Muxin Chen

Papers

Total Citations

H-Index

About

Muxin Chen is a researcher whose work sits at the intersection of robotics, tactile sensing, and deep learning. Their primary research focus is on enhancing robotic manipulation through intelligent tactile perception, particularly in unstructured environments. Chen’s most notable contribution is the development of an attention-mechanism-based Long Short-Term Memory (LSTM) model for object tactile character recognition, published in 2020. This work directly addresses a critical challenge in robotic garbage sorting: the difficulty of adapting grasps to objects with varying physical properties like mass and stiffness. By integrating attention mechanisms with LSTM networks, Chen’s model enables robots to more accurately interpret tactile feedback, significantly improving the success rate of object handling. This paper has garnered 7 citations, reflecting its relevance to the growing field of robotic environmental interaction. Chen’s work is a valuable step toward more adaptive and autonomous robotic systems, offering practical solutions for waste management and beyond. Their research continues to influence how machines learn from touch, bridging the gap between sensory data and effective physical action.