Project Grant 2331904

Award Date 12/1/23
Completion Date 11/30/26
Dollars Obligated $800K
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Charlottesville, VA, USA
Similar Awards
This $316,963 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program will support research to enhance the safety and reliability of autonomous vehicles. The project aims to thoroughly examine and improve the controller and machine learning components of autonomous driving systems through a combination of model-based and data-driven approaches. The research will focus on identifying spatial and temporal vulnerabilities that...
This $564,734 Project Grant awarded by the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop principled algorithms and practical tools that systematically discover and repair unsafe behavior in autonomous vehicle systems. The key objectives are to: Create an automated method for constructing diverse test scenarios that can deeply explore realistic traffic situations and identify collision-inducing scenarios. Develop...
This $272,238 Project Grant, awarded on July 15, 2024 by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070), supports research to enhance the safety and reliability of autonomous vehicles. The project aims to identify vulnerabilities in the software and machine learning components of autonomous vehicle systems, and develop mitigation techniques to improve their overall resilience. The research will combine model-based and...
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,"...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) focuses on developing tools to ensure the safe operation of autonomous systems, such as robots and self-driving vehicles. The $375,000 award will be used by the University of Massachusetts to: 1) develop algorithms to align the learned norms of reinforcement learning agents with the intended design goals; 2) create formal verification...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program grant, awarded to the University of Delaware, provides $1,499,949 to develop safe learning-enabled systems for autonomous vehicles (AVs). The key innovations include: Developing rational machine learning (ML) models that produce accurate predictions based on valid rationales to improve AV safety. Integrating hardware reliability into ML model design to tolerate runtime faults. Designing a novel...
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 physical...
This $270,913 federal Project Grant award, funded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program, supports research to develop qualitative and quantitative methodologies for assessing the safety of learning-enabled autonomous systems. The project, led by the Augusta University Research Institute, Inc. (AURI), will target foundational challenges in capturing uncertainties from environments and providing timely, comprehensive, and...
This $120,000 Project Grant was awarded on July 1, 2024 by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to the Regents of the University of California at Riverside (UC Riverside). The funding will support a collaborative research project focused on enhancing the safety and reliability of autonomous driving systems through the development of advanced detection and countermeasure techniques at the application, system, and...
This $572,778 federal Project Grant award was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070). The award will support research and development at North Carolina State University (NC State) to address fundamental challenges in simulation-based testing of autonomous driving systems (ADS). The key objectives are to: 1) Improve the efficiency and effectiveness of simulation-based ADS testing by leveraging...

This $799,803 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports the development of a new framework named CRASH (Challenging Reinforcement-Learning Based Adversarial Scenarios for Safety Hardening) to effectively stress test and improve the safety of autonomous vehicle software.

The framework leverages multi-agent adversarial deep reinforcement learning to automatically generate realistic and challenging traffic scenarios in simulation that can identify potential failures in an autonomous vehicle's motion planning. The project then enhances the vehicle's safety performance by improving its ability to learn from and avoid repeating these identified failures, a process referred to as "safety hardening." This iterative refinement aims to fortify the autonomous vehicle's resilience in navigating unexpected traffic situations, ultimately advancing the safety testing and deployment of autonomous vehicles reliant on learning-enabled components. The award period runs from December 1, 2023 to November 30, 2026.

Generated 7/2/24, 8:11 AM