Authors: Cheng Chi

Published on: January 03, 2024

Impact Score: 8.15

Arxiv code: Arxiv:2401.01836

Summary

• What is new: A neural ODE-based method for controlling unknown dynamical systems that combines dynamics identification and optimal control learning.
• Why this is important: Inaccuracies in dynamics modeling of continuous-time dynamical systems can lead to sub-optimal control functions.
• What the research proposes: A coupled neural ODE structure that enables simultaneous learning of system dynamics and optimal control functions.
• Results: The model effectively learns optimal control of unknown dynamical systems.

Technical Details

Technological frameworks used: Neural ODE

Models used: Coupled neural networks

Data used: nan

Potential Impact

Automation, robotics, aerospace, and any sector relying on dynamical systems control.

Want to implement this idea in a business?

We have generated a startup concept here: OptiDynamics.