CS-Pi: Constraint-Satisfying Flow Matching Policy Sampling at Inference Time
What happened
Soumojit Bhattacharya and co-authors propose CS-Pi, a flow matching policy sampler that satisfies constraints not seen in demonstrations at inference time: each sampling step first projects to the nearest safe action, then adds noise back according to the magnitude of the projection displacement and reruns the original policy until the sample is safe. The authors report that on a 7-DoF shelf grasping task the safe success rate is 81%, and zero-shot Franka deployment is 55%, whereas pure projection gives 55% and 40% respectively. The method can be extended to continuous costs by replacing only the projection step. The paper has been accepted to CoRL 2026.
AI 根据报道生成 · 2 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROCS-Pi: Constraint-Satisfying Flow Policy Sampling at Inference Time
CS-Pi proposes a "sample-project-renoise" flow-matching policy sampler that satisfies constraints absent from demonstrations at inference time while keeping actions plausible under the policy. The method projects each sample onto the nearest safe action, then adds noise back according to the size of the projection displacement and reruns the original policy until the sample is safe. On a 7-DoF shelf grasping task it achieves an 81% safe success rate, and 55% in zero-shot deployment on Franka, versus 55% and 40% for projection alone. The paper has been accepted to CoRL 2026.
Activity for this event
- Current
- 3
- Peak
- 10Nov 9 14:00
- Past 24 hours
- -50%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.