Abstract
Vision-language-action (VLA) models often require costly real-world demonstrations to adapt to contact-rich manipulation tasks, particularly when generalization across object placements is needed. We propose SARI (Simulated Approach, Real Interaction), a phase-split sim-and-real co-training framework built on a simple insight: spatial coverage and contact physics should be acquired from the domains best suited to them. Specifically, free-space approaches require spatial diversity but tolerate modest simulation gaps, making them ideal for synthetic generation; conversely, contact interactions demand accurate physics but vary little across object placements, allowing a few real demonstrations to generalize across the workspace. SARI generates diverse simulated approaches in a photorealistic digital twin while collecting real contact interactions at only a few placements. Post-trained on these phase-segmented demonstrations, a single policy seamlessly stitches simulated approaches with real contact interactions using visual appearance alignment and a shared camera-relative action representation--without explicit phase labels or hand-coded switches. Across five real-world contact-rich manipulation tasks, SARI reduces real-data collection time by 34.3% and achieves 27.5% success at unseen placements, where all full-task sim-real baselines fail completely (0%).
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
He, X., Jiang, Y., Zhang, H., Cui, C., Li, K., Zheng, Z., Xu, C., & Wang, Z. (2026). SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation. https://omanscience.com/en/articles/sari-phase-split-sim-real-co-training-for-contact-rich-manipulation
MLA 9
He, Xingxin, et al. "SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation." https://omanscience.com/en/articles/sari-phase-split-sim-real-co-training-for-contact-rich-manipulation.
Chicago (author–date)
He, Xingxin, Yuxuan Jiang, Haonan Zhang, Chuhan Cui, Kaile Li, Zhongxing Zheng, Caihao Xu, and Ziqi Wang. 2026. "SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation." https://omanscience.com/en/articles/sari-phase-split-sim-real-co-training-for-contact-rich-manipulation.
Harvard
He, X., Jiang, Y., Zhang, H., Cui, C., Li, K., Zheng, Z., Xu, C. and Wang, Z. (2026) 'SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation', Available at: https://omanscience.com/en/articles/sari-phase-split-sim-real-co-training-for-contact-rich-manipulation.
Vancouver
He X, Jiang Y, Zhang H, Cui C, Li K, Zheng Z, et al. SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation. https://omanscience.com/en/articles/sari-phase-split-sim-real-co-training-for-contact-rich-manipulation
IEEE
X. He, Y. Jiang, H. Zhang, C. Cui, K. Li, Z. Zheng, C. Xu, and Z. Wang, "SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation," https://omanscience.com/en/articles/sari-phase-split-sim-real-co-training-for-contact-rich-manipulation.