A Preliminary Study on A Physical Model Oriented Learning Algorithm with Application to UAVs

TL;DR

This paper introduces a physics-based learning algorithm for UAVs that leverages physical principles to improve error correction, data efficiency, and adaptability in diverse scenarios, validated through numerical simulations.

Contribution

It presents a novel physics-oriented learning framework that enhances UAV control by integrating physical models with self-learning capabilities.

Findings

Improved error correction in UAV control

Enhanced data efficiency and learning reliability

Validated effectiveness through numerical studies

Abstract

This paper provides a preliminary study for an efficient learning algorithm by reasoning the error from first principle physics to generate learning signals in near real time. Motivated by iterative learning control (ILC), this learning algorithm is applied to the feedforward control loop of the unmanned aerial vehicles (UAVs), enabling the learning from errors made by other UAVs with different dynamics or flying in different scenarios. This learning framework improves the data utilization efficiency and learning reliability via analytically incorporating the physical model mapping, and enhances the flexibility of the model-based methodology with equipping it with the self-learning capability. Numerical studies are performed to validate the proposed learning algorithm.