University of Pennsylvania
George J. Pappas
Building safe systems and trustworthy AI for the physical world
AI now plans and acts for robots, vehicles and agents. My group develops the theory and tools to make those systems provably safe — drawing on control theory, formal methods and machine learning.
About
George J. Pappas is the UPS Foundation Professor of Electrical and Systems Engineering at the University of Pennsylvania, with secondary appointments in Computer and Information Science and in Mechanical Engineering and Applied Mechanics, and a member of the GRASP Laboratory. He previously chaired the Department of Electrical and Systems Engineering from 2012 to 2024. His research spans control systems, robotics, formal methods, and machine learning, with emphasis on the safety, security, and trustworthiness of AI-enabled autonomous and cyber-physical systems.
He is a member of the National Academy of Engineering and a Fellow of IEEE, IFAC, and AAAS. His honors include the IEEE Leon K. Kirchmayer Graduate Teaching Award, the NSF PECASE, the IEEE CSS Antonio Ruberti Young Researcher Prize, two IEEE CSS George S. Axelby Outstanding Paper Awards, and the Penn Provost’s Award for Distinguished Ph.D. Teaching and Mentoring. Many of his former Ph.D. students and postdoctoral researchers now hold faculty positions at leading universities worldwide.
Full biography, appointments, education and honors →
Forthcoming January 1, 2027
Linear Systems Theory: From Linear Algebra to the Kalman Filter
Pella Press · Free e-book, free course slides and paperback on Amazon
Research
All research areas →
Safe Physical AI
Safety of LLM, VLM and VLA-driven robots: jailbreaks, red-teaming and guardrails.
Trustworthy AI
Jailbreaks and defenses for LLMs, and verification and uncertainty for AI agents.
Learning and Control
Learning theory for identification and control, and multi-agent learning.
Formal Methods
Formal methods and control for provably safe robot autonomy.
Multi-Robot Systems
Semantic mapping and LLM-grounded missions for air–ground robot teams.
Latest Publications
All publications →-
C424
Z. Ravichandran, F. Cladera, A. Prabhu, J. Hughes, C. Nieto-Granda, V. Murali, C. J. Taylor, G. J. Pappas and V. Kumar, “Heterogeneous Robot Collaboration in Unstructured Environments with Grounded Generative Intelligence,” in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Pittsburgh, PA, September 2026. [Project] [Video] [Code]
-
C423
S. Noorani, O. Romero, N. Dal Fabbro, H. Hassani and G. J. Pappas, “Conformal Risk Minimization with Variance Reduction,” in Proc. 42nd Conference on Uncertainty in Artificial Intelligence (UAI), Amsterdam, Netherlands, August 2026. [Proceedings]
-
C422
S. Kiyani, S. Noorani, G. J. Pappas and H. Hassani, “When to Trust the Cheap Check: Weak and Strong Verification for Reasoning,” in Proc. International Conference on Machine Learning (ICML), PMLR vol. 306, pp. 59388–59414, Seoul, Korea, July 2026. ICML Spotlight [Proceedings] [Code]
-
C421
S. Noorani, S. Kiyani, H. Hassani and G. J. Pappas, “Multi-Round Human–AI Collaboration with User-Specified Requirements,” in Proc. International Conference on Machine Learning (ICML), PMLR vol. 306, pp. 93747–93776, Seoul, Korea, July 2026. [Proceedings]
-
C420
S. Noorani, S. Kiyani, G. J. Pappas and H. Hassani, “Human-AI Collaborative Uncertainty Quantification,” in Proc. International Conference on Machine Learning (ICML), PMLR vol. 306, pp. 93777–93800, Seoul, Korea, July 2026. [Proceedings] [Code]
-
C419
Z. Zhu, S. Kiyani, G. J. Pappas and H. Hassani, “Conformal Risk-Averse Decision Making with Action Conditional Guarantee,” in Proc. International Conference on Machine Learning (ICML), PMLR vol. 306, pp. 167248–167276, Seoul, Korea, July 2026. [Proceedings] [Code]
-
C418
D. Snyder, A. Badithela, N. Matni, G. J. Pappas, A. Majumdar, M. Itkina and H. Nishimura, “Beyond Binary Success: Sample-Efficient and Statistically Rigorous Robot Policy Comparison,” in Proc. Robotics: Science and Systems (RSS), Sydney, Australia, July 2026. [DOI]
-
J166
Z. Xie, W. Zhang, Y. Ren, Z. Wang, G. J. Pappas and W. Jin, “Safe MPC Alignment with Human Directional Feedback,” IEEE Transactions on Robotics, vol. 42, pp. 750–769, 2026. [DOI] [Code]