Speaker: Lei Zuo

Affiliation: Xi'dian University

Academic title: Professor

Honorary title: Heterogeneous UAVs Detection Area Allocation

Abstract:

In the Unmanned Aerial vehicles (UAVs) dynamic detection area Allocation problem, the scheme of UAVs needs to be fast reallocated to respond to emergencies. The common heuristic allocation method uses predesigned optimization rules to iteratively get the solution, which is time-consuming. To quickly assign  tasks  for  heterogeneous  UAVs,  we  propose  a  novel  tasks  allocation  algorithm  based  on multi-agent reinforcement learning (MARL) and a period training method (PTM). The period training method (PTM) is used to optimize the MARL model parameters in different training environments, improving the algorithm's robustness.

Biography:

Lei Zuo received the B.Sc. and Ph.D. degrees from Xidian University, Xi’an, China, in 2008 and 2014,    respectively. He currently works  as a professor with the National Key Laboratory of Radar  Signal    Processing, Xidian University. He received “First Prize in Natural Science, Chinese Electronics Society” and “Second Prize for National Defense Science and Technology Progress” .   He published more than    60 academic papers in authoritative journals,  such as IEEE TSP, IEEE TGRS, and IEEE TIE. His    interests include radar system design, task planning, and collaborative detection.