Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms

Hsin-Jung Yang, Mahsa Khosravi, Benjamin Walt, Girish Krishnan, Soumik Sarkar
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:1300-1312, 2025.

Abstract

Soft continuum arms (SCAs) soft and deformable nature presents challenges in modeling and control due to their infinite degrees of freedom and non-linear behavior. This work introduces a reinforcement learning (RL)-based framework for visual servoing tasks on SCAs with zero-shot sim-to-real transfer capabilities, demonstrated on a single section pneumatic manipulator capable of bending and twisting. The framework decouples kinematics from mechanical properties using an RL kinematic controller for motion planning and a local controller for actuation refinement, leveraging minimal sensing with visual feedback. Trained entirely in simulation, the RL controller achieved a 99.8% success rate. When deployed on hardware, it achieved a 67% success rate in zero-shot sim-to-real transfer, demonstrating robustness and adaptability. This approach offers a scalable solution for SCAs in 3D visual servoing, with potential for further refinement and expanded applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-yang25b, title = {Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms}, author = {Yang, Hsin-Jung and Khosravi, Mahsa and Walt, Benjamin and Krishnan, Girish and Sarkar, Soumik}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {1300--1312}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/yang25b/yang25b.pdf}, url = {https://proceedings.mlr.press/v283/yang25b.html}, abstract = {Soft continuum arms (SCAs) soft and deformable nature presents challenges in modeling and control due to their infinite degrees of freedom and non-linear behavior. This work introduces a reinforcement learning (RL)-based framework for visual servoing tasks on SCAs with zero-shot sim-to-real transfer capabilities, demonstrated on a single section pneumatic manipulator capable of bending and twisting. The framework decouples kinematics from mechanical properties using an RL kinematic controller for motion planning and a local controller for actuation refinement, leveraging minimal sensing with visual feedback. Trained entirely in simulation, the RL controller achieved a 99.8% success rate. When deployed on hardware, it achieved a 67% success rate in zero-shot sim-to-real transfer, demonstrating robustness and adaptability. This approach offers a scalable solution for SCAs in 3D visual servoing, with potential for further refinement and expanded applications.} }
Endnote
%0 Conference Paper %T Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms %A Hsin-Jung Yang %A Mahsa Khosravi %A Benjamin Walt %A Girish Krishnan %A Soumik Sarkar %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-yang25b %I PMLR %P 1300--1312 %U https://proceedings.mlr.press/v283/yang25b.html %V 283 %X Soft continuum arms (SCAs) soft and deformable nature presents challenges in modeling and control due to their infinite degrees of freedom and non-linear behavior. This work introduces a reinforcement learning (RL)-based framework for visual servoing tasks on SCAs with zero-shot sim-to-real transfer capabilities, demonstrated on a single section pneumatic manipulator capable of bending and twisting. The framework decouples kinematics from mechanical properties using an RL kinematic controller for motion planning and a local controller for actuation refinement, leveraging minimal sensing with visual feedback. Trained entirely in simulation, the RL controller achieved a 99.8% success rate. When deployed on hardware, it achieved a 67% success rate in zero-shot sim-to-real transfer, demonstrating robustness and adaptability. This approach offers a scalable solution for SCAs in 3D visual servoing, with potential for further refinement and expanded applications.
APA
Yang, H., Khosravi, M., Walt, B., Krishnan, G. & Sarkar, S.. (2025). Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:1300-1312 Available from https://proceedings.mlr.press/v283/yang25b.html.

Related Material