Learning a Generative Transition Model for Uncertainty-Aware Robotic Manipulation

Lars Berscheid, Pascal Meißner, Torsten Kröger

Research output: Contribution to conferencePaperpeer-review

1 Downloads (Pure)

Abstract

Robot learning of real-world manipulation tasks remains challenging and time consuming, even though actions are often simplified by single-step manipulation primitives. In order to compensate the removed time dependency, we additionally learn an image-to-image transition model that is able to predict a next state including its uncertainty. We apply this approach to bin picking, the task of emptying a bin using grasping as well as pre-grasping manipulation as fast as possible. The transition model is trained with up to 42000 pairs of real-world images before and after a manipulation action. Our approach enables two important skills: First, for applications with flange-mounted cameras, picks per hours (PPH) can be increased by around 15% by skipping image measurements. Second, we use the model to plan action sequences ahead of time and optimize time-dependent rewards, e.g. to minimize the number of actions required to empty the bin. We evaluate both improvements with real-robot experiments and achieve over 700 PPH in the YCB Box and Blocks Test.
Original languageEnglish
Publication statusAccepted/In press - 6 Jul 2021
Event2021 IEEE/RSJ International Conference on Intelligent Robots and Systems - Online, Prague
Duration: 27 Sep 20211 Oct 2021
https://www.iros2021.org

Conference

Conference2021 IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated titleIROS 2021
CityPrague
Period27/09/211/10/21
Internet address

Fingerprint

Dive into the research topics of 'Learning a Generative Transition Model for Uncertainty-Aware Robotic Manipulation'. Together they form a unique fingerprint.

Cite this