Back to Search
Start Over
VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation
- Publication Year :
- 2025
-
Abstract
- Bimanual dexterous manipulation remains significant challenges in robotics due to the high DoFs of each hand and their coordination. Existing single-hand manipulation techniques often leverage human demonstrations to guide RL methods but fail to generalize to complex bimanual tasks involving multiple sub-skills. In this paper, we introduce VTAO-BiManip, a novel framework that combines visual-tactile-action pretraining with object understanding to facilitate curriculum RL to enable human-like bimanual manipulation. We improve prior learning by incorporating hand motion data, providing more effective guidance for dual-hand coordination than binary tactile feedback. Our pretraining model predicts future actions as well as object pose and size using masked multimodal inputs, facilitating cross-modal regularization. To address the multi-skill learning challenge, we introduce a two-stage curriculum RL approach to stabilize training. We evaluate our method on a bottle-cap unscrewing task, demonstrating its effectiveness in both simulated and real-world environments. Our approach achieves a success rate that surpasses existing visual-tactile pretraining methods by over 20%.
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2501.03606
- Document Type :
- Working Paper