{"ID":2848283,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.27033","arxiv_id":"2510.27033","title":"A Multi-Modal Neuro-Symbolic Approach for Spatial Reasoning-Based Visual Grounding in Robotics","abstract":"Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language models (VLMs) excel at perception tasks but struggle with fine-grained spatial reasoning due to their implicit, correlation-driven reasoning and reliance solely on images. We propose a novel neuro_symbolic framework that integrates both panoramic-image and 3D point cloud information, combining neural perception with symbolic reasoning to explicitly model spatial and logical relationships. Our framework consists of a perception module for detecting entities and extracting attributes, and a reasoning module that constructs a structured scene graph to support precise, interpretable queries. Evaluated on the JRDB-Reasoning dataset, our approach demonstrates superior performance and reliability in crowded, human_built environments while maintaining a lightweight design suitable for robotics and embodied AI applications.","short_abstract":"Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language models (VLMs) excel at perception tasks but struggle with fine-grained spatial re...","url_abs":"https://arxiv.org/abs/2510.27033","url_pdf":"https://arxiv.org/pdf/2510.27033v1","authors":"[\"Simindokht Jahangard\",\"Mehrzad Mohammadi\",\"Abhinav Dhall\",\"Hamid Rezatofighi\"]","published":"2025-10-30T22:40:23Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}