Heng Yang  

 



  ![](/sites/default/files/person/hengy-small.jpg)

  

 Heng Yang is a Research Scientist in the Autonomous Vehicle Research group at NVIDIA. He is broadly interested in the algorithmic foundations of robot perception, action, and learning. His research vision is to enable safe and trustworthy autonomy for a broad range of high-integrity robotics applications, by designing tractable and provably correct algorithms that enjoy rigorous performance guarantees, developing fast implementations, and validating them on real robotic systems. At NVIDIA research, Heng Yang is particularly interested in bringing safety assurances and robustness guarantees to modern learning-based perception modules towards trustworthy autonomous driving.

Prior to joining NVIDIA, Heng Yang received his Ph.D. in Mechanical Engineering in 2022 under the supervision of Prof. Luca Carlone from the Laboratory for Information and Decision Systems at MIT. He obtained an M.S. in Mechanical Engineering in 2017 from MIT, and a B.E. in Automotive Engineering in 2015 from Tsinghua University.

Heng Yang will join Harvard University as an Assistant Professor of Electrical Engineering in 2023. Check out his [personal website](https://hankyang.seas.harvard.edu/) to find out more.



   Research Area(s)

[Algorithms and Numerical Methods](/research-area/algorithms)

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

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

[Computer Vision](/research-area/computer-vision)

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

[Robotics](/research-area/robotics)

 

 

  

 Main Field of Interest

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

 

  

 Google Scholar

[https://scholar.google.com/citations?user=GuKEDfixZqsC&hl=en](https://scholar.google.com/citations?user=GuKEDfixZqsC&hl=en)

 

  

 

 

 



 ### Publications

 

### 2025 

[Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation](/publication/2025-09_sim2val-leveraging-correlation-across-test-platforms-variance-reduced-metric)

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













### 2023 

[Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation](/publication/2023-06_object-pose-estimation-statistical-guarantees-conformal-keypoint-detection-and)

[Heng Yang](/person/heng-yang), [Marco Pavone](/person/marco-pavone)



[IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023](https://cvpr2023.thecvf.com/)



Selected as a Highlight Paper





[FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization](/publication/2023-03_freenerf-improving-few-shot-neural-rendering-free-frequency-regularization)

[Heng Yang](/person/heng-yang), [Marco Pavone](/person/marco-pavone)



[Arxiv](https://arxiv.org/abs/2303.12246)









[Verification and Synthesis of Robust Control Barrier Functions: Multilevel Polynomial Optimization and Semidefinite Relaxation](/publication/_verification-and-synthesis-robust-control-barrier-functions-multilevel-polynomial)

Shucheng Kang, [Yuxiao Chen](/person/yuxiao-chen), [Heng Yang](/person/heng-yang), [Marco Pavone](/person/marco-pavone)



[IEEE Conference on Decision and Control (CDC)](https://cdc2023.ieeecss.org/)