Songlin Cheng
Papers
1
Total Citations
2
H-Index
1
About
Songlin Cheng is a researcher advancing the frontiers of autonomous navigation and sensor fusion, with a particular focus on robust perception in challenging environments. His most-cited work, "A Glass Detection Method Based on Multi-sensor Data Fusion in Simultaneous Localization and Mapping" (2023), addresses a critical bottleneck in SLAM systems: the reliable detection of transparent surfaces, such as glass, which often confound standard LiDAR and camera-based approaches. By integrating data from multiple sensors, Cheng’s method enhances the accuracy and safety of robotic mapping in real-world settings, from indoor service robots to autonomous vehicles. This contribution has already garnered attention, with 2 citations in its early publication stage, signaling its growing relevance. Cheng’s research sits at the intersection of computer vision, probabilistic robotics, and sensor fusion, offering practical solutions to long-standing perception problems. His work not only improves SLAM robustness but also paves the way for more reliable autonomous systems in environments where traditional methods fail. For students and researchers in robotics, Cheng’s approach exemplifies how multi-modal data can overcome the limitations of single-sensor systems, making his contributions a valuable reference for those tackling real-world perception challenges.
Research Focus
Key Achievements
Top Papers
- 1