AERO2022-flying danger reduction for quadcopters by using machine learning to estimate current, voltage, and flight area

Abstract

Choosing the appropriate battery capacity for unmanned aerial vehicle (UAV) missions is critical, as draining the battery during flight nearly always results in vehicle damage and a significant risk of human harm or property damage. Predicting energy usage on a difficult trip is critical since the flying location, weather conditions, and other factors all impact power use. We develop a drone model that employs machine learning techniques to forecast battery and current consumption, as well as the quadcopter flying area, extremely precisely and quickly. As a result, the flight danger is lowered, and we will have a safe flight.