计算机科学
预警系统
人工智能
机器人学
推论
样品(材料)
机器学习
假阳性率
机器人
动作(物理)
色谱法
量子力学
电信
物理
化学
作者
Rachel Luo,Shengjia Zhao,Jonathan Kuck,Boris Ivanovic,Silvio Savarese,Edward Schmerling,Marco Pavone
标识
DOI:10.1177/02783649231221580
摘要
When deploying machine learning models in high-stakes robotics applications, the ability to detect unsafe situations is crucial. Early warning systems can provide alerts when an unsafe situation is imminent (in the absence of corrective action). To reliably improve safety, these warning systems should have a provable false negative rate; that is, of the situations that are unsafe, fewer than ϵ will occur without an alert. In this work, we present a framework that combines a statistical inference technique known as conformal prediction with a simulator of robot/environment dynamics, in order to tune warning systems to provably achieve an ϵ false negative rate using as few as 1/ ϵ data points. We apply our framework to a driver warning system and a robotic grasping application, and empirically demonstrate the guaranteed false negative rate while also observing a low false detection (positive) rate.
科研通智能强力驱动
Strongly Powered by AbleSci AI