S. M. Ahsan Kazmi
Papers
1
Total Citations
3
H-Index
1
About
S. M. Ahsan Kazmi is a researcher at the forefront of reinforcement learning (RL) and control theory for complex robotic systems. His work primarily addresses the challenge of controlling underactuated robots—systems with fewer actuators than degrees of freedom—under real-world conditions of parameter uncertainty. In his most-cited paper, "Reward Planning for Underactuated Robotic Systems: A Study on Pendubot with Parameters Uncertainty" (2023), Kazmi pioneers a novel RL-based reward-shaping framework that outperforms traditional control methods like semi-definite programming (SDP) and mixed integer programming (MIP), which often assume perfect system knowledge. By demonstrating robust stabilization of a Pendubot despite unknown dynamics, his approach bridges the gap between theoretical control and practical deployment. Though early in his career, his work has already garnered attention (3 citations), signaling growing impact in the robotics and machine learning communities. Kazmi’s contributions are particularly notable for their potential to enable adaptive, model-free control in real-world applications, from industrial manipulators to autonomous systems. His research offers a compelling pathway for students and engineers seeking to integrate RL with traditional control for resilient robotic design.
Research Focus
Key Achievements
Top Papers
- 1