Hoang Ngoc Tran
Papers
5
Total Citations
140
H-Index
4
About
Hoang Ngoc Tran is a rising researcher in robotics and autonomous systems, with a focus on enhancing machine perception and precision. His work spans robot calibration, computer vision, and deep learning, addressing critical challenges in both industrial and autonomous vehicle domains. Tran’s most impactful contribution is a novel robot calibration method that integrates an extended Kalman filter with an artificial neural network optimized by a butterfly and flower pollination algorithm (ANN-BFPA), achieving significant improvements in absolute pose accuracy—a paper that has garnered 82 citations. He further advanced precision positioning with a Levenberg-Marquardt–accelerated particle swarm optimization (LMAPSO) neural network (27 citations). In autonomous driving, Tran developed a traffic light detection system using an improved YOLOv5 deep learning model, deployed within the ROS2 framework (15 citations). His recent work includes enhancing indoor robot pedestrian detection via a novel PIXOR backbone with Gaussian heatmap regression in 3D LiDAR point clouds (12 citations), and semantic scene segmentation for indoor vision using an efficient U-NET architecture (4 citations). Tran’s research demonstrates a strong commitment to bridging theoretical optimization with practical, real-time robotic applications, making him a notable contributor to the fields of intelligent robotics and autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5