UAV Navigation

UAV: Unmanned Aerial Vehicle

UAV navigation studies how drones estimate their position, understand nearby space, and choose motions to reach goals while avoiding obstacles and respecting vehicle limits. State estimation commonly uses visual-inertial or LiDAR-inertial odometry, sometimes combined with satellite imagery, semantic maps, or other sensors when GNSS is unavailable. Planners range from model predictive control, graph search, and trajectory optimization to reinforcement learning and vision-language-action models that follow natural-language goals; safety filters and control barrier functions are often used to constrain motion. A central challenge is making these systems reliable in unfamiliar, dynamic conditions while balancing safety, speed, energy use, onboard computation, and transfer from simulation to real flight.

Latest papers

272 papers38 papers in the last four weeks, up 27% on the four weeks before. 0.2% of all new papers.

On Adversarial Attacks In Acoustic Drone Localization
Feb 27, 2025Tamir Shor, Chaim Baskin, Alex BronsteinAdversarial Attacks UAV Navigation
Department of Computer Science Technion – Israel Institute of Technology Haifa, Israel · School of Electrical and Computer Engineering Ben-Gurion University of the Negev Be’er Sheva, Israel · Technion – Israel Institute of Technology +1
Multi-Agent Reinforcement Learning-Based UAV Pathfinding for Obstacle Avoidance in Stochastic Environment
Oct 25, 2023Qizhen Wu, Kexin Liu, Lei Chen +1Mean-Field MARL Multi-Agent Path Finding
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China. · Advanced Research Institute of Multidisciplinary Sciences and State Key Laboratory of CNS/ATM, Beijing Institute of Technology, Beijing 100081, China.

Feb 27, 2025J/K move · Enter open · S save

On Adversarial Attacks In Acoustic Drone Localization

Tamir Shor, Chaim Baskin, Alex Bronstein

Department of Computer Science Technion – Israel Institute of Technology Haifa, Israel · School of Electrical and Computer Engineering Ben-Gurion University of the Negev Be’er Sheva, Israel · Technion – Israel Institute of Technology+1

Adversarial Attacks UAV Navigation Adversarial Robustness

Open paper AskPDF arXiv

Multi-rotor aerial autonomous vehicles (MAVs, more widely known as "drones") have been generating increased interest in recent years due to their growing applicability in a vast and diverse range of fields (e.g., agriculture, commercial delivery, search and rescue). The sensitivity of visual-based methods to lighting conditions and occlusions had prompted growing study of navigation reliant on other modalities, such as acoustic sensing. A major concern in using drones in scale for tasks in non-controlled environments is the potential threat of adversarial attacks over their navigational systems, exposing users to mission-critical failures, security breaches, and compromised safety outcomes that can endanger operators and bystanders. While previous work shows impressive progress in acoustic-based drone localization, prior research in adversarial attacks over drone navigation only addresses visual sensing-based systems. In this work, we aim to compensate for this gap by supplying a comprehensive analysis of the effect of PGD adversarial attacks over acoustic drone localization. We furthermore develop an algorithm for adversarial perturbation recovery, capable of markedly diminishing the affect of such attacks in our setting.

Latest papers

On Adversarial Attacks In Acoustic Drone Localization

Multi-Agent Reinforcement Learning-Based UAV Pathfinding for Obstacle Avoidance in Stochastic Environment