Siao-Cing Huang
Papers
2
Total Citations
57
H-Index
2
About
Siao-Cing Huang is a pioneering robotics researcher specializing in reinforcement learning (RL) and heterogeneous multi-robot systems for autonomous navigation. Their work addresses critical challenges in deploying robots in complex, unstructured environments, from subterranean search-and-rescue to dynamic indoor spaces. Huang’s most influential contribution, "Curriculum Reinforcement Learning From Avoiding Collisions to Navigating Among Movable Obstacles in Diverse Environments" (2023, 37 citations), introduces a novel curriculum learning framework that dramatically accelerates RL training convergence. By structuring training tasks from simple collision avoidance to complex navigation among movable obstacles, this work enables agents to achieve superior performance in varied, real-world settings. Complementing this, their 2022 study on a heterogeneous team of unmanned ground vehicles and blimp robots (20 citations) demonstrates a breakthrough in data-driven autonomy and communication-aware navigation for search-and-rescue missions in unknown subterranean environments. This system integrates advanced sensor suites on ground vehicles with the unique aerial mobility of blimps, showcasing robust coordination under extreme constraints. Huang’s research not only advances theoretical foundations in curriculum learning but also delivers practical, deployable solutions for life-saving autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2