Rachel Luo

Research Scientist · NVIDIA Research

I am a Research Scientist in the Autonomous Systems and Physical AI Research (ASPIRE) Group at NVIDIA Research. I develop methods for evaluating and monitoring the safety and reliability of learning-based autonomous systems. My research spans sample-efficient safety evaluation, detection of unreliable model behavior, and uncertainty quantification. My recent work focuses on statistically grounded safety validation when failures are rare: using abundant but imperfect evaluation data to draw reliable conclusions about system behavior in deployment.

Previously, I received my Ph.D. in Electrical Engineering from Stanford University in 2023, advised by Marco Pavone in the Autonomous Systems Lab and Silvio Savarese in the Stanford Vision and Learning Lab. I completed my B.S. in Electrical Engineering and Computer Science at MIT.

Selected Publications and Preprints

For a full list of publications, see my Google Scholar profile.

X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation
Rachel Luo, Michael Watson, Apoorva Sharma, Heng Yang, Han Qi, Edward Schmerling, Sushant Veer, Boris Ivanovic, Marco Pavone.
Preprint · 2026
Coverage Aware Active Evaluation for Failure Discovery with Paired Systems
Anjali Parashar, Rachel Luo, Apoorva Sharma, Sushant Veer, Edward Schmerling, Carson Sobolewski, Mingxin Yu, Chuchu Fan, Marco Pavone.
CoRL · 2026
Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation
Rachel Luo, Heng Yang, Michael Watson, Apoorva Sharma, Sushant Veer, Edward Schmerling, Marco Pavone.
CoRL · 2025
Sample-Efficient Safety Assurances using Conformal Prediction
Rachel Luo, Shengjia Zhao, Jonathan Kuck, Boris Ivanovic, Silvio Savarese, Edward Schmerling, Marco Pavone.
IJRR · 2024 · Extended journal version
Online Distribution Shift Detection via Recency Prediction
Rachel Luo, Rohan Sinha, Yixiao Sun, Ali Hindy, Shengjia Zhao, Silvio Savarese, Edward Schmerling, Marco Pavone.
ICRA · 2024
Local Calibration: Metrics and Recalibration
Rachel Luo*, Aadyot Bhatnagar*, Yu Bai, Shengjia Zhao, Huan Wang, Caiming Xiong, Silvio Savarese, Stefano Ermon, Edward Schmerling, Marco Pavone.
UAI · 2022
Sample-Efficient Safety Assurances using Conformal Prediction
Rachel Luo, Shengjia Zhao, Jonathan Kuck, Boris Ivanovic, Silvio Savarese, Edward Schmerling, Marco Pavone.
WAFR · 2022 · Conference version Talk
A System-Level View on Out-of-Distribution Data in Robotics
Rohan Sinha, Apoorva Sharma, Somrita Banerjee, Thomas Lew, Rachel Luo, Spencer M. Richards, Yixiao Sun, Edward Schmerling, Marco Pavone.
Preprint · 2022

Selected Talks

Safety in the Loop: Advancing Autonomous Vehicle Safety Validation Through Simulation
NVIDIA livestream; co-presenter. October 2025.
Sample-Efficient Uncertainty Calibration for Reliable Autonomous Systems
Safe and Intelligent Autonomy Lab, University of Southern California. April 2024.
Ph.D. defense, Stanford University. August 2023.
Incorporating Sample Efficient Monitoring into Learned Autonomy
Stanford Robotics Seminar. January 2023.
NASA University Leadership Initiative Seminar. November 2022.
Sample-Efficient Safety Assurances using Conformal Prediction
Workshop on the Algorithmic Foundations of Robotics. June 2022.