New Method for Dynamic Shape Control of Soft-Trunk Robots
What happened
Hehui Zheng and other authors published a study that learns from data an adiabatic spectral submanifold (aSSM) model of the whole body of a trimmed helicoid soft-trunk robot and uses it for model predictive control (MPC), completing multiple shape control tasks on hardware. The authors claim that in closed-loop dynamic shape regulation, this method is 10 times better than existing linear baselines; in a human-robot interaction demonstration, it completed segmented shaping and balanced a tennis ball for more than 25 seconds, whereas the linear baseline failed to complete it. The authors also claim that a model-free reinforcement learning policy trained on hardware for 12 hours failed on the same balancing task. These comparative results come from the authors' own account and have not yet been independently verified.
AI 根据报道生成 · 6 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.RODynamic Shape Control of Soft Trunk Robots Based on aSSM Model and MPC
The research team learned an adiabatic spectral submanifold (aSSM) model of the full body of a trimmed-helicoid soft trunk robot from data and used it in model predictive control (MPC), completing a range of shape control tasks on hardware. In closed-loop dynamic shape regulation, the method outperformed existing linear baselines by a factor of 10; in human-in-the-loop interactive demos, it completed section-by-section shaping and balanced a tennis ball for more than 25 seconds, whereas the linear baselines failed to complete the task. A model-free reinforcement learning policy trained on hardware for 12 hours failed on the same balancing task.
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.