Jing Liang

University of Electronic Science and Technology of China, University of Maryland, College Park

Papers

Total Citations

251

H-Index

About

Jing Liang is a researcher whose work sits at the intersection of robotics, autonomous navigation, and intelligent sensing systems. Their research focuses on multi-modal sensor fusion, deep learning, and robot navigation in complex environments — areas that are increasingly critical as autonomous systems become more prevalent in real-world applications. Liang's most impactful contribution is a comprehensive comparative review on multi-modal sensor fusion using deep learning, published in 2023, which has already garnered an impressive 236 citations, reflecting its value as a foundational reference for researchers working with heterogeneous sensor data. This work demonstrates Liang's ability to synthesize broad, fast-moving fields into accessible, high-impact scholarship. Beyond survey work, Liang has contributed original algorithmic innovations, notably through XAI-N, a sensor-based robot navigation framework that combines deep reinforcement learning with explainable AI via decision trees. This approach addresses a persistent challenge in autonomous robotics — navigating dense, dynamic environments with moving obstacles — while maintaining transparency and interpretability in decision-making, a quality increasingly demanded of real-world AI systems. Together, these contributions position Jing Liang as a meaningful voice in the robotics and AI sensing community, bridging theoretical frameworks with practical, deployable solutions.