Multi-scale assembly with robot teams

© The Author(s) 2015. In this paper we present algorithms and experiments for multi-scale assembly of complex structures by multi-robot teams. We also focus on tasks where successful completion requires multiple types of assembly operations with a range of precision requirements. We develop a hierar...

Full description

Bibliographic Details
Main Authors: Dogar, Mehmet, Knepper, Ross A, Spielberg, Andrew, Choi, Changhyun, Christensen, Henrik I, Rus, Daniela
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:English
Published: SAGE Publications 2021
Online Access:https://hdl.handle.net/1721.1/134289
_version_ 1826193185895874560
author Dogar, Mehmet
Knepper, Ross A
Spielberg, Andrew
Choi, Changhyun
Christensen, Henrik I
Rus, Daniela
author2 Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
author_facet Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Dogar, Mehmet
Knepper, Ross A
Spielberg, Andrew
Choi, Changhyun
Christensen, Henrik I
Rus, Daniela
author_sort Dogar, Mehmet
collection MIT
description © The Author(s) 2015. In this paper we present algorithms and experiments for multi-scale assembly of complex structures by multi-robot teams. We also focus on tasks where successful completion requires multiple types of assembly operations with a range of precision requirements. We develop a hierarchical planning approach to multi-scale perception in support of multi-scale manipulation, in which the resolution of the perception operation is matched with the required resolution for the manipulation operation. We demonstrate these techniques in the context of a multi-step task where robots assemble large box-like objects, inspired by the assembly of an airplane wing. The robots begin by transporting a wing panel, a coarse manipulation operation that requires a wide field of view, and gradually shifts to a narrower field of view but with more accurate sensors for part alignment and fastener insertion. Within this framework we also provide for failure detection and recovery: upon losing track of a feature, the robots retract to using wider field of view systems to re-localize. Finally, we contribute collaborative manipulation algorithms for assembling complex large objects. First, the team of robots coordinates to transport large assembly parts which are too heavy for a single robot to carry. Second, the fasteners and parts are co-localized for robust insertion and fastening. We implement these ideas using four KUKA youBot robots and present experiments where our robots successfully complete all 80 of the attempted fastener insertion operations.
first_indexed 2024-09-23T09:35:23Z
format Article
id mit-1721.1/134289
institution Massachusetts Institute of Technology
language English
last_indexed 2024-09-23T09:35:23Z
publishDate 2021
publisher SAGE Publications
record_format dspace
spelling mit-1721.1/1342892023-09-07T20:31:01Z Multi-scale assembly with robot teams Dogar, Mehmet Knepper, Ross A Spielberg, Andrew Choi, Changhyun Christensen, Henrik I Rus, Daniela Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © The Author(s) 2015. In this paper we present algorithms and experiments for multi-scale assembly of complex structures by multi-robot teams. We also focus on tasks where successful completion requires multiple types of assembly operations with a range of precision requirements. We develop a hierarchical planning approach to multi-scale perception in support of multi-scale manipulation, in which the resolution of the perception operation is matched with the required resolution for the manipulation operation. We demonstrate these techniques in the context of a multi-step task where robots assemble large box-like objects, inspired by the assembly of an airplane wing. The robots begin by transporting a wing panel, a coarse manipulation operation that requires a wide field of view, and gradually shifts to a narrower field of view but with more accurate sensors for part alignment and fastener insertion. Within this framework we also provide for failure detection and recovery: upon losing track of a feature, the robots retract to using wider field of view systems to re-localize. Finally, we contribute collaborative manipulation algorithms for assembling complex large objects. First, the team of robots coordinates to transport large assembly parts which are too heavy for a single robot to carry. Second, the fasteners and parts are co-localized for robust insertion and fastening. We implement these ideas using four KUKA youBot robots and present experiments where our robots successfully complete all 80 of the attempted fastener insertion operations. 2021-10-27T20:04:20Z 2021-10-27T20:04:20Z 2015 2019-07-17T13:05:50Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/134289 Dogar, M., et al. "Multi-Scale Assembly with Robot Teams." International Journal of Robotics Research 34 13 (2015): 1645-59. en 10.1177/0278364915586606 International Journal of Robotics Research Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf SAGE Publications Other repository
spellingShingle Dogar, Mehmet
Knepper, Ross A
Spielberg, Andrew
Choi, Changhyun
Christensen, Henrik I
Rus, Daniela
Multi-scale assembly with robot teams
title Multi-scale assembly with robot teams
title_full Multi-scale assembly with robot teams
title_fullStr Multi-scale assembly with robot teams
title_full_unstemmed Multi-scale assembly with robot teams
title_short Multi-scale assembly with robot teams
title_sort multi scale assembly with robot teams
url https://hdl.handle.net/1721.1/134289
work_keys_str_mv AT dogarmehmet multiscaleassemblywithrobotteams
AT knepperrossa multiscaleassemblywithrobotteams
AT spielbergandrew multiscaleassemblywithrobotteams
AT choichanghyun multiscaleassemblywithrobotteams
AT christensenhenriki multiscaleassemblywithrobotteams
AT rusdaniela multiscaleassemblywithrobotteams