Sökning: onr:"swepub:oai:DiVA.org:kth-338605" >
Sequential Topologi...
Sequential Topological Representations for Predictive Models of Deformable Objects
-
- Antonova, Rika (författare)
- Stanford University, Stanford, CA, USA
-
- Varava, Anastasiia (författare)
- KTH,Robotik, perception och lärande, RPL
-
- Shi, Peiyang (författare)
- KTH,Robotik, perception och lärande, RPL
-
visa fler...
-
- Pinto Basto de Carvalho, Joao Frederico, 1988- (författare)
- KTH,Robotik, perception och lärande, RPL
-
- Kragic, Danica, 1971- (författare)
- KTH,Robotik, perception och lärande, RPL
-
visa färre...
-
(creator_code:org_t)
- ML Research Press, 2021
- 2021
- Engelska.
-
Ingår i: Proceedings of the 3rd Conference on Learning for Dynamics and Control, L4DC 2021. - : ML Research Press. ; , s. 348-360
- Relaterad länk:
-
http://proceedings.m...
-
visa fler...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Deformable objects present a formidable challenge for robotic manipulation due to the lack of canonical low-dimensional representations and the difficulty of capturing, predicting, and controlling such objects. We construct compact topological representations to capture the state of highly deformable objects that are topologically nontrivial. We develop an approach that tracks the evolution of this topological state through time. Under several mild assumptions, we prove that the topology of the scene and its evolution can be recovered from point clouds representing the scene. Our further contribution is a method to learn predictive models that take a sequence of past point cloud observations as input and predict a sequence of topological states, conditioned on target/future control actions. Our experiments with highly deformable objects in simulation show that the proposed multistep predictive models yield more precise results than those obtained from computational topology libraries. These models can leverage patterns inferred across various objects and offer fast multistep predictions suitable for real-time applications.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
- NATURVETENSKAP -- Matematik -- Beräkningsmatematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Computational Mathematics (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)