Multi-robot grasp planning for sequential assembly operations
\This paper addresses the problem of finding robot configurations to grasp assembly parts during a sequence of collaborative assembly operations. We formulate the search for such configurations as a constraint satisfaction problem (CSP). Collision constraints in an operation and transfer constraints...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer US
2019
|
| Online Access: | http://hdl.handle.net/1721.1/121099 https://orcid.org/0000-0002-6896-5461 https://orcid.org/0000-0002-6937-6204 https://orcid.org/0000-0002-7654-2733 https://orcid.org/0000-0001-5473-3566 |
| _version_ | 1826217934728462336 |
|---|---|
| author | Dogar, MehmetRemzi Spielberg, Andrew Baker, Stuart Polak Rus, Daniela L |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Dogar, MehmetRemzi Spielberg, Andrew Baker, Stuart Polak Rus, Daniela L |
| author_sort | Dogar, MehmetRemzi |
| collection | MIT |
| description | \This paper addresses the problem of finding robot configurations to grasp assembly parts during a sequence of collaborative assembly operations. We formulate the search for such configurations as a constraint satisfaction problem (CSP). Collision constraints in an operation and transfer constraints between operations determine the sets of feasible robot configurations. We show that solving the connected constraint graph with off-the-shelf CSP algorithms can quickly become infeasible even for a few sequential assembly operations. We present an algorithm which, through the assumption of feasible regrasps, divides the CSP into independent smaller problems that can be solved exponentially faster. The algorithm then uses local search techniques to improve this solution by removing a gradually increasing number of regrasps from the plan. The algorithm enables the user to stop the planner anytime and use the current best plan if the cost of removing regrasps from the plan exceeds the cost of executing those regrasps. We present simulation experiments to compare our algorithm’s performance to a naive algorithm which directly solves the connected constraint graph. We also present a physical robot system which uses the output of our planner to grasp and bring parts together in assembly configurations. |
| first_indexed | 2024-09-23T17:11:23Z |
| format | Article |
| id | mit-1721.1/121099 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T17:11:23Z |
| publishDate | 2019 |
| publisher | Springer US |
| record_format | dspace |
| spelling | mit-1721.1/1210992022-10-03T11:02:46Z Multi-robot grasp planning for sequential assembly operations Dogar, MehmetRemzi Spielberg, Andrew Baker, Stuart Polak Rus, Daniela L Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Dogar, MehmetRemzi Spielberg, Andrew Baker, Stuart Polak Rus, Daniela L \This paper addresses the problem of finding robot configurations to grasp assembly parts during a sequence of collaborative assembly operations. We formulate the search for such configurations as a constraint satisfaction problem (CSP). Collision constraints in an operation and transfer constraints between operations determine the sets of feasible robot configurations. We show that solving the connected constraint graph with off-the-shelf CSP algorithms can quickly become infeasible even for a few sequential assembly operations. We present an algorithm which, through the assumption of feasible regrasps, divides the CSP into independent smaller problems that can be solved exponentially faster. The algorithm then uses local search techniques to improve this solution by removing a gradually increasing number of regrasps from the plan. The algorithm enables the user to stop the planner anytime and use the current best plan if the cost of removing regrasps from the plan exceeds the cost of executing those regrasps. We present simulation experiments to compare our algorithm’s performance to a naive algorithm which directly solves the connected constraint graph. We also present a physical robot system which uses the output of our planner to grasp and bring parts together in assembly configurations. Boeing Company Lincoln Laboratory 2019-03-26T14:17:02Z 2019-03-26T14:17:02Z 2018-04 2017-03 2019-03-14T08:14:04Z Article http://purl.org/eprint/type/JournalArticle 0929-5593 1573-7527 http://hdl.handle.net/1721.1/121099 Dogar, Mehmet, Andrew Spielberg, Stuart Baker, and Daniela Rus. “Multi-Robot Grasp Planning for Sequential Assembly Operations.” Autonomous Robots 43, no. 3 (April 16, 2018): 649–664. © 2018 The Authors https://orcid.org/0000-0002-6896-5461 https://orcid.org/0000-0002-6937-6204 https://orcid.org/0000-0002-7654-2733 https://orcid.org/0000-0001-5473-3566 en https://doi.org/10.1007/s10514-018-9748-z Autonomous Robots Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer US Springer US |
| spellingShingle | Dogar, MehmetRemzi Spielberg, Andrew Baker, Stuart Polak Rus, Daniela L Multi-robot grasp planning for sequential assembly operations |
| title | Multi-robot grasp planning for sequential assembly operations |
| title_full | Multi-robot grasp planning for sequential assembly operations |
| title_fullStr | Multi-robot grasp planning for sequential assembly operations |
| title_full_unstemmed | Multi-robot grasp planning for sequential assembly operations |
| title_short | Multi-robot grasp planning for sequential assembly operations |
| title_sort | multi robot grasp planning for sequential assembly operations |
| url | http://hdl.handle.net/1721.1/121099 https://orcid.org/0000-0002-6896-5461 https://orcid.org/0000-0002-6937-6204 https://orcid.org/0000-0002-7654-2733 https://orcid.org/0000-0001-5473-3566 |
| work_keys_str_mv | AT dogarmehmetremzi multirobotgraspplanningforsequentialassemblyoperations AT spielbergandrew multirobotgraspplanningforsequentialassemblyoperations AT bakerstuartpolak multirobotgraspplanningforsequentialassemblyoperations AT rusdanielal multirobotgraspplanningforsequentialassemblyoperations |