aiqbench analysis
This research advances actuator-level reinforcement learning for overactuated tilt-rotor quadrotors, addressing the significant sim-to-real gap inherent in hybrid actuation systems with rotational joints. By integrating system identification and domain randomization, the study demonstrates a zero-shot deployment on real hardware that trades off some steady-state position accuracy for faster pose transitions and reduced onboard computational load compared to NMPC baselines.
Learning End-to-End Control for Omnidirectional Aerial Motion on Overactuated Tilt-rotor Quadrotors
arXiv:2602.21583v2 Announce Type: replace Abstract: While reinforcement learning (RL) has been successfully applied to conventional quadrotors for agile and robust flight, whether actuator-level RL can be reliably deployed on tilt-rotor aerial robots remains an open question, as the hybrid actuation coupling brushless rotors with rotational joints introduces a substantially harder sim-to-real gap. In this work, we propose an end-to-end RL framework for omnidirectional motion control on overactuated tilt-rotor quadrotors, directly mapping target poses to joint and rotor commands. The learning framework combines actuator-level simulation with an asymmetric actor-critic architecture for 6D pose-reaching. For reliable sim-to-real transfer on the hybrid actuation, we integrate system identification with minimal yet physically grounded domain randomization. The trained policy is deployed zero-shot on real hardware and evaluated across waypoint hovering, external disturbances, payload variation and trajectory tracking, together with simulated traversal of allocation-singular configurations. The policy is compared with a state-of-the-art NMPC baseline: NMPC attains lower steady-state position error, whereas the RL policy offers a more uniform orientation error across evaluations, transitions between poses faster, and requires less onboard computation.
Abstract:While reinforcement learning (RL) has been successfully applied to conventional quadrotors for agile and robust flight, whether actuator-level RL can be reliably deployed on tilt-rotor aerial robots remains an open question, as the hybrid actuation coupling brushless rotors with rotational joints introduces a substantially harder sim-to-real gap. In this work, we propose an end-to-end RL framework for omnidirectional motion control on overactuated tilt-rotor quadrotors, directly mapping target poses to joint and rotor commands. The learning framework combines actuator-level simulation with an asymmetric actor-critic architecture for 6D pose-reaching. For reliable sim-to-real transfer on the hybrid actuation, we integrate system identification with minimal yet physically grounded domain randomization. The trained policy is deployed zero-shot on real hardware and evaluated across waypoint hovering, external disturbances, payload variation and trajectory tracking, together with simulated traversal of allocation-singular configurations. The policy is compared with a state-of-the-art NMPC baseline: NMPC attains lower steady-state position error, whereas the RL policy offers a more uniform orientation error across evaluations, transitions between poses faster, and requires less onboard computation.
Robotics (cs.RO)
arXiv:2602.21583 [cs.RO]
(or arXiv:2602.21583v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2602.21583 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 261 words
Related coverage
Preserving Full 6-DOF Actuation Under Abrupt Total Rotor Failures: Passive Fault-Tolerant Flight Control Using a Biaxial-Tilt Hexacopter
arXiv · Jun 5, 2026
MorphQuad: Morphable Quadrotor for Superhuman Maneuverability, Manipulation, and Resiliency
arXiv · Jul 22, 2026
Preserving Full 6-DOF Actuation Under Abrupt Total Rotor Failures: Passive Fault-Tolerant Flight Control Using a Biaxial-Tilt Hexacopter
arXiv · Sep 22, 2026
Communications-Aware NMPC for Multi-Rotor Aerial Relay Networks Under Jamming Interference
arXiv · Aug 20, 2026