IEEE

SCIL: Stage-Conditioned Imitation Learning for Multi-Stage Manipulation

Abstract: Recent advancements in end-to-end imitation learning have shown promise in handling multi-stage robotic manipulation, which involves executing structured sequences of actions to achieve ...
pv magazine International

US researchers use machine learning to detect hidden solar array defects

Researchers from Stony Brook University, in collaboration with Ecosuite and Ecogy Energy, have developed a self-supervised machine-learning algorithm designed to identify physical anomalies in solar ...
IEEE

A Reinforcement Learning Approach to Non-Prehensile Manipulation Through Sliding

Abstract: Although robotic applications increasingly demand versatile and dynamic object handling, most existing techniques are predominantly focused on grasp-based manipulation, limiting their ...
pv-magazine-usa

Machine learning models identify hidden physical defects in solar arrays

Researchers from Stony Brook University, in collaboration with Ecosuite and Ecogy Energy, have developed a self-supervised machine learning algorithm designed to identify physical anomalies in solar ...