Lucas K. de Oliveira | Search arXiv

arXiv2026

MIRA: A Modular Open-Source Micro-UAV for Indoor Research

Indoor robotics research increasingly relies on micro-UAV platforms whose airframes, electronics, and control software are open to modification. Off-the-shelf platforms often lack the low-level access that such modifications require, while building a custom vehicle demands substantial engineering effort before the first flight test, leaving many laboratories working within constraints that limit the scope of their research. We present MIRA (Modular Indoor Research Architecture), an open-source micro-UAV for indoor research, built around a replicable 3D-printed PLA airframe with detachable arms and a containerized low-level software package that manages the companion-to-autopilot communication bridge via Micro XRCE-DDS. Designed as a white-box architecture, its core subsystems, including the companion computer, are individually replaceable without firmware refactoring, which supports local fabrication, crash-localized repair, and component substitution from existing laboratory inventory. We characterize MIRA through autonomous flights comprising takeoff, hovering, trajectory tracking, and landing within an optical motion-capture volume. The communication pipeline sustains a median companion-to-autopilot latency of 0.02 ms, with the external motion-capture link as the main remaining latency source, and time-domain analysis shows that structural vibration remains stable during dynamic maneuvers and below the reference level adopted in this work. All design files and software are released openly to support replication and extension by other laboratories.

cs.RO↗

arXiv2025

Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach

Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for developing such policies, it presents a critical trade-off between on-policy and off-policy algorithms. Off-policy methods promise high sample efficiency, a vital trait for minimizing costly and unsafe real-world fine-tuning. In contrast, on-policy methods often exhibit greater training stability, which is essential for reliable convergence in hazard-dense environments. This paper directly investigates this trade-off by comparing a leading on-policy algorithm, Proximal Policy Optimization (PPO), against an off-policy counterpart, Soft Actor-Critic (SAC), for precision flight in procedurally generated ducts within a high-fidelity simulator. Our results show that PPO consistently learned a stable, collision-free policy that completed the entire course. In contrast, SAC failed to find a complete solution, converging to a suboptimal policy that navigated only the initial segments before failure. This work provides evidence that for high-precision, safety-critical navigation tasks, the reliable convergence of a well-established on-policy method can be more decisive than the nominal sample efficiency of an off-policy algorithm.

cs.RO↗