Mission-Based Energy Consumption Prediction of Multirotor UAV

Unmanned aerial vehicle (UAV) is lately one of many popular research topics. High variety of its usage makes it attentive to be studied on its construction or the control. However, without knowing the energy that will be consumed in each mission, the available flight duration will be unknown and the usages of this vehicle will be limited. A mission-based black box modeling of UAV's energy consumption prediction was proposed in this paper. The setup consists of ArduPilot with Mission Planner Firmware installed to a custom built hexarotor. The method consists of three consecutive steps: data collection, data preprocessing, and regression. To collect the required data, flight patterns that contained several types of movements were defined, where the flight data log that contained missions, GPS, and battery, was collected. The preprocessing included the movement separation and also included the acceleration and the deceleration of horizontal movement. Finally, the regression was done using the Elastic Net Regression from Sklearn. The model was then tested on two flight patterns to simulate a surveillance application of a UAV and could predict with 98.773% mean of energy accuracy of the missions that started from the takeoff and ended with the return to launch command.