This $800,000 Project Grant award to The Trustees of Princeton University, Department of Research and Project Administration, was provided by the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070). The award aims to develop new techniques for constructing a vision-based safety supervisor that can endow autonomous robotic systems, such as self-driving cars and home robots, with the safety property of "graceful degradation." This will enable these systems to detect unfamiliar scenarios and switch to safe, conservative actions rather than catastrophic failure. The project involves developing symbolic scene representations, reasoning algorithms for interpretable and verifiable safety assessments, and procedural validation methods using synthetic visual data. The research is integrated with educational activities at the K-12, undergraduate, and graduate levels. The award period runs from October 1, 2023 to September 30, 2026.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $800.0k | 9/18/23 |