Title:	Computer vision for robotic manipulation
DNr:	Berzelius-2022-226
Project Type:	LiU Berzelius
Principal Investigator:	Zehang Weng <zehang@kth.se>
Affiliation:	Kungliga Tekniska högskolan
Duration:	2022-11-07 – 2023-06-01
Classification:	10207
Keywords:

Abstract

Robotic manipulation is one of the main frontiers in the current robotics research. Modern machine-learning approaches can provide powerful tools for learning to represent and interpret objects' states, dynamics, and planning appropriate robotic motions. In this project, we investigate the state-of-the-art data-driven approach for improving robotic manipulation performance.