This $425,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research to develop a framework for ensuring the safety of future robotic systems. The research project, led by The Trustees of Princeton University, aims to lay the foundation for safe robot autonomy by enabling robots to continually prove the safety of their actions under a wide range of operating conditions, from complex...
The National Science Foundation (NSF) awarded a $375,000 Project Grant under the Computer and Information Science and Engineering (CISE) program to the Regents of the University of Michigan, Office of Research and Sponsored Projects, doing business as the University of Michigan. The grant, awarded on October 1, 2023, aims to develop foundational technologies for safe Reinforcement Learning (RL)-enabled systems, integrating research and education. The project focuses on three key thrusts: (1)...
This $750,000 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program to Arizona State University focuses on developing foundational technologies for safe Reinforcement Learning (RL)-enabled systems. The 4-year project aims to establish theories, algorithms, and experiments for distributional RL to enable policy safety, exploration safety, and environmental safety in RL-powered applications like 6G networking,...
This $375,000 Project Grant was awarded by the National Science Foundation (NSF) under its Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to the University of Massachusetts (UMass) for the project "COLLABORATIVE RESEARCH: SLES: NO BAD SURPRISES: ALIGNING AGENT AND HUMAN NORMS VIA SPECIFICATION REFINEMENTS". The goal is to develop tools and processes to design provably safe autonomous systems, focusing on aligning the norms of reinforcement learning...
This four-year, $1.2 million project grant from the National Science Foundation's Computer and Information Science and Engineering program aims to advance robotic mapping and navigation capabilities using semantic maps and spatial reasoning based on visual inputs and language instructions. Funded through the Division of Information and Intelligent Systems, the research seeks to enable robots to learn to predict maps of unseen environments using active learning techniques. It also focuses on...
This Project Grant award from the National Science Foundation's Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports collaborative research to design provably safe autonomous systems. The $375,000 award to the University of Texas at Austin aims to develop tools that can align the norms and behaviors of reinforcement learning (RL) agents with the intent of their designers. Key activities include developing inverse RL algorithms to learn agent reward functions,...
This Project Grant award, valued at $375,000 and awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070), supports The Ohio State University's research on safe and reliable reinforcement learning (RL) systems.
The key objectives of this 4-year project are to develop foundational technologies for safe RL-enabled systems, including policy safety, exploration safety, and environmental safety. The research will...
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 National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Program (CFDA 47.070) Project Grant award of $750,000 to Oregon State University (OSU) will develop tools to design and verify the safety of autonomous systems employing reinforcement learning. The key activities include:
Developing inverse reinforcement learning algorithms to align the agent's norms with the designers' intent, constrained by deontic logic.
Exploring the agent's norms to uncover...
This $500,000 project grant, awarded on January 1, 2024 by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070), aims to address the urgent need for end-to-end safety in learning-enabled autonomous systems across various application scenarios, such as self-driving cars and urban air mobility.
The project, titled "COLLABORATIVE RESEARCH: SLES: GUARANTEED TUBES FOR SAFE LEARNING ACROSS AUTONOMY ARCHITECTURES,"...