Teaching robots about human environments: Leveraging human interaction to efficiently learn and use multisensory object affordances

Chu, Vivian

Title:

Teaching robots about human environments: Leveraging human interaction to efficiently learn and use multisensory object affordances

dc.contributor.advisor	Thomaz, Andrea L.
dc.contributor.advisor	Chernova, Sonia
dc.contributor.author	Chu, Vivian
dc.contributor.committeeMember	Christensen, Henrik I.
dc.contributor.committeeMember	Kemp, Charles C.
dc.contributor.committeeMember	Srinivasa, Siddhartha
dc.contributor.department	Interactive Computing
dc.date.accessioned	2018-05-31T18:12:29Z
dc.date.available	2018-05-31T18:12:29Z
dc.date.created	2018-05
dc.date.issued	2018-01-09
dc.date.submitted	May 2018
dc.date.updated	2018-05-31T18:12:29Z
dc.description.abstract	The real world is complex, unstructured, and contains high levels of uncertainty. Although past work shows that robots can successfully operate in situations where a single skill is needed, they will need a framework that enables them to reason and learn continuously so that they can operate effectively in human-centric environments. One framework that allows robots to aggregate a library of skills is to model the world using affordances. In this thesis, we choose to model affordances as the relationship between a robot's actions on its environment and the effects of those actions. By modeling the world with affordances, robots can reason about what actions they need to take to achieve a goal. This thesis provides a framework that allows robots to learn affordance models through interaction and human guidance. Within the scope of robot affordance learning, there has been a large focus on learning visual skill representations due to the difficulty of getting robots to interact with the environment. Furthermore, utilizing different modalities (e.g., touch and sound) introduces challenges such as different sampling rates and data resolution. This thesis addresses the above challenges by contributing a human-centered framework for robot affordance learning that allows human teachers to guide the robot in the modeling process throughout the entire pipeline of affordance learning. We introduce several novel human-guided robot self-exploration algorithms that use human guidance to enable robots to efficiently explore the environment and learn affordance models for a diverse range of manipulation tasks. The work contributes a multisensory affordance model that integrates visual, haptic, and audio input, and a novel control framework that allows adaptive object manipulation using multisensory affordances.
dc.description.degree	Ph.D.
dc.format.mimetype	application/pdf
dc.identifier.uri	http://hdl.handle.net/1853/59839
dc.language.iso	en_US
dc.publisher	Georgia Institute of Technology
dc.subject	Robotics
dc.subject	Robot learning
dc.subject	Affordance learning
dc.subject	Human robot interaction
dc.subject	Multisensory data
dc.subject	Robot object manipulation
dc.subject	Human-guided robot exploration
dc.subject	Machine learning
dc.subject	Artificial intelligence
dc.subject	Haptics
dc.subject	Adaptable controllers
dc.subject	Multisensory robot control
dc.subject	Human-guided affordance learning
dc.subject	Interactive multisensory perception
dc.subject	Multimodal data
dc.subject	Sensor fusion
dc.title	Teaching robots about human environments: Leveraging human interaction to efficiently learn and use multisensory object affordances
dc.type	Text
dc.type.genre	Dissertation
dspace.entity.type	Publication
local.contributor.advisor	Chernova, Sonia
local.contributor.corporatename	College of Computing
local.contributor.corporatename	School of Interactive Computing
relation.isAdvisorOfPublication	c2c8220e-349a-4030-9c58-0981da9d1c5d
relation.isOrgUnitOfPublication	c8892b3c-8db6-4b7b-a33a-1b67f7db2021
relation.isOrgUnitOfPublication	aac3f010-e629-4d08-8276-81143eeaf5cc
thesis.degree.level	Doctoral