A Learning-based Control Methodology for Transitioning VTOL UAVs

TL;DR

This work addresses the challenging transition phase in VTOL UAVs by introducing ST3M, a learning-based methodology that couples altitude and position control during tilt-driven transitions. The approach consists of two stages: training a dynamic-hover RL controller (HRM) using a high-fidelity digital twin, and then planning balanced target paths with progressive training (BalancePath) for reliable trajectory following. By deriving a 6-DoF nonlinear model and performing trim analysis, the authors design RL rewards that promote stable hovering and smooth transitions. Experimental results in both simulation and real-world tests show reduced vibrations and improved trajectory tracking compared to conventional PID baselines, with effective sim-to-real transfer facilitated by remote, offboard computation. Overall, ST3M offers a practical, data-driven path to robust VTOL transitions without explicit phase-switching, accelerating controller development for varied hardware and environments.

Abstract

Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods' decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process.

Figures (9)

• Figure 1: Tri-rotor VTOL UAV transition.
• Figure 2: Tri-rotor VTOL UAV design.
• Figure 3: The pipeline of the ST3M method.
• Figure 4: RL control interface.
• Figure 5: a) shows the tri-rotor VTOL UAV configuration in the earth (e) and body (b) axis systems; b) defines cruise and hover modes.