arXiv：cs.LG· Alex Beaudin, Hanna Krasowski, Kartik Nagpal, Sanjit A. Seshia, Murat Arcak, Negar Mehr·· 4 小时前
X-Safe：面向机械臂操作策略的具身无关安全防护与动作掩码
X-Safe: Embodiment-Agnostic Safeguarding for Robot Arm Manipulation Policies via Action Masking
AI 导读
研究者提出具身无关的安全防护方法 X-Safe，通过在配置空间中围绕当前构型建立安全区域，并用动作掩码限制策略支持范围，为机械臂操作策略提供无需模型简化或学习安全函数的碰撞避免形式化概率保证。该方法在两种具身、三种策略上完成仿真与硬件验证，性能损失不到当前最先进安全防护方法的一半，并实证验证了其碰撞避免保证。
正文
Abstract:Ensuring safety of learning-enabled robotic manipulation across diverse embodiments and tasks still requires significant manual engineering. For collision avoidance, existing approaches typically rely on embodiment-specific learned safety approximations or simplified robot models together with stopping-based fallback controllers that compromise performance. In this paper, we propose an embodiment-agnostic safeguarding approach, X-Safe, which provides formal probabilistic guarantees for collision avoidance without model simplifications or learned safety functions. By operating in the configuration space, our safeguarding method works with different types of robot policies. X-Safe reasons locally around the current configuration to establish safe regions and uses action masking to restrict the policy's support to these safe regions. We demonstrate X-Safe on two embodiments and three policies, both in simulation and on hardware. We observe less than half of the performance degradation compared to state-of-the-art safeguarding, and empirically corroborate our formal collision avoidance guarantees.
| Subjects: | Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY) |
| Cite as: | arXiv:2606.22278 [cs.RO] |
| (or arXiv:2606.22278v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2606.22278 arXiv-issued DOI via DataCite |
Submission history
From: Hanna Krasowski [view email]
[v1]
Sun, 21 Jun 2026 00:11:46 UTC (4,125 KB)
[v2]
Wed, 14 Oct 2026 16:28:57 UTC (4,915 KB)
来源：arXiv：cs.LG · arxiv.org