Show simple item record

dc.contributor.authorVirani, Nurali
dc.contributor.authorJha, Devesh K.
dc.contributor.authorYuan, Zhenyuan
dc.contributor.authorShekhawat, Ishana
dc.contributor.authorRay, Asok
dc.date.accessioned2019-02-28T11:13:39Z
dc.date.available2019-02-28T11:13:39Z
dc.date.copyright11/8/2017 12:00:00 AM
dc.date.issued2018
dc.identifier.issn0022-0434
dc.identifier.otherds_140_03_030906.pdf
dc.identifier.urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4254052
dc.description.abstractThis paper addresses the problem of learning dynamic models of hybrid systems from demonstrations and then the problem of imitation of those demonstrations by using Bayesian filtering. A linear programming-based approach is used to develop nonparametric kernel-based conditional density estimation technique to infer accurate and concise dynamic models of system evolution from data. The training data for these models have been acquired from demonstrations by teleoperation. The trained data-driven models for mode-dependent state evolution and state-dependent mode evolution are then used online for imitation of demonstrated tasks via particle filtering. The results of simulation and experimental validation with a hexapod robot are reported to establish generalization of the proposed learning and control algorithms.
dc.publisherThe American Society of Mechanical Engineers (ASME)
dc.titleImitation of Demonstrations Using Bayesian Filtering With Nonparametric Data-Driven Models
dc.typeJournal Paper
dc.journal.volume140
dc.journal.issue3
dc.journal.titleJournal of Dynamic Systems, Measurement, and Control
dc.identifier.doi10.1115/1.4037782
dc.journal.fristpage30906
dc.journal.lastpage030906-9
dc.treeJournal of Dynamic Systems, Measurement, and Control:;2018:;volume( 140 ):;issue: 003
dc.contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record