UAV Target Tracking in Urban Environments Using Deep Reinforcement Learning

TL;DR

This paper presents TF-DQN, a deep reinforcement learning approach enabling UAVs to persistently track targets in urban environments by intelligently planning in 3D space, even with obstacles and uncertain target motion.

Contribution

Introduction of TF-DQN, a curriculum-trained deep reinforcement learning method for UAV target tracking in complex urban environments with obstacles.

Findings

UAV successfully tracks targets persistently in diverse simulated environments.

The method effectively avoids obstacles while maintaining target visibility.

Performance generalizes to unseen environments.

Abstract

Persistent target tracking in urban environments using UAV is a difficult task due to the limited field of view, visibility obstruction from obstacles and uncertain target motion. The vehicle needs to plan intelligently in 3D such that the target visibility is maximized. In this paper, we introduce Target Following DQN (TF-DQN), a deep reinforcement learning technique based on Deep Q-Networks with a curriculum training framework for the UAV to persistently track the target in the presence of obstacles and target motion uncertainty. The algorithm is evaluated through several simulation experiments qualitatively as well as quantitatively. The results show that the UAV tracks the target persistently in diverse environments while avoiding obstacles on the trained environments as well as on unseen environments.