Project Grant 2541316
- Purdue University was awarded a $746,412 Project Grant from the National Science Foundation Division of Research on Learning in Formal and Informal Settings to develop co-robots to enhance motivation and self-efficacy in formal STEM education. The grant falls under the Computer and Information Science and Engineering program (CFDA #47.070), which supports investigator-initiated research and education in computing, communications, and information science and engineering. Purdue University will...
- The National Science Foundation Division of Electrical, Communications and Cyber Systems awarded Arizona State University $350,980 on October 1, 2026, under the Engineering program (CFDA 47.041) to develop physics-composed generative policies that embed contact physics directly into the architecture of robot learning models. The project addresses a critical limitation in current generative AI approaches to robot autonomy: generated motions may appear plausible while failing to respect the...
- Federal Grant Award Summary Purdue University received a $214,334 Project Grant from the National Science Foundation's Office of Multidisciplinary Activities under the Social, Behavioral, and Economic Sciences program (CFDA 47.075), awarded August 1, 2025, with a completion date of July 31, 2027. The project delivers research findings and professional development activities focused on responsible robot-assisted therapy research and the translation of robotics innovations from laboratory settings...
- This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Award (CFDA 47.070) provides $202,082 to support a research project at Boston University that introduces a novel approach for robots to navigate unknown environments. The key technical aspects include: Developing compact, interpretable representations of the environment using structured elements extracted from sensor measurements and optimized over time. Synthesizing local and global...
- The National Science Foundation Division of Civil, Mechanical, and Manufacturing Innovation awarded Purdue University $650,000 on May 1, 2026, under the NSF Engineering program (CFDA 47.041) to develop contact-aware soft continuum robots capable of performing contact-rich tasks through passively designed adaptive responses to touch. The project, titled "CAREER: Towards a Framework for Emergent Adaptability in Soft Continuum Robots," will advance fundamental knowledge of soft robot...
- The National Science Foundation Division of Computer and Network Systems awarded the University of Virginia $839,037 on September 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to advance research in cyber-physical-cognitive systems for human-robot teaming. The project establishes scientific foundations for robots that can reason about human partners' goals, beliefs, and expectations, enabling proactive assistance and safe collaboration even when...
- Federal Project Grant Award Summary Purdue University received a $299,631 Early Concept Grants for Exploratory Research (EAGER) award from the National Science Foundation's Division of Information and Intelligent Systems under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070), effective August 1, 2025, through July 31, 2027. The project addresses fundamental limitations in reinforcement learning (RL) by developing theoretical frameworks and algorithms that...
- The National Science Foundation Division of Computing and Communication Foundations awarded Purdue University $357,921 on July 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop algorithmic advances in structure-aware machine learning. The research addresses computational efficiency, reliability, and data governance in modern artificial intelligence systems by studying how the structure of training data shapes the behavior of learning systems....
- The National Science Foundation Division of Computer and Network Systems awarded Purdue University $410,000 on October 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop methods and tools for verifying the trustworthiness of pre-trained artificial intelligence models shared through open online repositories before their incorporation into scientific workflows and operational systems. The project addresses three security vulnerabilities in the...
- The National Science Foundation Division of Information and Intelligent Systems awarded Purdue University $401,546 on June 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to conduct research on software engineering foundations for reusing pre-trained neural models. The project, titled "PTM-SEER: Software Engineering Foundations for Re-using Pre-Trained Neural Models," investigates how practitioners discover, evaluate, adapt, and maintain...
The National Science Foundation Division of Computer and Network Systems awarded Purdue University $440,718 on September 1, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070) to develop learning-based methods for robot motion planning using physics priors. The research addresses the gap between human intuitive physics understanding and current robot capabilities by creating methods that enable robots to interpret and apply physics principles for real-time movement planning in constrained and unknown environments. The project uses partial differential equations describing robot motion, constraints, and cost-to-go functions as physics priors, organized into two thrusts: identifying suitable PDEs and solving them to generate motion under complex collision and kinematic constraints, and developing learning-based methods to solve these equations. The work will validate methods on robot navigation, manipulation tasks involving known and unknown environments, tool handling, and home-assistance scenarios such as fetching, carrying, and cleaning in new homes, as well as factory and search-and-rescue applications requiring operation without extensive reprogramming. Outcomes will be shared through publications, open-source code, benchmarks, student research opportunities, and educational outreach activities designed to expand robotics access. The award runs through August 31, 2031, with performance taking place at Purdue University in West Lafayette, Indiana.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $440.7k | 7/20/26 |