VISOR: VIsual Spatial Object Reasoning for Language-driven Object Navigation

• URL: http://arxiv.org/abs/2602.07555v1
• Date: Sat, 07 Feb 2026 14:01:29 GMT
• Title: VISOR: VIsual Spatial Object Reasoning for Language-driven Object Navigation
• Authors: Francesco Taioli, Shiping Yang, Sonia Raychaudhuri, Marco Cristani, Unnat Jain, Angel X Chang,
• Abstract summary: Language-driven object navigation requires agents to interpret natural language descriptions of target objects.<n>Existing methods either (i) use end-to-end trained models with vision-language embeddings, which struggle to generalize beyond training data and lack action-level explainability, or (ii) rely on modular zero-shot pipelines with large language models (LLMs) and open-set object detectors, which suffer from error propagation, high computational cost, and difficulty integrating their reasoning back into the navigation policy.
• Score: 24.25129798349837
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language-driven object navigation requires agents to interpret natural language descriptions of target objects, which combine intrinsic and extrinsic attributes for instance recognition and commonsense navigation. Existing methods either (i) use end-to-end trained models with vision-language embeddings, which struggle to generalize beyond training data and lack action-level explainability, or (ii) rely on modular zero-shot pipelines with large language models (LLMs) and open-set object detectors, which suffer from error propagation, high computational cost, and difficulty integrating their reasoning back into the navigation policy. To this end, we propose a compact 3B-parameter Vision-Language-Action (VLA) agent that performs human-like embodied reasoning for both object recognition and action selection, removing the need for stitched multi-model pipelines. Instead of raw embedding matching, our agent employs explicit image-grounded reasoning to directly answer "Is this the target object?" and "Why should I take this action?" The reasoning process unfolds in three stages: "think", "think summary", and "action", yielding improved explainability, stronger generalization, and more efficient navigation. Code and dataset available upon acceptance.

Related papers

• ReasonNavi: Human-Inspired Global Map Reasoning for Zero-Shot Embodied Navigation [53.95797153529148]
  Embodied agents often struggle with efficient navigation because they rely primarily on partial egocentric observations.<n>We introduce ReasonNavi, a human-inspired framework that operationalizes this reason-then-act paradigm by coupling Multimodal Large Language Models (MLLMs) with deterministic planners.
  arXiv  Detail & Related papers  (2026-01-26T19:09:20Z)
• A Multimodal Depth-Aware Method For Embodied Reference Understanding [56.30142869506262]
  Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues.<n>We propose a novel ERU framework that jointly leverages data augmentation, depth-map modality, and a depth-aware decision module.
  arXiv  Detail & Related papers  (2025-10-09T14:32:21Z)
• MLFM: Multi-Layered Feature Maps for Richer Language Understanding in Zero-Shot Semantic Navigation [25.63797039823049]
  LangNav is an open-vocabulary multi-object navigation dataset with natural language goal descriptions.<n> MLFM builds a queryable, multi-layered semantic map from pretrained vision-language features.<n>Experiments on LangNav show that MLFM outperforms state-of-the-art zero-shot mapping-based navigation baselines.
  arXiv  Detail & Related papers  (2025-07-09T21:46:43Z)
• DOPE: Dual Object Perception-Enhancement Network for Vision-and-Language Navigation [1.4154022683679812]
  Vision-and-Language Navigation (VLN) is a challenging task where an agent must understand language instructions and navigate unfamiliar environments using visual cues.<n>We propose a Dual Object Perception-Enhancement Network (DOPE) to address these issues to improve navigation performance.
  arXiv  Detail & Related papers  (2025-04-30T06:47:13Z)
• Zero-shot Object Navigation with Vision-Language Models Reasoning [35.28869151048087]
  We propose a novel Vision Language model with a Tree-of-thought Network (VLTNet) for L-ZSON. VLTNet comprises four main modules: vision language model understanding, semantic mapping, tree-of-thought reasoning and exploration, and goal identification. Compared to conventional frontier selection without reasoning, navigation using ToT reasoning involves multi-path reasoning processes and backtracking when necessary.
  arXiv  Detail & Related papers  (2024-10-24T09:24:07Z)
• OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models [16.50443396055173]
  We propose OpenFMNav, an Open-set Foundation Model based framework for zero-shot object navigation. We first unleash the reasoning abilities of large language models to extract proposed objects from natural language instructions. We then leverage the generalizability of large vision language models to actively discover and detect candidate objects from the scene.
  arXiv  Detail & Related papers  (2024-02-16T13:21:33Z)
• $A^2$Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models [89.64729024399634]
  We study the task of zero-shot vision-and-language navigation (ZS-VLN), a practical yet challenging problem in which an agent learns to navigate following a path described by language instructions. Normally, the instructions have complex grammatical structures and often contain various action descriptions. How to correctly understand and execute these action demands is a critical problem, and the absence of annotated data makes it even more challenging.
  arXiv  Detail & Related papers  (2023-08-15T19:01:19Z)
• Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation [124.07372905781696]
  Actional Atomic-Concept Learning (AACL) maps visual observations to actional atomic concepts for facilitating the alignment. AACL establishes new state-of-the-art results on both fine-grained (R2R) and high-level (REVERIE and R2R-Last) VLN benchmarks.
  arXiv  Detail & Related papers  (2023-02-13T03:08:05Z)
• ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation [75.13546386761153]
  We present a novel zero-shot object navigation method, Exploration with Soft Commonsense constraints (ESC) ESC transfers commonsense knowledge in pre-trained models to open-world object navigation without any navigation experience. Experiments on MP3D, HM3D, and RoboTHOR benchmarks show that our ESC method improves significantly over baselines.
  arXiv  Detail & Related papers  (2023-01-30T18:37:32Z)
• Position-Aware Contrastive Alignment for Referring Image Segmentation [65.16214741785633]
  We present a position-aware contrastive alignment network (PCAN) to enhance the alignment of multi-modal features. Our PCAN consists of two modules: 1) Position Aware Module (PAM), which provides position information of all objects related to natural language descriptions, and 2) Contrastive Language Understanding Module (CLUM), which enhances multi-modal alignment.
  arXiv  Detail & Related papers  (2022-12-27T09:13:19Z)
• ReAct: Synergizing Reasoning and Acting in Language Models [44.746116256516046]
  We show that large language models (LLMs) can generate both reasoning traces and task-specific actions in an interleaved manner. We apply our approach, named ReAct, to a diverse set of language and decision making tasks. ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API.
  arXiv  Detail & Related papers  (2022-10-06T01:00:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.