Sumedh Sathe
Papers
1
Total Citations
6
H-Index
1
About
Sumedh Sathe is a researcher at the forefront of autonomous vehicle control, specializing in the intersection of deep reinforcement learning and off-road robotics. His work addresses the critical challenge of adapting path-tracking algorithms—traditionally designed for structured on-road environments—to the unpredictable terrain of skid-steered vehicles. In his most-cited paper, "Deep Reinforcement Learning Based Adaptation of Pure-Pursuit Path-Tracking Control for Skid-Steered Vehicles" (2022, 6 citations), Sathe pioneers a novel framework that uses reinforcement learning to dynamically tune the parameters of a pure-pursuit controller, enabling robust navigation over rough, uneven surfaces. This contribution is vital for advancing autonomy in agriculture, mining, and military applications, where conventional geometric controllers often fail. By bridging classical control theory with modern machine learning, Sathe demonstrates how adaptive systems can overcome the kinematic complexities of skid-steered platforms. His work has already garnered attention for its practical implications, offering a scalable solution to one of off-road autonomy’s most persistent hurdles. For students and researchers exploring adaptive control or field robotics, Sathe’s research provides a compelling blueprint for merging data-driven adaptation with real-world vehicle dynamics.
Research Focus
Key Achievements
Top Papers
- 1