Linzhuo Pang
Papers
2
Total Citations
27
H-Index
2
About
Linzhuo Pang is a researcher whose work lies at the intersection of robotics, deep reinforcement learning, and simultaneous localization and mapping (SLAM). His key contributions focus on enabling mobile robots to navigate and interact with unknown environments more intelligently and reliably. In his highly cited 2019 paper, "Efficient Hybrid-Supervised Deep Reinforcement Learning for Person Following Robot" (21 citations), Pang pioneered a novel hybrid-supervised approach that combines deep reinforcement learning with supervised signals, significantly improving the efficiency and robustness of person-following robots—a critical capability for applications in service robotics and human-robot interaction. Earlier, his 2017 work on "Loop Closure Detection for Visual SLAM Based on Deep Learning" (6 citations) tackled a fundamental challenge in SLAM: accurate loop closure detection, which is essential for correcting drift and ensuring long-term navigation stability. By applying deep learning to this problem, Pang demonstrated how neural networks could enhance the precision and reliability of map-building in unknown environments. His research bridges theoretical advances in learning algorithms with practical robotic systems, making him a notable contributor to the fields of autonomous navigation and intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2Loop Closure Detection for Visual SLAM Based on Deep Learning6 citations · 2017