Learning Agile and Robust Omnidirectional Aerial Motion on Overactuated Tiltable-Quadrotors

TL;DR

This paper introduces a reinforcement learning control framework for omnidirectional tiltable quadrotors that enhances robustness and agility, enabling reliable real-world deployment with minimal domain randomization.

Contribution

It presents a novel learning-based control approach that improves robustness and generalization for over-actuated aerial robots, outperforming traditional model-based controllers.

Findings

Comparable pose tracking accuracy to NMPC

Superior robustness and generalization

Effective sim-to-real transfer with minimal domain randomization

Abstract

Tilt-rotor aerial robots enable omnidirectional maneuvering through thrust vectoring, but introduce significant control challenges due to the strong coupling between joint and rotor dynamics. While model-based controllers can achieve high motion accuracy under nominal conditions, their robustness and responsiveness often degrade in the presence of disturbances and modeling uncertainties. This work investigates reinforcement learning for omnidirectional aerial motion control on over-actuated tiltable quadrotors that prioritizes robustness and agility. We present a learning-based control framework that enables efficient acquisition of coordinated rotor-joint behaviors for reaching target poses in the $SE(3)$ space. To achieve reliable sim-to-real transfer while preserving motion accuracy, we integrate system identification with minimal and physically consistent domain randomization. Compared with a state-of-the-art NMPC controller, the proposed method achieves comparable six-degree-of-freedom pose tracking accuracy, while demonstrating superior robustness and generalization across diverse tasks, enabling zero-shot deployment on real hardware.