2023-04-28 コロンビア大学
Credit: Columbia University ROAM Lab
この技術は、物流や製造分野での利用が期待されている。
研究者たちは、物理的なロボットが現実世界で有用になるためには、抽象的な知性と具体的な操作能力が必要であることを指摘している。
この研究により、具体的な操作能力が向上したことは、大規模言語モデルが提供する抽象的な知性と相補的であると考えられている。
＜関連情報＞
- https://www.engineering.columbia.edu/news/highly-dexterous-robot-hand-can-operate-in-the-dark
- https://arxiv.org/abs/2303.03486
器用な操作の強化学習のためのサンプリングに基づく探索
Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation
Gagan Khandate, Siqi Shang, Eric T. Chang, Tristan Luca Saidi, Johnson Adams, Matei Ciocarlie
arXiv Submitted on: 6 Mar 2023
DOI: https://doi.org/10.48550/arXiv.2303.03486
In this paper, we present a novel method for achieving dexterous manipulation of complex objects, while simultaneously securing the object without the use of passive support surfaces. We posit that a key difficulty for training such policies in a Reinforcement Learning framework is the difficulty of exploring the problem state space, as the accessible regions of this space form a complex structure along manifolds of a high-dimensional space. To address this challenge, we use two versions of the non-holonomic Rapidly-Exploring Random Trees algorithm; one version is more general, but requires explicit use of the environment’s transition function, while the second version uses manipulation-specific kinematic constraints to attain better sample efficiency. In both cases, we use states found via sampling-based exploration to generate reset distributions that enable training control policies under full dynamic constraints via model-free Reinforcement Learning. We show that these policies are effective at manipulation problems of higher difficulty than previously shown, and also transfer effectively to real robots. Videos of the real-hand demonstrations can be found on the project website: this https URL
