Chuang Gan Receives NSF CAREER Award to Advance Embodied AI Research
Content
Manning College of Information and Computer Sciences (CICS) Assistant Professor Chuang Gan has received a National Science Foundation (NSF) CAREER Award totaling $599,814 to support his project, “Modeling Physical and Social Worlds for Embodied General Intelligence.”
Gan’s research focuses on embodied artificial intelligence—agents capable of perceiving, reasoning about, and interacting with the physical world, humans, and other artificially intelligent beings in open, dynamic environments. Today’s embodied agents, such as robots and virtual assistants, perform well at the specific tasks or environments they were trained for, but often lack the flexibility to succeed when conditions change. Gan’s project aims to address this gap by integrating physics engines and generative foundation models to develop “physical” and “social” intelligence in embodied agents. The work hopes to provide advances in assistive robotics, virtual agents, and other applications where AI must cooperate with and adapt to humans in complex environments.
“The goal of our research is to develop general-purpose embodied agents capable of understanding and interacting with the physical world and other intelligent beings as flexibly as humans, which we term as embodied general intelligence. Our approach draws inspiration from cognitive science, which attributes human generalization and adaptability to internal mental models,” explains Gan. “We aim to replicate these mechanisms by developing a compositional and adaptive world model for embodied agents.”
The project is organized around three research thrusts: 1) developing generative simulation tools to expand embodied agents’ physical skills, 2) enhancing their social intelligence for open-world human interaction, and 3) prototyping real-world applications. Beyond research, Gan will integrate this work into the college’s graduate computer science curriculum, developing a new “Embodied General Intelligence” course and leading outreach initiatives designed to broaden participation in computing and robotics.
Gan joined CICS in 2023 after serving as principal researcher and manager at the MIT-IBM Watson AI Lab and a postdoctoral associate at the Massachusetts Institute of Technology. His research spans embodied AI, robotic manipulation, and generative models.
The CAREER Award is one of the NSF’s most prestigious honors in support of early-career faculty who exemplify the role of teacher-scholars through outstanding research, excellent education, and the integration of the two.
