Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fine-grained visual evidence and accumulating noise, while 3D reconstruction-based methods remain computationally prohibitive.
arXiv:2606.16569v2 Announce Type: replace Abstract: Registering two captures of the same indoor space taken at different times underpins persistent spatial memory for robots and AR systems, yet the r...
SceneTeract is a verification interface that separates semantic action understanding from physical feasibility in indoor 3D scenes. It decomposes activities into atomic actions and performs explicit geometric checks to determine executability, providing diagnostic traces for failures. The system reveals widespread functional and accessibility issues in synthetic scenes, shows that existing VLMs over‑predict action feasibility, and improves VLM performance through post‑training with verifier feedback, with benefits that generalize to real‑world scenes.
Reading the Room (RR) is a global‑local method that registers scale‑ambiguous, sparse semantic VSLAM maps to partially built floor plans. It introduces a single robust, differentiable, class‑balanced semantic‑geometric energy function that drives all pipeline stages, and offers two global initialization schemes—one using a single user‑provided correspondence and another using a cross‑modal matching network. Evaluated on 33 sequences from three construction sites, RR outperforms classical and learning‑based baselines, improving mean absolute trajectory error by 4.5× overall and 7.6× when an anchor is supplied.
arXiv:2607. 14514v1 Announce Type: cross Abstract: Object-goal navigation requires an embodied agent to locate and reach an instance of a specified object category in an indoor environment.
arXiv:2609.38620v1 Announce Type: new Abstract: Neural implicit representations have had a significant impact on scene reconstruction by enabling robots to build continuous, differentiable, and high-...
arXiv:2604. 08991v3 Announce Type: replace-cross Abstract: Reliable embodied interaction in indoor environments requires agents to precisely localize small everyday objects from visual observations.
arXiv:2609.38864v1 Announce Type: new Abstract: Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as...
LangMap introduces a human‑verified benchmark for language‑conditioned goal navigation (LGN) that spans four hierarchical semantic levels—scene, room, region, and instance—within real‑world indoor 3D scans. The dataset, built on HM3D, contains 18K tasks with concise and detailed descriptions for 414 object categories, and its contrastive annotation protocol ensures high‑quality, discriminative region and instance labels. Evaluation shows that LangMap’s descriptions improve text‑to‑view matching accuracy by 23 points over GOAT‑Bench and achieve a 92.5% unique‑and‑correct match rate in an independent human audit, while a proposed RGB‑only baseline, PlaNaVid, attains top‑tier success rates without depth or 3D scene representations.
arXiv:2606. 00095v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions.
arXiv:2608.29114v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires agents to reason over accumulated observations while continuously exploring unseen regions. However, ex...
Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as it can model holistic 3D spaces by encoding geome...