Interpreting object-referential language and grounding objects in 3D with spatial relations and attributes is essential for robots operating alongside humans. However, this task is often challenging due to the diversity of scenes, large number of fine-grained objects, and complex free-form nature of language references. Furthermore, in the 3D domain, obtaining large amounts of natural language training data is difficult. Thus, it is important for methods to learn from little data and zero-shot generalize to new environments. To address these challenges, we propose SORT3D, an approach that utilizes rich object attributes from 2D data and merges a heuristics-based spatial reasoning toolbox with the ability of large language models (LLMs) to perform sequential reasoning. Importantly, our method does not require text-to-3D data for training and can be applied zero-shot to unseen environments. We show that SORT3D achieves state-of-the-art performance on complex view-dependent grounding tasks on two benchmarks. We also implement the pipeline to run real-time on an autonomous vehicle and demonstrate that our approach can be used for object-goal navigation on previously unseen real-world environments. All source code for the system pipeline is publicly released atthis https URL.
View on arXiv@article{zantout2025_2504.18684,
title={ SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models },
author={ Nader Zantout and Haochen Zhang and Pujith Kachana and Jinkai Qiu and Ji Zhang and Wenshan Wang },
journal={arXiv preprint arXiv:2504.18684},
year={ 2025 }
}