Zexu Pan
Papers
1
Total Citations
3
H-Index
1
About
Zexu Pan is a researcher at the forefront of multi-modal human-robot interaction (HRI), with a primary focus on advancing speaker tracking and audio-visual sensor fusion. His most-cited work, "GLMB 3D Speaker Tracking with Video-Assisted Multi-Channel Audio Optimization Functions" (2024), introduces a novel framework that integrates complementary audio and visual signals to overcome persistent challenges in dynamic, real-world environments—such as occlusions, noise, and reverberation. By leveraging a generalized labeled multi-Bernoulli (GLMB) filter and video-assisted optimization of multi-channel audio, Pan’s approach significantly enhances the accuracy and robustness of 3D speaker localization, a critical capability for natural HRI. This contribution addresses a key gap in the field, where single-modality methods often falter. With 3 citations since its 2024 publication, his work is already gaining recognition for its practical implications in assistive robotics, smart meeting rooms, and autonomous systems. Pan’s research exemplifies how cross-modal synergy can push the boundaries of perceptual intelligence, making him a promising voice in the next generation of HRI innovation.
Research Focus
Key Achievements
Top Papers
- 1