Kai-Wei Chang

Papers

Total Citations

H-Index

About

Kai-Wei Chang is a researcher working at the intersection of artificial intelligence, robotics, and autonomous systems, with a particular focus on path planning and human-interpretable AI reasoning. His most recognized contribution, "LLM-A*," introduces a novel framework that enhances the classical A* search algorithm by integrating large language models, enabling more intelligent and context-aware route derivation for robotic and autonomous navigation applications. This work has garnered significant early attention, accumulating over 23 citations shortly after its 2024 publication, signaling strong community interest in hybrid AI-classical approaches to fundamental robotics challenges. Beyond navigation efficiency, Chang has demonstrated a commitment to making AI systems understandable to human operators. His 2018 work on generating structured language explanations for robotic planning counterexamples addresses a critical gap in human-robot collaboration — translating complex model-checking artifacts from Markov decision processes into accessible, interpretable feedback for engineers and designers diagnosing mission plan failures. Collectively, Chang's research bridges classical algorithmic rigor with modern AI capabilities, pushing toward autonomous systems that are not only more capable but also more transparent and trustworthy — qualities increasingly essential as robotics and AI move into real-world deployment.