Active Incremental Learning of a Contextual Skill Model

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.advisorHazara, Murtaza
dc.contributor.authorLi, Xiaopu
dc.contributor.schoolSähkötekniikan korkeakoulufi
dc.contributor.supervisorKyrki, Ville
dc.date.accessioned2019-10-27T19:43:26Z
dc.date.available2019-10-27T19:43:26Z
dc.date.issued2019-10-21
dc.description.abstractContextual skill models enable robot to generalize parameterized skills for a range of task parameters by using regression on several optimal policies. However, the task difficulty and task sequence of learning a contextual skill model is usually neglected. Thus, the learning process is usually time consuming since some tasks might be easier to learn or the knowledge of these tasks might be easier to share with other tasks. In this thesis, we introduce active incremental learning framework for actively learning a contextual skill model based on dynamical movement primitives which are widely used to learn parameterized policies on trajectory level as a dynamical system for robot. The proposed framework will first select a task which maximizes the expected improvement in skill performance over entire task parameters and then optimize the corresponding policy with a fixed number of iterations in policy search. We model the learning rate of policy search for predicting reward improvement over a single iteration. We evaluated the improvement of the skill performance in two tasks, ball-in-a-cup and basketball, with a simulated KUKA robot arm. In both, the results show that active task selection can improve the skill performance continuously over a baseline.en
dc.format.extent46
dc.format.mimetypeapplication/pdfen
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/40839
dc.identifier.urnURN:NBN:fi:aalto-201910275843
dc.language.isoenen
dc.locationP1fi
dc.programmeAEE - Master’s Programme in Automation and Electrical Engineering (TS2013)fi
dc.programme.majorControl, Robotics and Autonomous Systemsfi
dc.programme.mcodeELEC3025fi
dc.subject.keywordcontextual skill modelen
dc.subject.keywordactive incremental learningen
dc.subject.keyworddynamical movement primitivesen
dc.subject.keywordpolicy searchen
dc.titleActive Incremental Learning of a Contextual Skill Modelen
dc.typeG2 Pro gradu, diplomityöfi
dc.type.ontasotMaster's thesisen
dc.type.ontasotDiplomityöfi
local.aalto.electroniconlyyes
local.aalto.openaccessyes
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
master_Li_Xiaopu_2019.pdf
Size:
3.7 MB
Format:
Adobe Portable Document Format
Download
Collections
[dipl] Sähkötekniikan korkeakoulu / ELEC