Sample-efficient safety assurances using conformal prediction

Author:

Luo Rachel1ORCID,Zhao Shengjia1,Kuck Jonathan2,Ivanovic Boris1,Savarese Silvio1,Schmerling Edward1,Pavone Marco1

Affiliation:

1. Stanford University, Stanford, CA, USA

2. Dexterity, Inc., Redwood City, CA, USA

Abstract

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.

Funder

NASA University Leadership Initiative

Publisher

SAGE Publications

Subject

Applied Mathematics,Artificial Intelligence,Electrical and Electronic Engineering,Mechanical Engineering,Modeling and Simulation,Software

Reference43 articles.

1. Angelopoulos AN, Bates S, Malik J, et al. (2020) Uncertainty sets for image classifiers using conformal prediction. International Conference on Learning Representations, Vienna, Austria, May 7th, 2024 to May 11th, 2024.

2. Conformal prediction beyond exchangeability

3. nuScenes: A Multimodal Dataset for Autonomous Driving

4. Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systems

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3