Michael Kogan
Papers
2
Total Citations
31
H-Index
2
About
Michael Kogan’s research lies at the intersection of robotics, autonomous vehicle control, and machine learning, with a focus on adaptive and learning-based systems. His most impactful work, “Adaptive predictive control of a differential drive robot tuned with reinforcement learning” (28 citations), addresses a fundamental challenge in model predictive control: the laborious manual tuning of objective function weights. By introducing a reinforcement learning framework to automate this process, Kogan enabled robots to dynamically adapt their control parameters for optimal performance, significantly advancing the practicality of autonomous navigation. He further contributed to the field with “Architecture for testing learning-based autonomous vehicle control design” (3 citations), proposing a systematic testing infrastructure that integrates localization and ground station processing to validate machine learning-driven controllers. This work underscores his commitment to bridging theoretical control methods with real-world deployment. Kogan’s achievements demonstrate a clear trajectory from foundational control theory to applied autonomous systems, offering researchers and students a compelling model for integrating reinforcement learning into robotic control. His work continues to inspire innovations in adaptive, self-tuning autonomous platforms.
Research Focus
Key Achievements
Top Papers
- 1
- 2