A Meta-Learning-based Trajectory Tracking Framework for UAVs under Degraded Conditions

TL;DR

This paper introduces a meta-learning framework that enables UAVs to adaptively improve trajectory tracking performance under unforeseen actuator faults and disturbances, enhancing safety and robustness in real-world operations.

Contribution

It presents a novel meta-learning-based approach with runtime adaptation and data pruning techniques for improved UAV trajectory tracking under degraded conditions.

Findings

Significant performance improvement in trajectory tracking during faults.

Effective runtime adaptation with minimal data for quick learning.

Validated through simulations and real-world experiments.

Abstract

Due to changes in model dynamics or unexpected disturbances, an autonomous robotic system may experience unforeseen challenges during real-world operations which may affect its safety and intended behavior: in particular actuator and system failures and external disturbances are among the most common causes of degraded mode of operation. To deal with this problem, in this work, we present a meta-learning-based approach to improve the trajectory tracking performance of an unmanned aerial vehicle (UAV) under actuator faults and disturbances which have not been previously experienced. Our approach leverages meta-learning to train a model that is easily adaptable at runtime to make accurate predictions about the system's future state. A runtime monitoring and validation technique is proposed to decide when the system needs to adapt its model by considering a data pruning procedure for efficient learning. Finally, the reference trajectory is adapted based on future predictions by borrowing feedback control logic to make the system track the original and desired path without needing to access the system's controller. The proposed framework is applied and validated in both simulations and experiments on a faulty UAV navigation case study demonstrating a drastic increase in tracking performance.