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

arXiv: https://arxiv.org/abs/2606.30696 · HTML: https://mlsanity.com/paper/2606.30696/

## 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.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 20 of 20)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment](https://mlsanity.com/paper/2406.04882/) (2024)
- [PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning](https://mlsanity.com/paper/2201.10029/) (2022)
- [ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation](https://mlsanity.com/paper/2301.13166/) (2023)
- [L3MVN: Leveraging Large Language Models for Visual Target Navigation](https://mlsanity.com/paper/2304.05501/) (2023)
- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models](https://mlsanity.com/paper/2407.12366/) (2024)
- [NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models](https://mlsanity.com/paper/2305.07766/) (2023)
- [WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation](https://mlsanity.com/paper/2503.02247/) (2025)
- [GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance](https://mlsanity.com/paper/2410.23978/) (2024)
- [SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models](https://mlsanity.com/paper/2409.19471/) (2024)
- [NL2SpaTiaL: Generating Geometric Spatio-Temporal Logic Specifications from Natural Language for Manipulation Tasks](https://mlsanity.com/paper/2512.13670/) (2025)
- [LTLCodeGen: Code Generation of Syntactically Correct Temporal Logic for Robot Task Planning](https://mlsanity.com/paper/2503.07902/) (2025)
- [Motion Planning Under Temporal Logic Specifications In Semantically Unknown Environments](https://mlsanity.com/paper/2511.03652/) (2025)

## 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.