A preliminary study on a groping framework without external sensors to recognize near-environmental situation for risk-tolerance disaster response robots

Kui-Ting Chen, Mitsuhiro Kamezaki, Takahiro Katano, Taisei Kaneko, Kohga Azuma, Yusuke Uehara, T. Ishida, M. Seki, Ken Ichiryu, S. Sugano
{"title":"A preliminary study on a groping framework without external sensors to recognize near-environmental situation for risk-tolerance disaster response robots","authors":"Kui-Ting Chen, Mitsuhiro Kamezaki, Takahiro Katano, Taisei Kaneko, Kohga Azuma, Yusuke Uehara, T. Ishida, M. Seki, Ken Ichiryu, S. Sugano","doi":"10.1109/SSRR.2017.8088161","DOIUrl":null,"url":null,"abstract":"This paper proposes a basic near-environmental recognition framework based on groping for risk-tolerance disaster response robot (DRR). In extreme disaster sites, including high radiation and heavy smog, external sensors such as cameras and laser range finders do not work properly, and such sensors may be broken in accidents in the tasks. It is hoped that DRRs can continue to perform tasks, even if the external sensors cannot work, and at least, they can safely evacuate from the site. In this preliminary study, for recognizing near environments without using external sensors, we proposed a groping method. In this method, a robot actively touches the environment using arms or other movable parts, records the contact information, and then reconstructs a three-dimensional local map around the robot by the detected information, e.g., robot arm's position and reactive force. The proposed groping system can recognize the existence of three situations, such as an object, step, and pit, and those geometry, by exploring the designated space using arms. The groping strategy was designed considering both robot specification, time limitation, and required resolution. Experiments were performed using four-arm and four-crawler robot OCTOPUS. The results indicate that the proposed framework could recognize step, pit, and object, and calculate the position and size of the object, and confirm that the robot successfully removed the object on the basis of groped data.","PeriodicalId":403881,"journal":{"name":"2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE International Symposium on Safety, Security and Rescue Robotics (SSRR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SSRR.2017.8088161","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

This paper proposes a basic near-environmental recognition framework based on groping for risk-tolerance disaster response robot (DRR). In extreme disaster sites, including high radiation and heavy smog, external sensors such as cameras and laser range finders do not work properly, and such sensors may be broken in accidents in the tasks. It is hoped that DRRs can continue to perform tasks, even if the external sensors cannot work, and at least, they can safely evacuate from the site. In this preliminary study, for recognizing near environments without using external sensors, we proposed a groping method. In this method, a robot actively touches the environment using arms or other movable parts, records the contact information, and then reconstructs a three-dimensional local map around the robot by the detected information, e.g., robot arm's position and reactive force. The proposed groping system can recognize the existence of three situations, such as an object, step, and pit, and those geometry, by exploring the designated space using arms. The groping strategy was designed considering both robot specification, time limitation, and required resolution. Experiments were performed using four-arm and four-crawler robot OCTOPUS. The results indicate that the proposed framework could recognize step, pit, and object, and calculate the position and size of the object, and confirm that the robot successfully removed the object on the basis of groped data.
无外部传感器摸索框架识别近环境风险容灾机器人的初步研究
提出了一种基于摸索的风险容忍型灾害响应机器人近环境识别基本框架。在高辐射、重雾霾等极端灾害现场,摄像机、激光测距仪等外部传感器无法正常工作,在执行任务过程中可能发生意外损坏。希望drr在外部传感器无法工作的情况下,仍能继续执行任务,至少能安全撤离现场。在这项初步研究中,我们提出了一种不使用外部传感器的近距离环境识别方法。在该方法中,机器人使用手臂或其他可移动部件主动接触环境,记录接触信息,然后根据检测到的信息,如机器人手臂的位置和反作用力,重建机器人周围的三维局部地图。该摸索系统可以识别物体、台阶、坑等三种情况的存在,以及这些几何形状,通过使用手臂探索指定的空间。同时考虑机器人的规格、时间限制和所需的分辨率,设计了探索策略。实验采用四臂四履带机器人OCTOPUS进行。结果表明,所提出的框架能够识别台阶、坑和物体,并计算出物体的位置和大小,确认机器人在探测数据的基础上成功移除了物体。
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
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信