Hanwei Liu

Tongji University, Université Laval, Nanjing University of Science and Technology, Chinese Academy of Sciences

Papers

Total Citations

H-Index

About

Hanwei Liu is a robotics researcher whose work bridges the critical gap between robotic perception and autonomous manipulation. His research primarily focuses on three interconnected areas: facial expression recognition, robotic grasping of unknown objects, and kinematic modeling for reconfigurable robots. Liu’s most impactful contribution is his work on **FEDA: Fine-grained Emotion Difference Analysis for facial expression recognition**, which has garnered 27 citations and introduces a novel approach to capturing subtle emotional cues—a significant advancement for human-robot interaction. In robotic grasping, Liu has developed innovative methods for **grasp pose detection based on point cloud shape simplification**, enabling robots to autonomously grasp unfamiliar objects without relying on pre-existing models or RGB data, a critical capability for unstructured environments. His earlier foundational work includes a **polynomial inverse kinematic solution for the Jaco robot**, a 6R serial manipulator without a wrist-partitioned design, where he derived a univariate 16-degree polynomial to solve the complex inverse kinematics problem. Additionally, Liu has contributed to **topology description and modeling for reconfigurable modular robots**, establishing a 4×n characteristic matrix for kinematic analysis. Through these contributions, Liu demonstrates a consistent focus on enabling robots to perceive, understand, and physically interact with their environment more intelligently and autonomously.