A Survey on Visual Navigation for Artificial Agents With Deep Reinforcement Learning

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 robo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020, Vol.8, p.135426-135442
Main Authors: Zeng, Fanyu, Wang, Chen, Ge, Shuzhi Sam
Format: Article
Language:English
Subjects:
Agents (artificial intelligence)
Algorithms
artificial agents
Artificial intelligence
Decision making
Deep learning
deep reinforcement learning
Learning (artificial intelligence)
Machine learning
Navigation
Robotics
Simultaneous localization and mapping
Survey
Task analysis
visual navigation
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.3011438