Nowadays, multirotors are versatile systems that can be employed in several scenarios, where their increasing autonomy allows them to achieve complex missions without human intervention. This paper presents a framework for autonomous missions with low-cost Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System-denied (GNSS-denied) environments. This paper presents hardware choices and software modules for localization, perception, global planning, local re-planning for obstacle avoidance, and a state machine to dictate the overall mission sequence. The entire software stack has been designed exploiting the Robot Operating System (ROS) middleware and has been extensively validated in both simulation and real environment tests. The proposed solution can run both in simulation and in real-world scenarios without modification thanks to a small sim-to-real gap with PX4 software-in-the-loop functionality. The overall system has competed successfully in the Leonardo Drone Contest, an annual competition between Italian Universities with a focus on low-level, resilient, and fully autonomous tasks for vision-based UAVs, proving the robustness of the entire system design.

The present letter tackles the problem of planning a collision-free path in a known environment from a general point of view. We address the problem by using an unsupervised learning algorithm to generate a sparse graph representing the topological structure of the environment and use it for planning paths in 3D spaces. We propose GNGraph, an integrated solution combining the Growing Neural Gas algorithm to generate the sparse graph, a stop criterion to guarantee the graph's connectivity and a collision check to assess the edges and nodes validity. The proposed solution has been tested on simulated and real environment maps, and compared against a state-of-the-art graph planning algorithm among other global planning methods.

This article presents the design, implementation, and experimental validation of an autonomous drone system for search and rescue operations in cluttered GNSS-denied environments. The proposed platform integrates advanced navigation, mapping, and victim-detection capabilities, leveraging a suite of RGB-D cameras and edge-AI computation for real-time perception and decision-making. A key contribution is the integration of an eye-blink-detection pipeline for onboard assessment of the consciousness states of detected victims, enabling the drone to prioritize rescue efforts based on victim alertness. The system employs a modular software architecture with a pipeline that combines a U-Net segmentation network with a MultiScaleLSTM classifier, achieving approximately 97.73% accuracy and a combined inference latency of 6.35 ms on the NVIDIA Jetson Xavier-NX. Experimental results demonstrate the drone’s ability to autonomously explore unknown environments, accurately detect and classify victims, and operate effectively in real-world scenarios. The article also discusses observed challenges, such as computational bottlenecks and false positive detections, and outlines future directions for improving system robustness and autonomy.