BayesFP: 基于Feynman-Kac采样的流策略后验估计
BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
AI总结：
提出BayesFP框架，将预训练扩散/流匹配策略的约束轨迹生成视为贝叶斯后验采样，利用Feynman-Kac校正器实现无需重训练的推理时采样，在模拟和真实操作任务中提升零样本性能。
摘要：
机器人必须生成既忠实于学习到的专家行为，又满足仅在推理时指定的安全约束和任务特定目标的轨迹。我们将预训练扩散和流匹配策略的约束轨迹生成形式化为贝叶斯后验采样，将学习到的演示分布作为先验，并通过推理时、成本导出的似然将其向可行、最优轨迹倾斜。为了在不重新训练基础策略的情况下从该后验中采样，我们利用最初为扩散模型制定的Feynman-Kac校正器框架，并将其扩展到确定性流匹配策略。结果是一个统一的、推理时、无需重训练的扩散和流策略采样器。我们在预训练的Diffusion Policy、GR00T-N1.6和$\pi_{0.5}$检查点上验证了该方法，涉及模拟和真实世界的操作任务，包括在推理时引入的非凸障碍物周围的规划，并展示了在零样本任务上相对于基础$\pi_{0.5}$的改进。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
