Voltage Prediction of Drone Battery Reflecting Internal Temperature
TimeTuesday, July 12th5:06pm - 5:30pm PDT
Location3000, Level 3
Autonomous Systems (Automotive, Robotics, Drones)
DescriptionDrone's operation time depends directly on the accuracy of the battery voltage prediction. In this paper, we propose an accurate method for predicting the voltage in a drone battery by reflecting its internal temperature. To this end, we devise a temporal temperature factor (TTF) metric that is calculated by accumulating time series data about the battery’s discharge history. TTF is reflected to a machine learning–based model, achieving high prediction accuracy with low computation cost. A case study with a real flight scenario showed that the operating time of the drone is increased by up to 23.4% over the baseline method.