Real-Time Reinforcement Learning for Dynamic Tasks with a Parallel Soft Robot
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916966680231936 |
|---|---|
| author | Avtges, James Ketchum, Jake Schlafly, Millicent Young, Helena Kim, Taekyoung Pinosky, Allison Truby, Ryan L. Murphey, Todd D. |
| author_facet | Avtges, James Ketchum, Jake Schlafly, Millicent Young, Helena Kim, Taekyoung Pinosky, Allison Truby, Ryan L. Murphey, Todd D. |
| contents | Closed-loop control remains an open challenge in soft robotics. The nonlinear responses of soft actuators under dynamic loading conditions limit the use of analytic models for soft robot control. Traditional methods of controlling soft robots underutilize their configuration spaces to avoid nonlinearity, hysteresis, large deformations, and the risk of actuator damage. Furthermore, episodic data-driven control approaches such as reinforcement learning (RL) are traditionally limited by sample efficiency and inconsistency across initializations. In this work, we demonstrate RL for reliably learning control policies for dynamic balancing tasks in real-time single-shot hardware deployments. We use a deformable Stewart platform constructed using parallel, 3D-printed soft actuators based on motorized handed shearing auxetic (HSA) structures. By introducing a curriculum learning approach based on expanding neighborhoods of a known equilibrium, we achieve reliable single-deployment balancing at arbitrary coordinates. In addition to benchmarking the performance of model-based and model-free methods, we demonstrate that in a single deployment, Maximum Diffusion RL is capable of learning dynamic balancing after half of the actuators are effectively disabled, by inducing buckling and by breaking actuators with bolt cutters. Training occurs with no prior data, in as fast as 15 minutes, with performance nearly identical to the fully-intact platform. Single-shot learning on hardware facilitates soft robotic systems reliably learning in the real world and will enable more diverse and capable soft robots. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19525 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Reinforcement Learning for Dynamic Tasks with a Parallel Soft Robot Avtges, James Ketchum, Jake Schlafly, Millicent Young, Helena Kim, Taekyoung Pinosky, Allison Truby, Ryan L. Murphey, Todd D. Robotics Closed-loop control remains an open challenge in soft robotics. The nonlinear responses of soft actuators under dynamic loading conditions limit the use of analytic models for soft robot control. Traditional methods of controlling soft robots underutilize their configuration spaces to avoid nonlinearity, hysteresis, large deformations, and the risk of actuator damage. Furthermore, episodic data-driven control approaches such as reinforcement learning (RL) are traditionally limited by sample efficiency and inconsistency across initializations. In this work, we demonstrate RL for reliably learning control policies for dynamic balancing tasks in real-time single-shot hardware deployments. We use a deformable Stewart platform constructed using parallel, 3D-printed soft actuators based on motorized handed shearing auxetic (HSA) structures. By introducing a curriculum learning approach based on expanding neighborhoods of a known equilibrium, we achieve reliable single-deployment balancing at arbitrary coordinates. In addition to benchmarking the performance of model-based and model-free methods, we demonstrate that in a single deployment, Maximum Diffusion RL is capable of learning dynamic balancing after half of the actuators are effectively disabled, by inducing buckling and by breaking actuators with bolt cutters. Training occurs with no prior data, in as fast as 15 minutes, with performance nearly identical to the fully-intact platform. Single-shot learning on hardware facilitates soft robotic systems reliably learning in the real world and will enable more diverse and capable soft robots. |
| title | Real-Time Reinforcement Learning for Dynamic Tasks with a Parallel Soft Robot |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.19525 |