Development of model-structured neural networks for modelling, estimation, and control of autonomous robotic systems
Scientific-Disciplinary Group
09/IIND-02 - Applied Mechanics
Description
The development of advanced autonomous robotic intelligence requires methodologies and tools that enable the efficient deployment of learning-based solutions on embedded and resource-constrained hardware platforms. In this context, this project aims to develop an open-source, modular, and scalable framework for the design and implementation of model-structured neural networks for modeling, estimation, and control of physical systems. These networks explicitly incorporate prior knowledge of the underlying physical processes, reducing model complexity, computational cost, and data requirements while improving interpretability and suitability for real-time embedded applications.
Job posting website
Number of positions
1
Funding body
Università degli Studi di Trento
View the original posting on the MUR website: Go to MUR website