Dongdong Bai

National University of Defense Technology

Papers

Total Citations

H-Index

About

Dongdong Bai is a researcher focused on advancing visual simultaneous localization and mapping (SLAM) systems, with a particular emphasis on loop closure detection (LCD)—a critical component that enables robots to recognize previously visited places, correct localization drift, and build consistent maps over long-term operation. His major contributions lie in integrating deep convolutional neural network (CNN) features into real-time LCD frameworks, significantly improving robustness to viewpoint and environmental condition changes. Bai’s most cited work, “Matching-range-constrained real-time loop closure detection with CNNs features” (2016), has accumulated 14 citations, demonstrating its influence in the field. He further extended this approach in “CNN Feature boosted SeqSLAM for Real-Time Loop Closure Detection” (2017), which combines CNN features with the SeqSLAM algorithm to enhance performance under challenging conditions. Bai’s research addresses a key bottleneck in autonomous robotics—ensuring reliable place recognition during extended missions—and his methods have helped bridge the gap between deep learning and practical SLAM applications. His work continues to inspire researchers seeking efficient, real-time solutions for robust robot navigation.