Gauraang Dhamankar

Papers

Total Citations

H-Index

About

Gauraang Dhamankar is a researcher at the forefront of adaptive robotics and autonomous navigation. His primary contributions lie in developing intelligent frameworks that enable mobile robots to dynamically tune their own navigation parameters, eliminating the need for laborious, expert-driven re-tuning in unfamiliar environments. Dhamankar’s seminal work, “APPL: Adaptive Planner Parameter Learning,” and its reinforcement learning-based successor, “APPLR,” have garnered over 80 combined citations, reflecting their significant impact on the field. These papers pioneered a paradigm shift from static, hand-picked navigation settings—such as maximum speed and inflation radius—to systems that learn optimal parameters in real time. By integrating reinforcement learning with classical navigation stacks, Dhamankar demonstrated how robots can autonomously adapt to diverse terrains and tasks, dramatically improving robustness and deployment efficiency. His research bridges the gap between traditional planning algorithms and modern learning-based approaches, offering a practical pathway toward truly autonomous systems. Dhamankar’s work is particularly notable for its direct applicability to real-world robotics, making him a key figure in advancing adaptive, self-tuning navigation for field robots.