Online Safety Filter for Deformable Object Manipulation with Horizon Agnostic Neural Operators

TL;DR

This paper introduces an online safety filter for deformable object manipulation that guarantees safety constraints in real time using neural operators and control barrier functions, improving safety and efficiency.

Contribution

It proposes a novel horizon agnostic neural operator combined with a boundary control barrier function for real-time safety enforcement in deformable media manipulation.

Findings

Safety filter increases safe trajectory rates by up to 22%.

Reduces steps needed to reach safe states.

Outperforms reward shaping approaches in safety and efficiency.

Abstract

Safety critical control of robotic manipulation tasks involving deformable media such as fluids, cloth, and soft objects remains challenging because existing learning based approaches encode safety indirectly through reward shaping, which provides no guarantee of constraint satisfaction at deployment. We present a constraint driven online safety filter for deformable object manipulation that enforces explicit task level safety constraints in real time by minimally modifying any nominal control policy. Our approach combines two key components: a horizon agnostic neural operator that learns the boundary input output mapping of the underlying PDE dynamics and generalizes across variable rollout lengths without retraining, and a boundary control barrier function that certifies safety at the task relevant output level via a lightweight quadratic program. The resulting safety constraint is affine in the boundary input rate, enabling real time online filtering. We evaluate the proposed method on fluid manipulation tasks in FluidLab, where the filter improves safe trajectory rates by up to 22% over unfiltered base policies while also reducing the number of steps required to reach the safe set, demonstrating that constraint driven safety enforcement is both more reliable and more efficient than reward shaping approaches.