This Project Grant award for $50,000.00, provided by the National Science Foundation (NSF) Engineering program (CFDA 47.041), aims to develop a framework for learning complex, long-horizon tasks from few-shot vision-language demonstrations. The primary objective is to enable robots to learn personalized tasks through natural interactions with users, who can provide visual demonstrations combined with language narration. The research leverages large language models to summarize vision-language demonstrations, verify automatically generated plans, and efficiently solve multi-step tasks. If successful, this project could transform consumer robotics applications by making robots more usable, personalized, and aligned with user values. The award is held by The Leland Stanford Junior University, with the research taking place at Stanford University in California. No subawards are planned under this grant.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $50.0k | 9/11/23 |