Generalized Environment-Enabled Object Grasping using a Fixture-Aware Double Deep Q-Network

Loading...

View/Download File

Sasagawa_umn_0130M_23419.pdf (6.18 MB)

Persistent link to this item

https://hdl.handle.net/11299/241537

Statistics

View Statistics

Journal Title

Journal ISSN

Volume Title

Title

Generalized Environment-Enabled Object Grasping using a Fixture-Aware Double Deep Q-Network

Authors

Sasagawa, Eddie

Published Date

2022-06

Publisher

Type

Thesis or Dissertation

Abstract

This thesis expands on the problem of grasping an object that can only be grasped bya single parallel gripper when a fixture (e.g., wall, heavy object) is harnessed. Preceding work that tackle this problem are limited in that the employed networks implicitly learn specific targets and fixtures to leverage. However, the notion of a usable fixture can vary in different environments, at times without any outwardly noticeable differences. In this work, we propose a method to relax this limitation and further handle environments where the fixture location is unknown. The problem is formulated as visual affordance learning in a partially observable setting. We present a self-supervised reinforcement learning algorithm, Fixture-Aware Double Deep Q-Network (FA-DDQN), that processes the scene observation to 1) identify the target object based on a reference image, 2) distinguish possible fixtures based on interaction with the environment, and finally 3) fuse the information to generate a visual affordance map to guide the robot to successful Slide-to-Wall grasps. We demonstrate our proposed solution in simulation and in real robot experiments to show that in addition to achieving higher success than baselines, it also performs zero-shot generalization to novel scenes with unseen object configurations.

Keywords

Deep Learning in Grasping and Manipulation

Grasping

Perception for Grasping and Manipulation

Description

University of Minnesota M.S. thesis. June 2022. Major: Computer Science. Advisor: Changhyun Choi. 1 computer file (PDF); vii, 38 pages.

Related to

Replaces

License

Collections

Master's Theses (Plan A and Professional Engineering Design Projects)

Series/Report Number

Funding information

Isbn identifier

Doi identifier

Previously Published Citation

Suggested citation

Sasagawa, Eddie. (2022). Generalized Environment-Enabled Object Grasping using a Fixture-Aware Double Deep Q-Network. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/241537.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.