Rishik Bhandary is a Masters student who completed his Bachelors degree in 2019 and is currently completing a Masters in Data Science. He is under the supervision of Prof. Athman Bouguettaya and is conducting research based around using machine learning techniques to aid in the precision landing of drones.
Machine Learning Powered Precision Landing in Unmanned Aerial Systems
Using drones in delivery services is a fast-growing industry that gained a lot of commercial attention from companies such as Amazon, DHL, and Google. Drone precision landing is critical for the environment’s safety and success of various package delivery missions. We propose a machine learning-based strategy for navigating the drone to the landing position precisely. In contrast, current methods mostly focus on camera-based precision landing, in which an image target is identified, and an exact landing position is determined. When vision is obscured, these solutions frequently suffer from inaccuracy during severe weather circumstances such as fog and sandstorms. Additionally, these solutions have inaccuracies due to shadows. To overcome these limitations, we propose to train different supervised machine learning algorithms to predict the exact landing position under diverse scenarios by collecting a dataset of repeated landings using real drones and mapping it to real-world coordinates. Our proposed approach is primarily based on historical data and a set of variables that may influence an accurate landing. The battery state, wind conditions, acceleration, rotation of the drones, and other parameters could all play a role in forecasting the correct landing coordinates. Common trends and behaviours analysed from the dataset could be used to develop error correction strategies for precise landings.