期刊
IEEE ACCESS
卷 8, 期 -, 页码 135426-135442出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.3011438
关键词
Visualization; Navigation; Simultaneous localization and mapping; Learning (artificial intelligence); Machine learning; Task analysis; Survey; visual navigation; artificial agents; deep reinforcement learning
资金
- National Natural Science Foundation of China [U1813202, 61773093]
- National Key Research and Development Program of China [2018YFC0831800]
- Research Programs of Sichuan Science and Technology Department [17ZDYF3184]
- Important Science and Technology Innovation Projects in Chengdu [2018-YF08-00039-GX]
Visual navigation (vNavigation) is a key and fundamental technology for artificial agents' interaction with the environment to achieve advanced behaviors. Visual navigation for artificial agents with deep reinforcement learning (DRL) is a new research hotspot in artificial intelligence and robotics that incorporates the decision making of DRL into visual navigation. Visual navigation via DRL, an end-to-end method, directly receives the high-dimensional images and generates an optimal navigation policy. In this paper, we first present an overview on reinforcement learning (RL), deep learning (DL) and deep reinforcement learning (DRL). Then, we systematically describe five main categories of visual DRL navigation: direct DRL vNavigation, hierarchical DRL vNavigation, multi-task DRL vNavigation, memory-inference DRL vNavigation and vision-language DRL vNavigation. These visual DRL navigation algorithms are reviewed in detail. Finally, we discuss the challenges and some possible opportunities to visual DRL navigation for artificial agents.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据