Method and apparatus for managing flight plan

A method for managing, by a computing device, a flight plan of an unmanned aerial vehicle, the method comprising:

• inputting a departure location and a destination of the unmanned aerial vehicle, received from a user terminal, to an artificial intelligence model such that the artificial intelligence model outputs a plurality of flight plans;
• selecting at least one of the plurality of flight plans;
• transmitting, to the user terminal, the selected at least one flight plan;
• and
• controlling the unmanned aerial vehicle based on the selected at least one flight plan,
• wherein the artificial intelligence model is a model trained by adjusting parameters so that the sum of rewards calculated using state and actions included in training datasets is maximized,
• wherein the state includes at least one of departure location information, stopover information, destination information, a type of the unmanned aerial vehicle, or a payload of the unmanned aerial vehicle,
• wherein the actions include at least one of a takeoff scheme, an altitude climb scheme at the departure location, an arrival scheme at the destination, or a landing scheme on the destination,
• wherein the method further comprises:
• prior to the inputting of the input information to the artificial intelligence model,
• acquiring environmental information including at least one of a traffic volume, a noise intensity, a wind velocity, and a wind direction along a flight path from the departure location to the destination;
• and
• applying the environmental information to the artificial intelligence model, and
• wherein the acquiring of the environmental information includes acquiring the noise intensity based on a following Equation:
• Lw,f,m,i=Eaircraft,t,i+Cv,f,i log(vi/vo)+10logni+Ctrack,f,m+Ccorridor,f,m
• where Lw,f,m,i denotes the noise intensity;
• Eaircraft,t,i denotes an equivalent level in decibels (dB) of a sound intensity at each octave band as emitted from an air corridor of a unit length when the unmanned aerial vehicle passes through an air corridor under a reference condition;
• Cv,f,i denotes a velocity coefficient;
• vi denotes a velocity of the unmanned aerial vehicle;
• vo denotes a reference velocity of the unmanned aerial vehicle;
• ni denotes the number of unmanned aerial vehicles that have passed through the flight path;
• Ctrack.f.m denotes a correction value based on a trajectory of the unmanned aerial vehicle;
• and
• Ccorridor,f,m denotes a correction value based on an air corridor condition.

A computing device comprising:

• at least one processor;
• a memory for loading thereon a computer program executed by the processor;
• the memory comprising storage for storing therein the computer program,
• wherein the computer program includes instructions for:
• receiving, from a user terminal, input information including a departure location and destination of an unmanned aerial vehicle, the input information being selected based on a user input on a user interface displayed in the user terminal;
• inputting the input information to a pre-constructed artificial intelligence model;
• outputting a plurality of flight plans including at least one of a travel path, a takeoff scheme, an altitude climb scheme at the departure location, an arrival scheme at the destination, or a landing scheme on the destination from the artificial intelligence model;
• transmitting, to the user terminal, at least one flight plan among the plurality of flight plans;
• and
• controlling the unmanned aerial vehicle based on the at least one flight plan,
• wherein the pre-constructed artificial intelligence model is a model trained by adjusting parameters so that the sum of rewards calculated using state and actions included in training datasets is maximized,
• wherein the state includes at least one of departure location information, stopover information, destination information, a type of the unmanned aerial vehicle, or a payload of the unmanned aerial vehicle,
• wherein the actions include at least one of a takeoff scheme, an altitude climb scheme at the departure location, an arrival scheme at the destination, or a landing scheme on the destination,
• wherein the computer program further includes instructions for:
• prior to the inputting of the input information to the pre-constructed artificial intelligence model,
• acquiring environmental information including at least one of a traffic volume, a noise intensity, a wind velocity, and a wind direction along a flight path from the departure location to the destination;
• and
• applying the environmental information to the artificial intelligence model, and
• wherein the acquiring of the environmental information includes acquiring the noise intensity based on a following Equation:
• L
• w
• ,
• f
• ,
• m
• ,
• i
• =
• E
• aircraft
• ,
• t
• ,
• i
• +
• c
• v
• ,
• f
• ,
• i
• ⁢
• log
• ⁡
• (
• v
• i
• v
• o
• )
• +
• 10
• ⁢
• log
• ⁢
• n
• i
• +
• C
• t
• ⁢
• r
• ⁢
• a
• ⁢
• ck
• ,
• f
• ,
• m
• +
• C
• corridor
• ,
• f
• ,
• m
• where Lw,f,m,i denotes the noise intensity;
• Eaircraft,t,i denotes an equivalent level in decibels (dB) of a sound intensity at each octave band as emitted from an air corridor of a unit length when the unmanned aerial vehicle passes through an air corridor under a reference condition;
• Cv,f,i denotes a velocity coefficient;
• vi denotes a velocity of the unmanned aerial vehicle;
• vo denotes a reference velocity of the unmanned aerial vehicle;
• ni denotes the number of unmanned aerial vehicles that have passed through the flight path;
• Ctrack,f,m denotes a correction value based on a trajectory of the unmanned aerial vehicle;
• and
• Ccorridor,f,m denotes a correction value based on an air corridor condition.