Back to search

University of Washington

Intelligence Through the Lens of Interaction

Abstract

dc:description.abstract

In this thesis, I will discuss the problem of acquiring visual intelligence from the interaction, focusing on two aspects of visual understanding: (1) visual perception and (2) embodied intelligence. To address the first question, I designed experiments to learn visual representations by observing animals and humans interact with the visual world. Further, I investigated the idea of learning perception from hands-on interaction -- acquiring generalizable physical understanding by predicting the forces applied in an observed video and trying to replicate the motion observed in simulation, with no additional supervision provided. To address the second question, I discuss our findings on training intelligent embodied agents using interaction from two perspectives. I designed a training paradigm that enables learning-to-learn from interactions. This training regime helps us to continue to learn from our interactions even during inference time. Moreover, I introduce a visually rich object manipulation framework, ManipulaTHOR, which opens the gate for directly training embodied agents to interact intelligently in a physically realistic environment via low-level object manipulation and navigation.

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Ehsani, kiana
Advisors dc:contributor.advisor
  • Farhadi, Ali
  • Mottaghi, Roozbeh

Subjects

dc:subject × 7

Rights

dc:rights
Statement dc:rights
  • none
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1773/47997

Chain of custody

source
Harvested from
University of Washington
Base URL
digital.lib.washington.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Ehsani, kiana. Intelligence Through the Lens of Interaction. 2021. http://hdl.handle.net/1773/47997