Santiago Paternainمشاهده پروفایل
استادیار
Santiago Paternain is an Assistant Professor in the Department of Electrical, Computer and Systems Engineering at Rensselaer Polytechnic Institute's School of Engineering. He joined RPI in 2020 after completing his Ph.D. and postdoctoral work at the University of Pennsylvania, where he developed foundational algorithms at the intersection of machine learning and control theory. His research bridges theoretical rigor with practical applications in robotics, power systems, and autonomous vehicles. His academic credentials include: B.Sc. in Electrical Engineering, Universidad de la República, Uruguay (2012) M.Sc. in Statistics, The Wharton School, University of Pennsylvania (2018) Ph.D. in Electrical and Systems Engineering, University of Pennsylvania (2018) Paternain's research centers on reinforcement learning and control of dynamical systems, with emphasis on safety guarantees, optimization, and real-world deployment. He develops algorithms that integrate model-based control with data-driven methods to overcome limitations of pure reinforcement learning, particularly for constrained and safety-critical applications. Current projects explore in-context learning for robotics, physics-guided AI for power grids, and multi-agent coordination in uncertain environments, always prioritizing theoretical soundness and practical viability. Analysis of his 15 most recent publications reveals a dominant focus on constrained reinforcement learning (60% of works), with growing applications in power systems (20%) and robotics (15%). A clear trend shows increasing integration of foundation models with control theory, particularly for safety-critical decision making. His work consistently addresses scalability challenges while maintaining rigorous safety guarantees, reflecting his commitment to bridging theoretical and applied research. His scientific contributions have earned significant recognition: Best Student Paper Award at ICASSP 2020 Joseph and Rosaline Wolfe Best Doctoral Dissertation Award (2019) Best Student Paper Award at CDC 2017 Best Student Paper Award at I2MTC 2014 Best Teaching Assistant at University of Pennsylvania (2017) CTL's Graduate Fellowship for Teaching Excellence (2018) Paternain actively mentors six doctoral students across diverse research areas including safe reinforcement learning, multi-robot systems, and power grid applications. His research is supported by substantial funding including multiple RPI-IBM Future of Computing Research Collaboration grants (quantum computing and LLM reasoning), a DOE grant for EV battery assessment, an ONR grant for autonomous helicopter refueling, and industry partnerships with Boeing and ARM. He leads a high-impact research group that organizes influential workshops like "Learning under Requirements" at premier conferences including AAAI and L4DC. His laboratory focuses on translating theoretical advances into industrial applications through partnerships with GE Research, The Boeing Company, and national laboratories. Current projects include autonomous helicopter aerial refueling systems, real-time power grid stability assessment tools using graph neural networks, and safety-certified multi-robot coordination frameworks, all emphasizing deployable solutions for critical infrastructure challenges.
