Mingjian Liang

Papers

Total Citations

H-Index

About

Mingjian Liang is a robotics researcher whose work focuses on advancing autonomous positioning and navigation systems, particularly through the quality assurance of occupancy grid maps. His most cited paper, "Abnormal Occupancy Grid Map Recognition using Attention Network" (2022, 4 citations), addresses a critical bottleneck in mobile robotics: the need for automated detection of map anomalies. Liang’s key contribution lies in developing attention-based deep learning models that can identify abnormal grid maps, replacing the previously tedious and time-consuming manual recognition process. This work directly improves the reliability of downstream systems like path planning and localization, which depend heavily on accurate map data. By leveraging attention networks, Liang has introduced a more efficient and scalable approach to map quality control, enabling autonomous systems to operate with greater robustness in real-world environments. His research sits at the intersection of computer vision, deep learning, and robotic perception, offering practical solutions for enhancing the safety and performance of autonomous mobile robots. Though early in his career, Liang’s targeted contributions to map validation demonstrate a clear impact on the field, with potential for broader adoption in industrial and service robotics applications.