Autonomous learning of object models on a mobile robot
In this article, we present and evaluate a system, which allows a mobile robot to autonomously detect, model, and re-recognize objects in everyday environments. While other systems have demonstrated one of these elements, to our knowledge, we present the first system, which is capable of doing all o...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Journal article |
| Published: |
IEEE
2016
|
| _version_ | 1797059913529163776 |
|---|---|
| author | Faulhammer, T Ambrus, R Burbridge, C Zillich, M Folkesson, J Hawes, N Jensfelt, P Vincze, M |
| author_facet | Faulhammer, T Ambrus, R Burbridge, C Zillich, M Folkesson, J Hawes, N Jensfelt, P Vincze, M |
| author_sort | Faulhammer, T |
| collection | OXFORD |
| description | In this article, we present and evaluate a system, which allows a mobile robot to autonomously detect, model, and re-recognize objects in everyday environments. While other systems have demonstrated one of these elements, to our knowledge, we present the first system, which is capable of doing all of these things, all without human interaction, in normal indoor scenes. Our system detects objects to learn by modeling the static part of the environment and extracting dynamic elements. It then creates and executes a view plan around a dynamic element to gather additional views for learning. Finally, these views are fused to create an object model. The performance of the system is evaluated on publicly available datasets as well as on data collected by the robot in both controlled and uncontrolled scenarios. |
| first_indexed | 2024-03-06T20:10:48Z |
| format | Journal article |
| id | oxford-uuid:2a803da3-b7c2-4105-aef7-1084d382b20c |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:10:48Z |
| publishDate | 2016 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:2a803da3-b7c2-4105-aef7-1084d382b20c2022-03-26T12:25:23ZAutonomous learning of object models on a mobile robotJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:2a803da3-b7c2-4105-aef7-1084d382b20cSymplectic Elements at OxfordIEEE2016Faulhammer, TAmbrus, RBurbridge, CZillich, MFolkesson, JHawes, NJensfelt, PVincze, MIn this article, we present and evaluate a system, which allows a mobile robot to autonomously detect, model, and re-recognize objects in everyday environments. While other systems have demonstrated one of these elements, to our knowledge, we present the first system, which is capable of doing all of these things, all without human interaction, in normal indoor scenes. Our system detects objects to learn by modeling the static part of the environment and extracting dynamic elements. It then creates and executes a view plan around a dynamic element to gather additional views for learning. Finally, these views are fused to create an object model. The performance of the system is evaluated on publicly available datasets as well as on data collected by the robot in both controlled and uncontrolled scenarios. |
| spellingShingle | Faulhammer, T Ambrus, R Burbridge, C Zillich, M Folkesson, J Hawes, N Jensfelt, P Vincze, M Autonomous learning of object models on a mobile robot |
| title | Autonomous learning of object models on a mobile robot |
| title_full | Autonomous learning of object models on a mobile robot |
| title_fullStr | Autonomous learning of object models on a mobile robot |
| title_full_unstemmed | Autonomous learning of object models on a mobile robot |
| title_short | Autonomous learning of object models on a mobile robot |
| title_sort | autonomous learning of object models on a mobile robot |
| work_keys_str_mv | AT faulhammert autonomouslearningofobjectmodelsonamobilerobot AT ambrusr autonomouslearningofobjectmodelsonamobilerobot AT burbridgec autonomouslearningofobjectmodelsonamobilerobot AT zillichm autonomouslearningofobjectmodelsonamobilerobot AT folkessonj autonomouslearningofobjectmodelsonamobilerobot AT hawesn autonomouslearningofobjectmodelsonamobilerobot AT jensfeltp autonomouslearningofobjectmodelsonamobilerobot AT vinczem autonomouslearningofobjectmodelsonamobilerobot |