PVRA: A Pointwise Key-point Voting Framework for Robotic Assembly

Abstract:Modern computer vision has enabled partial autonomy in robotic assembly manipulation. However, performing autonomous manipulation of a progressive assembly demands a more specific set of skills, in addition to perceiving the objects. Through a comparative analysis of research in the associated domains, we deduce that object-centric perception must advance towards learning assembly dependencies to predict meaningful actionable outputs for autonomous assembly manipulation. Subsequently, we present a 3D keypoint-based modular learning framework to learn assembly dependencies to infer actionable outputs given a RGB-D input of an assembly scene. We train and evaluate our trained network on an assembly pose estimation dataset and compare it against object-centric baselines with an augmented set of metrics for progressive assemblies.

14 pages, 3 figures. Accepted for presentation at the European Conference on Robotics (ECoR) 2026

Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)

arXiv:2608.19968 [cs.RO]

(or arXiv:2608.19968v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2608.19968 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.