Peigen Sun

University of Hong Kong, City University of Hong Kong

Papers

Total Citations

195

H-Index

About

Peigen Sun is a leading researcher in robotic manipulation, with a primary focus on the challenging domain of deformable object manipulation. His work addresses the fundamental problem of enabling robots to interact with and control non-rigid materials like cloth, food, and biological tissues, which lack a fixed shape and are notoriously difficult to model. Sun’s major contributions lie in developing data-driven, learning-based control systems that bypass the need for complex physical models. His most influential work, "3-D Deformable Object Manipulation Using Deep Neural Networks" (2019, 95 citations), pioneered the use of deep neural networks to servo-control both the position and shape of unknown deformable objects in three dimensions. This was complemented by his earlier work using fast online Gaussian Process regression (2018, 85 citations), which achieved similar goals with a different learning paradigm. Together, these papers have established foundational techniques for real-time, model-free deformable object control. Sun has also advanced practical applications, such as his work on automated cloth assembly for garment manufacturing, and developed robust, real-time shape estimation methods to handle noisy sensor data. With over 195 citations across his key works, Peigen Sun is recognized for bridging the gap between theoretical robotics and real-world manipulation of soft, deformable materials.