Uncertainty-aware active exploration learning of soft robot dynamics
What happened
Hehui Zheng and other authors propose an uncertainty-aware active exploration framework that enables soft robot systems to autonomously learn task-agnostic, generalizable dynamics models. The authors state that the framework was evaluated on three simulation platforms (a continuum arm, a jointed fish in fluid, and a musculoskeletal leg) and on one real pneumatic continuum arm, and that compared with random exploration and task-specific baselines, it achieved higher modeling accuracy by actively collecting informative data. The authors also state that improved model quality led to higher returns in zero-shot control on unseen tasks, and remained robust under sensor noise, actuation delay, and material nonlinearity. These results are all as described by the authors in the paper.
AI 根据报道生成 · 6 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROLearning Soft Robot Dynamics: An Uncertainty-Aware Active Exploration Framework
The authors propose an uncertainty-aware active exploration framework that can autonomously learn task-agnostic, generalizable dynamics models for soft robots. The method was evaluated on three simulation platforms—a continuum arm, an articulated fish in fluid, and a musculoskeletal leg—as well as on a real pneumatically actuated continuum arm. Compared with random exploration and task-specific baselines, it achieves higher modeling accuracy and yields higher returns in zero-shot control on unseen tasks, while remaining robust under sensing noise, actuation delays, and material nonlinearities.
Activity for this event
- Current
- 3
- Peak
- 10Nov 5 14:00
- Past 24 hours
- -49%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.