Inferring team task plans from human meetings: A generative modeling approach with logic-based prior
We aim to reduce the burden of programming and deploying autonomous systems to work in concert with people in time-critical domains such as military field operations and disaster response. Deployment plans for these operations are frequently negotiated on-the-fly by teams of human planners. A human...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for the Advancement of Artificial Intelligence
2015
|
| Online Access: | http://hdl.handle.net/1721.1/97138 https://orcid.org/0000-0003-1338-8107 |
| _version_ | 1826200220238610432 |
|---|---|
| author | Kim, Been Chacha, Caleb M. Shah, Julie A. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Kim, Been Chacha, Caleb M. Shah, Julie A. |
| author_sort | Kim, Been |
| collection | MIT |
| description | We aim to reduce the burden of programming and deploying autonomous systems to work in concert with people in time-critical domains such as military field operations and disaster response. Deployment plans for these operations are frequently negotiated on-the-fly by teams of human planners. A human operator then translates the agreed-upon plan into machine instructions for the robots. We present an algorithm that reduces this translation burden by inferring the final plan from a processed form of the human team's planning conversation. Our hybrid approach combines probabilistic generative modeling with logical plan validation used to compute a highly structured prior over possible plans, enabling us to overcome the challenge of performing inference over a large solution space with only a small amount of noisy data from the team planning session. We validate the algorithm through human subject experimentations and show that it is able to infer a human team's final plan with 86% accuracy on average. We also describe a robot demonstration in which two people plan and execute a first-response collaborative task with a PR2 robot. To the best of our knowledge, this is the first work to integrate a logical planning technique within a generative model to perform plan inference. |
| first_indexed | 2024-09-23T11:33:03Z |
| format | Article |
| id | mit-1721.1/97138 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:33:03Z |
| publishDate | 2015 |
| publisher | Association for the Advancement of Artificial Intelligence |
| record_format | dspace |
| spelling | mit-1721.1/971382022-09-27T20:16:47Z Inferring team task plans from human meetings: A generative modeling approach with logic-based prior Kim, Been Chacha, Caleb M. Shah, Julie A. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Kim, Been Chacha, Caleb M. Shah, Julie A. We aim to reduce the burden of programming and deploying autonomous systems to work in concert with people in time-critical domains such as military field operations and disaster response. Deployment plans for these operations are frequently negotiated on-the-fly by teams of human planners. A human operator then translates the agreed-upon plan into machine instructions for the robots. We present an algorithm that reduces this translation burden by inferring the final plan from a processed form of the human team's planning conversation. Our hybrid approach combines probabilistic generative modeling with logical plan validation used to compute a highly structured prior over possible plans, enabling us to overcome the challenge of performing inference over a large solution space with only a small amount of noisy data from the team planning session. We validate the algorithm through human subject experimentations and show that it is able to infer a human team's final plan with 86% accuracy on average. We also describe a robot demonstration in which two people plan and execute a first-response collaborative task with a PR2 robot. To the best of our knowledge, this is the first work to integrate a logical planning technique within a generative model to perform plan inference. United States. Dept. of Defense. Assistant Secretary of Defense for Research & Engineering (United States. Air Force Contract FA8721-05-C-0002) 2015-06-01T16:19:46Z 2015-06-01T16:19:46Z 2015-03 2014-07 Article http://purl.org/eprint/type/JournalArticle 1943-5037 1076-9757 http://hdl.handle.net/1721.1/97138 Kim, Been, Caleb M. Chacha, and Julie A. Shah. "Inferring team task plans from human meetings: A generative modeling approach with logic-based prior." Journal of Artificial Intelligence Research 52 (2015): 361-398. © 2015 AI Access Foundation https://orcid.org/0000-0003-1338-8107 en_US http://dx.doi.org/10.1613/jair.4496 Journal of Artificial Intelligence Research Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Association for the Advancement of Artificial Intelligence Association for the Advancement of Artificial Intelligence |
| spellingShingle | Kim, Been Chacha, Caleb M. Shah, Julie A. Inferring team task plans from human meetings: A generative modeling approach with logic-based prior |
| title | Inferring team task plans from human meetings: A generative modeling approach with logic-based prior |
| title_full | Inferring team task plans from human meetings: A generative modeling approach with logic-based prior |
| title_fullStr | Inferring team task plans from human meetings: A generative modeling approach with logic-based prior |
| title_full_unstemmed | Inferring team task plans from human meetings: A generative modeling approach with logic-based prior |
| title_short | Inferring team task plans from human meetings: A generative modeling approach with logic-based prior |
| title_sort | inferring team task plans from human meetings a generative modeling approach with logic based prior |
| url | http://hdl.handle.net/1721.1/97138 https://orcid.org/0000-0003-1338-8107 |
| work_keys_str_mv | AT kimbeen inferringteamtaskplansfromhumanmeetingsagenerativemodelingapproachwithlogicbasedprior AT chachacalebm inferringteamtaskplansfromhumanmeetingsagenerativemodelingapproachwithlogicbasedprior AT shahjuliea inferringteamtaskplansfromhumanmeetingsagenerativemodelingapproachwithlogicbasedprior |