Meghann Lomas

Papers

Total Citations

H-Index

About

Meghann Lomas is a robotics researcher whose work sits at the critical intersection of human-robot interaction and explainable AI. Her primary research focus is on building transparent robotic systems that can communicate their internal reasoning to human users. Lomas’s most influential contribution is her pioneering work on robot explainability, most notably in her 2012 paper "Explaining robot actions" (74 citations). In this work, she developed a system that allows robots to answer natural language questions about their own behavior—for instance, explaining a turn by stating, "I detected a person at the end of the hallway." This research directly addresses the fundamental challenge of building human trust in autonomous systems. Her earlier work on a "Robotic World Model Framework" (2011) laid the groundwork for this by designing a knowledge representation system that supports situated human-robot communication, enabling robots to store and use semantic information shared by humans in the same physical environment. Lomas also contributed foundational work in reinforcement learning for mobile robot controllers (2006), exploring how robots can autonomously learn to select and tune their own behaviors. Her research remains highly relevant as the field of explainable robotics continues to grow.