Aditya Singh
PhD Student, Electrical and Systems Engineering, University of Pennsylvania
University of Pennsylvania
Philadelphia, PA
I am a Ph.D. Student in Electrical and Systems Engineering at the University of Pennsylvania, where I am a member of the xLab advised by Prof. Rahul Mangharam. My research interests broadly lie in Safe Autonomy. More specifically, I am interested in integrating formal safety frameworks, such as Control Barrier Functions and Hamilton-Jacobi Reachability, with learning-enabled control to develop high-performance autonomous systems with provable safety guarantees. In parallel, I am also interested in uncertainty quantification to enhance the reliability and robustness of real-world autonomous systems.
Before beginning my Ph.D., I collaborated extensively with Prof. Somil Bansal at Stanford University on problems in Safe Autonomy. I also spent a wonderful one and a half years as a Research Assistant in the Stochastic Robotics Lab at the Indian Institute of Science (IISc), where I worked with Prof. Shishir Kolathaya on Safe Robot Learning.
I received my Bachelor’s degree in Electrical and Electronics Engineering from the Indian Institute of Technology (IIT) Patna in 2024, where I was advised by Prof. Sudhir Kumar. My undergraduate thesis was awarded the Institute Proficiency Prize for the Best Bachelor’s Thesis. During my undergraduate studies, I was also fortunate to receive the MITACS Globalink Research Fellowship. As a Ph.D. student at the University of Pennsylvania, I was honored to receive the Ganster Engineering Fellowship.
* indicates equal contribution on publications.
selected publications
-
A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous SystemsIn International Conference on Machine Learning (ICML), 2025 -
Exact Imposition of Safety Boundary Conditions in Neural Reachable TubesIn 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025 -
Semi-Supervised Safe Visuomotor Policy Synthesis using Barrier CertificatesIn 2025 IEEE 64th Annual Conference on Decision and Control (CDC), 2024 -
V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier FunctionsTransactions on Machine Learning Research (TMLR), 2025 -
AdaptNC: Adaptive Nonconformity Scores for Uncertainty-Aware Autonomous Systems in Dynamic EnvironmentsIn ICLR 2026 Workshop on Principled Design for Trustworthy AI, 2026