Prototyping of a multirotor UAV for precision landing under rotor failures

TL;DR

This paper addresses autonomous precision landing for multirotor UAVs under rotor failures by integrating a fault-tolerant hexarotor with tilting rotors and a two-stage fault-detection-and-control scheme, together with a vision-based navigation system using fiducial markers. The approach uses a pre-computed torque/force mapping $A$ and a bank of observers for fault detection to switch between nominal and failure states, paired with a pose estimation pipeline based on the pinhole camera model and ArUco markers, including $p_{k+1|k} = p_{k|k} + v_k \Delta t$ and $p_{k+1|k+1} = p_{k+1|k} + K(y_k - p_{k+1|k})$ updates and frame transformations $C^b_c$, $C^i_{b,k}$. The paper validates the concept through outdoor fault-injection experiments and an autonomous landing prototype on an NVIDIA Jetson TX2 with an Intel RealSense SR305, achieving landing accuracy on the order of $10$-$15$ cm under nominal conditions and demonstrating fault-tolerant recovery. It lays groundwork for integrated testing with abort/restart strategies and moving-target scenarios, aiming to enable reliable autonomous precision landing in urban and emergency contexts.

Abstract

This work presents a prototype of a multirotor aerial vehicle capable of precision landing, even under the effects of rotor failures. The manuscript presents the fault-tolerant techniques and mechanical designs to achieve a fault-tolerant multirotor, and a vision-based navigation system required to achieve a precision landing. Preliminary experimental results will be shown, to validate on one hand the fault-tolerant control vehicle and, on the other hand, the autonomous landing algorithm. Also, a prototype of the fault-tolerant UAV is presented, capable of precise autonomous landing, which will be used in future experiments.

Figures (10)

• Figure 1: Hexarotor fault-tolerant vehicle. On the bottom-left arm, a servo allows to tilt the re-configurable motor. Two computers can be seen: inside a black case, the NVIDIA Jetson TX2, and inside a green case, the flight controller.
• Figure 2: Architecture of the Fault Detection and Identification (FDI) module.
• Figure 3: Detection (left) and identification (right) residues for several flights in which a failure is injected at $t=0s$ in motor 3.
• Figure 4: Control scheme diagram attitude and position nested controllers.
• Figure 5: Attitude of the hexarotor in and outdoor flight, where a fault is injected at $t=6.3s$.