Mirko Leomanni

Papers

Total Citations

H-Index

About

Mirko Leomanni is a robotics researcher advancing the autonomy of Micro Aerial Vehicles (MAVs) through novel integrations of computer vision, control theory, and machine learning. His work focuses on enabling drones to perceive and react to their environment without human intervention. In his highly cited 2024 paper, "D-VAT: End-to-End Visual Active Tracking for Micro Aerial Vehicles" (16 citations), Leomanni addresses the critical challenge of active visual tracking—where a drone must not only detect a target but also plan and execute its own motion to follow it, a capability vital for human assistance, disaster recovery, and surveillance. He further tackles the safety of teleoperated drones in his 2023 work on "Monocular Reactive Collision Avoidance for MAV Teleoperation with Deep Reinforcement Learning" (6 citations), developing semi-autonomous systems that help remote operators avoid obstacles they cannot see. Demonstrating his versatility in motion planning, Leomanni also authored "A Convex Programming Approach to Multipoint Optimal Motion Planning for Unicycle Robots" (2023, 3 citations), which provides a globally optimal solution to a traditionally nonconvex problem. Through these contributions, Leomanni is shaping a future where drones are more capable, safer, and truly autonomous partners.