Show simple item record

dc.contributor.authorPark, Daehyung
dc.contributor.authorKapusta, Ariel
dc.contributor.authorKim, You Keun
dc.contributor.authorRehg, James M.
dc.contributor.authorKemp, Charles C.
dc.date.accessioned2015-05-04T18:13:53Z
dc.date.available2015-05-04T18:13:53Z
dc.date.issued2014-09
dc.identifier.citationPark, D.; Kapusta, A.; Kim, Y.K.; Rehg, J.M.; & Kemp, C.C. (2014). "Learning to Reach into the Unknown: Selecting Initial Conditions When Reaching in Clutter". IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), 14-18 September, pp. 630-637.en_US
dc.identifier.urihttp://hdl.handle.net/1853/53330
dc.description©2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.descriptionPresented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), 14-18 September 2014, Chicago, IL.
dc.descriptionDOI: 10.1109/IROS.2014.6942625
dc.description.abstractOften in highly-cluttered environments, a robot can observe the exterior of the environment with ease, but cannot directly view nor easily infer its detailed internal structure (e.g., dense foliage or a full refrigerator shelf). We present a data-driven approach that greatly improves a robot’s success at reaching to a goal location in the unknown interior of an environment based on observable external properties, such as the category of the clutter and the locations of openings into the clutter (i.e., apertures). We focus on the problem of selecting a good initial configuration for a manipulator when reaching with a greedy controller. We use density estimation to model the probability of a successful reach given an initial condition and then perform constrained optimization to find an initial condition with the highest estimated probability of success. We evaluate our approach with two simulated robots reaching in clutter, and provide a demonstration with a real PR2 robot reaching to locations through random apertures. In our evaluations, our approach significantly outperformed two alter- native approaches when making two consecutive reach attempts to goals in distinct categories of unknown clutter. Notably, our approach only uses sparse readily-apparent features.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectAperturesen_US
dc.subjectConstrained optimizationen_US
dc.subjectDensity estimationen_US
dc.subjectGreedy controlleren_US
dc.titleLearning to Reach into the Unknown: Selecting Initial Conditions When Reaching in Clutteren_US
dc.typePost-printen_US
dc.typeProceedingsen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Institute for Robotics and Intelligent Machinesen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Healthcare Robotics Laben_US
dc.publisher.originalInstitute of Electrical and Electronics Engineers
dc.identifier.doi10.1109/IROS.2014.6942625
dc.embargo.termsnullen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record