Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning
This work addresses the problem of robust quadrotor control under dynamic disturbances for real-world deployment, offering a practical solution that improves upon conservative domain randomization approaches.
The paper presents an adaptive outer-loop control architecture for quadrotors that uses a Residual Dynamics Predictor to estimate external disturbances online, achieving precise trajectory tracking under severe uncertainties such as mass variations and dynamic slung loads, outperforming baselines in real-world tests.
Deep Reinforcement Learning (DRL) for quadrotor flight control typically relies on Domain Randomization (DR) for sim-to-real transfer, resulting in overly conservative policies that struggle with dynamic disturbances. To overcome this, we propose a novel adaptive control architecture that actively perceives and reacts to instantaneous perturbations. First, we train an optimal outer-loop policy, then replace its reliance on ground-truth disturbance data with a Residual Dynamics Predictor (RDP). The RDP estimates the external forces and moments acting on the aircraft in flight online using only the history of states and control actions. For seamless hardware transfer, we introduce a data-efficient linear calibration bridge and an online thrust correction mechanism that align the simulated latent space with reality using mere seconds of flight data. Real-world validations on a Crazyflie micro-quadrotor demonstrate that our adaptive controller significantly outperforms baselines, maintaining precise trajectory tracking under severe uncertainties including mass variations, asymmetric payloads, and dynamic slung loads