Guihua Xia

About

Guihua Xia is a researcher whose work lies at the intersection of robotics, computer vision, and intelligent control systems. His primary research areas include 3D object detection, simultaneous localization and mapping (SLAM), and advanced force/position control for robotic manipulators. Xia’s most impactful contribution is the development of DVFENet, a dual-branch voxel feature extraction network for 3D object detection (2021, 42 citations), which significantly advanced autonomous perception by enabling more efficient and accurate processing of LiDAR point cloud data. In the domain of industrial robotics, he proposed a hybrid force/position controller based on Kalman filtering (2016, 15 citations), providing a robust mathematical model for estimating real contact forces—a critical safety and precision enhancement for manufacturing tasks. Xia also pioneered an adaptive impedance control method for industrial manipulators to write Chinese characters (2018), demonstrating the fusion of force estimation with delicate motion control. His earlier work on EKF-based SLAM for omnidirectional vision (2012) and Monte Carlo localization with modified SIFT (2009) laid foundational improvements for mobile robot navigation in complex environments. Through these contributions, Xia has shaped practical solutions for autonomous systems, from perception to manipulation.

Research Focus

Key Achievements

Top Papers

1. 1
   DVFENet: Dual-branch voxel feature extraction network for 3D object detection

   42 citations · 2021
2. 2
   Hybrid force/position control of industrial robotic manipulator based on Kalman filter

   15 citations · 2016
3. 3
   The SLAM algorithm of mobile robot with omnidirectional vision based on EKF

   8 citations · 2012
4. 4
   Adaptive Impedance Control Method for Industrial Manipulator Writing Based on Kalman Filter

   4 citations · 2018
5. 5
   Monte Carlo Localization of Mobile Robot with Modified SIFT

   3 citations · 2009

Key Collaborators

Contact & Links