cs.RONov 14, 2026

Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies

Authors: Angelo Moroncelli, Loris Roveda

Organizations: SUPSI-IDSIA, USI, Lugano, Switzerland · SUPSI-IDSIA, Lugano, Switzerland · Politecnico di Milano, Milan, Italy

Abstract

Diffusion policies, which generate short action sequences by denoising random noise, are a leading way to learn robot skills from demonstrations. Once deployed, they meet constraints the demonstrations never contained, and retraining for each is impractical. A safety filter edits the policy's action to satisfy them, but the edit ignores the task, and a large edit can leave the policy where it cannot continue. We propose CAST (Certified Action Selection at Test time): draw a few action chunks from the frozen policy, certify each with a barrier condition, and execute the certified chunk that a learned value ensemble ranks highest. We prove that a certified step is safe whatever the critic does; that, whenever a certified sample exists, the executed chunk stays within log N nats of the policy conditioned on feasibility, while a safety-filter projection can be singular to it; and that an exact closed-loop identity splits the gain of ranking into availability, spread and the critic's target. Certifying the next chunk is not enough: a generative controller can have safe actions available now and none later. We characterise the safe control authority of a frozen policy under finite sampling, and CAST-V preserves it through a policy-conditioned viability, estimated with a model under a finite-sample guarantee or learned from the controller's own logs (CAST-VL). On robomimic manipulation, a planar quadrotor, a MuJoCo humanoid and a unicycle, with frozen policies, CAST raises joint task-and-constraint success above the output filter in nearly every setting; certifying before ranking is decisive where a filter's edit is large, and viability removes most dead ends that one-step certification cannot see. Project page: https://clmoro.github.io/cast.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Temporal Logic Guidance for Action-Only Diffusion Policies with World Models

    Jun 22, 2026Moritz Zoellner, Anastasios Manganaris, Rohan PalejaDiffusion Model GuidanceDiffusion Policy

  2. Reachability-Aware Diffusion Policy Optimization

    Oct 5, 2026Hikmet Simsir, Kutay Demiray, Ozgur S. OguzConstrained RLDiffusion Policy