InsightMap: Structured Spatial Modeling for Embodied Multimodal Reasoning

InsightMap is a framework that uses top‑down maps as explicit spatial memory and action‑conditioned prediction targets for language‑guided navigation. It links historical views to labeled map locations and employs a shared multimodal backbone to jointly learn navigation action prediction and post‑action map generation, providing auxiliary training supervision. The approach supports a unified RGB‑D pipeline for navigation, visual question answering, situated reasoning, and 3D grounding, achieving state‑of‑the‑art results on R2R‑CE, RxR‑CE, ScanQA, SQA3D, ScanRefer, and outperforming baselines on the Unitree Go2 platform.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• nlp
• robotics
• multimodal
• data-engineering