.png){kind=icon}
返回
Task-Driven Hybrid Model Reduction for Dexterous Manipulation
.png){kind=icon}
OA
AI
DOI：10.1109/TRO.2024.3359531.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In contact-rich tasks, like dexterous manipulation, the hybrid nature of making and breaking contact creates challenges for model representation and control. For example, choosing and sequencing contact locations for in-hand manipulation, where there are thousands of potential hybrid modes, is not generally tractable. In this article, we are inspired by the observation that far fewer modes are actually necessary to accomplish many tasks. Building on our prior work learning hybrid models, represented as linear complementarity systems, we find a reduced-order hybrid model requiring only a limited number of task-relevant modes. This simplified representation, in combination with model predictive control, enables real-time control yet is sufficient for achieving high performance. We demonstrate the proposed method first on synthetic hybrid systems, reducing the mode count by multiple orders of magnitude while achieving task performance loss of less than 5%. We also apply the proposed method to a three-fingered robotic hand manipulating a previously unknown object. With no prior knowledge, we achieve state-of-the-art closed-loop performance within a few minutes of online learning, by collecting only a few thousand environment samples.
Keyword:
Dexterous manipulation
hybrid control systems
model predictive control (MPC)
model reduction
model-based reinforcement learning
期刊
IF:
10.5
论文数:
3.3K
被引数:
2.8W
机构
引用论文
.png){kind=icon}
CasADi: a software framework for nonlinear optimization and optimal controlCasADi: 非线性优化和最优控制的软件框架
PREAI
分享收藏分享收藏
查看更多内容