Variable-Pitch-Propeller Mechanism Design, and Development of Heliquad for Mid-flight Flipping and Fault-Tolerant-Control

TL;DR

This paper introduces a novel variable-pitch propeller mechanism for a quadcopter, enabling mid-flight flipping and fault-tolerant control, validated through experimental flights demonstrating full-attitude control with actuator failures.

Contribution

It presents a new variable-pitch mechanism, a neural-network-based control allocation, and demonstrates full-attitude control including yaw-rate on three actuators, a first in the literature.

Findings

Successful mid-flight flip validation

Full-attitude control with three actuators

Effective fault recovery and landing

Abstract

This paper presents the design of Variable-Pitch-Propeller mechanism and its application on a quadcopter called Heliquad to demonstrate its unique capabilities. The input-output relationship is estimated for a generic mechanism. Various singularities and actuator sizing requirements are also analyzed. The mechanism is manufactured, and the validated input-output relationship is implemented in the controller of Heliquad. Heliquad is controlled by a unified non-switching cascaded attitude-rate controller, followed by a unique Neural-Network-based reconfigurable control allocation to approximate nonlinear relationship between the control input and actuator command. The Heliquad prototype's mid-flight flip experiment validates the controller's tracking performance in upright as well as inverted conditions. The prototype is then flown in upright condition with only three of its working actuators. To the best of the authors' knowledge, the cambered airfoil propeller-equipped Heliquad prototype demonstrates full-attitude control, including yaw-rate, on three working actuators for the first time in the literature. Finally, the utility of this novel capability is demonstrated by safe recovery and precise landing post-mid-flight actuator failure crisis. Overall, the controller tracks the references well for all the experiments, and the output of the NN-based control allocation remains bounded throughout.