CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation
This addresses the challenge of affordable and convenient data collection for robotics, though it appears incremental in leveraging simulation for real-world tasks.
The paper tackles the problem of robotic imitation learning for real-world dexterous manipulation by using simulated human demonstrations with data augmentation, achieving higher success rates and generalizability to unseen objects compared to traditional real-world demonstrations.
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