Precise drone landing remains a persistent challenge due to the high level of accuracy needed. We propose a novel technique that collects actual drone landing data and employs machine learning algorithms to predict errors in autonomous landing. Our model considers variables like battery charge, flight path, altitude, and velocity for prediction. Various trends associated with the drone's flight and landing are determined and visualised. We propose neural network models that use time series data from the drone's flight before landing to predict its landing position. Our best model reduced landing error to 2.34 cm, a 7% improvement over the baseline.
原文链接
分享
引用
