Daniel Maccaline

Papers

Total Citations

H-Index

About

Daniel Maccaline is a rising researcher at the forefront of human-robot interaction, specializing in making autonomous systems more transparent and trustworthy. His core research focuses on robot failure explanation, explainable AI (XAI), and the integration of Large Language Models (LLMs) with robotic architectures. Maccaline’s major contribution lies in developing generalizable frameworks that enable robots to communicate their failures to humans in real-world settings. His most-cited work, “A Generalizable Architecture for Explaining Robot Failures Using Behavior Trees and Large Language Models” (7 citations), introduces a novel system that combines structured behavior trees with the generative power of LLMs to produce context-aware explanations. In a follow-up study, “Templated vs. Generative: Explaining Robot Failures” (2 citations), he systematically compares pre-scripted explanation templates against LLM-generated narratives, revealing critical trade-offs between reliability and flexibility. Though early in his career, Maccaline’s work is already shaping how researchers approach robot transparency, directly addressing the growing need for robots deployed in public, home, and workplace environments to answer questions about their own failures. His research promises to bridge the gap between rigid robotic systems and the nuanced communication expected in human-shared spaces.