# OpenNav: Open-World Navigation with Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2507.18033 · HTML: https://mlsanity.com/paper/2507.18033/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- 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, 17 of 17)

- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning](https://mlsanity.com/paper/2309.16650/) (2023)
- [Recognize Anything: A Strong Image Tagging Model](https://mlsanity.com/paper/2306.03514/) (2023)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [Improving Vision-and-Language Navigation with Image-Text Pairs from the Web](https://mlsanity.com/paper/2004.14973/) (2020)
- [Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.02764/) (2022)
- [Airbert: In-domain Pretraining for Vision-and-Language Navigation](https://mlsanity.com/paper/2108.09105/) (2021)
- [Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale](https://mlsanity.com/paper/2204.03514/) (2022)
- [General Evaluation for Instruction Conditioned Navigation using Dynamic Time Warping](https://mlsanity.com/paper/1907.05446/) (2019)
- [NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models](https://mlsanity.com/paper/2407.12366/) (2024)
- [Language Models as Zero-Shot Trajectory Generators](https://mlsanity.com/paper/2310.11604/) (2023)
- [Tokenize Anything via Prompting](https://mlsanity.com/paper/2312.09128/) (2023)
- [OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments](https://mlsanity.com/paper/2403.09412/) (2024)
- [Lifelong Robot Learning with Human Assisted Language Planners](https://mlsanity.com/paper/2309.14321/) (2023)
- [City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation](https://mlsanity.com/paper/2209.14072/) (2022)

## Built on by (most cited first, 3 of 3)

- [TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments](https://mlsanity.com/paper/2602.02459/) (2026)
- [TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues](https://mlsanity.com/paper/2605.31121/) (2026)
- [Instance-Enriched Semantic Maps for Visual Language Navigation](https://mlsanity.com/paper/2607.12630/) (2026)

## Abstract (arXiv)

Pre-trained large language models (LLMs) have demonstrated strong common-sense reasoning abilities, making them promising for robotic navigation and planning tasks. However, despite recent progress, bridging the gap between language descriptions and actual robot actions in the open-world, beyond merely invoking limited predefined motion primitives, remains an open challenge. In this work, we aim to enable robots to interpret and decompose complex language instructions, ultimately synthesizing a sequence of trajectory points to complete diverse navigation tasks given open-set instructions and open-set objects. We observe that multi-modal large language models (MLLMs) exhibit strong cross-modal understanding when processing free-form language instructions, demonstrating robust scene comprehension. More importantly, leveraging their code-generation capability, MLLMs can interact with vision-language perception models to generate compositional 2D bird-eye-view value maps, effectively integrating semantic knowledge from MLLMs with spatial information from maps to reinforce the robot's spatial understanding. To further validate our approach, we effectively leverage large-scale autonomous vehicle datasets (AVDs) to validate our proposed zero-shot vision-language navigation framework in outdoor navigation tasks, demonstrating its capability to execute a diverse range of free-form natural language navigation instructions while maintaining robustness against object detection errors and linguistic ambiguities. Furthermore, we validate our system on a Husky robot in both indoor and outdoor scenes, demonstrating its real-world robustness and applicability. Supplementary videos are available at https://trailab.github.io/OpenNav-website/