Navigation without Global Navigation Satellite Systems (GNSS) poses a significant challenge in aerospace engineering, particularly in the environments where satellite signals are obstructed or unavailable. This paper offers an in-depth review of various methods, sensors, and algorithms for Unmanned Aerial Vehicle (UAV) localization in outdoor environments where GNSS signals are unavailable or denied. A key contribution of this study is the establishment of a critical classification system that divides GNSS-denied navigation techniques into two primary categories: absolute and relative localization. This classification enhances the understanding of the strengths and weaknesses of different strategies in various operational contexts. Vision-based localization is identified as the most effective approach in GNSS-denied environments. Nonetheless, it’s clear that no single-sensor-based localization algorithm can fulfill all the needs of a comprehensive navigation system in outdoor environments. Therefore, it’s vital to implement a hybrid strategy that merges various algorithms and sensors for effective outcomes. This detailed analysis emphasizes the challenges and possible solutions for achieving reliable and effective outdoor UAV localization in environments where GNSS is unreliable or unavailable. This multi-faceted analysis, highlights the complexities and potential pathways for achieving efficient and dependable outdoor UAV localization in GNSS-denied environments.

This paper addresses the challenge of predicting 3D trajectories for Unmanned Aerial Vehicles (UAVs) in real-time, a critical task for applications like aerial surveillance and defense. Current prediction models primarily leverage only position data, which may not provide the most accurate forecasts for UAV movements and usually fail outside the position domain used in the training phase. Our research identifies a gap in utilizing velocity estimates and first-order dynamics to better capture the dynamics and enhance prediction accuracy and generalizability in any position domain. To bridge this gap, we introduce a trajectory prediction scheme using sequence-based neural networks with Gated Recurrent Units (GRUs) to forecast future velocity and positions based on historical velocity estimates instead of position measurements. This approach is designed to improve the predictive capabilities over traditional methods that rely solely on recurrent neural networks (RNNs) or transformers, which can struggle with scalability in this context. Our methodology employs both synthetic and real-world 3D UAV trajectory data, incorporating diverse patterns of agility, curvature, and speed. Synthetic data are generated using the Gazebo robotics simulator and PX4 Autopilot, while real-world data are sourced from the UZH-FPV and Mid-Air drone racing datasets. We train the GRU-based models on drone 3D position and velocity samples to capture the dynamics of UAV movements effectively. Quantitatively, the proposed GRU-based prediction algorithm demonstrates superior performance, achieving a mean square error (MSE) ranging from $2\times {10}^{-8}$ to $2\times {10}^{-7}$. This performance outstrips existing state-of-the-art RNN models. Overall, our findings confirm the effectiveness of incorporating velocity data in improving the accuracy of UAV trajectory predictions across both synthetic and real-world scenarios, in and out of position data distributions. Finally, we open-source our 5000 trajectories dataset and a ROS2 package to facilitate the integration with existing ROS-based UAV systems.

This survey offers the most comprehensive and systematic review to date of Robot Operating System 2 (ROS 2), addressing the lack of a cohesive synthesis of its technical advances, challenges, and ecosystem evolution relative to ROS 1. Our analysis is guided by three research questions: (RQ1) How does ROS 2 improve upon ROS 1, and what new limitations arise? (RQ2) What advances address redesign challenges and enable deployment? (RQ3) Which frameworks and tools shape its ecosystem and reveal gaps? To answer RQ1, we discuss the motivations for ROS 2, its advantages over ROS 1, and remaining limitations. For RQ2, we distill the ROS literature to identify work focused on ROS 2 and organize it into four pillars: (a) middleware architecture, (b) real-time scheduling and hardware acceleration, (c) security and safety, and (d) multi-robot and distributed systems, showing how the literature mitigates limitations and enables deployments across domains such as autonomous vehicles, healthcare, agriculture, aerospace, logistics, and public safety. Finally, for RQ3, we survey the ROS 2 ecosystem, covering frameworks, simulators, and more than 150 open-source packages, and we highlight gaps in deployed tools. This is complemented by an open-access database unifying ROS 1 and ROS 2 literature at https://asmbatati.github.io/ros2_survey/.

This study presents a comprehensive review that addresses the critical transition from ROS 1 to ROS 2, spotlighting the significant enhancements and the pressing need for a detailed exploration of ROS 2 within the robotics community. Despite the extensive deployment and adaptations of ROS in varied robotics applications, literature lacks a cohesive synthesis that delineates the advancements, limitations, and broader impacts of ROS 2 compared to its predecessor, ROS 1. Our contribution bridges this gap by assembling the largest database of ROS-related research, encompassing 7,371 articles, with a focused analysis in this survey on 435 ROS2-specific publications. We categorize these into i.) articles that discuss and analyze core ROS 2 concepts, ii.) articles that propose frameworks or tools for ROS 2, and iii.) articles utilizing ROS 2. Furthermore, we summarize literature findings of ROS 2 challenges, advancements, and future direction in the fields of a.) security, b.) real-time, c.) middleware, d.) embedded and distributed systems, e.) communication reliability and QoS, and f.) multi-robot systems. The methodology involved meticulous data collection and categorization from multiple databases, facilitating an in-depth online accessible resource. Results underscore ROS2’s enhancements in modularity, real-time capabilities, and security, extending its applicability across various robotic platforms and industries. However, challenges in scalability and reliability persist, signaling avenues for future enhancements. This review not only deepens the understanding of ROS2’s contributions but also charts a path for ongoing improvements in robotic systems design. The original data presented in the study are openly available in https://www.ros.riotu-lab.org/.