AI & ML
Evaluating Language Models as Spatial Priors for Object-Goal Navigation
arXiv cs.RO0 views
arXiv:2611.18123v1 Announce Type: new Abstract: Semantic exploration methods for object-goal navigation use large language models (LLMs) to score how strongly a target object is associated with a room type or with a nearby object. This paper considers obtaining from the LLM a spatial prior instead: a distribution over the position of the target in a room. We evaluate whether two open-weight LLMs, Qwen3.5-27B and Gemma-4-31B-it, can provide such a prior. Using real room layouts from CubiCasa5K and ScanNet, we measure the likelihood the models assign to real and perturbed layouts, and the layouts they generate. The object frequencies and room sizes of the generated rooms follow the room type, but the proximity of the objects to the walls does not follow the differences between room types found in real rooms. The likelihood distinguishes real layouts from perturbed ones partly through their geometry and partly through the agreement between the coordinates and a field that states the wall each object touches; for the movable furniture of ScanNet, it is higher for layouts with all objects piled near the room center than for the real layouts in most rooms. When an object is given in the prompt, the models place a related object relative to it. When the wall of each object is given, they place most objects against that wall, but do not keep all objects inside a given room rectangle. As a prior for object search, the generated placements reduce the searched area relative to a uniform prior, but by less than a third of the reduction obtained with a prior built from real layouts, and by less than two thirds when both priors are spatially smoothed. These results support the use of LLMs for object-room associations and for writing coordinates under constraints determined by another component, followed by a geometric check, but not as a source of placement priors where real layouts are available.
Source:https://arxiv.org/abs/2611.18123PreviousPoliMop: Policy-in-the-Loop Motion Planning in 3D Spaces for Mobile RobotsNextESI: An Embodied Self-Improvement Flywheel for LLM-VLA Agents
Related posts

How to Use Git Stash Step by Step
0dev.to Git
GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
0arXiv cs.DB
Larch: Learned Query Optimization for Semantic Predicates
0arXiv cs.DB
Use-case-driven ontology modeling with the NeOn methodology for ambient assisted living
0arXiv cs.DB
Enhancing Quality of Experience in Future Telecommunication Networks: A Review of Frameworks and Machine Learning Algorithms
0arXiv cs.NI
Who sets the consent signal? Platform defaults and crawl coverage in measuring opt-outs from AI training
0arXiv cs.NI