Abstract
Simulation demonstrations can supplement scarce real-world data for robot policy co-training. However, the value of using data curation to actively select these demonstrations for sim-to-real co-training remains underexplored. Existing curation methods also lack a unified criterion for measuring trajectory-level utility and set-level coverage from closed-loop target behavior. To address these gaps, we present the first systematic study of data curation for sim-to-real robot policy co-training and propose Trajectory-level Utility and set-level Coverage Optimization (TUCO). TUCO uses influence functions to trace how each source demonstration affects target-domain scoring rollouts. Our key insight is that these effects can be decomposed into an overall contribution to target return and variation across rollouts, providing a common closed-loop basis for measuring trajectory utility and set coverage. We further propose a performance-aligned subset optimizer that combines these measures in a unified curation objective to reduce redundancy and select complementary demonstrations. Extensive experiments on RoboMimic and OmniReset establish the value of active simulation data curation for sim-to-real policy co-training and show that TUCO achieves state-of-the-art performance across single-simulator, sim-to-sim, and sim-to-real settings.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhu, N., Zhao, M., Tang, Y., Sun, Z., Li, P., Ni, D., Jia, J., & Yang, J. (2026). TUCO: Curating Simulation Demonstrations for Sim-to-Real Robot Policy Co-Training. https://omanscience.com/en/articles/tuco-curating-simulation-demonstrations-for-sim-to-real-robot-policy-co-training
MLA 9
Zhu, Ning, et al. "TUCO: Curating Simulation Demonstrations for Sim-to-Real Robot Policy Co-Training." https://omanscience.com/en/articles/tuco-curating-simulation-demonstrations-for-sim-to-real-robot-policy-co-training.
Chicago (author–date)
Zhu, Ning, Mengfei Zhao, Yikai Tang, Zhangyujie Sun, Peihao Li, Dongyue Ni, Jindou Jia, and Jianfei Yang. 2026. "TUCO: Curating Simulation Demonstrations for Sim-to-Real Robot Policy Co-Training." https://omanscience.com/en/articles/tuco-curating-simulation-demonstrations-for-sim-to-real-robot-policy-co-training.
Harvard
Zhu, N., Zhao, M., Tang, Y., Sun, Z., Li, P., Ni, D., Jia, J. and Yang, J. (2026) 'TUCO: Curating Simulation Demonstrations for Sim-to-Real Robot Policy Co-Training', Available at: https://omanscience.com/en/articles/tuco-curating-simulation-demonstrations-for-sim-to-real-robot-policy-co-training.
Vancouver
Zhu N, Zhao M, Tang Y, Sun Z, Li P, Ni D, et al. TUCO: Curating Simulation Demonstrations for Sim-to-Real Robot Policy Co-Training. https://omanscience.com/en/articles/tuco-curating-simulation-demonstrations-for-sim-to-real-robot-policy-co-training
IEEE
N. Zhu, M. Zhao, Y. Tang, Z. Sun, P. Li, D. Ni, J. Jia, and J. Yang, "TUCO: Curating Simulation Demonstrations for Sim-to-Real Robot Policy Co-Training," https://omanscience.com/en/articles/tuco-curating-simulation-demonstrations-for-sim-to-real-robot-policy-co-training.