University of Missouri

09/09/2024 | News release | Distributed by Public on 09/09/2024 19:34

Mushuang Liu receives DARPA Young Faculty Award for autonomous systems research

[Link]

Sept. 9, 2024

Mushuang Liu received the Defense Advanced Research Projects Agency Young Faculty Award for her research around reinforcement learning in autonomous systems. It's the first time a University of Missouri faculty member has received the recognition.

Liu is an assistant professor of mechanical engineering in the MU College of Engineering. The award allows her to develop a new framework to optimize how autonomous systems - including vehicles - make decisions and interact with their environment.

"The goal of the project is to develop a multi-agent reinforcement learning paradigm that is both socially intelligent and adaptable," Liu said. "Being socially intelligent working with and interacting with its peers, which might include team members, competitors or both, and adjust its policies accordingly. Being adaptable means performing a broad range of tasks and quickly adapting to various environments."

Reinforcement learning has been a fundamental driver of many recent advances in artificial intelligence. However, despite their effectiveness, autonomous systems powered by reinforced learning have not yet been widely applied to real-world systems.

Liu is planning to verify her novel algorithms using autonomous driving applications.

"Fully autonomous vehicles can bring about significant societal benefits, such as reduced accident rates and improved traffic efficiency," she said. "But major technical challenges still exist before these vehicles can routinely drive on public roads. This algorithm has the potential to address these challenges."

The impact of Liu's work and its potential applications are wide-ranging. Integrating interaction awareness and adaptiveness will allow agents to learn from peers who are also learning, which in turn allows technology to evolve. It's a process that resembles how students learn through group projects, teaching each other as they understand concepts more thoroughly.

Read more from the College of Engineering