aiqbench analysis
This research introduces ChunkVLA-AM, a framework that applies parallel action chunking to Vision-Language-Action models for robot control in additive manufacturing. By executing eight-step action chunks open-loop before capturing new observations, the system achieves 92.9% success rates in physical object transfer tasks while identifying specific environmental constraints like optimal lighting ranges. The work addresses critical deployment challenges such as embodiment adaptation and performance degradation under changing conditions, offering a practical pathway for integrating advanced AI models into fixed industrial workcells.
ChunkVLA-AM: Parallel Action Chunking for Vision-Language-Action Robot Control in Additive Manufacturing
arXiv:2610.01856v1 Announce Type: new Abstract: Vision-language-action (VLA) models unify visual perception, language understanding, and action generation, offering new opportunities for automation in additive manufacturing (AM). However, deployment in AM remains challenging because adapting these models to unseen robot embodiments is costly, and performance can degrade under environment changes. In this work, we present a framework for deploying OpenVLA-OFT on a FAIRINO FR3 robot in a fixed AM workcell. A data pipeline converts monocular real-world demonstrations into OpenVLA-compatible TFDS/RLDS datasets to support adaptation to the FR3 embodiment. At runtime, each inference request predicts an eight-step chunk of 7-D actions. The FR3 executes each chunk open loop before capturing a new observation, providing closed-loop feedback between chunks. The system uses a cloud-edge architecture in which the FR3 client streams observations to a remote inference server through a FastAPI interface. In 42 physical A-to-B object-transfer trials, evenly split between red and blue targets, the system succeeded in 39 (92.9%). All three failures occurred during final placement, when insufficient release-height control caused the object to topple. An illumination sweep identified a low-error luminance range of 85-125 on a 0-255 scale, with the lowest mean spatial error at 95.
Abstract:Vision-language-action (VLA) models unify visual perception, language understanding, and action generation, offering new opportunities for automation in additive manufacturing (AM). However, deployment in AM remains challenging because adapting these models to unseen robot embodiments is costly, and performance can degrade under environment changes. In this work, we present a framework for deploying OpenVLA-OFT on a FAIRINO FR3 robot in a fixed AM workcell. A data pipeline converts monocular real-world demonstrations into OpenVLA-compatible TFDS/RLDS datasets to support adaptation to the FR3 embodiment. At runtime, each inference request predicts an eight-step chunk of 7-D actions. The FR3 executes each chunk open loop before capturing a new observation, providing closed-loop feedback between chunks. The system uses a cloud-edge architecture in which the FR3 client streams observations to a remote inference server through a FastAPI interface. In 42 physical A-to-B object-transfer trials, evenly split between red and blue targets, the system succeeded in 39 (92.9%). All three failures occurred during final placement, when insufficient release-height control caused the object to topple. An illumination sweep identified a low-error luminance range of 85-125 on a 0-255 scale, with the lowest mean spatial error at 95.
Robotics (cs.RO)
arXiv:2610.01856 [cs.RO]
(or arXiv:2610.01856v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.01856 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 282 words
Related coverage
LeRobot v0.6.0: Imagine, Evaluate, Improve
Hugging Face · Jul 7, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026
2026 BAIR Graduate Showcase
BAIR Blog · Jul 1, 2026
Colosseum V2: Benchmarking Generalization for Vision-Language-Action Models
arXiv · Sep 15, 2026