ParaPose: Parameter and Domain Randomization Optimization for Pose Estimation using Synthetic Data

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

27 Downloads (Pure)

Abstract

Pose estimation is the task of determining the 6D position of an object in a scene. Pose estimation aid the abilities and flexibility of robotic set-ups. However, the system must be configured towards the use case to perform adequately. This configuration is time-consuming and limits the usability of pose estimation and, thereby, robotic systems.


Deep learning is a method to overcome this configuration procedure by learning parameters directly from the dataset. However, obtaining this training data can also be very time-consuming. The use of synthetic training data avoids this data collection problem, but a configuration of the training procedure is necessary to overcome the domain gap problem. Additionally, the pose estimation parameters also need to be configured. This configuration is jokingly known as grad student descent as parameters are manually adjusted until satisfactory results are obtained.

This paper presents a method for automatic configuration using only synthetic data. This is accomplished by learning the domain randomization during network training, and then using the domain randomization to optimize the pose estimation parameters. The developed approach shows state-of-the-art performance of 82.0% recall on the challenging OCCLUSION dataset, outperforming all previous methods with a large margin. These results prove the validity of automatic set-up of pose estimation using purely synthetic data.
Original languageEnglish
Title of host publication2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Place of PublicationIEEE
PublisherIEEE
Publication date2022
Pages6788-6795
ISBN (Print)978-1-6654-7928-8
ISBN (Electronic)978-1-6654-7927-1
DOIs
Publication statusPublished - 2022
Event2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Late Breaking Results Poster - Kyoto, Japan
Duration: 23. Oct 202227. Oct 2022

Conference

Conference2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Country/TerritoryJapan
CityKyoto
Period23/10/202227/10/2022
SeriesI E E E International Conference on Intelligent Robots and Systems. Proceedings
ISSN2153-0858

Fingerprint

Dive into the research topics of 'ParaPose: Parameter and Domain Randomization Optimization for Pose Estimation using Synthetic Data'. Together they form a unique fingerprint.

Cite this