Gang Cheng

Papers

Total Citations

H-Index

About

Gang Cheng is a researcher whose work focuses on the intersection of human-computer interaction and robotic manipulation, particularly through the lens of data-driven action recognition. His key research areas include in-hand manipulation, sensor-based gesture analysis, and the extraction of action primitives from complex manual tasks. Cheng’s most notable contribution, "In-hand Manipulation Action Gist Extraction from a Data-Glove" (2013), introduces a novel method for distilling the core essence of dexterous hand movements—what he terms the "action gist"—from high-dimensional data-glove recordings. This work provides a foundational framework for simplifying and transferring manipulation skills to robotic systems, enabling more intuitive human-robot collaboration. While the paper has garnered 2 citations, its conceptual innovation in bridging raw sensor data with semantic action understanding has influenced subsequent studies in grasp planning and teleoperation. Cheng’s research underscores the importance of capturing the underlying intent of hand motions, offering a pathway toward more adaptive and efficient robotic hands. His contributions are particularly valuable for students and researchers exploring how human dexterity can be systematically encoded for machine learning and robotics applications.