GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model
GemNav is a novel visual robot navigation policy that adapts a frozen Multimodal Large Language Model (MLLM) via Low-Rank Adaptation (LoRA) on the language tower alone, without auxiliary visual encoders or continuous regression heads. It uses a shared discrete token vocabulary for waypoints and navigation signals, and a soft-decoded auxiliary loss recovers metric structure. Trained on just 8.7 hours of data, it zero-shot transfers to four unseen environments, stopping within 0.25-0.42m of goals across 20 trials. Results indicate discrete-token adaptation of frozen MLLMs is a data-efficient, deployable alternative for robot navigation.
-->
[Submitted on 8 Jul 2026]
Title:GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model
View a PDF of the paper titled GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model, by Peter Bohm and 5 other authors
View PDF HTML (experimental)
Abstract:Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe is necessary. In this paper, we introduce GemNav, a visual robot navigation policy that adapts a frozen Multimodal Large Language Model (MLLM) for short-to-medium horizon waypoint navigation using Low-Rank Adaptation (LoRA) on the language tower alone, with no auxiliary visual encoder and no continuous regression head. Waypoints and categorical navigation signals share a single discrete token vocabulary generated by the language-model head, and a soft-decoded auxiliary loss recovers the metric structure that pure cross-entropy training discards. On a single 8.7-hour open corpus, roughly three orders of magnitude smaller than competing training sets, the policy transfers zero-shot to four physically distinct unseen environments and stops within 0.25-0.42m of the goal across 20 real-world trials covering an open carpark, an obstacle carpark, a long outdoor chemical yard, and an indoor warehouse. Conditioning on short image histories improves offline metrics but yields no robot benefit, pointing to a ceiling on what temporal context adds once pretrained vision features are in place. These results indicate that discrete-token adaptation of frozen MLLMs can provide a data-efficient, deployable alternative for foundation model robot navigation.
Subjects:
Robotics (cs.RO); Artificial Intelligence (cs.AI)
Cite as: arXiv:2607.06882 [cs.RO]
(or arXiv:2607.06882v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.06882
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Peter Bohm [view email] [v1] Wed, 8 Jul 2026 00:46:57 UTC (4,080 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model, by Peter Bohm and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-07
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)