Kai-Chi Chan

Papers

Total Citations

H-Index

About

Kai-Chi Chan is a researcher whose work lies at the intersection of robotics, computer vision, and human-robot interaction, with a primary focus on advancing human-pose estimation. His key contributions address the fundamental challenge of enabling robots to perceive and understand human motion, a critical capability for developing more intuitive and responsive robotic systems. Chan’s most notable work introduces a novel 3D point-cloud geometric feature designed to robustly estimate human poses from depth sensor data, providing a foundation for robots to cognitively interpret human actions. In a complementary study, he tackled the problem of viewpoint selection, proposing a two-phase approach that determines the optimal sensor position to maximize pose estimation accuracy. This work is particularly significant for mobile robots, as it allows them to actively adjust their perspective to overcome the difficulties posed by the human body’s high articulation. While his citation counts (12 and 4) reflect a focused, early-career impact, his research addresses a core bottleneck in embodied AI: how a machine can dynamically and accurately perceive a moving human. Chan’s contributions are a stepping stone for future work in autonomous navigation, collaborative robotics, and assistive technologies.