1. [Publications](/publications)
2. Sample-Efficient Safety Assurances using Conformal Prediction
 
 # Sample-Efficient Safety Assurances using Conformal Prediction

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 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; i.e. 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 guaranteed false negative rate while also observing low false detection (positive) rate.



 ## Authors



Rachel Luo (Stanford University)

Shengjia Zhao (Stanford Univeristy)

Jonathan Kuck (Dexterity)

[Boris Ivanovic](/person/boris-ivanovic)

Silvio Savarese (Stanford University)

Edward Schmerling (Stanford University)

[Marco Pavone](/person/marco-pavone)

 

 

 ## Publication Date



Tuesday, September 21, 2021

 

 ## Published in



[Arxiv](https://arxiv.org/abs/2109.14082)

 

 ## Research Area



[Autonomous Vehicles](/research-area/autonomous-vehicles)