Drone Soccer: Learning to Manipulate with Multicopter Downwash

2026-09-29

AI Summary

This study addresses the limitation of conventional unmanned aerial vehicles (UAVs), which typically treat rotor downwash as a disturbance rather than an exploitable resource for active manipulation. We propose a novel airflow-based paradigm for aerial manipulation by constructing a simplified downwash dynamics model integrated with reinforcement learning. This approach enables UAVs to actively manipulate objects using their own downwash, demonstrated through a soccer dribbling task. The trained policy successfully transfers from simulation to real-world environments, validating the feasibility of UAV dribbling. By revealing the substantial potential of transforming downwash into a controllable tool, this work opens new avenues for physical interaction in aerial robotics.

Abstract

Although multicopter drones are traditionally designed for "perception-only" tasks, like mapping and exploration, recent work has sought to develop Unmanned Aerial Manipulators (UAMs) to solve mobile manipulation tasks. Aerial manipulation performance can be impacted by "downwash," the airflow produced by propellers, but current state-of-the-art UAMs either ignore downwash or treat it as a disturbance. Instead, is it possible to actively use downwash as a tool during manipulation? We design a drone soccer task to explore the feasibility of downwash-based manipulation. Specifically, we develop a simplified downwash dynamics model which we use to train an RL policy to dribble a soccer ball. We further demonstrate that our policy transfers to real world deployment. This work provides key insights into novel manipulation capabilities for multicopters.

Problem

• Downwash
• Aerial Manipulation
• Unmanned Aerial Manipulators
• Multicopter
• Drone Soccer

Innovation

• Downwash Manipulation
• Aerial Manipulation
• Reinforcement Learning
• Sim-to-Real Transfer
• Unmanned Aerial Manipulator