mlsanityData to 14 Oct 2026

ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language Models

arXiv 2606.30696 ↗First posted 29 Jun 2026cs.RO cs.CL cs.LGcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Enabling robots to follow natural language commands to complete zero-shot long-horizon tasks remains challenging. It requires extracting implicit temporal and logical constraints from natural language commands and executing multiple sub-tasks accordingly. Recent zero-shot object navigation methods use vision-language models (VLMs) to guide frontier-based exploration in unknown environments, but they are limited to single-target tasks. Real-world commands such as "Clean either the chair or the couch, then turn on the tv." require navigating to multiple targets in a temporally constrained order, which no existing zero-shot system can handle. We present ViTL, a framework that addresses this gap at two levels. At the task level, we use a large language model (LLM) to compile natural language commands into Linear Temporal Logic (LTL) formulas, which are then converted into Deterministic Finite Automata~(DFA) that coordinate multi-channel value maps and trigger dynamic replanning when new objects are detected. At the navigation level, we introduce directional score: rather than producing a direction-agnostic value across the entire field of view, we label frontier directions on the observation image and extract per-direction scores from the VLM. Experiments on Habitat-Matterport 3D (HM3D) show that the full framework enables zero-shot long-horizon completion of natural language navigation tasks with temporal constraints, and that directional score improves single-target navigation accuracy and efficiency over the baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 20 of its 28 references that are in the map. First posted on arXiv 29 Jun 2026.

Builds on

20 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation4 Mar
  2. 2024NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models17 Jul
  3. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation6 Dec

Other references · 17

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  3. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 592
  4. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  5. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  6. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 294
  7. 2024InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environmentcited by 157
  8. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 150
  9. 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 127
  10. 2023L3MVN: Leveraging Large Language Models for Visual Target Navigationcited by 120
  11. 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 109
  12. 2023NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Modelscited by 59
5 more
  1. 2024GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidancecited by 23
  2. 2024SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Modelscited by 21
  3. 2025NL2SpaTiaL: Generating Geometric Spatio-Temporal Logic Specifications from Natural Language for Manipulation Taskscited by 3
  4. 2025LTLCodeGen: Code Generation of Syntactically Correct Temporal Logic for Robot Task Planningcited by 1
  5. 2025Motion Planning Under Temporal Logic Specifications In Semantically Unknown Environmentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory
  2. 2025Boosting Zero-Shot VLN via Abstract Obstacle Map-Based Waypoint Prediction with TopoGraph-and-VisitInfo-Aware Prompting
  3. 2025VLN-Zero: Rapid Exploration and Cache-Enabled Neurosymbolic Vision-Language Planning for Zero-Shot Transfer in Robot Navigation
  4. 2026SFCo-Nav: Efficient Zero-Shot Visual Language Navigation via Collaboration of Slow LLM and Fast Attributed Graph Alignment
  5. 2023A2Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models
  6. 2023Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation
  7. 2025History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation
  8. 2026C2Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation