OpenNav: Open-World Navigation with Multimodal Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Mingfeng, Wang, Letian, Waslander, Steven L.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915693720502272
author Yuan, Mingfeng
Wang, Letian
Waslander, Steven L.
author_facet Yuan, Mingfeng
Wang, Letian
Waslander, Steven L.
contents 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/
format Preprint
id arxiv_https___arxiv_org_abs_2507_18033
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenNav: Open-World Navigation with Multimodal Large Language Models
Yuan, Mingfeng
Wang, Letian
Waslander, Steven L.
Robotics
Artificial Intelligence
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/
title OpenNav: Open-World Navigation with Multimodal Large Language Models
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2507.18033