Show simple item record

dc.creatorCochrane, Eric C
dc.date.accessioned2017-10-10T20:11:27Z
dc.date.available2017-10-10T20:11:27Z
dc.date.created2017-05
dc.date.issued2015-09-21
dc.date.submittedMay 2017
dc.identifier.urihttps://hdl.handle.net/1969.1/164392
dc.description.abstractWe address the problem of controlling continuum manipulators and evaluate Reinforcement Learning to produce a control policy for a robotic platform. Our approach discretizes the state and action spaces to reduce the training needed to converge to an optimal policy. We integrate Q-Learning, computer vision, and a pneumatic system into a single robotic platform. The agent is tasked with tracking and striking a target with a continuum manipulator modeled by a party-blower. We describe Reinforcement Learning, the methods used to train the agent, and describe the performance of the optimal policy successfully striking the target.en
dc.format.mimetypeapplication/pdf
dc.subjectReinforcement Learningen
dc.subjectContinuum Manipulatoren
dc.subjectArtificial Intelligenceen
dc.subjectRoboticsen
dc.subjectMachine Learningen
dc.subjectComputer Scienceen
dc.subjecten
dc.titleA Novel Continuum Manipulatoren
dc.typeThesisen
thesis.degree.disciplineComputer Sci. & Engren
thesis.degree.grantorUndergraduate Research Scholars Programen
dc.contributor.committeeMemberShell, Dylan A
dc.type.materialtexten
dc.date.updated2017-10-10T20:11:27Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record