Our project titled “A Demonstration Platform for Dynamic Mission Planning with Multi-domain Autonomous Systems” is selected for funding by the DARPA STO program! Our project aims to develop a demonstration platform for teams of quad-rotors and ground-based robots competing in games of capture-the-flag, along with hierarchical reinforcement learning (RL) methods for teams of agents to win these games.

This project is a collaboration with Dr. Girish Chowdhary, Dr. RS Sreenivas, Dr. Jaggi Yedetore, and Dr. Heather Filippini from UIUC.

Update: We received funding to expand this project to develop multi-agent reinforcement learning (MARL) algorithms for adversarial environments and create an integrated pipeline for using these and other machine learning algorithms with DARPA’s STITCHES framework.