Sachin Grover

Papers

Total Citations

H-Index

About

Sachin Grover is a researcher advancing the frontiers of human-robot interaction and explainable AI, with a focus on bridging the gap between autonomous systems and human understanding. His work centers on model reconciliation—a framework that explains an AI agent’s decisions by addressing mismatches between the system’s internal model and a human’s mental model. In his most-cited paper, “Plan Explanations as Model Reconciliation—An Empirical Study” (2019, 8 citations), Grover empirically demonstrates how explanations can be framed as a process of aligning these divergent models, laying groundwork for more intuitive robot behavior. He further explores this in “Model Elicitation through Direct Questioning” (2020, 3 citations), where he investigates how robots can actively query human teammates to infer their mental models, enabling more effective collaboration in complex environments. Though early in his career, Grover’s contributions are pivotal for designing transparent, trustworthy AI systems that can explain their actions and learn from human feedback—a critical step toward seamless human-robot teamwork. His research is particularly relevant for students and engineers working on explainable planning, interactive AI, and human-aware decision-making.