High Fidelity Modeling, Control and Coordination of Multi-Vehicle Systems for Traversing Cluttered Off-Road Terrains

This project is on system and algorithm design for motion control and coordination in a vehicle team composed of one ground vehicle (GV) and one or multiple cooperating unmanned aerial vehicles (UAVs). The GV here is either an advanced light armored vehicle (LAV) or an all-terrain unmanned GV (UGV) to traverse a cluttered off-road terrain for surveillance, terrain mapping, and other missions. The UAVs continuously surveil the current locality of the GV and update the mapping and navigation information.

Multi-agent reinforcement learning for decentralized UAV/UGV cooperative exploration - Year two

Over the last decade, artificial intelligence has flourished. From a research niche, it has been developed into a versatile tool, seemingly on route to bring automation into every aspect of human life. At the same time, robotics technology has also advanced significantly, and inexpensive multi-robot systems promise to accomplish all those tasks that require both physical parallelism and inherent fault tolerance—such as surveillance and extreme-environment exploration.

Multi-agent reinforcement learning for decentralized UAV/UGV cooperative exploration

Over the last decade, artificial intelligence has flourished. From a research niche, it has been developed into a versatile tool, seemingly on route to bring automation into every aspect of human life. At the same time, robotics technology has also advanced significantly, and inexpensive multi-robot systems promise to accomplish all those tasks that require both physical parallelism and inherent fault tolerance—such as surveillance and extreme-environment exploration.