BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
For robotics practitioners, it enables constrained trajectory generation from pretrained policies without retraining, addressing a key bottleneck in deploying learned policies under inference-time constraints.
The paper introduces BayesFP, a retraining-free inference-time method for sampling from diffusion and flow-matching policies under constraints, formulated as Bayesian posterior sampling. It improves zero-shot task performance over the base π0.5 policy on manipulation tasks with non-convex obstacles.
Robots must generate trajectories that remain faithful to learned expert behavior while satisfying safety constraints and task-specific objectives specified only at inference time. We formulate constrained trajectory generation for pretrained diffusion and flow-matching policies as Bayesian posterior sampling, with the learned demonstration distribution as a prior and an inference-time, cost-derived likelihood tilting it toward feasible, optimal trajectories. To sample from this posterior without any retraining of the base policy, we leverage the Feynman--Kac corrector framework, originally formulated for diffusion models, and extend it to deterministic flow-matching policies. The result is a unified, inference-time, retraining-free sampler for diffusion and flow policies. We validate the approach on pretrained Diffusion Policy, GR00T-N1.6, and $π_{0.5}$ checkpoints across simulated and real-world manipulation tasks, including planning around non-convex obstacles introduced at inference time, and show improvements over the base $π_{0.5}$ on zero-shot tasks.