Naman Shah

Papers

Total Citations

H-Index

About

Naman Shah is a rising researcher in artificial intelligence, focusing on the intersection of robot planning, hierarchical learning, and explainable AI. His work centers on making autonomous systems more reliable and intuitive, particularly through the development of skill-aligned abstractions and multi-task learning frameworks. In his highly cited 2022 paper, "Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning," Shah introduced a novel method that leverages deep learning to automatically generate planning abstractions, significantly boosting robot performance while maintaining strong reliability guarantees—a critical contribution to long-horizon motion planning. His 2021 work, "JEDAI: A System for Skill-Aligned Explainable Robot Planning," showcases his commitment to accessible AI, creating an educational platform that integrates task and motion planning with explainable AI to help non-experts understand and design high-level robot plans. Additionally, Shah’s research on multi-task option learning for stochastic path planning addresses the challenge of efficiently solving diverse, long-horizon problems in uncertain environments. With over a dozen citations across his top papers, Shah is establishing himself as a key contributor to scalable, trustworthy robot autonomy.