Humt, Matthias und Winkelbauer, Dominik und Hillenbrand, Ulrich (2023) Shape Completion with Prediction of Uncertain Regions. In: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023. IEEE. IEEE/RSJ International Conference on Intelligent Robots (IROS) 2023, 2023-10-01 - 2023-10-05, Detroit, IL, USA. doi: 10.1109/IROS55552.2023.10342487. ISBN 978-166549190-7. ISSN 2153-0858.
![]() |
PDF
4MB |
Offizielle URL: https://ieeexplore.ieee.org/document/10342487
Kurzfassung
Shape completion, i.e., predicting the complete geometry of an object from a partial observation, is highly relevant for several downstream tasks, most notably robotic manipulation. When basing planning or prediction of real grasps on object shape reconstruction, an indication of severe geometric uncertainty is indispensable. In particular, there can be an irreducible uncertainty in extended regions about the presence of entire object parts when given ambiguous object views. To treat this important case, we propose two novel methods for predicting such uncertain regions as straightforward extensions of any method for predicting local spatial occupancy, one through postprocessing occupancy scores, the other through direct prediction of an uncertainty indicator. We compare these methods together with two known approaches to probabilistic shape completion. Moreover, we generate a dataset, derived from ShapeNet [1], of realistically rendered depth images of object views with ground-truth annotations for the uncertain regions. We train on this dataset and test each method in shape completion and prediction of uncertain regions for known and novel object instances and on synthetic and real data. While direct uncertainty prediction is by far the most accurate in the segmentation of uncertain regions, both novel methods outperform the two baselines in shape completion and uncertain region prediction, and avoiding the predicted uncertain regions increases the quality of grasps for all tested methods. Web: https://github.com/DLR-RM/shape-completion
elib-URL des Eintrags: | https://elib.dlr.de/195724/ | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Konferenzbeitrag (Vortrag, Poster) | ||||||||||||||||
Titel: | Shape Completion with Prediction of Uncertain Regions | ||||||||||||||||
Autoren: |
| ||||||||||||||||
Datum: | 13 Dezember 2023 | ||||||||||||||||
Erschienen in: | 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023 | ||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||
Open Access: | Ja | ||||||||||||||||
Gold Open Access: | Nein | ||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||
In ISI Web of Science: | Nein | ||||||||||||||||
DOI: | 10.1109/IROS55552.2023.10342487 | ||||||||||||||||
Verlag: | IEEE | ||||||||||||||||
ISSN: | 2153-0858 | ||||||||||||||||
ISBN: | 978-166549190-7 | ||||||||||||||||
Status: | veröffentlicht | ||||||||||||||||
Stichwörter: | Shape completion, 3D point cloud, range image, grasp prediction | ||||||||||||||||
Veranstaltungstitel: | IEEE/RSJ International Conference on Intelligent Robots (IROS) 2023 | ||||||||||||||||
Veranstaltungsort: | Detroit, IL, USA | ||||||||||||||||
Veranstaltungsart: | internationale Konferenz | ||||||||||||||||
Veranstaltungsbeginn: | 1 Oktober 2023 | ||||||||||||||||
Veranstaltungsende: | 5 Oktober 2023 | ||||||||||||||||
Veranstalter : | IEEE | ||||||||||||||||
HGF - Forschungsbereich: | Luftfahrt, Raumfahrt und Verkehr | ||||||||||||||||
HGF - Programm: | Raumfahrt | ||||||||||||||||
HGF - Programmthema: | Robotik | ||||||||||||||||
DLR - Schwerpunkt: | Raumfahrt | ||||||||||||||||
DLR - Forschungsgebiet: | R RO - Robotik | ||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | R - Autonomie & Geschicklichkeit [RO] | ||||||||||||||||
Standort: | Oberpfaffenhofen | ||||||||||||||||
Institute & Einrichtungen: | Institut für Robotik und Mechatronik (ab 2013) > Perzeption und Kognition | ||||||||||||||||
Hinterlegt von: | Hillenbrand, Ulrich | ||||||||||||||||
Hinterlegt am: | 28 Jun 2023 22:08 | ||||||||||||||||
Letzte Änderung: | 24 Apr 2024 20:56 |
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags