Song Peng
Papers
2
Total Citations
19
H-Index
2
About
Song Peng is a leading researcher in the field of robotics perception, with a primary focus on Visual Simultaneous Localization and Mapping (SLAM) in dynamic environments. His major contributions lie in developing probabilistic models and robust perception frameworks that move beyond simple dynamic object rejection. Instead of discarding valuable information from moving objects, Peng’s work introduces novel dynamic detection and data association methods that actively integrate this data, enabling robots to maintain accurate localization and tracking even in complex, cluttered scenes. His 2024 paper on a "Dynamic detection and data association method based on probabilistic models for visual SLAM" has already garnered 12 citations, while his subsequent work on "Robust Perception-Based Visual Simultaneous Localization and Tracking" has earned 7 citations, highlighting the immediate impact of his research. By addressing the critical failure modes of traditional SLAM in dynamic settings, Peng is paving the way for more resilient and intelligent autonomous systems, making his work essential reading for students and researchers tackling real-world robotic navigation challenges.
Research Focus
Key Achievements
Top Papers
- 1
- 2