Aneseh Alvanpour

Papers

Total Citations

H-Index

About

Aneseh Alvanpour is a robotics researcher whose work sits at the critical intersection of machine learning, explainable AI, and human-robot collaboration. Her primary research focus is on predicting and explaining robotic grasp failures—a fundamental challenge in autonomous manipulation. Alvanpour’s major contribution lies in developing predictive models that can determine whether a robot’s grasp is likely to fail *before* it happens, enabling proactive re-grasping or strategy adjustment. Her most-cited paper, “Robot Failure Mode Prediction with Explainable Machine Learning” (2020, 26 citations), pioneered this approach by combining ML-based failure prediction with interpretable outputs. She has since advanced the field with deep learning sequence models (2024) and a comparative analysis of post-hoc explainability methods (2025, 3 citations), directly addressing the “black box” problem that limits trust in robotic systems. By making failure predictions transparent and actionable, Alvanpour’s work is essential for safe, effective human-robot collaboration in manufacturing, healthcare, and service robotics. Her research continues to shape how robots communicate their limitations, paving the way for more reliable and trustworthy autonomous systems.