Differentiable Discrete Elastic Rods for Real-Time Modeling of Deformable Linear Objects

Yizhou Chen, Yiting Zhang, Zachary Brei, Tiancheng Zhang, Yuzhen Chen, Julie Wu, Ram Vasudevan
Proceedings of The 8th Conference on Robot Learning, PMLR 270:2996-3014, 2025.

Abstract

This paper addresses the task of modeling Deformable Linear Objects (DLOs), such as ropes and cables, during dynamic motion over long time horizons. This task presents significant challenges due to the complex dynamics of DLOs. To address these challenges, this paper proposes differentiable Discrete Elastic Rods For deformable linear Objects with Real-time Modeling (DEFORM), a novel framework that combines a differentiable physics-based model with a learning framework to model DLOs accurately and in real-time. The performance of DEFORM is evaluated in an experimental setup involving two industrial robots and a variety of sensors. A comprehensive series of experiments demonstrate the efficacy of DEFORM in terms of accuracy, computational speed, and generalizability when compared to state-of-the-art alternatives. To further demonstrate the utility of DEFORM, this paper integrates it into a perception pipeline and illustrates its superior performance when compared to the state-of-the-art methods while tracking a DLO even in the presence of occlusions. Finally, this paper illustrates the superior performance of DEFORM when compared to state-of-the-art methods when it is applied to perform autonomous planning and control of DLOs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-chen25d, title = {Differentiable Discrete Elastic Rods for Real-Time Modeling of Deformable Linear Objects}, author = {Chen, Yizhou and Zhang, Yiting and Brei, Zachary and Zhang, Tiancheng and Chen, Yuzhen and Wu, Julie and Vasudevan, Ram}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {2996--3014}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/chen25d/chen25d.pdf}, url = {https://proceedings.mlr.press/v270/chen25d.html}, abstract = {This paper addresses the task of modeling Deformable Linear Objects (DLOs), such as ropes and cables, during dynamic motion over long time horizons. This task presents significant challenges due to the complex dynamics of DLOs. To address these challenges, this paper proposes differentiable Discrete Elastic Rods For deformable linear Objects with Real-time Modeling (DEFORM), a novel framework that combines a differentiable physics-based model with a learning framework to model DLOs accurately and in real-time. The performance of DEFORM is evaluated in an experimental setup involving two industrial robots and a variety of sensors. A comprehensive series of experiments demonstrate the efficacy of DEFORM in terms of accuracy, computational speed, and generalizability when compared to state-of-the-art alternatives. To further demonstrate the utility of DEFORM, this paper integrates it into a perception pipeline and illustrates its superior performance when compared to the state-of-the-art methods while tracking a DLO even in the presence of occlusions. Finally, this paper illustrates the superior performance of DEFORM when compared to state-of-the-art methods when it is applied to perform autonomous planning and control of DLOs.} }
Endnote
%0 Conference Paper %T Differentiable Discrete Elastic Rods for Real-Time Modeling of Deformable Linear Objects %A Yizhou Chen %A Yiting Zhang %A Zachary Brei %A Tiancheng Zhang %A Yuzhen Chen %A Julie Wu %A Ram Vasudevan %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-chen25d %I PMLR %P 2996--3014 %U https://proceedings.mlr.press/v270/chen25d.html %V 270 %X This paper addresses the task of modeling Deformable Linear Objects (DLOs), such as ropes and cables, during dynamic motion over long time horizons. This task presents significant challenges due to the complex dynamics of DLOs. To address these challenges, this paper proposes differentiable Discrete Elastic Rods For deformable linear Objects with Real-time Modeling (DEFORM), a novel framework that combines a differentiable physics-based model with a learning framework to model DLOs accurately and in real-time. The performance of DEFORM is evaluated in an experimental setup involving two industrial robots and a variety of sensors. A comprehensive series of experiments demonstrate the efficacy of DEFORM in terms of accuracy, computational speed, and generalizability when compared to state-of-the-art alternatives. To further demonstrate the utility of DEFORM, this paper integrates it into a perception pipeline and illustrates its superior performance when compared to the state-of-the-art methods while tracking a DLO even in the presence of occlusions. Finally, this paper illustrates the superior performance of DEFORM when compared to state-of-the-art methods when it is applied to perform autonomous planning and control of DLOs.
APA
Chen, Y., Zhang, Y., Brei, Z., Zhang, T., Chen, Y., Wu, J. & Vasudevan, R.. (2025). Differentiable Discrete Elastic Rods for Real-Time Modeling of Deformable Linear Objects. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:2996-3014 Available from https://proceedings.mlr.press/v270/chen25d.html.

Related Material