Vision, Instruction, and Action
This thesis describes Sonja, a system which uses instructions in the course of visually-guided activity. The thesis explores an integration of research in vision, activity, and natural language pragmatics. Sonja's visual system demonstrates the use of several intermediate visual processes,...
Main Author: | |
---|---|
Language: | en_US |
Published: |
2004
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/6819 |
_version_ | 1826195482537361408 |
---|---|
author | Chapman, David |
author_facet | Chapman, David |
author_sort | Chapman, David |
collection | MIT |
description | This thesis describes Sonja, a system which uses instructions in the course of visually-guided activity. The thesis explores an integration of research in vision, activity, and natural language pragmatics. Sonja's visual system demonstrates the use of several intermediate visual processes, particularly visual search and routines, previously proposed on psychophysical grounds. The computations Sonja performs are compatible with the constraints imposed by neuroscientifically plausible hardware. Although Sonja can operate autonomously, it can also make flexible use of instructions provided by a human advisor. The system grounds its understanding of these instructions in perception and action. |
first_indexed | 2024-09-23T10:13:23Z |
id | mit-1721.1/6819 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T10:13:23Z |
publishDate | 2004 |
record_format | dspace |
spelling | mit-1721.1/68192019-04-10T09:58:43Z Vision, Instruction, and Action Chapman, David visual attention visual search visual routines activity sinstruction use reference This thesis describes Sonja, a system which uses instructions in the course of visually-guided activity. The thesis explores an integration of research in vision, activity, and natural language pragmatics. Sonja's visual system demonstrates the use of several intermediate visual processes, particularly visual search and routines, previously proposed on psychophysical grounds. The computations Sonja performs are compatible with the constraints imposed by neuroscientifically plausible hardware. Although Sonja can operate autonomously, it can also make flexible use of instructions provided by a human advisor. The system grounds its understanding of these instructions in perception and action. 2004-10-20T19:58:10Z 2004-10-20T19:58:10Z 1990-04-01 AITR-1204 http://hdl.handle.net/1721.1/6819 en_US AITR-1204 244 p. 9076736 bytes 13802270 bytes application/postscript application/pdf application/postscript application/pdf |
spellingShingle | visual attention visual search visual routines activity sinstruction use reference Chapman, David Vision, Instruction, and Action |
title | Vision, Instruction, and Action |
title_full | Vision, Instruction, and Action |
title_fullStr | Vision, Instruction, and Action |
title_full_unstemmed | Vision, Instruction, and Action |
title_short | Vision, Instruction, and Action |
title_sort | vision instruction and action |
topic | visual attention visual search visual routines activity sinstruction use reference |
url | http://hdl.handle.net/1721.1/6819 |
work_keys_str_mv | AT chapmandavid visioninstructionandaction |