CyberDemo：增強模擬人類示範以進行現實世界的熟練操作

CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation

February 22, 2024

作者: Jun Wang, Yuzhe Qin, Kaiming Kuang, Yigit Korkmaz, Akhilan Gurumoorthy, Hao Su, Xiaolong Wang

cs.AI

摘要

我們介紹了 CyberDemo，這是一種新穎的機器人模仿學習方法，利用模擬人類示範來執行真實世界任務。通過在模擬環境中加入大量數據擴增，CyberDemo 在轉移到真實世界時優於傳統的同領域真實世界示範，能處理多樣的物理和視覺條件。儘管在數據收集方面具有可負擔性和便利性，CyberDemo 在各種任務的成功率方面優於基準方法，展現對先前未見物體的泛化能力。例如，它可以旋轉新穎的四閥和五閥，儘管人類示範只涉及三閥。我們的研究展示了模擬人類示範對於真實世界靈巧操作任務具有重要潛力。更多詳細信息請參閱 https://cyber-demo.github.io

English

We introduce CyberDemo, a novel approach to robotic imitation learning that leverages simulated human demonstrations for real-world tasks. By incorporating extensive data augmentation in a simulated environment, CyberDemo outperforms traditional in-domain real-world demonstrations when transferred to the real world, handling diverse physical and visual conditions. Regardless of its affordability and convenience in data collection, CyberDemo outperforms baseline methods in terms of success rates across various tasks and exhibits generalizability with previously unseen objects. For example, it can rotate novel tetra-valve and penta-valve, despite human demonstrations only involving tri-valves. Our research demonstrates the significant potential of simulated human demonstrations for real-world dexterous manipulation tasks. More details can be found at https://cyber-demo.github.io