使用深度强化学习的自主视觉导航:概述

M. Ejaz, T. Tang, Cheng-Kai Lu
{"title":"使用深度强化学习的自主视觉导航:概述","authors":"M. Ejaz, T. Tang, Cheng-Kai Lu","doi":"10.1109/SCORED.2019.8896352","DOIUrl":null,"url":null,"abstract":"Reinforcement Learning (RL) algorithm with deep learning techniques helps to solve many complex problems of today's world, such as to play a video game and autonomous navigation in the robots using the raw image as an input. Deep learning provides the mechanism to RL which enables the agent to solve the human level task. The rise of RL begins when a computer player beat the human expert in the most difficult game Go [6]. In this paper, we discuss some important topics such as the general view of reinforcement learning, methods, and algorithms of reinforcement learning and challenges which reinforcement learning is facing. Finally, we discussed a survey of implemented algorithms of RL in the field of robotics for autonomous visual navigation.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Autonomous Visual Navigation using Deep Reinforcement Learning: An Overview\",\"authors\":\"M. Ejaz, T. Tang, Cheng-Kai Lu\",\"doi\":\"10.1109/SCORED.2019.8896352\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Reinforcement Learning (RL) algorithm with deep learning techniques helps to solve many complex problems of today's world, such as to play a video game and autonomous navigation in the robots using the raw image as an input. Deep learning provides the mechanism to RL which enables the agent to solve the human level task. The rise of RL begins when a computer player beat the human expert in the most difficult game Go [6]. In this paper, we discuss some important topics such as the general view of reinforcement learning, methods, and algorithms of reinforcement learning and challenges which reinforcement learning is facing. Finally, we discussed a survey of implemented algorithms of RL in the field of robotics for autonomous visual navigation.\",\"PeriodicalId\":231004,\"journal\":{\"name\":\"2019 IEEE Student Conference on Research and Development (SCOReD)\",\"volume\":\"48 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE Student Conference on Research and Development (SCOReD)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SCORED.2019.8896352\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE Student Conference on Research and Development (SCOReD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SCORED.2019.8896352","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

采用深度学习技术的强化学习(RL)算法有助于解决当今世界的许多复杂问题,例如使用原始图像作为输入来玩视频游戏和机器人自主导航。深度学习为强化学习提供了一种机制,使智能体能够解决人类级别的任务。强化学习的兴起始于一名计算机玩家在最困难的围棋游戏b[6]中击败了人类专家。在本文中,我们讨论了一些重要的主题,如强化学习的一般观点,强化学习的方法和算法,以及强化学习面临的挑战。最后,我们讨论了在机器人自主视觉导航领域中RL实现算法的概况。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Autonomous Visual Navigation using Deep Reinforcement Learning: An Overview
Reinforcement Learning (RL) algorithm with deep learning techniques helps to solve many complex problems of today's world, such as to play a video game and autonomous navigation in the robots using the raw image as an input. Deep learning provides the mechanism to RL which enables the agent to solve the human level task. The rise of RL begins when a computer player beat the human expert in the most difficult game Go [6]. In this paper, we discuss some important topics such as the general view of reinforcement learning, methods, and algorithms of reinforcement learning and challenges which reinforcement learning is facing. Finally, we discussed a survey of implemented algorithms of RL in the field of robotics for autonomous visual navigation.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Preliminary Implementation of the Next Generation Cannulation Simulator Multi-Input Power Converter for Renewable Energy Sources using Active Current Sharing Schemes Understanding the differences in students' attitudes towards social media use: A case study from Oman Effect Of Neurofeedback 2D and 3D Stimulus Content On Stress Mitigation Investigation of Segmented Rotor FEFSSM with Non-Overlap Windings in Various Slot-Pole Configurations
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1