, mouse, microphone, touch screen, etc., or other control buttons.
  • the input device inputs a corresponding operation instruction; based on the operation instruction, the display device is controlled to display a setting window on the display interface, and the user can input the corresponding changed state information through the setting window;
  • the setting instruction is used to set the changed state information as the data information of the changed state information; based on the data information of the changed state information, the update threshold of the restricted area data of the movable platform is adjusted.
  • adjusting the update threshold of the restricted area data of the movable platform includes: inputting the data information of the changed state information of the movable platform into the trained A good neural network for processing to obtain update thresholds for data in restricted areas of the movable platform.
  • the trained neural network includes a trained RBF neural network.
  • the trained neural network can be any suitable network, and the trained neural network includes a neural network with a feedback structure, wherein the neural network includes an input side, a hidden layer, an output layer, and a feedback connection, so The output layer feeds back output information to the hidden layer through the feedback connection to adjust the input information of the hidden layer.
  • the neural network can be trained based on any suitable method, for example, the trained neural network is trained based on the movement data information of the movable platform in at least one historical movement process.
  • the mobile movement data information includes first movement movement data information and second movement movement data information
  • the first movement movement data information includes at least one of the following information: a restricted area is triggered during the historical movement of the mobile platform Movement speed when data update is triggered, CPU load when triggering restricted area data update, and search radius of restricted area when triggering restricted area data update, country when triggering restricted area data update, restriction of current region when triggering restricted area data update
  • the density of the area, the temperature of the onboard computing unit when the update of the restricted area data is triggered, and the second movement data information includes the moving distance of the movable platform from the start of the update of the restricted area data to the completion of the update.
  • the first mobile data information is used as the input information of the input layer of the neural network
  • the second mobile data information is used for the output result of the neural network output layer. Correction.
  • step S701 the restricted area data of the movable platform is updated according to the adjusted update threshold.
  • updating the restricted area data of the movable platform according to the adjusted update threshold includes: based on the position information of the movable platform and the movable platform based on the last time when the restricted area data was updated.
  • the current position information of the mobile platform to determine the movement distance of the movable platform; based on the movement distance and the adjusted update threshold, update the restricted area data, for example, when the movement distance is greater than or equal to the adjusted
  • the update threshold is set, trigger the update of the restricted area data, so as to update the restricted area data of the restricted area with the distance from the movable platform within the restricted area search radius to the movable platform in the restricted area database.
  • the execution subject can be a movable platform such as an aircraft, or a movable platform such as an aircraft can directly obtain the updated restricted area data from other external devices and update it into its memory, and the method for updating the restricted area data is: Implemented by other external devices, and iteratively updated in real time through the external device row.
  • the update threshold of the restricted area data of the movable platform is adjusted, so as to adjust the update threshold of the restricted area data in real time. While the area restricts the movement of the movable platform, it saves the on-board computing power and effectively avoids the problem of the movable platform entering the forbidden area by mistake.
  • the on-board computing power also refers to the computing power of the hardware carried by the mobile platform itself, such as a processor.
  • the apparatus may be the aforementioned movable platform, or may also be other external devices.
  • a device 800 for updating restricted area data includes one or more memories 802, one or more processors 801, a display device 803, etc., and these components are connected through a bus system and/or other forms of connection mechanisms (not shown). shown) interconnect. It should be noted that the components and structures of the apparatus 800 shown in FIG. 8 are only exemplary and not restrictive, and the apparatus 800 may also have other components and structures as required.
  • the memory 802 is used for storing various data and executable program instructions generated during the movement of the relevant movable platform, for example, for storing various application programs or algorithms for realizing various specific functions.
  • One or more computer program products may be included, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the volatile memory may include, for example, random access memory (RAM) and/or cache memory, or the like.
  • the non-volatile memory may include, for example, read only memory (ROM), hard disk, flash memory, and the like.
  • Processor 801 may be a central processing unit (CPU), graphics processing unit (GPU), application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other form of processing with data processing capabilities and/or instruction execution capabilities unit, and may control other components in device 800 to perform desired functions.
  • a processor can include one or more embedded processors, processor cores, microprocessors, logic circuits, hardware finite state machines (FSMs), digital signal processors (DSPs), graphics processing units (GPUs), or the like The combination.
  • FSMs hardware finite state machines
  • DSPs digital signal processors
  • GPUs graphics processing units
  • the processor 801 is configured to execute the program instructions stored in the memory, so that the processor performs the following actions:
  • the update threshold of the restricted area data of the movable platform is adjusted, and the state information includes one or more of the following information: the current moving speed of the movable platform, The current processor load of the mobile platform, the restricted area query radius currently used by the mobile platform, the country where the mobile platform is currently located, the restricted area density in the area where the mobile platform is currently located, or the mobile platform the current onboard compute unit temperature of the platform;
  • the restricted area data of the movable platform is updated.
  • the processor 801 is further configured to: output prompt information when at least one state information of the movable platform is detected by the sensor to change, wherein the prompt information at least includes the changed state information
  • the sensor can be a plurality of sensors on the movable platform, and when the device is an external device independent of the movable platform, it can obtain the status information of the movable platform from the sensors of the movable platform.
  • the apparatus 800 further includes an output device that can output various information (eg, images or sounds) to the outside (eg, a user), and may include one or more of a display device, a speaker, and the like.
  • an output device that can output various information (eg, images or sounds) to the outside (eg, a user), and may include one or more of a display device, a speaker, and the like.
  • the apparatus 800 further includes a display apparatus 803, configured to acquire the prompt information and display the prompt information on the display interface.
  • the device 800 further includes a communication interface (not shown) for communication between the various components in the device 800 and between the various components of the device 800 and other devices outside the system, for example, when the device is When the external device is used, it can communicate with the movable platform through the communication interface, so that the information can be exchanged between the two.
  • a communication interface (not shown) for communication between the various components in the device 800 and between the various components of the device 800 and other devices outside the system, for example, when the device is When the external device is used, it can communicate with the movable platform through the communication interface, so that the information can be exchanged between the two.
  • the communication interface is an interface that can be any currently known communication protocol, such as a wired interface or a wireless interface, wherein the communication interface can include one or more serial ports, USB interfaces, Ethernet ports, WiFi, wired networks, DVI interfaces, device Integrated interconnect modules or other suitable various ports, interfaces, or connections.
  • Device 800 may also access wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G, 5G, or a combination thereof.
  • the communication interface receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel.
  • the communication interface further includes a Near Field Communication (NFC) module to facilitate short-range communication.
  • the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • the device 800 also includes an input device (not shown) that may be a device used by a user to input instructions, and may include one or more of a keyboard, trackball, mouse, microphone, touch screen, and the like, or An input device consisting of other control buttons.
  • an input device may be a device used by a user to input instructions, and may include one or more of a keyboard, trackball, mouse, microphone, touch screen, and the like, or An input device consisting of other control buttons.
  • the processor 801 is further configured to: acquire an operation instruction input by the user, the operation instruction is used to display the setting window on the display interface of the display device; based on the operation instruction, control the display device to display the display interface on the display interface A setting window is displayed on the screen; the setting instruction input by the user is obtained, and the setting instruction is used to set the changed state information as the data information of the changed state information; based on the data information of the changed state information, adjust the Update threshold for restricted area data for removable platforms.
  • the processor 801 is configured to update the restricted area data of the movable platform according to the adjusted update threshold, including:
  • the restricted area data is updated based on the movement distance and the adjusted update threshold.
  • the processor 801 is configured to adjust the update threshold of the restricted area data of the movable platform when the state information of the movable platform changes, including:
  • the data information of the changed state information of the movable platform is input into the trained neural network for processing, and the update threshold of the restricted area data of the movable platform is obtained.
  • the trained neural network includes a trained RBF neural network.
  • the trained neural network includes a neural network with a feedback structure, wherein the neural network includes an input side, a hidden layer, an output layer, and a feedback connection, and the output layer is connected through the feedback The output information is fed back to the hidden layer to adjust the input information of the hidden layer.
  • the trained neural network is trained based on movement data information of the movable platform during at least one historical movement process.
  • the mobile mobile data information includes first mobile mobile data information and second mobile mobile data information, and the first mobile mobile data information includes at least one of the following information: triggered during the historical movement of the mobile platform Movement speed when the restricted area data update is triggered, CPU load when the restricted area data update is triggered, and search radius of the restricted area when the restricted area data update is triggered, the country where the restricted area data update is triggered, and the current region when the restricted area data update is triggered.
  • the density of the restricted area, the temperature of the onboard computing unit when the update of the restricted area data is triggered, and the second movement data information includes the moving distance of the movable platform from the start of the restricted area data update to the completion of the update.
  • the first mobile data information is used as the input information of the input layer of the neural network
  • the second mobile data information is used to perform the output results of the output layer of the neural network
  • the processor is configured to update the restricted area data based on the movement distance and the adjusted update threshold, including: when the movement distance is greater than or equal to the update threshold, triggering an update of the and the restricted area data, so as to update the restricted area data of the restricted area whose distance from the movable platform is within the restricted area search radius to the restricted area database of the movable platform.
  • the apparatus in the embodiment of the present application is used to implement the aforementioned method, and therefore also has the advantages of the aforementioned method.
  • the update threshold of the restricted area data of the movable platform is adjusted to adjust the update threshold in real time.
  • the update threshold of the restricted area data not only guarantees the restricted area's function of restricting the movement of the movable platform, but also saves the on-board computing power, and effectively avoids the problem of the movable platform entering the forbidden area by mistake.
  • the embodiments of the present application also provide a computer storage medium, such as a computer-readable storage medium, on which a computer program is stored.
  • a computer storage medium such as a computer-readable storage medium
  • One or more computer program instructions may be stored on the computer storage medium, and the processor may execute the program instructions stored in the memory to implement the functions (implemented by the processor) in the embodiments of the present application described herein and/or or other desired functions, for example, to perform the corresponding steps of the methods 200 and 700 for updating restricted area data according to embodiments of the present application
  • various application programs and various data may also be stored in the computer-readable storage medium, such as Various data used and/or generated by the application, etc.
  • the computer-readable storage medium may include, for example, a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, a read only memory (ROM), an erasable programmable read only memory (EPROM), a portable compact disk read only memory (CD-ROM), USB memory, or any combination of the above storage media.
  • the computer-readable storage medium can be any combination of one or more computer-readable storage media.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or May be integrated into another device, or some features may be omitted, or not implemented.
  • Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules according to the embodiments of the present application.
  • DSP digital signal processor
  • the present application can also be implemented as a program of apparatus (eg, computer programs and computer program products) for performing part or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such signals may be downloaded from Internet sites, or provided on carrier signals, or in any other form.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

提供一种更新限制区域数据的方法、装置、可移动平台和计算机存储介质，该更新限制区域数据的方法应用于可移动平台，包括：基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值（S201），当前状态信息包括以下信息中的一种或多种：可移动平台的当前移动速度、可移动平台的当前处理器负载、可移动平台当前所用的限制区域查询半径、可移动平台当前所在国家、可移动平台当前所在地区的限制区域密度或可移动平台的当前机载计算单元温度；基于前一次开始更新限制区域数据时可移动平台的位置信息以及可移动平台的当前位置信息，确定可移动平台的运动距离（S202）；基于运动距离和更新阈值，确定是否更新限制区域数据（S203）。

Description

更新限制区域数据的方法、装置、可移动平台和计算机存储介质
说明书
技术领域
本发明总地涉及数据处理技术领域，更具体地涉及一种更新限制区域数据的方法、装置、可移动平台和计算机存储介质。
背景技术
在一些无人机上，因为算力与内存的限制，都没有一次性把所有限飞数据读入内存，而是在飞行过程中，根据无人机当前的位置将无人机周围的限飞数据读入内存。因为载入内存的只是无人机周围的限飞数据，所以在执行限飞判断的过程中，随着飞行距离的扩大，当无人机飞离上一次的更新位置一段距离后，需要重新读取无人机周围的限飞数据并将其更新到内存中。
常规技术中，限飞数据库的更新阈值的选择是依靠经验设置的固定值，不灵活，因此如何对限飞数据库的更新阈值进行优化是目前需要解决的技术问题。
发明内容
为了解决上述问题中的至少一个而提出了本申请。具体地，本申请一方面提供一种更新限制区域数据的方法，所述方法应用于可移动平台，所述方法包括：
基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，当前状态信息包括以下信息中的一种或多种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；
基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据。
本申请再一方面提供一种可移动平台，所述可移动平台包括：
动力机构，所述动力机构用于使所述可移动平台移动；
存储器，用于存储可执行的程序指令；
一个或多个处理器，用于执行所述存储器中存储的所述程序指令，使得所述处理器执行以下动作：
基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，当前 状态信息包括以下信息中的至少一种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；
基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据。
本申请另一方面还提供一种更新限制区域数据的方法，所述方法包括：
当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，所述状态信息包括以下信息中的一种或多种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据。
本申请又一方面还提供一种更新限制区域数据的装置，所述装置包括：
存储器，用于存储可执行的程序指令；
处理器，用于执行所述存储器中存储的所述程序指令，使得所述处理器执行以下动作：
当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，所述状态信息包括以下信息中的一种或多种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据。
本申请又一方面提供一种计算机存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现前述的更新限制区域数据的方法。
本申请实施例中的更新限制区域数据的方法和可移动平台，基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，以实时调整限制区域数据的更新阈值，在保障限制区域功能的同时，节省了机载算力，并有效避免可移动平台误闯限制移动区(例如限飞区)的问题出现。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1示出了本申请一个实施例中的飞行器的示意图；
图2示出了本申请一个实施例中的更新限制区域数据的方法的流程图；
图3示出了本申请另一个实施例中的更新限制区域数据的方法的流程图；
图4示出了本申请另一个实施例中的飞行器查找限飞区的示意图；
图5示出了本申请一个实施例中的基于已训练的神经网络获取更新阈值的示意图；
图6示出了本申请一个实施例中的递归RBF神经网络的结构图；
图7示出了本申请再一个实施例中的更新限制区域数据的方法的流程图；
图8示出了本申请一个实施例中的更新限制区域数据的装置的示意性框图。
具体实施方式
为了使得本申请的目的、技术方案和优点更为明显，下面将参照附图详细描述根据本申请的示例实施例。显然，所描述的实施例仅仅是本申请的一部分实施例，而不是本申请的全部实施例，应理解，本申请不受这里描述的示例实施例的限制。
在下文的描述中，给出了大量具体的细节以便提供对本申请更为彻底的理解。然而，对于本领域技术人员而言显而易见的是，本申请可以无需一个或多个这些细节而得以实施。在其他的例子中，为了避免与本申请发生混淆，对于本领域公知的一些技术特征未进行描述。
应当理解的是，本申请能够以不同形式实施，而不应当解释为局限于这里提出的实施例。相反地，提供这些实施例将使公开彻底和完全，并且将本申请的范围完全地传递给本领域技术人员。
在此使用的术语的目的仅在于描述具体实施例并且不作为本申请的限制。在此使用时，单数形式的“一”、“一个”和“所述/该”也意图包括复数形式，除非上下文清楚指出另外的方式。还应明白术语“组成”和/或“包括”，当在该说明书中使用 时，确定所述特征、整数、步骤、操作、元件和/或部件的存在，但不排除一个或更多其它的特征、整数、步骤、操作、元件、部件和/或组的存在或添加。在此使用时，术语“和/或”包括相关所列项目的任何及所有组合。
为了彻底理解本申请，将在下列的描述中提出详细的结构和方法，以便阐释本申请提出的技术方案。本申请的可选实施例详细描述如下，然而除了这些详细描述外，本申请还可以具有其他实施方式。
下面结合附图，对本申请的更新限制区域(例如限飞区)数据库的方法和可移动平台进行详细说明。在不冲突的情况下，下述的实施例及实施方式中的特征可以相互组合。
需要说明的是，本申请实施例提供的更新限制区域(例如限飞区、限高区等)数据库的方法，可以应用于可移动平台以及其他任意涉及限制区域(例如限飞区)区的应用场景中，例如，可移动平台可以包括飞行器(例如无人机)、机器人、无人车、无人船，本申请实施例对具体的应用场景不做限制。相应的，当可移动平台为飞行器，则限制区域可以是限飞区、禁飞区、或者限高区等。当可移动平台为机器人，则限制区域可以是限制活动区域、禁止活动区域、或者限制活动高度等区域等。当可移动平台为无人车，则限制区域可以是限行区、禁行区、或者限制行驶高度等区域等。当可移动平台为无人船，则限制区域可以是限行区、禁行区等。
需要说明的是在网络带宽高于阈值带宽的前提下，本申请实施例的更新限制区域(例如限飞区)数据库的方法还可以适用于两个设备之间的限制区域(例如限飞区)数据库的更新，包括通过其他的设备例如终端或服务器更新限制区域数据，而可移动平台获取该更新的限制区域数据，并存储该数据，例如，终端通过服务器更新限制区域(例如限飞区)数据，而可移动平台通过终端获取该更新的限制区域(例如限飞区)数据，并存储至内存，或者，飞行器通过终端更新限制区域(例如限飞区)数据，或者可移动平台通过服务器更新限制区域(例如限飞区)数据，而可移动平台直接动服务器获取该更新后的限制区域数据。
需要说明的是，本文中限制区域(例如限飞区)可以包括以下至少一种：(1)民航大型机场；(2)通航固定翼机场；(3)直升机机场；(4)特殊区域限制区域(例如限飞区)，比如华盛顿、北京、商业区、军事区、办公区等；(5)其他限制区域(例如限飞区)，例如临时限制区域(例如限飞区)。
本申请实施例中主要以可移动平台为飞行器的情况为例，对本申请的方案进 行描述，但可以理解的是，这并不意欲对本申请的应用场景构成限制。
在一个示例中，图1示出了本申请一个实施例中的飞行器100的示意图。该飞行器100包括承载体(也即机架)102及负载104。本领域技术人员应该了解，本文所描述的任何关于飞行器的实施例适用于任何飞行器(如无人飞行器，也称无人机)。在某些实施例中，负载104可以直接位于飞行器100上，而不需要承载体102。飞行器100可以包括处理器101、存储器102、动力机构106，传感系统108、以及通讯系统110。这些组件通过总线系统和/或其它形式的连接机构(未示出)互连。
动力机构106可以包括一个或者多个旋转体、螺旋桨、桨叶、引擎、电机、轮子、轴承、磁铁、喷嘴。例如，所述动力机构的旋转体可以是自紧固(self-tightening)旋转体、旋转体组件、或者其它的旋转体动力单元。飞行器可以有一个或多个动力机构。所有的动力机构可以是相同的类型。可选的，一个或者多个动力机构可以是不同的类型。动力机构106可以通过合适的手段安装在飞行器上，如通过支撑元件(如驱动轴)。动力机构106可以安装在飞行器100任何合适的位置，如顶端、下端、前端、后端、侧面或者其中的任意结合。
在某些实施例中，动力机构106能够使飞行器垂直地从表面起飞，或者垂直地降落在表面上，而不需要飞行器100任何水平运动(如不需要在跑道上滑行)。可选的，动力机构106可以允许飞行器100在空中预设位置和/或方向盘旋。一个或者多个动力机构106在受到控制时可以独立于其它的动力机构。可选的，一个或者多个动力机构106可以同时受到控制。例如，飞行器100可以有多个水平方向的旋转体，以追踪目标的提升及/或推动。水平方向的旋转体可以被致动以提供飞行器100垂直起飞、垂直降落、盘旋的能力。在某些实施例中，水平方向的旋转体中的一个或者多个可以顺时针方向旋转，而水平方向的旋转体中的其它一个或者多个可以逆时针方向旋转。例如，顺时针旋转的旋转体与逆时针旋转的旋转体的数量一样。每一个水平方向的旋转体的旋转速率可以独立变化，以实现每个旋转体导致的提升及/或推动操作，从而调整飞行器100的空间方位、速度及/或加速度(如相对于多达三个自由度的旋转及平移)。
传感系统108可以包括一个或者多个传感器，以感测飞行器100的空间方位、速度及/或加速度(如相对于多达三个自由度的旋转及平移)。所述一个或者多个传感器包括前述描述的任何传感器，包括GPS传感器、运动传感器、惯性传感器、近程传感器或者影像传感器。传感系统108提供的感测数据可以用于追踪目标 100的空间方位、速度及/或加速度(如下所述，利用适合的处理单元及/或控制单元)。可选的，传感系统108可以用于采集飞行器的环境的数据，如气候条件、要接近的潜在的障碍、地理特征的位置、人造结构的位置等。
通讯系统110能够实现与具有通讯系统114的终端112通过无线信号116进行通讯。通讯系统110、114可以包括任何数量的用于无线通讯的发送器、接收器、及/或收发器。所述通讯可以是单向通讯，这样数据可以从一个方向发送。例如，单向通讯可以包括，只有飞行器100传送数据给终端112，或者反之亦然。通讯系统110的一个或者多个发送器可以发送数据给通讯系统112的一个或者多个接收器，反之亦然。可选的，所述通讯可以是双向通讯，这样，数据可以在飞行器100与终端112之间在两个方向传输。双向通讯包括通讯系统110的一个或者多个发送器可以发送数据给通讯系统114的一个或者多个接收器，及反之亦然。
在某些实施例中，终端112可以向飞行器100、承载体102及负载104中的一个或者多个提供控制数据，并且从飞行器100、承载体102及负载104中的一个或者多个中接收信息(如飞行器、承载体或者负载的位置及/或运动信息，负载感测的数据，如相机捕获的影像数据)。在某些实施例中，终端的控制数据可以包括关于位置、运动、致动的指令，或者对飞行器、承载体及/或负载的控制。例如，控制数据可以导致飞行器位置及/或方向的改变(如通过控制动力机构106)，或者导致承载体相对于飞行器的运动(如通过对承载体102的控制)。终端的控制数据可以导致负载控制，如控制相机或者其它影像捕获设备的操作(捕获静止或者运动的影像、变焦、开启或关闭、切换成像模式、改变影像分辨率、改变焦距、改变景深、改变曝光时间、改变可视角度或者视场)。在某些实施例中，飞行器、承载体及/或负载的通讯可以包括一个或者多个传感器(如传感系统108或者负载104)发出的信息。所述通讯可以包括从一个或者多个不同类型的传感器(如GPS传感器、运动传感器、惯性传感器、近程传感器或者影像传感器)传送的感应信息。所述感应信息是关于飞行器、承载体及/或负载的位置(如方向、位置)、运动、或者加速度。从负载传送的感应信息包括负载捕获的数据或者负载的状态。终端112传送提供的控制数据可以用于追踪飞行器100、承载体102或者负载104中一个或者多个的状态。可选的或者同时地，承载体102及负载104每一个都可以包括通讯模块，用于与终端112通讯，以便终端可以单独地通讯或者追踪飞行器100、承载体102及负载104。
在某些实施例中，飞行器100可以与除了终端112之外的其它远程设备通讯， 终端112也可以与除飞行器100之外的其它远程设备进行通讯。例如，飞行器及/或终端112可以与另一个飞行器或者另一个飞行器的承载体或负载通讯。当有需要的时候，所述另外的远程设备可以是第二终端或者其它计算设备(如计算机、桌上型电脑、平板电脑、智能手机、或者其它移动设备)。该远程设备可以向飞行器100传送数据，从飞行器100接收数据，传送数据给终端112，及/或从终端112接收数据。可选的，该远程设备可以连接到因特网或者其它电信网络，以使从飞行器100及/或终端112接收的数据上传到网站或者服务器上。
在某些实施例中，飞行器的运动、承载体的运动及负载相对固定参照物(如外部环境)的运动，及/或者彼此间的运动，都可以由终端所控制。所述终端可以是远程控制终端，位于远离飞行器、承载体及/或负载的地方。终端可以位于或者粘贴于支撑平台上。可选的，所述终端可以是手持的或者穿戴式的。例如，所述终端可以包括智能手机、平板电脑、桌上型电脑、计算机、眼镜、手套、头盔、麦克风或者其中任意的结合。所述终端可以包括用户界面，如键盘、鼠标、操纵杆、触摸屏或者显示器。任何适合的用户输入可以与终端交互，如手动输入指令、声音控制、手势控制或者位置控制(如通过终端的运动、位置或者倾斜)。
飞行器100可以包括一个或者多个存储器102，存储器102上存储有由所述处理器运行的计算机程序，例如用于存储用于实现根据本申请实施例的更新限制区域(例如限飞区)数据库的方法中的相应步骤和程序指令。可以包括一个或多个计算机程序产品，所述计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。所述易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。所述非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。
飞行器100可以包括一个或者多个处理器101，处理器101可以是中央处理单元(CPU)、图像处理单元(GPU)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元，并且可以控制飞行器100中的其它组件以执行期望的功能。所述处理器能够执行存储器中存储的程序指令，以执行下文描述的本申请实施例的更新限制区域(例如限飞区)数据库的方法中的相关步骤。例如，处理器能够包括一个或多个嵌入式处理器、处理器核心、微型处理器、逻辑电路、硬件有限状态机(FSM)、数字信号处理器(DSP)或它们的组合。在本实施例中，所述处理器包括现场可编程门阵列(FPGA)，或者一个或者多个ARM处理器。
根据对空域管制的规定以及对无人机的管理规定，无人机必须在规定的空域中飞行，无人机地理围栏系统是一种用于限制无人机飞行的一种方式，无人机地理围栏系统在目前一些无人机上呈现两种形态：一种是不具备高性能处理器的无人机(无前视避障等高级功能)，在这种无人机上面目前只能实现最简单的圆形限制区域(例如限飞区)，这种限制区域(例如限飞区)数据存储格式非常简单，数据库的数量也较少；另一种是具备高性能处理器的无人机(具有视觉避障，tracking等高级功能)，在这类产品上面目前实现了复杂的多边形限制区域(例如限飞区)，并且限制区域(例如限飞区)数量也很多。
不具备高性能处理器的无人机的限制区域(例如限飞区)功能只能在飞控系统(Flight control system，简称FC)所在的微控制单元(MCU)上实现，而具备高性能处理器的无人机其限制区域(例如限飞区)功能主要在AP(Application Processer，应用处理器)上实现，FC上只是进行执行。
在现有无人机中，机场限制区域(例如限飞区)大多是将无人机在水平方向和竖直方向分别进行考虑，对于机场限制区域(例如限飞区)区的常见形态为，在完全不允许起飞的禁飞区外围有一个固定高度限制的扩大区域(也称限制区域(例如限飞区))。无人机在飞行过程中可能会进入限制区域(例如限飞区)或禁飞区(后面统称为限制区域(例如限飞区))，若不按照规定飞行，则有可能会影响到该无人机和其他飞行器的飞行安全，为此需要对无人机进行限制区域(例如限飞区)。
在一些例如无人机的飞行器上，因为算力与内存的限制，都没有一次性把所有限制区域(例如限飞区)数据读入内存，而是在飞行过程中，根据无人机当前的位置将无人机周围的限制区域(例如限飞区)数据读入内存。因为载入内存的只是无人机周围的限制区域(例如限飞区)数据，所以在执行限制区域(例如限飞区)判断的过程中，随着飞行距离的扩大，当无人机飞离上一次的更新位置一段距离后，需要重新读取无人机周围的限制区域(例如限飞区)数据并将其更新到内存中。
常规技术中，限制区域(例如限飞区)数据库的更新阈值的选择是依靠经验设置的固定值，没有结合无人机实际的飞行动态进行实时优化调整，如果更新阈值设置过小，则可能造成对限制区域(例如限飞区)数据库的频繁读取，浪费机载算力，如果更新阈值设置过大，则可能出现无人机已经接近前一次的数据边界了，新的限制区域(例如限飞区)数据还没更新完，或者还没开始更新，从而导 致无人机误闯入禁飞区，造成不必要的风险。
鉴于上述问题的存在，本申请实施例中提供一种更新限制区域数据的方法，所述方法应用于可移动平台，所述方法包括：基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，当前状态信息包括以下信息中的至少一种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台(例如飞行器)的当前机载计算单元温度；基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据。
本申请实施例中的更新限制区域数据的方法，基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，以实时调整限制区域数据的更新阈值，在保障限制区域对可移动平台移动的限制功能的同时，节省了机载算力，并有效避免可移动平台误闯禁止活动区域的问题出现。
需要说明的是，本申请实施例提供的更新限制区域(例如限飞区)数据库的方法，其执行主体可以是可移动平台(例如飞行器)，还可以是可以通过软件、硬件或者软硬件结合的方式实现更新限制区域(例如限飞区)数据库的方法的计算机设备的部分或者全部。
下面，参考图2至图6对本申请实施例提供的更新限制区域数据的方法进行描述。
作为示例，如图2所示，本申请实施例提供的更新限制区域数据的方法200包括以下步骤S201至步骤S203。
首先，在步骤S201中，基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值。基于可移动平台的当前状态信息，实时调整限制区域数据的更新阈值，在保障限制区域功能的同时，节省了机载算力，并有效避免可移动平台误闯禁止活动区域的问题出现。
当前状态信息包括以下信息中的至少一种：所述可移动平台(例如飞行器)的当前移动速度(例如飞行速度)移动速度、所述可移动平台(例如飞行器)的当前处理器负载、所述可移动平台(例如飞行器)当前所用的限制区域(例如限飞区)查询半径、所述可移动平台(例如飞行器)当前所在国家、所述可移动平台(例如飞行器)当前所在地区的限制区域(例如限飞区)密度或所述可移动平 台(例如飞行器)的当前机载计算单元温度。或者，还可以包括其他的影响可移动平台(例如飞行器)的限制区域(例如限飞区)数据库更新的信息。
可以基于所述可移动平台(例如飞行器)的当前状态信息，通过任意适合的计算方式获得获取当前限制区域(例如限飞区)数据库的更新阈值，例如，可以通过例如表格的方式指示当前状态信息中的多个信息和更新阈值的映射关系，从而获取当前限制区域(例如限飞区)数据库的更新阈值。再例如，可以利用各种机器学习算法来学习识别可移动平台(例如飞行器)的当前状态信息和更新阈值的映射关系，一旦经过训练，已训练的机器学习算法便可以由可移动平台(例如飞行器)存储，用于基于可移动平台(例如飞行器)的当前状态信息，获取当前限制区域(例如限飞区)数据库的更新阈值，机器学习算法的一些示例可以包括有监督或无监督的机器学习算法，包括回归算法(例如，普通最小二乘回归)、基于实例的算法(例如，学习向量量化)、决策树算法(例如，分类和回归树)、贝叶斯算法(例如，朴素贝叶斯)、聚类算法(例如，k均值聚类)，关联规则学习算法(例如，先验算法)、人工神经网络算法(例如，感知器)、深度学习算法(例如，深度玻尔兹曼机、或深度神经网络)、降维算法(例如，主成分分析)、集成算法(例如，堆叠泛化)和/或其它机器学习算法。
在一个示例中，所述基于所述可移动平台(例如飞行器)的当前状态信息，获取当前限制区域(例如限飞区)数据库的更新阈值，包括：将所述可移动平台(例如飞行器)的当前状态信息输入已训练好的神经网络进行处理，获取当前限制区域(例如限飞区)数据库的更新阈值。例如如图5所示，将所述可移动平台(例如飞行器)的当前移动速度(例如飞行速度)、所述可移动平台(例如飞行器)的当前处理器负载、所述可移动平台(例如飞行器)当前所用的限制区域(例如限飞区)查询半径输入已训练好的神经网络进行处理，从而获取当前限制区域(例如限飞区)数据库的更新阈值X。或者还可以将前述的当前状态信息中的一个或更多个信息作为输入量，输入已训练好的神经网络进行处理，获取当前限制区域(例如限飞区)数据库的更新阈值。通过已训练后的神经网络能够更快、更准确有效的获取到当前限制区域(例如限飞区)数据库的更新阈值。
其中，飞行器的飞行速度可以为飞行器的对地飞行速度，通常风速会影响飞行器的对地速度，因此，在一些示例中，飞行器的对地飞行速度可以是飞行器的空速和风速之和。
已训练好的神经网络可以是任意适合类型的神经网络，其中，较佳地，所述 已训练好的神经网络包括已训练好的递归(RBF)神经网络。RBF神经网络能够通过简单的拓扑结构直接利用输入输出数据逼近复杂的非线性关系。
在一个示例中，所述已训练好的神经网络包括具有反馈结构的神经网络，例如具有反馈结构的神经网络，更例如反馈结构的递归RBF神经网络，其中，如图6所示，反馈结构的递归RBF神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。更新半径的动态选择对系统动态特性要求很高，本申请通过采用具有反馈结构的递归RBF神经网络，RBF神经网络能够通过简单的拓扑结构直接利用输入输出数据逼近复杂的非线性关系，通过反馈通道将输出信息反馈到隐含层来调节隐含层的输入，因此具有很强的反馈性，从而能够提高系统动态特性。
可以基于任何适合的训练方法对神经网络进行训练，以获得已训练的神经网络。下文中将对用于输出限制区域(例如限飞区)数据库更新阈值的RBF神经网络的训练过程进行描述，该训练过程仅作为示例，对于其他的适合的训练方法也可以适用于本申请。
图6示出了递归RBF神经网络的一种结构图，该网络结构包括输入层、隐含层和输出层。输入层共包含n个神经元，每个神经元的输出为：
o i(t)＝x i(t),i＝(1,2,…,n)
其中，x＝[x 1(t),x 2(t),…x n(t)] T是递归RBF神经网络的输入，o i(t)对应的是t时刻第i个神经元的输出。本申请中n为三，三个输入分别是可移动平台例如飞行器的当前移动速度(例如飞行速度)移动速度、当前CPU负载情况、设定的限制区域(例如限飞区)区查找半径。或者还可以输入其他适合的移动数据信息(例如飞行器的飞行数据信息)。
隐含层的每个神经元不仅与输入层的神经元相连，也与输出的每个神经元相连，该隐含层的每个神经元输出为：
Figure PCTCN2020113312-appb-000001
其中，c j(t)为t时刻隐含层第j个神经元高斯计函数中心点的坐标向量，b j(t)为t时刻隐含层第j个神经元高斯计函数的宽度,‖·‖表示欧氏距离，σ j(t)表示：
σ j(t)＝[o 1(t),o 2(t),…o n(t),p j(t)y(t-1)] T
其中，p j(t)为t时刻输出神经元与隐含层的第j个神经元之间的反馈连接权重，y(t-1)为t-1输出层神经元的输出。
输出层仅有一个神经元，可以表示为：
Figure PCTCN2020113312-appb-000002
其中，ω j(t)为输出神经元与第j个隐含层神经元之间的连接权重。
网络逼近的误差指标为：
Figure PCTCN2020113312-appb-000003
采用梯度下降法对网络的权值进行调节，具体优化更新方法如下：
Figure PCTCN2020113312-appb-000004
Figure PCTCN2020113312-appb-000005
Figure PCTCN2020113312-appb-000006
Figure PCTCN2020113312-appb-000007
其中，η∈(0，1)为学习速率，本申请取η＝0.5，或者其他适合的值，网络的初始权值取0到1的随机值。通过训练使得定义的误差指标最小化。
所述已训练好的神经网络是基于所述可移动平台(例如飞行器)在至少一次历史移动过程(例如飞行器的历史飞行过程)中的移动数据信息(例如飞行器的飞行数据信息)训练而成的，也即以所述可移动平台(例如飞行器)在至少一次历史移动过程中的移动数据信息(例如飞行器的飞行数据信息)作为训练数据集，由于历史移动过程中的移动数据信息(例如飞行器的飞行数据信息)能够反应可移动平台(例如飞行器)的移动(例如飞行)状态信息，基于该些数据对神经网络进行训练，能够使已训练的神经网络在使用时的输出值更加可靠和准确有效。
所述可移动平台(例如飞行器)在至少一次历史移动过程中的移动数据信息(例如飞行器的飞行数据信息)可以通过实际历史移动中的日志(log)进行获取，也即在实际历史移动过程中记录移动数据信息(例如飞行器的飞行数据信息)， 并存储至存储器，在需要是只需在存储器中调取即可。
在一个示例中，所述移动数据信息(例如飞行器的飞行数据信息)包括第一移动数据信息(例如飞行器的第一飞行数据信息)和第二移动数据信息(例如飞行器的第二飞行数据信息)，所述第一移动数据信息(例如飞行器的飞行数据信息)包括以下信息中的至少一种：所述可移动平台(例如飞行器)历史移动过程中触发限制区域(例如限飞区)数据库更新时的移动速度(例如飞行速度)、触发限制区域(例如限飞区)数据库更新时的CPU负载和触发限制区域(例如限飞区)数据库更新时的限制区域(例如限飞区)的查找半径、触发限制区域(例如限飞区)数据库更新时所在国家、触发限制区域(例如限飞区)数据库更新时当前所在地区的限制区域(例如限飞区)密度、触发限制区域(例如限飞区)数据库更新时的机载计算单元温度，所述第二移动数据信息(例如飞行器的飞行数据信息)包括从限制区域(例如限飞区)数据库开始更新至更新完成所述可移动平台(例如飞行器)的飞行距离。其中，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息(例如飞行器的第一飞行数据信息)作为神经网络输入层的输入信息，例如，将第一移动数据信息(例如飞行器的飞行数据信息)中的所述可移动平台(例如飞行器)历史移动过程中触发限制区域(例如限飞区)数据库更新时的移动速度(例如飞行速度)移动速度、触发限制区域(例如限飞区)数据库更新时的CPU负载和触发限制区域(例如限飞区)数据库更新时的限制区域(例如限飞区)区的查找半径作为神经网络输入层的输入信息。或者将第一移动数据信息(例如飞行器的第一飞行数据信息)中的至少一种或者几种数据信息作为输入层的输入信息，具体地，可以根据实际可移动平台(例如飞行器)的状况而定。
在可移动平台(例如飞行器)的历史移动过程中，当限制区域(例如限飞区)数据库更新完成后记录所述第二移动数据信息(例如飞行器的飞行数据信息)，例如记录从开始更新到完成更新可移动平台(例如无人机)的移动距离例如无人机的飞行距离(也即飞过的距离)。所述第二移动数据信息(例如飞行器的飞行数据信息)用于对神经网络输出层的输出结果进行修正，也即基于从限制区域(例如限飞区)数据库开始更新至更新完成所述可移动平台(例如飞行器)的移动距离例如无人机的飞行距离，对神经网络输出层的输出结果进行修正，利用该移动距离例如无人机的飞行距离修正出期望的更新阈值。例如，如图4所示，期望的更新阈值应该是数据库更新位置B的限飞数据库更新完成时，飞行器恰好飞行 至以数据库更新位置A为圆点，以限飞区查找半径R为半径的限飞数据查找圆的边界，如果数据库更新位置B的限飞数据库更新完成时，飞行器的位置在数据库更新位置A的限飞数据查找圆内，则表示输出的更新阈值小于期望值，会导致更新次数的增加，影响记载算力，而如果飞行器的位置在数据库更新位置A的限飞数据查找圆外，则表示输出的更新阈值大于期望值，则可能出现无人机已经接近前一次的数据边界(例如位置在数据库更新位置A的限飞数据查找圆的边界)了，新的限飞数据还没更新完，或者还没开始更新，从而导致无人机误闯入禁飞区，造成不必要的风险，因此，需要用数据库更新位置B的限飞数据库开始更新至更新完成所述飞行器的飞行距离对输出值进行修正，从而获得期望的更新阈值。
利用可移动平台(例如飞行器)多次移动后例如飞行后离线存储的数据，来完成神经网络的训练，将离线训练好的神经网络(也即已训练的神经网络)集成到可移动平台(例如飞行器)上用于根据可移动平台(例如飞行器)的当前状态信息实时获取更新阈值即可。
接着，继续如图2所示，在步骤S202中，基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离。
可以基于可移动平台(例如飞行器)上的传感器例如GPS传感器获得前一次开始更新所述限制区域(例如限飞区)数据库时所述可移动平台(例如飞行器)的位置信息(例如GPS位置)以及所述可移动平台(例如飞行器)的当前位置信息(例如GPS位置)。例如，以飞行器为例，通过将两者的经纬度坐标进行对比，获得飞行器的运动距离D。
接着，继续如图2所示，在步骤S203中，基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据。
通过前述步骤S201中的方法获得了当前的更新阈值X，如图3所示，当所述运动距离D大于或等于该更新阈值X时，触发更新所述限制区域(例如限飞区)数据库，也即触发一次新的限制区域(例如限飞区)数据库更新，以将与所述可移动平台(例如飞行器)之间的距离在所述限制区域(例如限飞区)查找半径范围R内的限制区域(例如限飞区)的限制区域(例如限飞区)数据更新至 所述限制区域(例如限飞区)数据库中，例如将飞行器周围R米内的限飞区的限飞数据读入内存中备用。
如图3所示，当运动距离D小于更新阈值X时，则不触发更新，而是继续可移动平台(例如飞行器)的移动例如飞行，并在可移动平台(例如飞行器)的移动过程中继续根据前述步骤S201中的方法实时的获取数据库更新阈值X。
例如，如图4所示，前一次开始更新所述限制区域(例如限飞区)数据库时所述可移动平台(例如飞行器)的位置信息为数据库更新位置A，可移动平台(例如飞行器)的当前位置为图4中数据库更新位置B，数据库更新位置A和数据库更新位置B之间的运动距离D，在数据库更新位置B处，基于可移动平台(例如飞行器)当前状态信息获取到数据库的更新阈值X，此时，运动距离D大于更新阈值X，因此在数据库更新位置B处触发一次限制区域(例如限飞区)数据库的更新，也即，以数据库更新位置B为中心查找其周围R米内的限制区域(例如限飞区)的限制区域(例如限飞区)数据并将其更新至限制区域(例如限飞区)数据库中，例如存入内存中的限制区域(例如限飞区)数据库中备用。
可选地，所述可移动平台(例如飞行器)包括第一存储器和第二存储器，例如，第一存储器包括内存，第二存储器包括硬盘，其中，所述限制区域(例如限飞区)数据库存储于所述第一存储器中，所述限制区域(例如限飞区)数据为从所述第二存储器中读取到的数据，例如从存储于第二存储其中的结构化数据库中查询读取到的数据，或者，也可以是从geohash组织的数据库中查询读取到的数据，或者，也可以是从其他的具有限制区域(例如限飞区)数据的数据库中读取到的数据。本申请的方案中，从物理存储介质中读取可移动平台(例如飞行器)周围一定范围内的限制区域(例如限飞区)数据至内存中，可以方便快速从内存中获取周围的限制区域(例如限飞区)区数据，进而及时判断无人机与限制区域(例如限飞区)区的相对位置关系，从而对可移动平台(例如飞行器)的移动轨迹、速度、高度等进行控制。
限制区域(例如限飞区)查找半径范围R可以是预先设定的限制区域(例如限飞区)查找半径，其可以根据经验而合理设定。
需要说明的是，本申请中的限制区域(例如限飞区)区的限制区域(例如限飞区)数据可以包括例如限制区域(例如限飞区)区的长度、宽度、限制区域(例如限飞区)高度、中心位置、形状、类型等数据信息。
进一步，本申请的方法还包括以下步骤：
首先，根据所述可移动平台(例如飞行器)的当前位置信息和更新后的限制区域(例如限飞区)数据库，获取所述可移动平台(例如飞行器)与其周围至少一个限制区域(例如限飞区)的位置关系。例如，获取可移动平台(例如飞行器)和周围的多个限制区域(例如限飞区)的几何关系。
可移动平台(例如飞行器)与限制区域(例如限飞区)区的几何关系的判断方法有多种，可以采用平面几何方法进行计算，也可以采用立体几何方法、势能函数方法等方法完成判断，或者还可以采用其他适合的方法进行计算。
随后，根据所述几何关系，确定目标限制区域(例如限飞区)，其中，所述目标限制区域(例如限飞区)为所述至少一个限制区域(例如限飞区)中与所述可移动平台(例如飞行器)水平移动方向(例如飞行方向)上距离最近的限制区域(例如限飞区)，例如在多个限制区域(例如限飞区)区中确定一个目标限制区域(例如限飞区)，该目标限制区域(例如限飞区)区会最先影响到可移动平台(例如飞行器)的移动。
最后，根据所述目标限制区域(例如限飞区)区与所述可移动平台(例如飞行器)的位置关系，控制所述可移动平台(例如飞行器)的移动参数(例如飞行参数)，所述移动参数(例如飞行参数)至少包括移动速度(例如飞行速度)、移动高度(例如飞行高度)和移动方向(例如飞行方向)中的至少一种。当确定目标限制区域(例如限飞区)区之后，根据目标限制区域(例如限飞区)区的限制区域(例如限飞区)数据，执行对可移动平台(例如飞行器)的相关限制，例如控制飞行器进行减速逻辑、改变飞行方向、降低飞行高度等。从而避免可移动平台(例如飞行器)违反限制区域(例如限飞区)规则，而导致不必要的风险。
基于目标限制区域(例如限飞区)区的坐标、位置等判断其与可移动平台(例如飞行器)的相对位置关系，进而控制可移动平台(例如飞行器)的移动，例如，以飞行器为例，如果飞行器位于限飞区内，若飞行器的飞行高度高于限飞区的限飞高度，则控制飞行器降低其飞行高度至限飞高度以下，又例如，如果飞行器位于限飞区内，调整所述飞行器的航向(也即飞行方向)，以控制所述无人机在所述限飞区域外飞行。再例如，如果飞行器位于限飞区外且距离限飞区预设距离内，则阻止飞行器起飞或者禁止飞行器朝向限飞区的方向进行飞行。还例如，如果飞行器处于禁飞区内，则控制飞行器降落至地面。还例如，飞行器位于限飞区内，控制飞行器进行减速，或者，减速后改变航向，以防止误闯入禁飞区。
综上所述，在可移动平台(例如飞行器)的整个移动过程(飞行过程)中会 实时的根据前述的方法来重新获取更新阈值，以及在满足前述的条件时触发限制区域(例如限飞区)数据库的更新，并根据限制区域(例如限飞区)数据库实时的检查与周围限制区域(例如限飞区)的几何关系，从而执行合理的移动策略(例如飞行策略)，避免可移动平台(例如飞行器)误入限制区域(例如限飞区)的问题出现。同时由于实时的对数据库的更新阈值进行更新，因此可以避免由于更新阈值过小，更新次数过多，而导致的影响机载算力的问题出现，以及避免由于更新阈值过大，而导致可移动平台(例如飞行器)误闯入禁止活动区，造成不必要的风险。也即，本申请的方法，能够在保障限制区域(例如限飞区)功能正常的同时，节省了机载算力。
本申请实施例还提供的一种可移动平台，可移动平台可以包括飞行器(例如无人机)、机器人、无人车、无人船，可移动平台可以包括动力机构，所述动力机构用于使所述可移动平台移动；存储器，用于存储可执行的程序指令；一个或多个处理器，用于执行所述存储器中存储的所述程序指令，使得所述处理器执行前文中描述的更新限制区域数据的方法200的相关步骤。
继续参考图1，以可移动平台为飞行器100的情况为例，该飞行器100包括一个或多个处理器101，用于执行所述存储器中存储的所述程序指令，使得所述处理器执行前述实施例中的更新限制区域数据的方法200的相关步骤。
作为示例中，该可移动平台(例如飞行器)100包括一个或多个处理器101，用于执行所述存储器中存储的所述程序指令，使得所述处理器执行以下动作：基于可移动平台(例如飞行器)的当前状态信息，获取当前限制区域(例如限飞区)数据库的更新阈值，当前状态信息包括以下信息中的至少一种：所述可移动平台(例如飞行器)的当前移动速度(例如飞行速度)移动速度、所述可移动平台(例如飞行器)的当前处理器负载、所述可移动平台(例如飞行器)当前所用的限制区域(例如限飞区)查询半径、所述可移动平台(例如飞行器)当前所在国家、所述可移动平台(例如飞行器)当前所在地区的限制区域(例如限飞区)区密度或所述可移动平台(例如飞行器)的当前机载计算单元温度；基于前一次开始更新所述限制区域(例如限飞区)数据库时所述可移动平台(例如飞行器)的位置信息以及所述可移动平台(例如飞行器)的当前位置信息，确定所述可移动平台(例如飞行器)的运动距离；基于所述运动距离和所述更新阈值，确定是否更新所述限制区域(例如限飞区)数据库。
在一个示例中，所述处理器101用于基于所述可移动平台(例如飞行器)的当前状态信息，获取当前限制区域(例如限飞区)数据的更新阈值，包括：
将所述可移动平台(例如飞行器)的当前状态信息输入已训练好的神经网络进行处理，获取当前限制区域(例如限飞区)数据的更新阈值。
在一个示例中，所述已训练好的神经网络包括已训练好的RBF神经网络。
在一个示例中，所述已训练好的神经网络包括具有反馈结构的神经网络，其中，所述神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。
在一个示例中，所述已训练好的神经网络是基于所述可移动平台(例如飞行器)在至少一次历史移动过程中的移动数据信息(例如飞行器的飞行数据信息)训练而成的。
在一个示例中，所述移动数据信息(例如飞行器的飞行数据信息)包括第一移动数据信息(例如飞行器的飞行数据信息)和第二移动数据信息(例如飞行器的飞行数据信息)，所述第一移动数据信息(例如飞行器的飞行数据信息)包括以下信息中的至少一种：所述可移动平台(例如飞行器)历史飞行过程中触发限制区域(例如限飞区)数据更新时的移动速度(例如飞行速度)移动速度、触发限制区域(例如限飞区)数据更新时的CPU负载和触发限制区域(例如限飞区)数据更新时的限制区域(例如限飞区)区的查找半径、触发限制区域(例如限飞区)数据更新时所在国家、触发限制区域(例如限飞区)数据更新时当前所在地区的限制区域(例如限飞区)区密度、触发限制区域(例如限飞区)数据更新时的机载计算单元温度，所述第二移动数据信息(例如飞行器的飞行数据信息)包括从限制区域(例如限飞区)数据开始更新至更新完成所述可移动平台(例如飞行器)的移动距离。
在一个示例中，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息(例如飞行器的飞行数据信息)作为神经网络输入层的输入信息，所述第二移动数据信息(例如飞行器的飞行数据信息)用于对神经网络输出层的输出结果进行修正。
在一个示例中，处理器101还用于基于所述运动距离和所述更新阈值，确定是否更新所述限制区域(例如限飞区)数据，包括：
当所述运动距离大于或等于所述更新阈值时，触发更新所述限制区域(例如限飞区)数据，以将与所述可移动平台(例如飞行器)之间的距离在所述限制区 域(例如限飞区)查找半径范围内的限制区域(例如限飞区)区的限制区域(例如限飞区)数据更新至所述限制区域(例如限飞区)数据库中。
在一个示例中，所述可移动平台(例如飞行器)包括第一存储器和第二存储器，例如，第一存储器包括内存，第二存储器包括硬盘，其中，所述限制区域(例如限飞区)数据库存储于所述第一存储器中，所述限制区域(例如限飞区)数据为从所述第二存储器中读取到的数据，例如从存储于第二存储其中的结构化数据库中查询读取到的数据，或者，也可以是从geohash组织的数据库中查询读取到的数据，或者，也可以是从其他的具有限制区域(例如限飞区)数据的数据库中读取到的数据。
在一个示例中，所述处理器还用于：
根据所述可移动平台(例如飞行器)的当前位置信息和更新后的限制区域(例如限飞区)数据，获取所述可移动平台(例如飞行器)与其周围至少一个限制区域(例如限飞区)区的几何关系；
根据所述几何关系，确定目标限制区域(例如限飞区)区，其中，所述目标限制区域(例如限飞区)区为所述至少一个限制区域(例如限飞区)区中与所述可移动平台(例如飞行器)水平飞行方向上距离最近的限制区域(例如限飞区)区；
根据所述目标限制区域(例如限飞区)区与所述可移动平台(例如飞行器)的几何关系，控制所述可移动平台(例如飞行器)的飞行参数，所述飞行参数至少包括移动速度(例如飞行速度)移动速度、飞行高度和飞行方向中的至少一种。
由于本申请实施例的可移动平台(例如飞行器)能够用于执行前述的更新限制区域(例如限飞区)数据的方法，因此其同样具有前述的优点。该可移动平台(例如飞行器)能够在保证限制区域(例如限飞区)功能的同时，节省机载的算力。
下面，参考图7对本申请另一个实施例中的更新限制区域数据的方法进行解释和说明，其中，该方法的一些步骤可以参考前文中的描述，在此不再进行赘述，在不冲突的前提下，前文中的技术特征可以结合到本实施中。
作为示例，如图7所示，本申请的更新限制区域数据的方法，包括以下步骤：
在步骤S701中，当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，所述状态信息包括以下信息中的一种或多种：所述 可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度。
在一个示例中，所述当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：当通过传感器检测到所述可移动平台的至少一种状态信息发生变化时，输出提示信息，其中所述提示信息至少包括变化后的状态信息的数据信息；可移动平台的显示装置获取所述提示信息，并在显示界面上显示所述提示信息。可选地，提示信息可以以文字符号的形式呈现在显示界面上，还可以通过高亮显示、闪烁显示、附加符号显示、区别化的底纹颜色显示或区别化的字体颜色显示。该提示信息还可以同时以例如声音的方式呈现。通过该提示信息，可以提醒用户发生变化的状态信息的类型，以及变化后的状态信息的数据信息例如具体数值等，从而使得用户可以根据该变化确实是否调整更新阈值。
在一个示例中，所述当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：获取用户输入的操作指令，所述操作指令用于使设置窗口显示于显示装置的显示界面上，例如在显示装置的显示界面上具有第一按键，用户可以通过包括键盘、轨迹球、鼠标、麦克风和触摸屏等中的一个或多个，或其它控制按钮构成的输入装置输入相应的操作指令；基于所述操作指令，控制所述显示装置在显示界面上显示设置窗口，用户可以通过该设置窗口输入相应的变化后的状态信息；获取用户输入的设置指令，所述设置指令用于将发生变化的状态信息设置为变化后的状态信息的数据信息；基于所述变化后的状态信息的数据信息，调整所述可移动平台的限制区域数据的更新阈值。
在一个示例中，当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：将所述可移动平台的变化后的状态信息的数据信息输入已训练好的神经网络进行处理，获取可移动平台的限制区域数据的更新阈值。可选地，所述已训练好的神经网络包括已训练好的RBF神经网络。
已训练好的神经网络可以为任意适合的网络，所述已训练好的神经网络包括具有反馈结构的神经网络，其中，所述神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。
可以基于任意适合的方法对神经网络进行训练，例如，所述已训练好的神经 网络是基于所述可移动平台在至少一次历史移动过程中的移动移动数据信息训练而成的。
所述移动移动数据信息包括第一移动移动数据信息和第二移动移动数据信息，所述第一移动移动数据信息包括以下信息中的至少一种：所述可移动平台历史移动过程中触发限制区域数据更新时的移动速度、触发限制区域数据更新时的CPU负载和触发限制区域数据更新时的限制区域的查找半径、触发限制区域数据更新时所在国家、触发限制区域数据更新时当前所在地区的限制区域密度、触发限制区域数据更新时的机载计算单元温度，所述第二移动数据信息包括从限制区域数据开始更新至更新完成所述可移动平台的移动距离。其中，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息作为神经网络输入层的输入信息，所述第二移动数据信息用于对神经网络输出层的输出结果进行修正。
在步骤S701中，根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据。
在一个示例中，根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据，包括：基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；基于所述运动距离和调整后的所述更新阈值，更新所述限制区域数据，例如，当所述运动距离大于或等于调整后的所述更新阈值时，触发更新所述限制区域数据，以将与所述可移动平台之间的距离在所述限制区域查找半径范围内的限制区域的限制区域数据更新至所述可移动平台的限制区域数据库中。
上述方法中其执行主体可以是可移动平台例如飞行器，还可以是可移动平台例如飞行器从其他外部设备中直接获取更新后的限制区域数据更新至其内存中，而更新限制区域数据的方法则是由其他外部设备所实现，通过外部设备行实时迭代更新。或者，还可以是通过外部设备实时迭代调整更新阈值，而可移动平台从外部设备获取调整后的更新阈值，进而进行限制区域数据的更新，从其例如物理硬盘的存储器中读取更新的限制区域数据到内存中。
本申请实施例中的更新限制区域数据的方法当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，以实时调整限制区域数据的更新阈值，在保障限制区域对可移动平台移动的限制功能的同时，节省了机载算力，并有效避免可移动平台误闯禁止活动区域的问题出现。
本文中，机载算力也即为可移动平台自身携带的硬件例如处理器等的算力。
下面，参考图8对本申请的更新限制区域数据的装置进行描述，该装置可以为前述的可移动平台，或者还可以是其他的外部设备。
如图8所示，更新限制区域数据的装置800，包括一个或多个存储器802、一个或多个处理器801、显示装置803等，这些组件通过总线系统和/或其它形式的连接机构(未示出)互连。应当注意，图8所示的装置800的组件和结构只是示例性的，而非限制性的，根据需要，装置800也可以具有其他组件和结构。
存储器802用于存储相关可移动平台移动过程中产生的各种数据和可执行程序指令，例如用于存储各种应用程序或实现各种具体功能的算法。可以包括一个或多个计算机程序产品，所述计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。所述易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。所述非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。
处理器801可以是中央处理单元(CPU)、图像处理单元(GPU)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元，并且可以控制装置800中的其它组件以执行期望的功能。例如，处理器能够包括一个或多个嵌入式处理器、处理器核心、微型处理器、逻辑电路、硬件有限状态机(FSM)、数字信号处理器(DSP)、图像处理单元(GPU)或它们的组合。
处理器801用于执行所述存储器中存储的所述程序指令，使得所述处理器执行以下动作：
当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，所述状态信息包括以下信息中的一种或多种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据。
在一个示例中，所述处理器801还用于：当通过传感器检测到所述可移动平台的至少一种状态信息发生变化时，输出提示信息，其中所述提示信息至少包括变化后的状态信息的数据信息；该传感器可以是可移动平台上的多个传感器，当装置为独立于可移动平台的外部设备时，其可以从可移动平台的传感器获得可移动平台的状态信息。
在一个示例中，所述装置800还包括输出装置可以向外部(例如用户)输出各种信息(例如图像或声音)，并且可以包括显示装置、扬声器等中的一个或多个。
在一个示例中，所述装置800还包括显示装置803，用于获取所述提示信息，并在显示界面上显示所述提示信息。
在一个示例中，装置800还包括通信接口(未示出)，用于装置800中各个组件之间以及装置800的各个组件和该系统之外的其他装置之间进行通信，例如，当装置为外部设备时，可以通过通信接口和可移动平台进行通信，从而使两者之间能进行信息交互。
通信接口是可以是目前已知的任意通信协议的接口，例如有线接口或无线接口，其中，通信接口可以包括一个或者多个串口、USB接口、以太网端口、WiFi、有线网络、DVI接口，设备集成互联模块或其他适合的各种端口、接口，或者连接。装置800还可以接入基于通信标准的无线网络，如WiFi、2G、3G、4G、5G或它们的组合。在一个示例性实施例中，通信接口经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信接口还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在一个示例中，所述装置800还包括输入装置(未示出)可以是用户用来输入指令的装置，并且可以包括键盘、轨迹球、鼠标、麦克风和触摸屏等中的一个或多个，或其它控制按钮构成的输入装置。
进一步，所述处理器801还用于：获取用户输入的操作指令，所述操作指令用于使设置窗口显示于显示装置的显示界面上；基于所述操作指令，控制所述显示装置在显示界面上显示设置窗口；获取用户输入的设置指令，所述设置指令用于将发生变化的状态信息设置为变化后的状态信息的数据信息；基于所述变化后的状态信息的数据信息，调整所述可移动平台的限制区域数据的更新阈值。
在一个示例中，所述处理器801用于根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据，包括：
基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；
基于所述运动距离和调整后的所述更新阈值，更新所述限制区域数据。
在一个示例中，所述处理器801用于当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：
将所述可移动平台的变化后的状态信息的数据信息输入已训练好的神经网络进行处理，获取可移动平台的限制区域数据的更新阈值。可选地，所述已训练好的神经网络包括已训练好的RBF神经网络。
在一个示例中，所述已训练好的神经网络包括具有反馈结构的神经网络，其中，所述神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。
在一个示例中，所述已训练好的神经网络是基于所述可移动平台在至少一次历史移动过程中的移动移动数据信息训练而成的。例如，所述移动移动数据信息包括第一移动移动数据信息和第二移动移动数据信息，所述第一移动移动数据信息包括以下信息中的至少一种：所述可移动平台历史移动过程中触发限制区域数据更新时的移动速度、触发限制区域数据更新时的CPU负载和触发限制区域数据更新时的限制区域的查找半径、触发限制区域数据更新时所在国家、触发限制区域数据更新时当前所在地区的限制区域密度、触发限制区域数据更新时的机载计算单元温度，所述第二移动数据信息包括从限制区域数据开始更新至更新完成所述可移动平台的移动距离。进一步，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息作为神经网络输入层的输入信息，所述第二移动数据信息用于对神经网络输出层的输出结果进行修正。
在一个示例中，所述处理器用于基于所述运动距离和调整后的所述更新阈值，更新所述限制区域数据，包括：当所述运动距离大于或等于所述更新阈值时，触发更新所述限制区域数据，以将与所述可移动平台之间的距离在所述限制区域查找半径范围内的限制区域的限制区域数据更新至所述可移动平台的限制区域数据库中。
本申请实施例中的装置用于实现前述的方法，因此也具有前述方法的优点，当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，以实时调整限制区域数据的更新阈值，在保障限制区域对可移动平台移动的限制功能的同时，节省了机载算力，并有效避免可移动平台误闯禁止活动区域的问题出现。
另外，本申请实施例还提供了一种计算机存储介质，例如计算机可读存储介 质，其上存储有计算机程序。在所述计算机存储介质上可以存储一个或多个计算机程序指令，处理器可以运行存储器存储的所述程序指令，以实现本文所述的本申请实施例中(由处理器实现)的功能以及/或者其它期望的功能，例如以执行根据本申请实施例的更新限制区域数据的方法200和700的相应步骤，在所述计算机可读存储介质中还可以存储各种应用程序和各种数据，例如所述应用程序使用和/或产生的各种数据等。
例如，所述计算机可读存储介质例如可以包括智能电话的存储卡、平板电脑的存储部件、个人计算机的硬盘、只读存储器(ROM)、可擦除可编程只读存储器(EPROM)、便携式紧致盘只读存储器(CD-ROM)、USB存储器、或者上述存储介质的任意组合。所述计算机可读存储介质可以是一个或多个计算机可读存储介质的任意组合。
应当理解，本申请的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。如，如果用硬件来实现和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(Programmable Gate Array；以下简称：PGA)，现场可编程门阵列(Field Programmable Gate Array；简称：FPGA)等。
尽管这里已经参考附图描述了示例实施例，应理解上述示例实施例仅仅是示例性的，并且不意图将本申请的范围限制于此。本领域普通技术人员可以在其中进行各种改变和修改，而不偏离本申请的范围和精神。所有这些改变和修改意在被包括在所附权利要求所要求的本申请的范围之内。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。例如，以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个设备，或一些特征可以忽略， 或不执行。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本申请并帮助理解各个发明方面中的一个或多个，在对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该本申请的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如相应的权利要求书所反映的那样，其发明点在于可以用少于某个公开的单个实施例的所有特征的特征来解决相应的技术问题。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域的技术人员可以理解，除了特征之间相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本申请的范围之内并且形成不同的实施例。例如，在权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本申请实施例的一些模块的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在 权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。

Claims (43)

  1. 一种更新限制区域数据的方法，所述方法应用于可移动平台，其特征在于，所述方法包括：
    基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，当前状态信息包括以下信息中的一种或多种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
    基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；
    基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据。
  2. 如权利要求1所述的方法，其特征在于，所述基于所述可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，包括：
    将所述可移动平台的当前状态信息输入已训练好的神经网络进行处理，获取当前限制区域数据的更新阈值。
  3. 如权利要求2所述的方法，其特征在于，所述已训练好的神经网络包括已训练好的RBF神经网络。
  4. 如权利要求2或3所述的方法，其特征在于，所述已训练好的神经网络包括具有反馈结构的神经网络，其中，所述神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。
  5. 如权利要求2至4任一项所述的方法，其特征在于，所述已训练好的神经网络是基于所述可移动平台在至少一次历史移动过程中的移动数据信息训练而成的。
  6. 如权利要求5所述的方法，其特征在于，所述移动数据信息包括第一移动数据信息和第二移动数据信息，所述第一移动数据信息包括以下信息中的至少一种：所述可移动平台历史移动过程中触发限制区域数据更新时的移动速度、触发限制区域数据更新时的CPU负载和触发限制区域数据更新时的限制区域的查找半径、触发限制区域数据更新时所在国家、触发限制区域数据更新时当前所在地区的限制区域密度、触发限制区域数据更新时的机载计算单元温度，所述第二移动数据信息包括从限制区域数据开始更新至更新完成所述可移动平台的飞行 距离。
  7. 如权利要求6所述的方法，其特征在于，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息作为神经网络输入层的输入信息，所述第二移动数据信息用于对神经网络输出层的输出结果进行修正。
  8. 如权利要求1所述的方法，其特征在于，基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据，包括：
    当所述运动距离大于或等于所述更新阈值时，触发更新所述限制区域数据，以将与所述可移动平台之间的距离在所述限制区域查找半径范围内的限制区域的限制区域数据更新至所述限制区域数据中。
  9. 如权利要求8述的方法，其特征在于，所述可移动平台包括第一存储器和第二存储器，其中，所述限制区域数据存储于所述第一存储器中，所述限制区域数据为从所述第二存储器中读取到的数据。
  10. 如权利要求1所述的方法，其特征在于，所述方法还包括：
    根据所述可移动平台的当前位置信息和更新后的限制区域数据，获取所述可移动平台与其周围至少一个限制区域的几何关系；
    根据所述几何关系，确定目标限制区域，其中，所述目标限制区域为所述至少一个限制区域中与所述可移动平台水平移动方向上距离最近的限制区域；
    根据所述目标限制区域与所述可移动平台的几何关系，控制所述可移动平台的移动参数，所述飞行参数包括移动速度、移动高度和移动方向中的至少一种。
  11. 一种可移动平台，其特征在于，所述可移动平台包括：
    动力机构，所述动力机构用于使所述可移动平台移动；
    存储器，用于存储可执行的程序指令；
    一个或多个处理器，用于执行所述存储器中存储的所述程序指令，使得所述处理器执行以下动作：
    基于可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，当前状态信息包括以下信息中的至少一种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
    基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；
    基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据。
  12. 如权利要求11所述的可移动平台，其特征在于，所述处理器用于基于所述可移动平台的当前状态信息，获取当前限制区域数据的更新阈值，包括：
    将所述可移动平台的当前状态信息输入已训练好的神经网络进行处理，获取当前限制区域数据的更新阈值。
  13. 如权利要求12所述的可移动平台，其特征在于，所述已训练好的神经网络包括已训练好的RBF神经网络。
  14. 如权利要求12或13所述的可移动平台，其特征在于，所述已训练好的神经网络包括具有反馈结构的神经网络，其中，所述神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。
  15. 如权利要求12至14任一项所述的可移动平台，其特征在于，所述已训练好的神经网络是基于所述可移动平台在至少一次历史飞行过程中的移动数据信息训练而成的。
  16. 如权利要求15所述的可移动平台，其特征在于，所述移动数据信息包括第一移动数据信息和第二移动数据信息，所述第一移动数据信息包括以下信息中的至少一种：所述可移动平台历史移动过程中触发限制区域数据更新时的移动速度、触发限制区域数据更新时的CPU负载和触发限制区域数据更新时的限制区域的查找半径、触发限制区域数据更新时所在国家、触发限制区域数据更新时当前所在地区的限制区域密度、触发限制区域数据更新时的机载计算单元温度，所述第二移动数据信息包括从限制区域数据开始更新至更新完成所述可移动平台的移动距离。
  17. 如权利要求16所述的可移动平台，其特征在于，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息作为神经网络输入层的输入信息，所述第二移动数据信息用于对神经网络输出层的输出结果进行修正。
  18. 如权利要求11所述的可移动平台，其特征在于，基于所述运动距离和所述更新阈值，确定是否更新所述限制区域数据，包括：
    当所述运动距离大于或等于所述更新阈值时，触发更新所述限制区域数据，以将与所述可移动平台之间的距离在所述限制区域查找半径范围内的限制区域的限制区域数据更新至限制区域数据库中。
  19. 如权利要求18述的可移动平台，其特征在于，所述可移动平台包括第 一存储器和第二存储器，其中，所述限制区域数据库存储于所述第一存储器中，所述限制区域数据为从所述第二存储器中读取到的数据。
  20. 如权利要求11所述的可移动平台，其特征在于，所述处理器还用于：
    根据所述可移动平台的当前位置信息和更新后的限制区域数据，获取所述可移动平台与其周围至少一个限制区域的几何关系；
    根据所述几何关系，确定目标限制区域，其中，所述目标限制区域为所述至少一个限制区域中与所述可移动平台水平移动方向上距离最近的限制区域；
    根据所述目标限制区域与所述可移动平台的几何关系，控制所述可移动平台的移动参数，所述移动参数至少包括移动速度、移动高度和移动方向中的至少一种。
  21. 一种更新限制区域数据的方法，其特征在于，所述方法包括：
    当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，所述状态信息包括以下信息中的一种或多种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
    根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据。
  22. 如权利要求21所述的方法，其特征在于，所述当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：
    当通过传感器检测到所述可移动平台的至少一种状态信息发生变化时，输出提示信息，其中所述提示信息至少包括变化后的状态信息的数据信息；
    可移动平台的显示装置获取所述提示信息，并在显示界面上显示所述提示信息。
  23. 如权利要求22所述的方法，其特征在于，所述当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：
    获取用户输入的操作指令，所述操作指令用于使设置窗口显示于显示装置的显示界面上；
    基于所述操作指令，控制所述显示装置在显示界面上显示设置窗口；
    获取用户输入的设置指令，所述设置指令用于将发生变化的状态信息设置为变化后的状态信息的数据信息；
    基于所述变化后的状态信息的数据信息，调整所述可移动平台的限制区域数 据的更新阈值。
  24. 如权利要求21所述的方法，其特征在于，根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据，包括：
    基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；
    基于所述运动距离和调整后的所述更新阈值，更新所述限制区域数据。
  25. 如权利要求21或22所述的方法，其特征在于，当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：
    将所述可移动平台的变化后的状态信息的数据信息输入已训练好的神经网络进行处理，获取可移动平台的限制区域数据的更新阈值。
  26. 如权利要求25所述的方法，其特征在于，所述已训练好的神经网络包括已训练好的RBF神经网络。
  27. 如权利要求25所述的方法，其特征在于，所述已训练好的神经网络包括具有反馈结构的神经网络，其中，所述神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。
  28. 如权利要求25所述的方法，其特征在于，所述已训练好的神经网络是基于所述可移动平台在至少一次历史移动过程中的移动移动数据信息训练而成的。
  29. 如权利要求28所述的方法，其特征在于，所述移动移动数据信息包括第一移动移动数据信息和第二移动移动数据信息，所述第一移动移动数据信息包括以下信息中的至少一种：所述可移动平台历史移动过程中触发限制区域数据更新时的移动速度、触发限制区域数据更新时的CPU负载和触发限制区域数据更新时的限制区域的查找半径、触发限制区域数据更新时所在国家、触发限制区域数据更新时当前所在地区的限制区域密度、触发限制区域数据更新时的机载计算单元温度，所述第二移动数据信息包括从限制区域数据开始更新至更新完成所述可移动平台的移动距离。
  30. 如权利要求29所述的方法，其特征在于，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息作为神经网络输入层的输入信息，所述第二移动数据信息用于对神经网络输出层的输出结果进行修正。
  31. 如权利要求24所述的方法，其特征在于，基于所述运动距离和调整后 的所述更新阈值，更新所述限制区域数据，包括：
    当所述运动距离大于或等于所述更新阈值时，触发更新所述限制区域数据，以将与所述可移动平台之间的距离在所述限制区域查找半径范围内的限制区域的限制区域数据更新至所述可移动平台的限制区域数据库中。
  32. 一种更新限制区域数据的装置，其特征在于，所述装置包括：
    存储器，用于存储可执行的程序指令；
    处理器，用于执行所述存储器中存储的所述程序指令，使得所述处理器执行以下动作：
    当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，所述状态信息包括以下信息中的一种或多种：所述可移动平台的当前移动速度、所述可移动平台的当前处理器负载、所述可移动平台当前所用的限制区域查询半径、所述可移动平台当前所在国家、所述可移动平台当前所在地区的限制区域密度或所述可移动平台的当前机载计算单元温度；
    根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据。
  33. 如权利要求31所述的装置，其特征在于，所述处理器还用于：当通过传感器检测到所述可移动平台的至少一种状态信息发生变化时，输出提示信息，其中所述提示信息至少包括变化后的状态信息的数据信息；
    所述装置还包括显示装置，用于获取所述提示信息，并在显示界面上显示所述提示信息。
  34. 如权利要求33所述的装置，其特征在于，所述处理器还用于：
    获取用户输入的操作指令，所述操作指令用于使设置窗口显示于显示装置的显示界面上；
    基于所述操作指令，控制所述显示装置在显示界面上显示设置窗口；
    获取用户输入的设置指令，所述设置指令用于将发生变化的状态信息设置为变化后的状态信息的数据信息；
    基于所述变化后的状态信息的数据信息，调整所述可移动平台的限制区域数据的更新阈值。
  35. 如权利要求32所述的装置，其特征在于，所述处理器用于根据调整后的所述更新阈值，更新所述可移动平台的限制区域数据，包括：
    基于前一次开始更新所述限制区域数据时所述可移动平台的位置信息以及所述可移动平台的当前位置信息，确定所述可移动平台的运动距离；
    基于所述运动距离和调整后的所述更新阈值，更新所述限制区域数据。
  36. 如权利要求34或35所述的装置，其特征在于，所述处理器用于当可移动平台的状态信息发生变化时，调整所述可移动平台的限制区域数据的更新阈值，包括：
    将所述可移动平台的变化后的状态信息的数据信息输入已训练好的神经网络进行处理，获取可移动平台的限制区域数据的更新阈值。
  37. 如权利要求36所述的装置，其特征在于，所述已训练好的神经网络包括已训练好的RBF神经网络。
  38. 如权利要求36所述的装置，其特征在于，所述已训练好的神经网络包括具有反馈结构的神经网络，其中，所述神经网络包括输入侧、隐含层、输出层和反馈连接，所述输出层通过所述反馈连接将输出信息反馈到所述隐含层，以调节所述隐含层的输入信息。
  39. 如权利要求36所述的装置，其特征在于，所述已训练好的神经网络是基于所述可移动平台在至少一次历史移动过程中的移动移动数据信息训练而成的。
  40. 如权利要求39所述的装置，其特征在于，所述移动移动数据信息包括第一移动移动数据信息和第二移动移动数据信息，所述第一移动移动数据信息包括以下信息中的至少一种：所述可移动平台历史移动过程中触发限制区域数据更新时的移动速度、触发限制区域数据更新时的CPU负载和触发限制区域数据更新时的限制区域的查找半径、触发限制区域数据更新时所在国家、触发限制区域数据更新时当前所在地区的限制区域密度、触发限制区域数据更新时的机载计算单元温度，所述第二移动数据信息包括从限制区域数据开始更新至更新完成所述可移动平台的移动距离。
  41. 如权利要求40所述的装置，其特征在于，在所述已训练好的神经网络的训练过程中，所述第一移动数据信息作为神经网络输入层的输入信息，所述第二移动数据信息用于对神经网络输出层的输出结果进行修正。
  42. 如权利要求35所述的装置，其特征在于，所述处理器用于基于所述运动距离和调整后的所述更新阈值，更新所述限制区域数据，包括：
    当所述运动距离大于或等于所述更新阈值时，触发更新所述限制区域数据，以将与所述可移动平台之间的距离在所述限制区域查找半径范围内的限制区域的限制区域数据更新至所述可移动平台的限制区域数据库中。
  43. 一种计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现1至10任一项所述的更新限制区域数据的方法，或者，所述计算机程序指令被处理器执行时实现21至31任一项所述的更新限制区域数据的方法。
PCT/CN2020/113312 2020-09-03 2020-09-03 更新限制区域数据的方法、装置、可移动平台和计算机存储介质 WO2022047709A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202080031236.5A CN113853596A (zh) 2020-09-03 2020-09-03 更新限制区域数据的方法、装置、可移动平台和计算机存储介质
PCT/CN2020/113312 WO2022047709A1 (zh) 2020-09-03 2020-09-03 更新限制区域数据的方法、装置、可移动平台和计算机存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/113312 WO2022047709A1 (zh) 2020-09-03 2020-09-03 更新限制区域数据的方法、装置、可移动平台和计算机存储介质

Publications (1)

Publication Number Publication Date
WO2022047709A1 true WO2022047709A1 (zh) 2022-03-10

Family

ID=78972227

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/113312 WO2022047709A1 (zh) 2020-09-03 2020-09-03 更新限制区域数据的方法、装置、可移动平台和计算机存储介质

Country Status (2)

Country Link
CN (1) CN113853596A (zh)
WO (1) WO2022047709A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115616907A (zh) * 2022-09-22 2023-01-17 上海海事大学 一种无人艇航向智能规划方法及控制器

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114371735B (zh) * 2022-01-07 2023-11-03 广东汇天航空航天科技有限公司 一种飞行器地理围栏数据处理方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101128051A (zh) * 2007-09-18 2008-02-20 中国科学院软件研究所 基于交通网络和gps的移动对象位置更新方法
US20160240087A1 (en) * 2015-02-12 2016-08-18 Aerobotic Innovations, LLC System and method of preventing and remedying restricted area intrusions by unmanned aerial vehicles
US20180068570A1 (en) * 2016-01-06 2018-03-08 Qualcomm Incorporated Systems and Methods for Managing Restricted Areas for Unmanned Autonomous Vehicles
CN108780459A (zh) * 2017-12-29 2018-11-09 深圳市大疆创新科技有限公司 无人机控制方法和装置
CN108780461A (zh) * 2017-12-20 2018-11-09 深圳市大疆创新科技有限公司 限飞数据更新方法及相关设备、限飞数据管理平台

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101128051A (zh) * 2007-09-18 2008-02-20 中国科学院软件研究所 基于交通网络和gps的移动对象位置更新方法
US20160240087A1 (en) * 2015-02-12 2016-08-18 Aerobotic Innovations, LLC System and method of preventing and remedying restricted area intrusions by unmanned aerial vehicles
US20180068570A1 (en) * 2016-01-06 2018-03-08 Qualcomm Incorporated Systems and Methods for Managing Restricted Areas for Unmanned Autonomous Vehicles
CN108780461A (zh) * 2017-12-20 2018-11-09 深圳市大疆创新科技有限公司 限飞数据更新方法及相关设备、限飞数据管理平台
CN108780459A (zh) * 2017-12-29 2018-11-09 深圳市大疆创新科技有限公司 无人机控制方法和装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115616907A (zh) * 2022-09-22 2023-01-17 上海海事大学 一种无人艇航向智能规划方法及控制器

Also Published As

Publication number Publication date
CN113853596A (zh) 2021-12-28

Similar Documents

Publication Publication Date Title
US11914370B2 (en) System and method for providing easy-to-use release and auto-positioning for drone applications
US11726498B2 (en) Aerial vehicle touchdown detection
EP3500903B1 (en) Systems and methods of unmanned aerial vehicle flight restriction for stationary and moving objects
US11604479B2 (en) Methods and system for vision-based landing
US10134299B2 (en) Systems and methods for flight simulation
US20210341949A1 (en) Simple multi-sensor calibration
JP2020098567A (ja) 適応検知・回避システム
US20180348793A1 (en) Assisted takeoff
US20200026720A1 (en) Construction and update of elevation maps
US11531336B2 (en) Systems and methods for automatically customizing operation of a robotic vehicle
WO2016033795A1 (en) Velocity control for an unmanned aerial vehicle
JP2019537306A (ja) 撮像装置により取得された画像を制御するためのシステム及び方法
JP2019507924A (ja) Ｕａｖ軌道を調整するシステム及び方法
WO2022047709A1 (zh) 更新限制区域数据的方法、装置、可移动平台和计算机存储介质
JP6748797B1 (ja) 無人航空機制御システム、無人航空機制御方法、及びプログラム
US20230280763A1 (en) Method for protection unmanned aerial vehicle and unmanned aerial vehicle
WO2022061614A1 (zh) 可移动平台的控制方法、控制装置、可移动平台和计算机存储介质
WO2022188151A1 (zh) 影像拍摄方法、控制装置、可移动平台和计算机存储介质
JP2021073796A (ja) 制御装置、及び画像を取得する方法
US20230296793A1 (en) Motion-Based Calibration Of An Aerial Device
JP2021036452A (ja) Ｕａｖ軌道を調整するシステム及び方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20951956

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20951956

Country of ref document: EP

Kind code of ref document: A1