Yoshihiro Ohama
Papers
1
Total Citations
3
H-Index
1
About
Yoshihiro Ohama is a researcher whose work lies at the intersection of robotics, neural networks, and control systems. His most notable contribution is the development of a forward-propagation learning rule (FPL) for neural networks, a novel approach designed to enable robots to learn inverse dynamics models. This method allows a robot to refine its movements by propagating trajectory errors forward through the network, offering a distinct alternative to traditional backpropagation. While his most-cited paper has accumulated 3 citations, the conceptual innovation of FPL—requiring careful tuning of just two learning parameters—represents a focused effort to simplify and improve real-time robot learning. Ohama’s research is particularly relevant for students and engineers interested in bridging neural computation with physical robotic control, especially in tasks where accurate modeling of a robot’s own dynamics is critical. His work contributes to the broader goal of making robots more adaptive and autonomous through efficient, on-board learning algorithms.
Research Focus
Key Achievements
Top Papers
- 1