让机器人在感知异常时仍能安全运行，无需标注数据。
ATOM-CBF: Adaptive Safe Perception-Based Control under Out-of-Distribution Measurements
- 根据感知误差自适应调整安全边界，动态应对异常输入。
- 仿真验证中，无人车与四足机器人在异常传感器数据下保持安全。
- 无需真实标签或分布变化信息，适合实际部署场景。
确保真实系统安全极具挑战性，尤其当系统依赖学习型感知模块从高维传感器数据中推断状态时。这些感知模块易受认知不确定性影响，在遇到训练中未见的分布外（OoD）测量时往往失效。为解决这一问题，我们提出 ATOM-CBF（自适应分布外感知控制屏障函数），一种新型安全控制框架，可显式计算并适应来自 OoD 测量的认知不确定性，且无需真实标签或分布偏移信息。该方法包含两个核心组件：(1) 面向 OoD 的自适应感知误差裕度；(2) 融合此自适应误差裕度的安全滤波器，使其能实时调节保守程度。我们在仿真中进行了实证验证，结果显示，使用激光雷达扫描的 F1Tenth 无人车和使用 RGB 图像的四足机器人在面对分布外测量时均能维持安全性能。
原文摘要 · Abstract (English)
Ensuring the safety of real-world systems is challenging, especially when they rely on learned perception modules to infer the system state from high-dimensional sensor data. These perception modules are vulnerable to epistemic uncertainty, often failing when encountering out-of-distribution (OoD) measurements not seen during training. To address this gap, we introduce ATOM-CBF (Adaptive-To-OoD-Measurement Control Barrier Function), a novel safe control framework that explicitly computes and adapts to the epistemic uncertainty from OoD measurements, without the need for ground-truth labels or information on distribution shifts. Our approach features two key components: (1) an OoD-aware adaptive perception error margin and (2) a safety filter that integrates this adaptive error margin, enabling the filter to adjust its conservatism in real-time. We provide empirical validation in simulations, demonstrating that ATOM-CBF maintains safety for an F1Tenth vehicle with LiDAR scans and a quadruped robot with RGB images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。