Outdoor aerial robots perform manipulation using onboard sensors and learning
Aerial Manipulation in the Wild with Onboard Perception, Policy Learning, and Whole-Body Control
Robotics
Summary
Doing tasks with flying robots outside is hard because they have to know exactly where they are, fly steadily, and move their arms precisely despite outside forces. The authors built a flying robot that uses its own sensors to figure out its position without extra equipment, learns how to move its arm from example demonstrations, and controls its whole body together to do tasks. They tested their system outdoors and showed it can handle manipulation tasks well in real-world conditions. This technology helps flying robots work better outside controlled labs.
What this means in practice
- •For drone developers: Build drones that manipulate objects outdoors using onboard sensors without relying on external tracking systems.
- •For agricultural technology teams: Implement aerial robotic systems for performing manipulation tasks like crop inspection or fruit picking in outdoor fields.
Authors
Yuanzhu Zhan, Yufei Jiang, Zemu Zhang, Junyi Geng
Abstract
Aerial manipulation in outdoor environments remains challenging due to the simultaneous requirements of reliable state estimation, stable aerial motion, and precise manipulation under external disturbances. In this work, we present a real-world outdoor aerial manipulation framework that integrates imitation learning, onboard LiDAR-inertial state estimation, and whole-body model predictive control. A Diffusion Policy is trained from manipulation demonstrations to generate desired end-effector motions from onboard observations. These learned commands are executed by a whole-body MPC that jointly coordinates the aerial platform and manipulator to realize the desired end-effector trajectory. To eliminate reliance on external motion-capture infrastructure, the platform employs onboard LiDAR-inertial odometry for state estimation during outdoor operation. We validate the complete framework on a physical aerial manipulator and demonstrate successful execution of outdoor manipulation tasks. The experimental results show that demonstration-driven manipulation policies can be effectively integrated with onboard state estimation and model-based whole-body control to enable aerial manipulation beyond controlled indoor environments.