arXiv cs.AI· Jianming Ma, Rongjun Jin, Yizhi Chen, Yue Gao·· 14 小时前AI 评分31
从二元可行性预言机学习安全流匹配机器人策略
Learning Safe Flow Matching Robot Policies from Binary Feasibility Oracles
AI 导读
针对流匹配机器人策略生成的动作无法保证满足关节限位、避障等物理约束的问题，研究者提出一种预言机引导的可微安全防护机制，仅通过二元可行性查询在前向传播中修正不安全更新，并在反向传播中提取局部边界信息提供约束感知学习信号。该方法与离散时间流匹配结合，训练与推理共用同一防护机制，无需显式或可微约束模型。在障碍感知机器人操作实验中实现 100% 约束满足，同时保持任务性能。
正文 · 原文
Abstract:Robot foundation models increasingly rely on flow-based action generation for general-purpose manipulation, yet the generated actions are not guaranteed to satisfy physical constraints such as joint limits and collision avoidance. This problem is especially challenging when the feasible set cannot be described analytically and is accessible only through black-box feasibility oracles. We study this practical oracle-only setting and propose an oracle-guided differentiable safeguard for safe flow-matching robot policies. The safeguard uses binary feasibility queries to correct unsafe updates in the forward pass, while extracting local boundary information to provide constraint-aware learning signals in the backward pass. Combined with discrete-time flow matching, the same safeguard is used during training and inference, enabling forward--backward aligned policy learning without explicit or differentiable constraint models. Experiments on obstacle-aware robotic manipulation demonstrate 100% constraint satisfaction while preserving task performance.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.40075 [cs.RO] |
| (or arXiv:2610.40075v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40075 arXiv-issued DOI via DataCite |
Submission history
From: Jianming Ma [view email]
[v1]
Thu, 29 Oct 2026 13:53:04 UTC (465 KB)
来源：arXiv cs.AI · arxiv.org