Grasping and retrieving unknown hazardous objects with a mobile manipulator

Author:

Roennau Arne1ORCID,Mangler Johannes1,Keller Philip1,Grosse Besselmann Marvin1,Huegel Nicolas1,Dillmann Ruediger1ORCID

Affiliation:

1. FZI Forschungszentrum Informatik , Karlsruhe , Baden-Württemberg , Germany

Abstract

Abstract Robots show impressive flexibility and reliability in various applications. This makes them suitable to help and support humans in hazardous environments. They can handle dangerous, unknown objects with no risk for the operator’s health. In this work we present a shared operation approach for the identification and localization of unknown hazardous objects as well as a 3D mapping approach for mobile robots in challenging environments. A shared control force-based grasping approach complete these two components and makes it easy for a human operator to grasp and retrieve unknown hazardous objects. Including the human expertise in the operation and control is additionally supported by providing intuitive visualization on different levels of abstraction. The presented approach was successfully evaluated with two different mobile robots within a field test.

Funder

ROBDEKON project funded by the German Federal Ministry of Education and Research

Publisher

Walter de Gruyter GmbH

Subject

Electrical and Electronic Engineering,Computer Science Applications,Control and Systems Engineering

Reference35 articles.

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Adaptive tracking control of a nonholonomic wheeled mobile robot with multiple disturbances and input constraints;at - Automatisierungstechnik;2024-01-01

2. Distributed Behavior Trees for Heterogeneous Robot Teams;2023 IEEE 19th International Conference on Automation Science and Engineering (CASE);2023-08-26

3. Robotic Sorting of Batteries Using Visual Few-shot Learning and Fusion with Depth Data;2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME);2023-07-19

4. An Object Recognition Grasping Approach Using Proximal Policy Optimization With YOLOv5;IEEE Access;2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3