Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sinha, Aman, Nikdel, Payam, Paul, Supratik, Whiteson, Shimon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915036402810880
author Sinha, Aman
Nikdel, Payam
Paul, Supratik
Whiteson, Shimon
author_facet Sinha, Aman
Nikdel, Payam
Paul, Supratik
Whiteson, Shimon
contents Ensuring the safety of autonomous vehicles (AVs) requires both accurate estimation of their performance and efficient discovery of potential failure cases. This paper introduces Bayesian adaptive multifidelity sampling (BAMS), which leverages the power of adaptive Bayesian sampling to achieve efficient discovery while simultaneously estimating the rate of adverse events. BAMS prioritizes exploration of regions with potentially low performance, leading to the identification of novel and critical scenarios that traditional methods might miss. Using real-world AV data we demonstrate that BAMS discovers 10 times as many issues as Monte Carlo (MC) and importance sampling (IS) baselines, while at the same time generating rate estimates with variances 15 and 6 times narrower than MC and IS baselines respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17826
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling
Sinha, Aman
Nikdel, Payam
Paul, Supratik
Whiteson, Shimon
Robotics
Machine Learning
Ensuring the safety of autonomous vehicles (AVs) requires both accurate estimation of their performance and efficient discovery of potential failure cases. This paper introduces Bayesian adaptive multifidelity sampling (BAMS), which leverages the power of adaptive Bayesian sampling to achieve efficient discovery while simultaneously estimating the rate of adverse events. BAMS prioritizes exploration of regions with potentially low performance, leading to the identification of novel and critical scenarios that traditional methods might miss. Using real-world AV data we demonstrate that BAMS discovers 10 times as many issues as Monte Carlo (MC) and importance sampling (IS) baselines, while at the same time generating rate estimates with variances 15 and 6 times narrower than MC and IS baselines respectively.
title Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling
topic Robotics
Machine Learning
url https://arxiv.org/abs/2411.17826