Skip to content
AI Atlas
PaperActive

ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching Policies

arxiv.org/abs/2609.11697

quality89

Updated 2 h ago · first seen 12 Sept 2026

paper_01M29X34ZM9KDT8T7R5D4CTWM3

Published
12 Sept 2026
T1 · 2 h ago
arXiv
2609.11697
T1 · 2 h ago
Category
cs.RO
T1 · 2 h ago

Abstract

Vision-Language-Action (VLA) and World-Action Models (WAMs) have demonstrated strong capabilities in general-purpose robotic manipulation, yet their generated actions may violate hard physical constraints and therefore be unsafe or infeasible for deployment. Existing safety approaches either optimize statistical safety objectives without deterministic per-step guarantees or correct unsafe actions only during inference, creating a mismatch between policy training and execution. We introduce ActSafeGuard, a differentiable and training-aligned safeguard layer for flow-matching based policies. ActSafeGuard integrates hard action feasibility into policy learning, not merely treating safety as an inference-time external component. Through an analytical ray-scaling operator design, ActSafeGuard enables boundary-aware gradients to guide the model to naturally learn constrained manifolds. Extensive experiments on multiple standard foundation backbones ($\pi_{0.5}$ and Fast-WAM) across various tasks demonstrate that ActSafeGuard consistently achieves a $100\%$ step safety rate while fully preserving or even boosting task success rates, providing a scalable and minimally invasive solution for safe embodied AI deployment.

Authors 6

Jianming Ma, Rongjun Jin, Xiaxi Si, Yang Zhang, Yiheng Li, Yue Gao

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

arXiv id
2609.11697

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Categories
cs.AI, cs.RO

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Primary category
cs.RO

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Published
12 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

2 h ago

Conflicts

None