Rate My Professor Shankar Deka

Deka's research synergistically combines nonlinear stability theory, optimal control, and machine learning to create certifiably safe and robust robotic and learning-enabled systems. Key application areas include telerobotic surgery, precision agriculture, and human-multirobot systems. The Nonlinear Systems and Control group under his leadership focuses on the intersection of control theory and machine learning, developing systems with provable guarantees on safety and performance for medical and rehabilitation robotics, precision agriculture, and multi-agent systems with human-in-the-loop. He is the principal investigator of the project 'INFORM: Intelligent Forest Fire Management via Multi-Resolution Risk Maps,' funded until 2029. Deka's publications include 'Supervised Learning of Lyapunov Functions Using Laplace Averages of Approximate Koopman Eigenfunctions' (IEEE Control Systems Letters, 2023), 'Path-Integral Formula for Computing Koopman Eigenfunctions' (62nd IEEE Conference on Decision and Control, 2023), 'Koopman-based Neural Lyapunov functions for general attractors' (61st IEEE Conference on Decision and Control, 2022), 'Towards Cyber–Physical Systems Robust to Communication Delays: A Differential Game Approach' (IEEE Control Systems Letters, 2022), and 'Convexifying State-Constrained Optimal Control Problem' (IEEE Transactions on Automatic Control, 2023). He serves as an editor for Unmanned Systems (World Scientific) and guest editor for Mathematics.