Max Robotics — Global Service Robot Directory + US Certification

About

Yu Tang Liu is a robotics researcher whose work sits at the intersection of deep reinforcement learning (DRL), autonomous aerial systems, and robot control. With a growing body of highly cited work, Liu has made significant contributions to two primary domains: aerial human motion capture and autonomous airship navigation. Liu's most recognized contribution, "AirCapRL" (2020, 34 citations), introduced a pioneering DRL-based multi-robot formation controller enabling autonomous aerial human motion capture — a technically demanding problem requiring real-time pose and shape estimation of moving individuals. This work demonstrated the viability of learned controllers for complex, vision-dependent multi-agent tasks. A substantial thread of Liu's research addresses the underexplored challenge of blimp autonomy. Across multiple publications spanning 2021–2023, Liu developed progressively sophisticated controllers — from baseline DRL approaches to deep residual reinforcement learning and H∞ robust frameworks — tackling blimp dynamics, deformation under turbulence, and real-world disturbances. The 2022 simulation work (12 citations) further established essential infrastructure for the broader airship robotics community. More recently, Liu has pursued greater generalization in robot learning, exploring multi-task reinforcement learning and adaptive controllers capable of transferring across tasks and environments. Collectively, Liu's work charts an ambitious path toward robust, deployable autonomous aerial systems.