Deepak Kumar Verma

Papers

Total Citations

H-Index

About

Deepak Kumar Verma has made significant contributions to the fields of robotics, artificial intelligence, and decision-making under uncertainty. His research focuses on developing probabilistic frameworks for planning and acting in noisy, uncertain environments—a core challenge in autonomous systems. Verma’s most influential work, "Planning and Acting in Uncertain Environments using Probabilistic Inference" (2006, 26 citations), addresses the problem of goal-directed behavior in partially observable Markov decision processes (POMDPs). This paper provides efficient algorithms for learning policies, bridging the gap between probabilistic inference and decision-making, and has been foundational for subsequent work in robotics and AI. His additional research on imitation learning using graphical models (2007, 8 citations) explores how agents can learn complex behaviors from demonstrations, leveraging structured probabilistic representations to improve learning efficiency. Verma’s contributions have advanced the practical deployment of autonomous systems in real-world scenarios, from robotic navigation to interactive agents. His work remains a key reference for researchers tackling uncertainty in planning and learning, demonstrating lasting impact in the AI and robotics communities.