Weihong Song

Zhejiang Lab, Southwest Jiaotong University

Papers

Total Citations

H-Index

About

Weihong Song is a researcher at the forefront of robotics and artificial intelligence, with a primary focus on robotic task planning, multi-robot coordination, and the integration of large language models (LLMs) into autonomous systems. Their most notable contribution is the development of **MLDT (Multi-Level Decomposition for Complex Long-Horizon Robotic Task Planning)**, a pioneering framework that leverages open-source LLMs to break down intricate, long-duration tasks into manageable sub-goals—a critical advancement for real-world robotics. This work, published in 2024, has already garnered 15 citations, signaling its rapid impact on the field. Song’s research also extends to multi-robot systems, as demonstrated in their 2022 study on task allocation and rescue strategies for mowing robots, which addresses practical challenges like minimizing operational time and handling robot failures. By bridging the gap between high-level AI reasoning and low-level robotic execution, Song is helping to make autonomous robots more adaptable and efficient. Their work is particularly relevant for students and researchers interested in LLM-driven robotics, task decomposition, and swarm coordination, offering a glimpse into the future of intelligent, collaborative machines.