Saved in:
Bibliographic Details
Main Authors: Zhu, Brian, Schmitt, Philipp, Meister, Philine, Gensler, Lukas, Khalil, Momen, Poggi, Emmanuele, Hechtl, Johannes, Braunroth, Carsten, Wurm, Kai, Narayanan, Gokul, Solowjow, Eugen, von Wichert, Georg, Scholz, Andre, Albrecht, Felix, Metzner, Maxmillian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.27461
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918525940006912
author Zhu, Brian
Schmitt, Philipp
Meister, Philine
Gensler, Lukas
Khalil, Momen
Poggi, Emmanuele
Hechtl, Johannes
Braunroth, Carsten
Wurm, Kai
Narayanan, Gokul
Solowjow, Eugen
von Wichert, Georg
Scholz, Andre
Albrecht, Felix
Metzner, Maxmillian
author_facet Zhu, Brian
Schmitt, Philipp
Meister, Philine
Gensler, Lukas
Khalil, Momen
Poggi, Emmanuele
Hechtl, Johannes
Braunroth, Carsten
Wurm, Kai
Narayanan, Gokul
Solowjow, Eugen
von Wichert, Georg
Scholz, Andre
Albrecht, Felix
Metzner, Maxmillian
contents Vision-Language-Action (VLA) policies have shown promising manipulation capabilities, yet their practical impact is often limited by the reliability demands of real-world deployment. We present a deployment study of an industrial packaging task at Siemens Factory (GWE, Erlangen, Germany), where a robot must pick a transparent accessory bag from a cluttered pile, insert it into the remaining cavity of a cardboard package, and ensure that the bag and its contents remain below the closing plane. Our goal is to understand the practical effort required to adapt a pretrained Pi0.5 policy to a single factory-floor task through iterative fine-tuning and deployment-driven refinement. The pipeline consists of repeated loops of data collection, curation, fine-tuning, evaluation, and targeted recovery data collection. We have accumulated 2535 episodes (10 hours) from the on-site factory settings. In this paper, we contribute an empirical account of a factory-floor VLA deployment, highlighting recurring failure modes and lessons that inform how to improve the deployment workflow.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27461
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Factory-Floor Deployment Case Study of VLA Pipelines for Industrial Packaging Task: Workflow, Failures, and Lessons
Zhu, Brian
Schmitt, Philipp
Meister, Philine
Gensler, Lukas
Khalil, Momen
Poggi, Emmanuele
Hechtl, Johannes
Braunroth, Carsten
Wurm, Kai
Narayanan, Gokul
Solowjow, Eugen
von Wichert, Georg
Scholz, Andre
Albrecht, Felix
Metzner, Maxmillian
Robotics
Vision-Language-Action (VLA) policies have shown promising manipulation capabilities, yet their practical impact is often limited by the reliability demands of real-world deployment. We present a deployment study of an industrial packaging task at Siemens Factory (GWE, Erlangen, Germany), where a robot must pick a transparent accessory bag from a cluttered pile, insert it into the remaining cavity of a cardboard package, and ensure that the bag and its contents remain below the closing plane. Our goal is to understand the practical effort required to adapt a pretrained Pi0.5 policy to a single factory-floor task through iterative fine-tuning and deployment-driven refinement. The pipeline consists of repeated loops of data collection, curation, fine-tuning, evaluation, and targeted recovery data collection. We have accumulated 2535 episodes (10 hours) from the on-site factory settings. In this paper, we contribute an empirical account of a factory-floor VLA deployment, highlighting recurring failure modes and lessons that inform how to improve the deployment workflow.
title A Factory-Floor Deployment Case Study of VLA Pipelines for Industrial Packaging Task: Workflow, Failures, and Lessons
topic Robotics
url https://arxiv.org/abs/2605.27461