Inferring Maps and Behaviors from Natural Language Instructions
Natural language provides a flexible, intuitive way for people to command robots, which is becoming increasingly important as robots transition to working alongside people in our homes and workplaces. To follow instructions in unknown environments, robots will be expected to reason about parts of th...
| Main Authors: | , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Springer Nature
2018
|
| Online Access: | http://hdl.handle.net/1721.1/114638 https://orcid.org/0000-0002-8293-0492 |
| _version_ | 1811076043540267008 |
|---|---|
| author | Duvallet, Felix Oh, Jean Stentz, Anthony Walter, Matthew Robert Howard, Thomas M. Hemachandra, Sachithra Madhawa Teller, Seth Roy, Nicholas |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Duvallet, Felix Oh, Jean Stentz, Anthony Walter, Matthew Robert Howard, Thomas M. Hemachandra, Sachithra Madhawa Teller, Seth Roy, Nicholas |
| author_sort | Duvallet, Felix |
| collection | MIT |
| description | Natural language provides a flexible, intuitive way for people to command robots, which is becoming increasingly important as robots transition to working alongside people in our homes and workplaces. To follow instructions in unknown environments, robots will be expected to reason about parts of the environments that were described in the instruction, but that the robot has no direct knowledge about. However, most existing approaches to natural language understanding require that the robot’s environment be known a priori. This paper proposes a probabilistic framework that enables robots to follow commands given in natural language, without any prior knowledge of the environment. The novelty lies in exploiting environment information implicit in the instruction, thereby treating language as a type of sensor that is used to formulate a prior distribution over the unknown parts of the environment. The algorithm then uses this learned distribution to infer a sequence of actions that are most consistent with the command, updating our belief as we gather Keywords
Natural Language; Mobile Robot; Parse Tree; World Model; Behavior Inference |
| first_indexed | 2024-09-23T10:15:12Z |
| format | Article |
| id | mit-1721.1/114638 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T10:15:12Z |
| publishDate | 2018 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | mit-1721.1/1146382022-09-30T19:57:30Z Inferring Maps and Behaviors from Natural Language Instructions Duvallet, Felix Oh, Jean Stentz, Anthony Walter, Matthew Robert Howard, Thomas M. Hemachandra, Sachithra Madhawa Teller, Seth Roy, Nicholas Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Walter, Matthew Robert Howard, Thomas M. Hemachandra, Sachithra Madhawa Teller, Seth Roy, Nicholas Natural language provides a flexible, intuitive way for people to command robots, which is becoming increasingly important as robots transition to working alongside people in our homes and workplaces. To follow instructions in unknown environments, robots will be expected to reason about parts of the environments that were described in the instruction, but that the robot has no direct knowledge about. However, most existing approaches to natural language understanding require that the robot’s environment be known a priori. This paper proposes a probabilistic framework that enables robots to follow commands given in natural language, without any prior knowledge of the environment. The novelty lies in exploiting environment information implicit in the instruction, thereby treating language as a type of sensor that is used to formulate a prior distribution over the unknown parts of the environment. The algorithm then uses this learned distribution to infer a sequence of actions that are most consistent with the command, updating our belief as we gather Keywords Natural Language; Mobile Robot; Parse Tree; World Model; Behavior Inference 2018-04-09T18:44:05Z 2018-04-09T18:44:05Z 2015-11 2018-04-09T18:31:43Z Article http://purl.org/eprint/type/ConferencePaper 978-3-319-23777-0 978-3-319-23778-7 1610-7438 1610-742X http://hdl.handle.net/1721.1/114638 Duvallet, Felix, Matthew R. Walter, Thomas Howard, Sachithra Hemachandra, Jean Oh, Seth Teller, Nicholas Roy, and Anthony Stentz. “Inferring Maps and Behaviors from Natural Language Instructions.” Experimental Robotics (November 2015): 373–388 © 2016 Springer International Publishing Switzerland https://orcid.org/0000-0002-8293-0492 http://dx.doi.org/10.1007/978-3-319-23778-7_25 Experimental Robotics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Springer Nature Other univ. web domain |
| spellingShingle | Duvallet, Felix Oh, Jean Stentz, Anthony Walter, Matthew Robert Howard, Thomas M. Hemachandra, Sachithra Madhawa Teller, Seth Roy, Nicholas Inferring Maps and Behaviors from Natural Language Instructions |
| title | Inferring Maps and Behaviors from Natural Language Instructions |
| title_full | Inferring Maps and Behaviors from Natural Language Instructions |
| title_fullStr | Inferring Maps and Behaviors from Natural Language Instructions |
| title_full_unstemmed | Inferring Maps and Behaviors from Natural Language Instructions |
| title_short | Inferring Maps and Behaviors from Natural Language Instructions |
| title_sort | inferring maps and behaviors from natural language instructions |
| url | http://hdl.handle.net/1721.1/114638 https://orcid.org/0000-0002-8293-0492 |
| work_keys_str_mv | AT duvalletfelix inferringmapsandbehaviorsfromnaturallanguageinstructions AT ohjean inferringmapsandbehaviorsfromnaturallanguageinstructions AT stentzanthony inferringmapsandbehaviorsfromnaturallanguageinstructions AT waltermatthewrobert inferringmapsandbehaviorsfromnaturallanguageinstructions AT howardthomasm inferringmapsandbehaviorsfromnaturallanguageinstructions AT hemachandrasachithramadhawa inferringmapsandbehaviorsfromnaturallanguageinstructions AT tellerseth inferringmapsandbehaviorsfromnaturallanguageinstructions AT roynicholas inferringmapsandbehaviorsfromnaturallanguageinstructions |