Online Reinforcement Learning for Safe Gain Scheduling in Nonlinear Quadrotor Control

TL;DR

This paper introduces an online reinforcement learning approach for safe gain scheduling in nonlinear quadrotor control, ensuring stability and safety during flight through a structured, adaptive gain selection process.

Contribution

It proposes a novel RL framework that selects gains from a pre-certified library, maintaining safety and stability in nonlinear quadrotor control while reducing action space complexity.

Findings

Accurate trajectory tracking demonstrated in simulations.

Stable hover regulation achieved with online gain scheduling.

Reduced control effort near convergence.

Abstract

This paper presents an online reinforcement-learning framework for safe gain scheduling of a nonlinear quadcopter controller. Rather than learning thrust and torque commands directly, the proposed method selects gain vectors online from a finite library of pre-certified stabilizing controllers, thereby preserving the structure of the underlying snap-based control law. Safety is enforced by restricting the policy to admissible gains that maintain forward invariance of a prescribed safe state set, while dwell-time constraints prevent excessively fast switching. To reduce the action-space dimension, translational gains are shared across spatial axes by exploiting the isotropic structure of the translational dynamics, whereas yaw gains are scheduled independently. A deep Q-network learns to adjust feedback authority according to the current flight condition, using aggressive gains during large transients and milder gains near hover. High-fidelity nonlinear simulations demonstrate accurate trajectory tracking, bounded attitude motion, reduced control effort near convergence, and stable hover regulation under online safe gain scheduling.