Autonomous Navigation of UAVs in Large-Scale Complex Environments: A Deep Reinforcement Learning Approach

• Published in: IEEE transactions on vehicular technology Vol. 68; no. 3; pp. 2124 - 2136
• Main Authors: Wang, Chao, Wang, Jian, Shen, Yuan, Zhang, Xudong
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aerospace electronics; Algorithms; Autonomous navigation; deep reinforcement learning; Markov analysis; Markov processes; Navigation; partially observable Markov decision process; Path planning; Reinforcement learning; Sensors; Simultaneous localization and mapping; Task complexity; Unmanned aerial vehicles; Virtual environments
• DOI: 10.1109/TVT.2018.2890773
• ISSN: 0018-9545

In this paper, we propose a deep reinforcement learning (DRL)-based method that allows unmanned aerial vehicles (UAVs) to execute navigation tasks in large-scale complex environments. This technique is important for many applications such as goods delivery and remote surveillance. The problem is formulated as a partially observable Markov decision process (POMDP) and solved by a novel online DRL algorithm designed based on two strictly proved policy gradient theorems within the actor-critic framework. In contrast to conventional simultaneous localization and mapping-based or sensing and avoidance-based approaches, our method directly maps UAVs' raw sensory measurements into control signals for navigation. Experiment results demonstrate that our method can enable UAVs to autonomously perform navigation in a virtual large-scale complex environment and can be generalized to more complex, larger-scale, and three-dimensional environments. Besides, the proposed online DRL algorithm addressing POMDPs outperforms the state-of-the-art.