Project Grant 2153854

Award Date 9/1/22
Completion Date 8/31/26
Dollars Obligated $467K
Federal Grant Program
47.041
Assistance Type
Project Grant
Place of Performance
Stanford, CA 94305, USA
Similar Awards
This National Science Foundation project grant of $376,203 supports research at the University of Wisconsin-Madison to develop new expressive and differentiable robotics simulators from 2022 to 2026. The research aims to address key limitations in existing simulators that hamper accurate physical modeling of robots and hinder closing the gap between simulation and real-world performance. Specifically, the researchers will establish the mathematical foundations for robotics simulators with...
This $50,000 Project Grant was awarded by the National Science Foundation (NSF) Engineering program (CFDA 47.041) to The Leland Stanford Junior University (Stanford University) to develop a novel approach for robotic dexterous manipulation that leverages the powerful new object representation of neural radiance fields (NeRFs). The primary objective is to create an algorithmic pipeline that can go from camera pixels to grasp to manipulation trajectory, enabling complex manipulation skills such as...
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...
The National Science Foundation awarded a $400,000 Project Grant to Stanford University under the Computer and Information Science and Engineering program (CFDA 47.070). The grant will fund a research collaboration titled "COLLABORATIVE RESEARCH: CPS: MEDIUM: CLOSING THE TELEOPERATION GAP: INTEGRATING SCENE AND NETWORK UNDERSTANDING FOR DEXTEROUS CONTROL OF REMOTE ROBOTS" from February 2021 through January 2024. The grant aims to advance investigator-initiated research and education in...
This $499,076 National Science Foundation (NSF) grant awarded under the CFDA 47.041 Engineering program aims to develop efficient computational methods for robots to learn reliable dexterous manipulation skills without relying on significant human effort or computational resources. The principal objectives are to: 1) Learn dexterous manipulation skills from observations, 2) Learn multi-sensory representations and models from self-guided play, and 3) Analyze and guarantee learned manipulation...
This $249,654 federal Project Grant awarded by the National Science Foundation's (NSF) Engineering program (CFDA 47.041) will support research by The Leland Stanford Junior University (Stanford University) to develop a foundational framework for providing continual safety assurances for closed-loop systems under perception-based controllers. The key goals are to: (a) develop techniques for learning robust perception policies; (b) construct safety monitors for perception policies to ensure safe...
The National Science Foundation Division of Computer and Network Systems awarded a $337,020 project grant to Stanford University under the Computer and Information Science and Engineering program (CFDA 47.070) to support research on visual tactile neural fields for active digital twin generation. Over a three-year period from October 2022 through September 2025, Stanford researchers will develop new algorithms and computational tools to allow robots to combine visual and tactile sensory data...
This Project Grant award of $530,000 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program will develop open-source software for differentiable simulation of physical systems with complex geometries, large deformations, contact, and friction. The project, entitled "Collaborative Research: Frameworks: Differentiable Dynamic Simulation on Complex Geometries for Parameter Inference, Design Optimization and Control," will create the...
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 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program, CFDA 47.070, supports a research project titled "CAREER: ACTIVE SCENE UNDERSTANDING BY AND FOR ROBOT MANIPULATION" at Stanford University. The $130,000 grant, awarded on October 1, 2023, aims to develop a self-improving robot perception system that leverages manipulation skills for active scene understanding. The key focus is on enabling robots to...

This $466,714 project grant from the National Science Foundation's Engineering program (CFDA 47.041) supports the development of new expressive and differentiable robotics simulators at Stanford University from September 2022 through August 2026. The researchers will establish the mathematical foundations for simulators with learnable components, prototype such simulators, and evaluate their ability to reduce the "sim-to-real gap" where robots perform differently in simulation versus reality. This work aims to advance robotics technologies by creating a new generation of simulators that can more accurately model real-world physics through combining known equations with empirical data, while also providing gradient information to automatically refine simulator parameters. If successful, these simulators could help accelerate robot design, lower costs, and enhance safety by enabling more effective training in virtual environments.

Generated 1/6/24, 11:39 AM