Learning to Open Doors with an Aerial Manipulator

This is the accompanying video of our IROS2023 paper "Learning to Open Doors with an Aerial Manipulator".

Abstract:
The field of aerial manipulation has seen rapid advances, transitioning from push-and-slide tasks to interaction with articulated objects. The motion trajectory of these complex actions is usually hand-crafted or a result of online optimization methods like Model Predictive Control (MPC) or Model Predictive Path Integral control (MPPI). However, these methods rely on heuristics or model simplifications to efficiently run on onboard hardware, limiting their robustness, and making them sensitive to disturbances and differences between the real environment and its model. In this work, we propose a Reinforcement Learning approach to learn reactive motion behaviors for a manipulation task while producing policies that are robust to disturbances and modeling errors. Specifically, we train a policy to perform a door-opening task with an Omnidirectional Micro Aerial Vehicle. The policy is trained in a physics simulator and shown in the real world, where it is able to generalize also to door closing tasks never seen in training. We also compare our method against a state-of-the-art MPPI solution in simulation, showing a considerable increase in robustness and speed.

Reference:
Eugenio Cuniato, Ismail Geles, Weixuan Zhang, Olov Andersson, Marco Tognon, Roland Siegwart "Learning to Open Doors with an Aerial Manipulator" 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Affiliations:
Autonomous Systems Laboratory, ETH Zurich, Switzerland.
Univ Rennes, CNRS, Inria, IRISA, Campus de Beaulieu, 35042 Rennes Cedex, France.