Target-driven visual navigation in indoor scenes using reinforcement learning and imitation learning

CAAI Transactions on Intelligence Technology

article

Qiang Fang¹  Xin Xu¹  Xitong Wang¹  Yujun Zeng¹ 

[1] Department of Intelligence Science and Technology, College of Intelligence Science and Technology, National University of Defense Technology

关键词: mobile robots;    image matching;    radionavigation;    reinforcement learning;   

DOI  :  10.1049/cit2.12043

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

Here, the challenges of sample efficiency and navigation performance in deep reinforcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed. Our contributions are mainly three folds: first, a framework combining imitation learning with deep reinforcement learning is presented, which enables a robot to learn a stable navigation policy faster in the target-driven navigation task. Second, the surrounding images is taken as the observation instead of sequential images, which can improve the navigation performance for more information. Moreover, a simple yet efficient template matching method is adopted to determine the stop action, making the system more practical. Simulation experiments in the AI-THOR environment show that the proposed approach outperforms previous end-to-end deep reinforcement learning approaches, which demonstrate the effectiveness and efficiency of our approach.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND