Aggressiveness-Aware Learning-based Control of Quadrotor UAVs with Safety Guarantees

TL;DR

This paper introduces an aggressiveness-aware control framework for quadrotors that uses learning-based oracles and adaptive gain scheduling to improve safety and performance by balancing robustness and control aggressiveness.

Contribution

It proposes a novel control scheme integrating learning-based disturbance estimation with adaptive gain scheduling for quadrotors, ensuring safety and reduced aggressiveness.

Findings

Guarantees practical exponential tracking performance.

Reduces feedback-induced aggressiveness.

Balances model accuracy, robustness, and control safety.

Abstract

This paper presents an aggressiveness-aware control framework for quadrotor UAVs that integrates learning-based oracles to mitigate the effects of unknown disturbances. Starting from a nominal tracking controller on $\mathrm{SE}(3)$, unmodeled generalized forces and moments are estimated using a learning-based oracle and compensated in the control inputs. An aggressiveness-aware gain scheduling mechanism adapts the feedback gains based on probabilistic model-error bounds, enabling reduced feedback-induced aggressiveness while guaranteeing a prescribed practical exponential tracking performance. The proposed approach makes explicit the trade-off between model accuracy, robustness, and control aggressiveness, and provides a principled way to exploit learning for safer and less aggressive quadrotor maneuvers.