Learning Soft Robotic Dynamics with Active Exploration
Learning Soft Robotic Dynamics with Active Exploration
This research introduces an uncertainty-aware active exploration framework to learn task-agnostic and generalizable dynamics models for soft robotic systems. The method is evaluated on three simulated platforms—a continuum arm, an articulated fish in fluid, and a musculoskeletal leg—as well as a real-world pneumatically actuated continuum arm. Compared with random exploration and task-specific baselines, the approach achieves higher modeling accuracy by actively collecting informative data. Improved model quality leads to better zero-shot control performance on unseen tasks and robust operation under sensing noise, actuation delays, and material nonlinearities. The results demonstrate that uncertainty-driven active exploration enables data-efficient dynamics learning across diverse soft robotic morphologies, supporting autonomous and adaptable control for compliant robots.
The authors present a data-driven framework for learning dynamics models of soft robots using active uncertainty-aware exploration, evaluated on three simulated platforms and one real-world pneumatically actuated continuum arm.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S3
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
framework that autonomously learns task-agnostic and generalizable dynamics models of soft robotic systems. We evaluate this framework on three simulated platforms---a continuum arm, an articulated fish in fluid, and a musculoskeletal leg---and on a real-world pneumatically actuated continuum arm. Compared with random exploration and task-specific baseline, our method achieves higher modeling accuracy by actively co
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org