Project Grant 2625831
- The National Science Foundation Division of Computer and Network Systems awarded Georgia TECH Research Corp $360,000 on August 15, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop a control-theoretic framework for reliable and robust deep neural networks with application to space cyber-physical systems. The project formulates deep neural network training as a feedback control design problem, leveraging optimal and robust control theory...
- The National Science Foundation Division of Information and Intelligent Systems awarded Georgia TECH Research Corp $600,000 on September 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop formal reasoning methods for reinforcement learning systems deployed in safety-critical applications. The project addresses the problem of reward hacking in reinforcement learning agents used in autonomous vehicles, robotic surgery, and autonomous trading, where...
- Federal Grant Award Summary The National Science Foundation (NSF) Division of Civil, Mechanical, and Manufacturing Innovation awarded Georgia TECH Research Corp a collaborative research project grant totaling $297,881 on August 1, 2025, with a completion date of July 31, 2028, under the Engineering program (CFDA 47.041). The research delivers advanced theory and computational algorithms for controlling distributions in large-scale dynamical systems, addressing critical gaps in precision...
- The National Science Foundation Division of Computer and Network Systems awarded Georgia TECH Research Corp six hundred thousand dollars on July 15, 2026, for research on cybersecurity in remotely controlled robots under the Computer and Information Science and Engineering program (CFDA 47.070). The project develops a security framework protecting remote-controlled and cloud-connected systems by performing control computations directly on encrypted data while embedding a detection mechanism that...
- This National Science Foundation Project Grant of $2,090,572 will fund research at Georgia Tech Research Corporation from June 2022 to May 2025 to develop next-generation advanced driver assistance systems. The research aims to increase safety and performance of deep neural networks operating within feedback loops that include human drivers. Specifically, the grant will support research to utilize reinforcement learning and formal methods techniques to design systems that can accommodate...
- The National Science Foundation (NSF) awarded a $194,000 Project Grant under the Engineering program (CFDA 47.041) to Georgia Tech Research Corp to conduct research on safe reinforcement learning. The project aims to develop new approaches for training, improving, and evaluating reinforcement learning policies that are robust to distribution shift and non-stationarity, with the goal of ensuring safety in applications such as robotics, autonomous driving, and power systems. Key innovations...
- Federal Grant Award Summary Georgia Tech Research Corporation received a $691,375 Project Grant from the National Science Foundation's Division of Civil, Mechanical, and Manufacturing Innovation under the Engineering program (CFDA 47.041), effective September 1, 2025 through August 31, 2028. This award supports fundamental research and development of defensive countermeasures against affine transformation-based false data injection attacks targeting networked robotic systems. The primary...
- This $250,000 Project Grant award from the National Science Foundation (NSF) Engineering program (CFDA 47.041) aims to address challenges in stochastic nonlinear control and learning for dynamical systems through a novel "Spectral Dynamic Embedding" approach. Led by the Georgia Tech Research Corporation, the research intends to develop computationally efficient control algorithms suitable for applications in robotics, aerospace, manufacturing, and beyond. The key innovations involve...
- The National Science Foundation awarded a $378,570 Project Grant to the Georgia TECH Research Corporation from September 1, 2021 through August 31, 2024 under the Engineering program (CFDA 47.041). The grant funds research on A GEOMETRIC APPROACH FOR GENERALIZED ENCRYPTED CONTROL OF NETWORKED DYNAMICAL SYSTEMS. The NSF Directorate for Engineering seeks to improve quality of life and economic strength by fostering innovation and excellence in engineering research and education. This award will...
- The National Science Foundation Division of Computing and Communication Foundations awarded the University of Florida $341,006 on October 1, 2025, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop formal verification methods and toolchains for learning-enabled autonomous systems. The project addresses safety and robustness of deep neural networks in safety-critical autonomy applications by creating new formal method foundations for modeling,...
The National Science Foundation Division of Electrical, Communications and Cyber Systems awarded Georgia TECH Research Corp $495,000 on January 1, 2027, under the Engineering program (CFDA 47.041) to develop differentiable reachability analysis for scalable verification and safe training of neural network controllers. The project will create mathematical theory and algorithmic tools that integrate safety verification directly into the design of learning-based feedback control systems, rather than performing verification as a separate post-design check. The work focuses on reachability analysis—computing the set of all possible future states a system may enter—to provide rigorous certification of safety properties in autonomous systems that use neural networks for control decisions. Delivery of foundational theory, scalable algorithms, and algorithmic tools will enable efficient safety guarantee computation and improvement during system design on modern computational platforms. The recipient is Georgia TECH Research Corp (doing business as the Office of Sponsored Programs), the research entity of the Georgia Institute of Technology, performing work in Atlanta, Georgia. The period of performance runs from January 1, 2027, through December 31, 2029. Broader impacts include training and engaging students at all educational levels through team-based research, developing interdisciplinary courses spanning control theory, machine learning, and computer vision, and releasing open-source software. The underlying methods apply to autonomous driving, assistive robotics, power grids, and transportation networks.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $495.0k | 8/6/26 |