Sequential Topological Representations for Predictive Models of Deformable Objects

Rika Antonova, Anastasia Varava, Peiyang Shi, J. Frederico Carvalho, Danica Kragic
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:348-360, 2021.

Abstract

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 that 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-antonova21a, title = {Sequential Topological Representations for Predictive Models of Deformable Objects}, author = {Antonova, Rika and Varava, Anastasia and Shi, Peiyang and Carvalho, J. Frederico and Kragic, Danica}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {348--360}, year = {2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and A. Parrilo, Pablo and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, volume = {144}, series = {Proceedings of Machine Learning Research}, month = {07 -- 08 June}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v144/antonova21a/antonova21a.pdf}, url = {https://proceedings.mlr.press/v144/antonova21a.html}, abstract = {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 that 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.} }
Endnote
%0 Conference Paper %T Sequential Topological Representations for Predictive Models of Deformable Objects %A Rika Antonova %A Anastasia Varava %A Peiyang Shi %A J. Frederico Carvalho %A Danica Kragic %B Proceedings of the 3rd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2021 %E Ali Jadbabaie %E John Lygeros %E George J. Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire J. Tomlin %E Melanie N. Zeilinger %F pmlr-v144-antonova21a %I PMLR %P 348--360 %U https://proceedings.mlr.press/v144/antonova21a.html %V 144 %X 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 that 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.
APA
Antonova, R., Varava, A., Shi, P., Carvalho, J.F. & Kragic, D.. (2021). Sequential Topological Representations for Predictive Models of Deformable Objects. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:348-360 Available from https://proceedings.mlr.press/v144/antonova21a.html.

Related Material