1. [Publications](/publications)
2. Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation
 
 # Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation

  ![](/sites/default/files/styles/wide/public/publications/Screenshot%202026-01-12%20at%202.39.39%E2%80%AFPM.png?itok=oaQV_w45)

 Learning-based robotic systems demand rigorous validation to assure reliable performance, but extensive real-world testing is often prohibitively expensive, and if conducted may still yield insufficient data for high-confidence guarantees. In this work we introduce Sim2Val, a general estimation framework that leverages paired data across test platforms, e.g., paired simulation and real-world observations, to achieve better estimates of real-world metrics via the method of control variates. By incorporating cheap and abundant auxiliary measurements (for example, simulator outputs) as control variates for costly real-world samples, our method provably reduces the variance of Monte Carlo estimates and thus requires significantly fewer real-world samples to attain a specified confidence bound on the mean performance. We provide theoretical analysis characterizing the variance and sample-efficiency improvement, and demonstrate empirically in autonomous driving and quadruped robotics settings that our approach achieves high-probability bounds with markedly improved sample efficiency. Our technique can lower the real-world testing burden for validating the performance of the stack, thereby enabling more efficient and cost-effective experimental evaluation of robotic systems.



 ## Authors



[Rachel Luo](/person/rachel-luo)

[Heng Yang](/person/heng-yang)

[Michael Watson](/person/michael-watson)

[Apoorva Sharma](/person/apoorva-sharma)

[Sushant Veer](/person/sushant-veer)

Edward Schmerling (NVIDIA)

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

 

 

 ## Publication Date



Saturday, September 27, 2025

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

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

[Physical AI](/research-area/physical-ai)

[Resilience and Safety](/research-area/resilience)

[Robotics](/research-area/robotics)

 

 

 ## External Links



[Paper](https://arxiv.org/abs/2506.20553)