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.