Yingzi Tan

Southeast University, Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Yingzi Tan is a robotics researcher whose work centers on intelligent perception, navigation, and task allocation for mobile robots operating in complex, real-world environments. Her primary contributions lie in advancing computer vision and object recognition for autonomous systems, particularly in industrial and hazardous settings. Tan’s most influential work, "Visual navigation method for indoor mobile robot based on extended BoW model" (16 citations), introduces a novel navigation approach using an extended Bag of Words model accelerated by GPU-based SIFT detection, enabling robust general object recognition indoors. She further enhanced inspection robot accuracy with "Detection of cabinet in equipment floor based on AlexNet and SSD model" (9 citations), applying deep learning to improve stability in industrial inspections. Her earlier research on "Generic object recognition based on feature fusion in robot perception" (3 citations) pioneered multi-feature fusion of 2D and 3D descriptors for richer robot perception. Addressing safety in extreme scenarios, Tan’s work on task allocation for rescue robots in chemical disaster environments (2 citations) optimizes path planning under hazardous, blocked conditions. Through these contributions, Tan has advanced the reliability and applicability of mobile robots in both routine industrial tasks and critical emergency response, demonstrating a clear trajectory from foundational perception algorithms to practical, safety-critical deployments.