Quad2Plane: An Intermediate Training Procedure for Online Exploration in Aerial Robotics via Receding Horizon Control

TL;DR

This paper introduces Quad2Plane, a method using receding horizon control to enable fixed-wing aircraft to learn from multi-rotor platforms safely and efficiently through behavior mimicry, facilitating online exploration in aerial robotics.

Contribution

The paper presents a novel intermediate training procedure that allows fixed-wing aircraft to learn behaviors by mimicking multi-rotor platforms using model predictive control.

Findings

Successful simulation of behavior mimicry between platforms.

Real-world validation of the control approach.

Potential to reduce costs and risks in aerial robotics training.

Abstract

Data driven robotics relies upon accurate real-world representations to learn useful policies. Despite our best-efforts, zero-shot sim-to-real transfer is still an unsolved problem, and we often need to allow our agents to explore online to learn useful policies for a given task. For many applications of field robotics online exploration is prohibitively expensive and dangerous, this is especially true in fixed-wing aerial robotics. To address these challenges we offer an intermediary solution for learning in field robotics. We investigate the use of dissimilar platform vehicle for learning and offer a procedure to mimic the behavior of one vehicle with another. We specifically consider the problem of training fixed-wing aircraft, an expensive and dangerous vehicle type, using a multi-rotor host platform. Using a Model Predictive Control approach, we design a controller capable of mimicking another vehicles behavior in both simulation and the real-world.