activity
20242026
collaborators

5 papers

cs.LG2026

Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning

Reza Pirayeshshirazinezhad

We propose a self-supervised physics-informed neural network (PINN) framework that adaptively balances physics-based and data-driven supervision for scientific machine learning und…

cs.RO2025

Explainable AI-Enhanced Supervisory Control for Robust Multi-Agent Robotic Systems

Reza Pirayeshshirazinezhad, Nima Fathi

We present an explainable AI-enhanced supervisory control framework for multi-agent robotics that combines (i) a timed-automata supervisor for safe, auditable mode switching, (ii)…

astro-ph.IM2025

Explainable AI-Enhanced Supervisory Control for High-Precision Spacecraft Formation

Reza Pirayeshshirazinezhad

We use artificial intelligence (AI) and supervisory adaptive control systems to plan and optimize the mission of precise spacecraft formation. Machine learning and robust control e…

cs.LG2025

SPINN: An Optimal Self-Supervised Physics-Informed Neural Network Framework

Reza Pirayeshshirazinezhad

A surrogate model is developed to predict the convective heat transfer coefficient of liquid sodium (Na) flow within rectangular miniature heat sinks. Initially, kernel-based machi…

eess.SY2024

Bicycle Stabilization using mechanism optimization and Digital LQR

Reza Pirayeshshirazinezhad

This study introduces lateral pendulum as an innovative balancer design for bicycle stabilization. This pendulum, operating in the bicycle's vertical plane, enables the bicycle to…