AI-assisted Multi-Agent Autonomy with Human in the Loop

Lead PI: Shaoshuai Mou ( Purdue)

Co-PIs: Daniel DeLaurentis (Purdue), Joydeep Biswas (The University of Texas at Austin), Bing Liu (University of Illinois at Chicago).

Abstract: This is a multi-university project funded by Northrop Grumman Corporation as part of the Real Application of Learning Machine consortium. This project aims to develop AI-assisted dynamic adaptive planning for multi-agent systems with human-in-the-loop shared autonomy. Methodologies come from a combination of control, optimization, learning and robotics by collaborations among faculties at multiple universities. The project develops techniques along with implementations for multi-agent platforms, which provide environment perception and situation awareness; perform real-time, dynamic and distributed solutions to control of assets, decision making and task assignment in changing environments; integrate human inputs/corrections to achieve mixed-human-machine autonomy; and utilize machine learning methods to continuously improve performance.

More Information

• AI research offers more eyes and ears to search and rescue missions