Integration of Physics-Informed Neural Networks in Scientific Machine Learning for Robotic Applications

EasyChair Preprint no. 11766

Abstract

The integration of Physics-Informed Neural Networks (PINNs) in Scientific Machine Learning (SciML) marks a significant advancement in the field of robotic applications. This research explores the synergies between PINNs and SciML to enhance the understanding and control of complex robotic systems. By fusing physics-based models with neural network architectures, this approach enables a more accurate and efficient representation of robotic dynamics and interactions with the environment. The abstract further delves into the potential applications and benefits of this integration, showcasing its promise in pushing the boundaries of robotic science and technology.

Keyphrases: data, driven, Methodologies

@Booklet{EasyChair:11766,
  author = {Jane Smith and Julia Anderson},
  title = {Integration of Physics-Informed Neural Networks in Scientific Machine Learning for Robotic Applications},
  howpublished = {EasyChair Preprint no. 11766},

  year = {EasyChair, 2024}}