A Factory-Floor Deployment Case Study of VLA Pipelines for Industrial Packaging Task: Workflow, Failures, and Lessons

• URL: http://arxiv.org/abs/2605.27461v1
• Date: Mon, 25 May 2026 20:46:22 GMT
• Title: A Factory-Floor Deployment Case Study of VLA Pipelines for Industrial Packaging Task: Workflow, Failures, and Lessons
• Abstract summary: 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.<n>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.<n>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
• Score: 2.4341902779357536
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning [19.23819338884138]
  DREAMSTEER is a deployment-time steering framework for pretrained vision-language-action (VLA) policies.<n>Itleverages a latent world model and a value model to steer pretrained VLA policies.<n>It improves task success rate from 23.75% to 66.25% and instruction-following accuracy from 38.75% to 56.25% over the base VLA policy.
  arXiv  Detail & Related papers  (2026-07-03T02:08:50Z)
• EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models [84.73890225707264]
  We present EXPO-FT, a system for stable, sample-efficient RL finetuning of pretrained VLA policies.<n>Our system achieves perfect task performance (30/30 successes) across all evaluated tasks within an average of 19.1 minutes of online robot data.<n>We release an open-source robustness with the aim of facilitating broader adoption of RL finetuning of VLA models in robotics.
  arXiv  Detail & Related papers  (2026-05-25T06:31:03Z)
• Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning [42.74142065376427]
  We propose Z-Perturbation Reinforcement Learning (ZPRL) to steer pretrained policies through a compact bottleneck latent.<n>In the real world, ZPRL improves the average success rate on four tasks by 33.7% over imitation base policies.
  arXiv  Detail & Related papers  (2026-05-19T14:43:26Z)
• BatchWeave: A Consistent Object-Store-Native Data Plane for Large Foundation Model Training [13.09314762856332]
  BatchWeave is an object-store-native training data plane for distributed LFM training.<n>It implements versioned manifests and conditional object writes to coordinate batch publication, recovery, and lifecycle management.<n>It provides full failure isolation, outperforms Apache Kafka in ingestion throughput, and achieves lower consumer read latency than Kafka.
  arXiv  Detail & Related papers  (2026-05-11T05:10:16Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings [53.09342573704396]
  We present a novel framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training.<n>Our method first trains a lightweight motion tokenizer to encode motion dynamics, then employs an unsupervised action segmenter to discover and segment semantically coherent action primitives.<n>This is the first fully automated end-to-end system for extracting and organizing VLA pre-training data from unstructured industrial videos, offering a scalable solution for embodied AI integration in manufacturing.
  arXiv  Detail & Related papers  (2025-11-26T14:19:44Z)
• Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion [8.05008302748311]
  We introduce VLA-Pilot, a plug-and-play inference-time policy steering method for zero-shot deployment of pre-trained VLA policies.<n> Experimental results demonstrate that VLA-Pilot substantially boosts the success rates of off-the-shelf pre-trained VLA policies.
  arXiv  Detail & Related papers  (2025-11-18T06:30:52Z)
• Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference [53.419249906014194]
  We study generative modeling for planning with datasets repurposed from offline reinforcement learning.<n>We introduce the Latent Plan Transformer (), a novel model that leverages a latent variable to connect a Transformer-based trajectory generator and the final return.
  arXiv  Detail & Related papers  (2024-02-07T08:18:09Z)
• A Modular Test Bed for Reinforcement Learning Incorporation into Industrial Applications [1.5136939451642133]
  We present a use case in which the task is to transport and assemble goods through a model factory following predefined rules. The objective is to transport the goods to the assembly station, where two rivets are installed in each product, connecting the upper part to the lower part. The study focuses on the application of reinforcement learning techniques to address this problem and improve the efficiency of the production process.
  arXiv  Detail & Related papers  (2023-06-02T11:00:46Z)
• Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning [60.501201259732625]
  We introduce task-adaptive saliency for EFCIL and propose a new framework, which we call Task-Adaptive Saliency Supervision (TASS) Our experiments demonstrate that our method can better preserve saliency maps across tasks and achieve state-of-the-art results on the CIFAR-100, Tiny-ImageNet, and ImageNet-Subset EFCIL benchmarks.
  arXiv  Detail & Related papers  (2022-12-16T02:43:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.