Wuhan University of Science and Technology Researcher Illuminates Research in Ro botics (Gas source localization using Dueling Deep Q-Network with an olfactory q uadruped robot)
Wuhan University of Science and Technology Researcher Illuminates Research in Ro botics (Gas source localization using Dueling Deep Q-Network with an olfactory q uadruped robot)
武汉科技大学研究员照亮机器人研究(嗅觉机器人对战深q网络气体源定位)
扫码查看
点击上方二维码区域，可以放大扫码查看
摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-机器人方面的最新数据在一份新的报告中呈现。根据来自中国人民代表大会武汉的新闻报道，NewsRx记者称，“气源定位是气体敏感移动机器人最常见的应用之一。”记者从武汉科技大学的研究中得到一句话：“然而，现有的工作大多集中在基于规则的轮式机器人算法上，这些算法很难应用于复杂的障碍物地形中，本文提出了一种嗅觉四足机器人，利用决斗深度Q网络(Dueling Deep Q-Network，Dueling D QN)算法完成气源定位任务。”设计了一套环境,并从计算流体力学(CFD)软件中导入气体扩散数据,构建了嗅觉四足机器人模拟器,采用决斗DQN算法训练嗅觉四足机器人学习如何找到气体源,然后将训练好的神经网络部署到嗅觉四足机器人上。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on robotics are presented i n a new report. According to news reporting originating from Wuhan, People's Rep ublic of China, by NewsRx correspondents, research stated, "Gas source localizat ion is one of the most common applications of a gas-sensitive mobile robot." The news reporters obtained a quote from the research from Wuhan University of S cience and Technology: "However, most of the existing work focuses on rule-based algorithms for wheeled robots, which are difficult to apply in complex terrain with obstacles. In this article, we propose an olfactory quadruped robot to perf orm the gas source localization task using the Dueling Deep Q-Network (Dueling D QN) algorithm. For training, we designed a set of environments and imported gas dispersion data from computational fluid dynamics (CFD) software to construct a simulator. The olfactory quadruped robot was trained in this simulator using the Dueling DQN algorithm to learn how to find the gas source. The trained neural n etwork was then deployed on the olfactory quadruped robot."
Key words
Wuhan University of Science and Technolo gy/Wuhan/People's Republic of China/Asia/Emerging Technologies/Machine Lear ning/Robot/Robotics
NETL
NSTL