Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control

TL;DR

This paper introduces a novel distributional reinforcement learning-based disturbance estimator combined with stochastic model predictive control to enhance quadrotor UAV tracking accuracy and reliability in complex environments.

Contribution

It proposes ConsDRED, an interpretable disturbance estimator with theoretical guarantees, integrated into a SMPC framework for improved quadrotor control.

Findings

Achieves at least 70% reduction in tracking errors.

Demonstrates convergent training in simulation and real-world.

Less sensitive to hyperparameters than existing methods.

Abstract

Simultaneously accurate and reliable tracking control for quadrotors in complex dynamic environments is challenging. As aerodynamics derived from drag forces and moment variations are chaotic and difficult to precisely identify, most current quadrotor tracking systems treat them as simple `disturbances' in conventional control approaches. We propose a novel, interpretable trajectory tracker integrating a Distributional Reinforcement Learning disturbance estimator for unknown aerodynamic effects with a Stochastic Model Predictive Controller (SMPC). The proposed estimator `Constrained Distributional Reinforced disturbance estimator' (ConsDRED) accurately identifies uncertainties between true and estimated values of aerodynamic effects. Simplified Affine Disturbance Feedback is used for control parameterization to guarantee convexity, which we then integrate with a SMPC. We theoretically guarantee that ConsDRED achieves at least an optimal global convergence rate and a certain sublinear rate if constraints are violated with an error decreases as the width and the layer of neural network increase. To demonstrate practicality, we show convergent training in simulation and real-world experiments, and empirically verify that ConsDRED is less sensitive to hyperparameter settings compared with canonical constrained RL approaches. We demonstrate our system improves accumulative tracking errors by at least 70% compared with the recent art. Importantly, the proposed framework, ConsDRED-SMPC, balances the tradeoff between pursuing high performance and obeying conservative constraints for practical implementations.