Quadrotor navigation in dynamic environments with deep reinforcement learning. Issue 3 (7th April 2021)

• Record Type: Journal Article
• Authors: Fang, Jinbao; Sun, Qiyu; Chen, Yukun; Tang, Yang
• Is Part Of: Assembly automation. Volume 41:Issue 3(2021)
• Page Start: 254
• Page End: 262
• Publication Date: 2021-04-07
• Subjects: Unmanned aerial vehicles -- Deep reinforcement learning -- Cloud robotics -- Dynamic navigation -- Learning and adaptive systems; Automation -- Periodicals; Automatic machinery -- Periodicals; Assembly-line methods -- Periodicals; Industrial engineering -- Periodicals; 670.42705
• DOI: 10.1108/AA-11-2020-0183
• Languages: English
• ISSNs: 0144-5154

Abstract

Abstract : Purpose: This work aims to combine the cloud robotics technologies with deep reinforcement learning to build a distributed training architecture and accelerate the learning procedure of autonomous systems. Especially, a distributed training architecture for navigating unmanned aerial vehicles (UAVs) in complicated dynamic environments is proposed. Design/methodology/approach: This study proposes a distributed training architecture named experience-sharing learner-worker (ESLW) for deep reinforcement learning to navigate UAVs in dynamic environments, which is inspired by cloud-based techniques. With the ESLW architecture, multiple worker nodes operating in different environments can generate training data in parallel, and then the learner node trains a policy through the training data collected by the worker nodes. Besides, this study proposes an extended experience replay (EER) strategy to ensure the method can be applied to experience sequences to improve training efficiency. To learn more about dynamic environments, convolutional long short-term memory (ConvLSTM) modules are adopted to extract spatiotemporal information from training sequences. Findings: Experimental results demonstrate that the ESLW architecture and the EER strategy accelerate the convergence speed and the ConvLSTM modules specialize in extract sequential information when navigating UAVs in dynamic environments. Originality/value: Inspired by the cloud robotics technologies, this study proposes a distributed ESLW architecture for navigating UAVs in dynamic environments. Besides, the EER strategy is proposed to speed up training processes of experience sequences, and the ConvLSTM modules are added to networks to make full use of the sequential experiences.