Learning to Push by Grasping: Using multiple tasks for effective learning

May 2017

Learning to Push by Grasping: Using multiple tasks for effective learning

Conference Paper
Proceedings of (ICRA) International Conference on Robotics and Automation

Abstract:

Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due to their huge data requirements for learning a task. The argument of the difficulty in scalability to multiple tasks is well founded, since training these tasks often require hundreds or thousands of examples. But do end-to-end approaches need to learn a unique model for every task? Intuitively, it seems that sharing across tasks should help since all tasks require some common understanding of the environment. In this paper, we attempt to take the next step in data-driven end-to-end learning frameworks: move from the realm of task-specific models to joint learning of multiple robot tasks. In an astonishing result we show that models with multi-task learning tend to perform better than task-specific models trained with same amounts of data. For example, a deep-network learned with 2.5K grasp and 2.5K push examples performs better on grasping than a network trained on 5K grasp examples.
@conference{Pinto-2017-113322,
author = {Lerrel Pinto And Abhinav Gupta},
title = {Learning to Push by Grasping: Using multiple tasks for effective learning},
booktitle = {Proceedings of (ICRA) International Conference on Robotics and Automation},
year = {2017},
month = {May},
pages = {2161 - 2168},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.