Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning

2026-05-15

AI Summary

This work addresses the limitations of conventional domain randomization approaches in quadrotor control, which often yield overly conservative policies and struggle with dynamic disturbances. The authors propose an adaptive outer-loop control architecture that employs a residual dynamics predictor—relying solely on historical state and control inputs—to estimate external disturbances online. By integrating a linear calibration bridge and an online thrust correction mechanism, the method enables efficient sim-to-real transfer, aligning the simulation environment with real-world dynamics using only seconds of actual flight data. The approach demonstrates robust high-precision trajectory tracking under significant uncertainties, such as mass variations and asymmetric payloads. Experimental validation on a Crazyflie micro quadrotor shows substantial performance improvements over existing baseline methods.

Abstract

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

Problem

• quadrotor
• dynamic disturbances
• trajectory tracking
• sim-to-real transfer
• uncertainty

Innovation

• Adaptive Control
• Reinforcement Learning
• Residual Dynamics Predictor
• Sim-to-Real Transfer
• Quadrotor