Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation
About
Reliable robotic manipulation requires control policies that can accurately represent and adapt to uncertainty arising from contact-rich interactions. Modern data-driven methods mitigate uncertainty through large-scale training and computation, and degrade significantly in performance with limited number of training samples. By contrast, classical model-based controllers are computationally efficient and reliable, but their limited ability to represent task-relevant uncertainty can hinder performance in contact-rich interactions. In this work, we propose to expand the capabilities of model-based manipulation control through more flexible uncertainty modeling that retains performance while exactly adapting to uncertainty. Our approach casts the manipulation problem as a distributionally robust control optimization and proposes a novel deterministic formulation based on Stein variational inference that preserves performance while explicitly modeling task-sensitive parameter uncertainty. As a result, the derived controllers are more aware of task sensitivities to uncertainty, yielding high reliability without compromising performance. Experimental results demonstrate up to 3$\times$ improved robustness across a range of contact-rich manipulation tasks under broad parametric uncertainty, outperforming existing model-based control methods.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Bimanual Manipulation | Bimanual Push-T ≤ 10 cm | Success Rate93.25 | 5 | |
| Bimanual Manipulation | Bimanual Push-T ≤ 1 cm | Success Percentage84.38 | 5 | |
| Within-Hand Dynamic Positioning | Within-Hand Dynamic Positioning ≤ 10 cm | Success Rate100 | 5 | |
| Within-Hand Dynamic Positioning | Within-Hand Dynamic Positioning (≤ 1 cm) | Success Rate100 | 5 |