Shenghui Chen

Papers

Total Citations

H-Index

About

Shenghui Chen is a researcher at the forefront of explainable robotics and human-robot interaction, with a focus on making autonomous decision-making transparent and trustworthy. His most cited work, "Towards Transparent Robotic Planning via Contrastive Explanations" (2020, 10 citations), introduces a novel framework that leverages insights from social science to improve robotic planning transparency. Chen’s key contribution lies in operationalizing contrastive explanations—explaining not only why a robot chose a particular action, but why it was chosen over plausible alternatives. This approach addresses a critical gap in human-robot collaboration, where users often distrust opaque AI decisions. By grounding his methodology in established theories of human explanation, Chen bridges cognitive science and robotics, offering a practical tool for building more intuitive and accountable autonomous systems. His work has been recognized for its interdisciplinary impact, influencing subsequent studies in explainable AI and human-robot teaming. For students and researchers, Chen’s research exemplifies how integrating social science principles can solve core challenges in robotics, paving the way for safer and more reliable autonomous agents in real-world applications.