This paper presents a supervised machine learning (SML) approach for accurate receiver-coil position detection in wireless power transfer (WPT) systems using only secondary-side measurements, targeting autonomous UAV charging. The model maps measured voltage and current features to the receiver’s spatial location with high precision, enabling autonomous alignment to the primary coil center for optimal charging efficiency. The sensing method is fully integrated into a standard WPT system, using the same coils for both power transfer and position detection without additional hardware. Operating at 6.78 MHz enhances positional sensitivity due to stronger spatial responsiveness of high-frequency near-field fields. A 30 W prototype with a 210 mm × 140 mm primary coil, a 50 mm × 80 mm receiver coil, and a 15 mm air gap validates the concept, demonstrating reliable position estimation and strong correlation with optimal alignment. This unified sensing-and-charging framework provides a compact, hardware-efficient basis for future autonomous eVTOL systems.
