Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation

Generalising vision-based manipulation policies to novel environments remains a challenging area with limited exploration. Current practices involve collecting data in one location, training imitation learning or reinforcement learning policies with this data, and deploying the policy in the same lo...

Full description

Saved in:
Bibliographic Details
Main Authors Teoh, Eugene, Patidar, Sumit, Ma, Xiao, James, Stephen
Format Journal Article
LanguageEnglish
Published 10.07.2024
Subjects
Online AccessGet full text

Cover

Loading…