Multi-Agent Reinforcement Learning based Drone Guidance for N-View Triangulation - LAAS - Laboratoire d'Analyse et d'Architecture des Systèmes Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Multi-Agent Reinforcement Learning based Drone Guidance for N-View Triangulation

Résumé

This article presents a novel approach for controlling a fleet of drones that can track the location of a flying target using onboard omnidirectional cameras. The drones use Multi-Agent Reinforcement Learning (MARL) to learn decentralized policies that optimize their formation and motion around the target, minimizing the uncertainty in the triangulated position. We design a reward function that encourages the trackers to minimize the trace of the covariance matrix of the triangulated position, which is derived from an analytical model of uncertainty propagation. We use Multi-Agent PPO (MAPPO), an extension of Proximal Policy Optimization (PPO) to the multi-agent setting, to train the policies using this common reward function that encourages good formation and avoids collisions. We validate our approach in simulation and real-flight experiments, demon- strating its effectiveness and potential in enhancing autonomous multi-drone coordination for precise tracking.
Fichier principal
Vignette du fichier
icuas-shield-2024.pdf (3.69 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04659183 , version 1 (22-07-2024)

Licence

Identifiants

Citer

Timothée Gavin, Simon Lacroix, Murat Bronz. Multi-Agent Reinforcement Learning based Drone Guidance for N-View Triangulation. 2024 International Conference on Unmanned Aircraft Systems (ICUAS), Jun 2024, Chania - Crete, Greece. pp.578-585, ⟨10.1109/ICUAS60882.2024.10556867⟩. ⟨hal-04659183⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More