Cut & recombine: reuse of robot action components based on simple language instructions

Author:

Tamosiunaite Minija12,Aein Mohamad Javad1,Braun Jan Matthias1ORCID,Kulvicius Tomas1,Markievicz Irena2,Kapociute-Dzikiene Jurgita2,Valteryte Rita2,Haidu Andrei3,Chrysostomou Dimitrios4,Ridge Barry5,Krilavicius Tomas2,Vitkute-Adzgauskiene Daiva2,Beetz Michael3,Madsen Ole4,Ude Ales5,Krüger Norbert6,Wörgötter Florentin1

Affiliation:

1. Department for Computational Neuroscience, Inst. Physics-3, Georg-August-Universität Göttingen, Germany

2. Faculty of Informatics, Vytautas Magnus University, Lithuania

3. Institute for Artificial Intelligence, University of Bremen, Germany

4. Department of Materials & Production, Robotics and Automation Group, Aalborg University, Denmark

5. Department of Automatics, Biocybernetics, and Robotics, Jožef Stefan Institute, Slovenia

6. Maersk Mc-Kinney Moeller Institut, South Denmark University, Denmark

Abstract

Human beings can generalize from one action to similar ones. Robots cannot do this and progress concerning information transfer between robotic actions is slow. We have designed a system that performs action generalization for manipulation actions in different scenarios. It relies on an action representation for which we perform code-snippet replacement, combining information from different actions to form new ones. The system interprets human instructions via a parser using simplified language. It uses action and object names to index action data tables (ADTs), where execution-relevant information is stored. We have created an ADT database from three different sources (KUKA LWR, UR5, and simulation) and show how a new ADT is generated by cutting and recombining data from existing ADTs. To achieve this, a small set of action templates is used. After parsing a new instruction, index-based searching finds similar ADTs in the database. Then the action template of the new action is matched against the information in the similar ADTs. Code snippets are extracted and ranked according to matching quality. The new ADT is created by concatenating code snippets from best matches. For execution, only coordinate transforms are needed to account for the poses of the objects in the new scene. The system was evaluated, without additional error correction, using 45 unknown objects in 81 new action executions, with 80% success. We then extended the method including more detailed shape information, which further reduced errors. This demonstrates that cut & recombine is a viable approach for action generalization in service robotic applications.

Publisher

SAGE Publications

Subject

Applied Mathematics,Artificial Intelligence,Electrical and Electronic Engineering,Mechanical Engineering,Modelling and Simulation,Software

Cited by 6 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

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