Manoopong Poramate
Papers
1
Total Citations
5
H-Index
1
About
Manoopong Poramate is a robotics researcher whose work lies at the intersection of bio-inspired control, reservoir computing, and legged locomotion. His key research areas include neural network-based state estimation and the application of Liquid State Machines (LSMs) to complex robot-environment interactions. Poramate’s major contribution is the development of a novel method for estimating ground reaction forces in quadruped robots using only local proprioceptive data, bypassing the need for expensive force sensors. This approach, detailed in his most-cited paper "Ground Reaction Force Estimation in a Quadruped Robot via Liquid State Networks" (2022, 5 citations), demonstrates the robustness and learning capability of LSMs in dynamic, real-world settings. By mapping tactile and joint information through a reservoir computing framework, his work paves the way for more adaptive and sensor-efficient robotic systems. Poramate’s research is particularly notable for bridging computational neuroscience principles with practical robotics, offering a lightweight solution for state estimation that could enhance the autonomy of legged machines in unstructured environments. His findings are a valuable resource for students and researchers interested in neuromorphic control and model-free robot learning.
Research Focus
Key Achievements
Top Papers
- 1