Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sathyanarayan, Hrishikesh, Vantilborgh, Victor, Ravichandar, Harish, Lefebvre, Tom, Abraham, Ian
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914579164954624
author Sathyanarayan, Hrishikesh
Vantilborgh, Victor
Ravichandar, Harish
Lefebvre, Tom
Abraham, Ian
author_facet Sathyanarayan, Hrishikesh
Vantilborgh, Victor
Ravichandar, Harish
Lefebvre, Tom
Abraham, Ian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19029
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation
Sathyanarayan, Hrishikesh
Vantilborgh, Victor
Ravichandar, Harish
Lefebvre, Tom
Abraham, Ian
Robotics
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.
title Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation
topic Robotics
url https://arxiv.org/abs/2605.19029