GIST: Multimodal Knowledge Extraction and Spatial Grounding via Intelligent Semantic Topology

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Agrawal, Shivendra, Hayes, Bradley
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917415710883840
author Agrawal, Shivendra
Hayes, Bradley
author_facet Agrawal, Shivendra
Hayes, Bradley
contents Navigating complex, densely packed environments like retail stores, warehouses, and hospitals poses a significant spatial grounding challenge for humans and embodied AI. In these spaces, dense visual features quickly become stale given the quasi-static nature of items, and long-tail semantic distributions challenge traditional computer vision. While Vision-Language Models (VLMs) help assistive systems navigate semantically-rich spaces, they still struggle with spatial grounding in cluttered environments. We present GIST (Grounded Intelligent Semantic Topology), a multimodal knowledge extraction pipeline that transforms a consumer-grade mobile point cloud into a semantically annotated navigation topology. Our architecture distills the scene into a 2D occupancy map, extracts its topological layout, and overlays a lightweight semantic layer via intelligent keyframe and semantic selection. We demonstrate the versatility of this structured spatial knowledge through critical downstream Human-AI interaction tasks: (1) an intent-driven Semantic Search engine that actively infers categorical alternatives and zones when exact matches fail; (2) a one-shot Semantic Localizer achieving a 1.04 m top-5 mean translation error; (3) a Zone Classification module that segments the walkable floor plan into high-level semantic regions; and (4) a Visually-Grounded Instruction Generator that synthesizes optimal paths into egocentric, landmark-rich natural language routing. In multi-criteria LLM evaluations, GIST outperforms sequence-based instruction generation baselines. Finally, an in-situ formative evaluation (N=5) yields an 80% navigation success rate relying solely on verbal cues, validating the system's capacity for universal design.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15495
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GIST: Multimodal Knowledge Extraction and Spatial Grounding via Intelligent Semantic Topology
Agrawal, Shivendra
Hayes, Bradley
Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
Robotics
I.2.9; I.2.7; H.5.2; C.2.4; H.5.2
Navigating complex, densely packed environments like retail stores, warehouses, and hospitals poses a significant spatial grounding challenge for humans and embodied AI. In these spaces, dense visual features quickly become stale given the quasi-static nature of items, and long-tail semantic distributions challenge traditional computer vision. While Vision-Language Models (VLMs) help assistive systems navigate semantically-rich spaces, they still struggle with spatial grounding in cluttered environments. We present GIST (Grounded Intelligent Semantic Topology), a multimodal knowledge extraction pipeline that transforms a consumer-grade mobile point cloud into a semantically annotated navigation topology. Our architecture distills the scene into a 2D occupancy map, extracts its topological layout, and overlays a lightweight semantic layer via intelligent keyframe and semantic selection. We demonstrate the versatility of this structured spatial knowledge through critical downstream Human-AI interaction tasks: (1) an intent-driven Semantic Search engine that actively infers categorical alternatives and zones when exact matches fail; (2) a one-shot Semantic Localizer achieving a 1.04 m top-5 mean translation error; (3) a Zone Classification module that segments the walkable floor plan into high-level semantic regions; and (4) a Visually-Grounded Instruction Generator that synthesizes optimal paths into egocentric, landmark-rich natural language routing. In multi-criteria LLM evaluations, GIST outperforms sequence-based instruction generation baselines. Finally, an in-situ formative evaluation (N=5) yields an 80% navigation success rate relying solely on verbal cues, validating the system's capacity for universal design.
title GIST: Multimodal Knowledge Extraction and Spatial Grounding via Intelligent Semantic Topology
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
Robotics
I.2.9; I.2.7; H.5.2; C.2.4; H.5.2
url https://arxiv.org/abs/2604.15495