Donghui Mao

Papers

Total Citations

H-Index

About

Donghui Mao is a rising researcher at the intersection of robotics, computer vision, and large language models (LLMs), with a focus on intelligent manipulation and automated assembly. His work tackles critical challenges in enabling robots to perceive and interact with complex, unstructured environments. Mao’s most cited paper, “VLMPC: Vision-Language Model Predictive Control for Robotic Manipulation” (2024, 13 citations), introduces a novel framework that integrates vision-language models with Model Predictive Control. This approach overcomes the traditional limitation of MPC—its lack of environmental perception—by allowing robots to interpret visual and linguistic cues for more robust and adaptive manipulation in complex scenarios. In parallel, his work on “3C Assembly Methods and Systems Based on Large Language Models” (2024, 2 citations) addresses pressing inefficiencies in the 3C (Computer, Communication, Consumer Electronics) assembly industry. By leveraging LLMs for intelligent assembly planning, Mao’s research aims to reduce reliance on manual labor, improve product quality, and streamline production changeovers. Though early in his career, Mao’s contributions are already demonstrating significant potential to advance both academic research and industrial automation, marking him as a promising innovator in embodied AI and smart manufacturing.