{"ID":2860293,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04171","arxiv_id":"2510.04171","title":"VBM-NET: Visual Base Pose Learning for Mobile Manipulation using Equivariant TransporterNet and GNNs","abstract":"In Mobile Manipulation, selecting an optimal mobile base pose is essential for successful object grasping. Previous works have addressed this problem either through classical planning methods or by learning state-based policies. They assume access to reliable state information, such as the precise object poses and environment models. In this work, we study base pose planning directly from top-down orthographic projections of the scene, which provide a global overview of the scene while preserving spatial structure. We propose VBM-NET, a learning-based method for base pose selection using such top-down orthographic projections. We use equivariant TransporterNet to exploit spatial symmetries and efficiently learn candidate base poses for grasping. Further, we use graph neural networks to represent a varying number of candidate base poses and use Reinforcement Learning to determine the optimal base pose among them. We show that VBM-NET can produce comparable solutions to the classical methods in significantly less computation time. Furthermore, we validate sim-to-real transfer by successfully deploying a policy trained in simulation to real-world mobile manipulation.","short_abstract":"In Mobile Manipulation, selecting an optimal mobile base pose is essential for successful object grasping. Previous works have addressed this problem either through classical planning methods or by learning state-based policies. They assume access to reliable state information, such as the precise object poses and envi...","url_abs":"https://arxiv.org/abs/2510.04171","url_pdf":"https://arxiv.org/pdf/2510.04171v1","authors":"[\"Lakshadeep Naik\",\"Adam Fischer\",\"Daniel Duberg\",\"Danica Kragic\"]","published":"2025-10-05T12:17:56Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Graph Neural Network\",\"Reinforcement Learning\"]","has_code":false}