Switching-aware multi-agent deep reinforcement learning for target interception

Fan, Dongyu; Shen, Haikuo; Dong, Lijing

doi:10.1007/s10489-022-03821-9

Cited by 3 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Few research attempts exist using DRL for drone navigation, obstacle avoidance, and landing. Fan et al [37] proposed a multi-agent interception approach for scenarios where the network topology can change due to communication restrictions or attacks. To overcome this challenge, the authors introduced a Multi-Agent Level-Fusion Actor-Critic (MALFAC) approach with a Direction Assisted (DA) actor, Dimensional Pyramid Fusion (DPF) critic, and an Experience Adviser (EA) function.…”

Section: Drone Trackingmentioning

confidence: 99%

Drone Navigation and Target Interception Using Deep Reinforcement Learning: A Cascade Reward Approach

Darwish,

Nakhmani

2023

J. Ind. Sea. Pos. Nav.

View full text Add to dashboard Cite

This paper proposes an architecture for drone navigation and target interception, utilizing a selfsupervised, model-free deep reinforcement learning approach. Unlike traditional methods relying on complex controllers, our approach uses deep reinforcement learning with cascade rewards, enabling a single drone to navigate obstacles and intercept targets using only a forward-facing depth-RGB camera. This research has significant implications for robotics, as it demonstrates how complex tasks can be tackled using deep reinforcement learning. Our work encompasses three key contributions. First, we tackle the challenge of partial observability when employing nonlinear function approximators for learning stochastic policies. Second, we optimize the task of maximizing the overall expected reward. Finally, we develop a software library for training drones to track and intercept targets Through our experiments, we demonstrated that our approach, incorporating cascade reward, outperforms stateof-the-art deep Q-network algorithms in terms of learning policies. By leveraging our methodology, drones can successfully navigate complex indoor and outdoor environments and effectively intercept targets based on visual cues.

show abstract

Section: Drone Trackingmentioning

confidence: 99%