Project Grant N000142612246

This three-year, $375,000 National Science Foundation project grant supports research at the University of Illinois to develop distributionally robust adaptive control methodologies for reinforcement learning algorithms. The goal is to enable safe and robust autonomous operation of complex systems by constructing a new class of adaptive controllers that are robust to errors in learned distributions. This will allow reinforcement learning algorithms to directly interact with the controllers...

Safe Stochastic Nonlinear Model Predictive Control for Agile Aircraft Maneuvers The Office of Naval Research (ONR) awarded The Johns Hopkins University a $654,073 project grant under the Basic and Applied Scientific Research program (CFDA 12.300) to conduct research on safe stochastic nonlinear model predictive control (NMPC) for agile aircraft maneuvers. The award, effective October 1, 2025 through September 30, 2029, supports fundamental and applied research with direct applications to naval...

CAREER: Safety-Centered Multi-Agent Reinforcement Learning Wake Forest University received $520,013 in Project Grant funding from the National Science Foundation's Division of Information and Intelligent Systems (CFDA 47.070) awarded on July 15, 2025, with a completion date of June 30, 2030. This CAREER award supports research and development of a comprehensive safety framework for multi-agent reinforcement learning (MARL) systems. The project delivers four key innovations: (1) learning...

This three-year Project Grant of $299,601, awarded July 1, 2026, by the National Science Foundation's Division of Mathematical Sciences under the Mathematical and Physical Sciences program (CFDA 47.049), supports fundamental research in distributional reinforcement learning (DRL) for risk-sensitive sequential decision-making. The University of Miami will develop theoretical foundations and practical methods that enable artificial intelligence systems to learn the full distribution of potential...

This NSF CISE program Project Grant award of $544,114 to New York University (NYU) is funding research on "NUMERICALLY EFFICIENT REINFORCEMENT LEARNING FOR CONSTRAINED SYSTEMS WITH SUPER-LINEAR CONVERGENCE (NERL)". The project aims to develop new reinforcement learning algorithms that can more efficiently create behaviors for real-world robotic applications, while ensuring operational safety. The research will explore ways to improve learning efficacy and guarantee safety, and will...

This three-year, $500,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program will fund research at the University of California, Davis to develop trustworthy machine learning systems through adversarial robust reinforcement learning. Specifically, the award supports investigating potential vulnerabilities in reinforcement learning models and algorithms, developing robust RL approaches that mitigate impacts from adversarial attacks, and...

This $300,027 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports research to develop secure and trustworthy learning-based control systems for cyber-physical systems (CPS). The project aims to: a) Develop a real-time reward manipulation scheme for learning-based controllers b) Design multi-level attack schemes on reward signals in a distributed CPS control architecture c) Develop data-enabled strategies for...

This National Science Foundation (NSF) Early-Concept Grant for Exploratory Research (EAGER) project, under the NSF Engineering program (CFDA 47.041), will support research at Arizona State University (ASU) to create a new modeling and learning framework enabling efficient coordination between a human and robot in urgent and safety-critical sensorimotor tasks. The $300,000 award, from September 2024 to August 2026, will integrate ideas from behavioral economics, game theory, optimal control,...

This three-year, $240,000 Project Grant from the National Science Foundation's Division of Electrical, Communications and Cyber Systems, under the Engineering program (CFDA 47.041), will support collaborative research between Columbia University and the University of Pennsylvania on scalable and communication-efficient learning-based distributed control. The researchers will develop a foundational and integrated theory of distributed learning-enabled control and approximated distributed...

The National Science Foundation (NSF) awarded a $188,410 Project Grant under the Computer and Information Science and Engineering (CISE) program to the University of California, Berkeley. This 18-month grant, which began on January 1, 2024, supports the development of risk-aware interactive control and planning algorithms to achieve safe cyber-physical-human (CPS-H) systems. The key objectives of this research project are: (i) creating computationally-tractable risk-aware trajectory planning...