Rwik Rana

University of Washington, Indian Institute of Technology Gandhinagar

Papers

Total Citations

H-Index

About

Rwik Rana is a robotics researcher whose work spans model predictive control, multirobot path planning, and tactile sensing. His most cited paper, "Deep Model Predictive Optimization" (2024, 7 citations), addresses a fundamental challenge in robotics: designing robust policies for complex, agile real-world behaviors. Rana bridges the gap between flexible but brittle model-free reinforcement learning and more structured model-based approaches, offering a hybrid framework that improves policy robustness without sacrificing adaptability. In "FF-RRT*" (2024, 2 citations), he extends the RRT* sampling-based planner to enable collision-free global formation path planning for multirobot systems, providing an efficient representation of formation geometry. Most recently, in "SuperTac" (2025, 1 citation), Rana tackles the spatial-temporal resolution trade-off in artificial tactile sensors by introducing a dimensionality-reduction-based super-resolution framework, enhancing tactile perception for robotics and prosthetics. Across these contributions, Rana demonstrates a commitment to advancing both the theoretical foundations and practical deployment of robotic systems, from planning and control to sensing.