Max Robotics — Global Service Robot Directory + US Certification

About

Yuejiang Liu is a researcher whose work sits at the dynamic intersection of robot navigation, social intelligence, and deep learning. His research focuses on enabling autonomous robots and AI systems to understand and respond to human behavior in complex, crowded environments — a challenge central to the future of human-robot coexistence. Liu's most influential contribution, "Crowd-Robot Interaction" (2019), introduced an attention-based deep reinforcement learning framework that allows robots to navigate socially-compliant paths through crowds by selectively weighing the influence of nearby individuals. With over 580 citations, this work has become a landmark reference in socially-aware robot navigation, demonstrating that robots can learn nuanced cooperative behaviors rather than purely collision-avoidance strategies. Complementing this, his "Social NCE" work (2021, 112 citations) advanced the field further by leveraging contrastive learning to develop socially-aware motion representations that generalize more robustly in multi-agent settings, addressing key limitations of existing neural approaches for both human trajectory forecasting and crowd navigation. His earlier work on map-based deep imitation learning for obstacle avoidance (2018) reflects a consistent commitment to computationally efficient, practical robotic decision-making. Across his portfolio, Liu has established himself as a thoughtful contributor shaping how intelligent systems move safely and respectfully alongside humans.