Kanan Roy Chowdhury

Papers

Total Citations

H-Index

About

Kanan Roy Chowdhury is a researcher at the intersection of control theory, reinforcement learning, and robotics, with a focus on solving complex, nonlinear dynamical systems. His most-cited work, "Q-Learning Based Control for Swing-Up and Balancing of Inverted Pendulum" (2024), tackles the classic and notoriously difficult inverted pendulum problem—a benchmark for instability and nonlinearity in control systems. By applying Q-learning, a model-free reinforcement learning algorithm, Chowdhury demonstrates how intelligent agents can learn stabilization policies without explicit system models, advancing the integration of machine learning into traditional control frameworks. This contribution has already garnered attention, with 3 citations in its first year, signaling growing interest in his approach. His research bridges the gap between classical control challenges and modern AI-driven solutions, offering practical pathways for robotics, autonomous systems, and adaptive control. Chowdhury’s work is particularly notable for its potential to simplify the design of controllers for unstable systems, making him a promising voice in the evolving field of learning-based control.