Obstacle avoidance in aerial robotics remains a critical challenge, particularly in environments with uncertain terrain and weather conditions. This study introduces a Constrained Q-Learning model that leverages spatio-temporal data from LiDAR and OctoMap to achieve Zero-Shot Execution (ZSE) for autonomous Unmanned Aerial Vehicle (UAV) navigation in unseen environments, eliminating the need for iterative training. Experimental evaluations are conducted using a high-fidelity simulator across three environments: random forests, clustered forests, and metropolitan areas, under varying obstacle densities and flight velocities. The proposed model demonstrates a 100% success rate, achieving average flight times of 45 s for slow velocities (below 2.5 m/s) and 34 s for fast velocities (above 2.5 m/s). Comparative analysis with 90 Human-to-Computer (HTC) flights (slow and fast velocities), conducted by three pilots under identical conditions, shows the proposed model reduces flight time by 33% (1.5 times faster) while enhancing path optimization. Additionally, the model matches the path selection efficiency of a standard Q-Learning approach without requiring iterative training, highlighting its robustness and scalability for autonomous UAV navigation in complex environments and GPS-denied locations.
Autonomous Navigation in Swarm of UAVs Using Spatio Temporal Data and Constrained-Reinforcement Learning
Communic.Comp.Inf.Science
International Conference on Engineering Applications of Neural Networks ; 2025 ; Limassol, Cyprus June 26, 2025 - June 29, 2025
22.06.2025
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Zero-Shot Execution (ZSE) , Human Computer Interaction(HCI) , Autonomous navigation , Computer Vision (CV) , Reinforcement Learning (RL) , OctoMap , Constrained Reinforcement Learning (CRL) , Human-To-Comuter (HTC) Software Engineering/Programming and Operating Systems , Computer Applications , Computer Communication Networks , Artificial Intelligence , Computer Science
The perfect swarm? Intelligent autonomous UAVs
Online Contents | 2012
Spatio‐temporal dynamic navigation for electric vehicle charging using deep reinforcement learning
DOAJ | 2024
|Spatio‐temporal dynamic navigation for electric vehicle charging using deep reinforcement learning
Wiley | 2024
|