Mangesh D. Ratolikar
Papers
3
Total Citations
9
H-Index
2
About
Mangesh D. Ratolikar is a robotics researcher specializing in underactuated systems, nonlinear control, and reinforcement learning, with a focus on applications in legged locomotion. His work bridges classical control theory and modern machine learning to address fundamental challenges in robotic balance and gait. Ratolikar’s most cited paper (2021, 4 citations) introduces a reinforcement learning framework for swinging up and balancing a pendulum on a vertically moving cart—a benchmark problem for underactuated systems that mirrors the dynamics of bipedal and humanoid robots. He further advanced this line of inquiry by developing a neural network controller for an inverted pendulum on a two-degree-of-freedom cart moving in the vertical plane (2021, 2 citations), demonstrating how learned policies can stabilize inherently unstable systems. In a complementary study (2021, 3 citations), Ratolikar optimized the design of a 5R planar parallel mechanism for quadruped robot gait cycles, proposing an asymmetric link-length configuration that accommodates unequal force requirements during forward and return strokes—a practical innovation for efficient locomotion. Though his citation counts are modest, his work is notable for integrating control theory, mechanism design, and reinforcement learning, offering foundational insights for students and researchers exploring underactuated robotics and bio-inspired locomotion.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3