Hanting Yang

Beijing University of Civil Engineering and Architecture

Papers

Total Citations

H-Index

About

Hanting Yang is a researcher specializing in humanoid robotics, computer vision, and deep learning, with a particular focus on enabling robots to interact intelligently with their environments. Their most cited work, "Multi‑target detection and grasping control for humanoid robot NAO" (2019, 21 citations), addresses a fundamental challenge in robotics: accurately recognizing and grasping multiple objects in complex, unstructured environments. By integrating deep learning-based object detection with robotic control, Yang proposed a method that significantly enhances a humanoid robot's ability to perform autonomous manipulation tasks—a critical capability for applications in service robotics and assistive technology. In a more recent contribution, "Lightweight CNN-based Expression Recognition on Humanoid Robot" (2020), Yang tackled the trade-off between computational efficiency and accuracy in deploying neural networks on resource-constrained robotic platforms. This work explores how compact convolutional neural networks can enable real-time facial expression recognition, opening doors for robots to detect human emotional states such as pain or fatigue. Yang’s research sits at the intersection of perception and action, demonstrating how efficient deep learning models can empower humanoid robots to better understand and assist humans in real-world settings.