Skip to content
AI News HubLIVE
Original source2 min read

CS-Pi: Constraint-Satisfying Flow Policy Sampling

Summary

CS-Pi introduces a sampling method that enforces novel constraints at inference time for flow-matching policies by combining projection efficiency with rejection-sampling plausibility. It achieves 81% safe success on a 7-DoF shelf task and 55% on a zero-shot Franka deployment, outperforming projection baselines.

SourcearXiv RoboticsAuthor: Soumojit Bhattacharya, Oliver Kroemer, Shubham Tulsiani
CS-Pi: Constraint-Satisfying Flow Policy Sampling
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 5 Nov 2026]

Title:CS-Pi: Constraint-Satisfying Flow Policy Sampling

View a PDF of the paper titled CS-Pi: Constraint-Satisfying Flow Policy Sampling, by Soumojit Bhattacharya and 1 other authors

View PDF HTML (experimental)

Abstract:A flow-matching policy deployed in the field must often satisfy a constraint that was absent from its demonstrations, such as avoiding an obstacle it has never seen. Retraining for every new constraint is impractical, so the constraint must be enforced at inference time. Enforcing it must not discard what the policy learned: an action the policy would rarely sample may avoid the obstacle yet fail the task. We therefore want actions that are both safe, satisfying the constraint, and plausible, remaining likely under the policy. Gradient guidance, the most common approach, steers noisy states, so it must evaluate its cost on the policy's running estimate of the clean action; when the policy is uncertain between passing left or right of an obstacle, this estimate is their average and can pass straight through it. We instead build on rejection and projection. Rejection redraws actions until one is safe: every output is plausible, but the wait is intractable when safe actions are rare. Projection moves an action to the nearest safe one: it is efficient, but the result need not be plausible. Our key insight is that flow-matching sampling lets us combine the two, keeping projection's efficiency and rejection's plausibility. CS-Pi, our draw-project-renoise sampler, projects each draw to the nearest safe action, adds noise back scaled to how far the projection moved it, and re-runs the unmodified policy until a draw is safe. Replacing only the projection step extends CS-Pi to continuous costs. Across a 2D diagnostic, a 7-DoF shelf pick-and-place, an orientation preference, and a zero-shot Franka deployment, CS-Pi reaches 81% safe success on the shelf and 55% on hardware, against 55% and 40% for projection, while staying plausible.

Comments: Accepted to CoRL 2026. Project page: this https URL

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.08654 [cs.RO]

(or arXiv:2611.08654v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.08654

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Soumojit Bhattacharya [view email] [v1] Thu, 5 Nov 2026 20:01:08 UTC (21,262 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CS-Pi: Constraint-Satisfying Flow Policy Sampling, by Soumojit Bhattacharya and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • CS-Pi combines projection's efficiency with rejection sampling's plausibility for constraint satisfaction in flow-matching policies.
  • The method extends to continuous costs by replacing only the projection step.
  • It reaches 81% safe success on a shelf pick-and-place task and 55% on hardware, versus 55% and 40% for projection.

Highlights and analysis are generated automatically and may contain errors. Check the original source.