Navigation and path planning using reinforcement learning for a Roomba robot

2016 XVIII Congreso Mexicano de Robotica Pub Date : 2016-11-01 DOI:10.1109/COMROB.2016.7955160

Daniel Paul Romero-Martí, J. I. Nuñez-Varela, C. Soubervielle-Montalvo, Alfredo Orozco-de-la-Paz

{"title":"Navigation and path planning using reinforcement learning for a Roomba robot","authors":"Daniel Paul Romero-Martí, J. I. Nuñez-Varela, C. Soubervielle-Montalvo, Alfredo Orozco-de-la-Paz","doi":"10.1109/COMROB.2016.7955160","DOIUrl":null,"url":null,"abstract":"Service robots are expected to help us in different tasks in various environments such as homes, hospitals and offices. This work presents the first steps towards building a service robot at our university. The robot is provided with a topological map of a building floor (environmental map). Using this map the robot learns a path from one location to another by means of reinfocerment learning. During execution the robot is provided with a navigation map, related to the environmental map. We make use of a comercial Roomba robot and show how to create an interface in order to control it. Service robots are expected to help us in different tasks in various environments such as homes, hospitals and offices. This work presents the first steps towards building a service robot at our university. The robot is provided with a topological map of a building floor (environmental map). Using this map the robot learns a path from one location to another by means of reinfocerment learning. During execution the robot is provided with a navigation map, related to the environmental map. We make use of a comercial Roomba robot and show how to create an interface in order to control it.","PeriodicalId":401137,"journal":{"name":"2016 XVIII Congreso Mexicano de Robotica","volume":"71 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 XVIII Congreso Mexicano de Robotica","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COMROB.2016.7955160","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 14

Abstract

Service robots are expected to help us in different tasks in various environments such as homes, hospitals and offices. This work presents the first steps towards building a service robot at our university. The robot is provided with a topological map of a building floor (environmental map). Using this map the robot learns a path from one location to another by means of reinfocerment learning. During execution the robot is provided with a navigation map, related to the environmental map. We make use of a comercial Roomba robot and show how to create an interface in order to control it. Service robots are expected to help us in different tasks in various environments such as homes, hospitals and offices. This work presents the first steps towards building a service robot at our university. The robot is provided with a topological map of a building floor (environmental map). Using this map the robot learns a path from one location to another by means of reinfocerment learning. During execution the robot is provided with a navigation map, related to the environmental map. We make use of a comercial Roomba robot and show how to create an interface in order to control it.

查看原文本刊更多论文

使用强化学习的Roomba机器人导航和路径规划

服务机器人有望在家庭、医院和办公室等各种环境中帮助我们完成不同的任务。这项工作为我们大学建造服务机器人迈出了第一步。为机器人提供建筑物楼层的拓扑图(环境图)。利用这张地图，机器人通过强化学习的方式学习从一个位置到另一个位置的路径。在执行过程中，为机器人提供与环境地图相关的导航地图。我们利用商业Roomba机器人，并展示如何创建一个接口，以控制它。服务机器人有望在家庭、医院和办公室等各种环境中帮助我们完成不同的任务。这项工作为我们大学建造服务机器人迈出了第一步。为机器人提供建筑物楼层的拓扑图(环境图)。利用这张地图，机器人通过强化学习的方式学习从一个位置到另一个位置的路径。在执行过程中，为机器人提供与环境地图相关的导航地图。我们利用商业Roomba机器人，并展示如何创建一个接口，以控制它。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2016 XVIII Congreso Mexicano de Robotica

自引率

0.00%

发文量