Robostral Navigate

Hugging Face Daily Papers Papers
vision-language-model navigation robotics monocular-rgb state-of-the-art simulation reinforcement-learning

Summary

Robostral Navigate is an 8B vision-language model that uses only monocular RGB images for robot navigation, achieving state-of-the-art on R2R-CE and RxR-CE benchmarks with 77.4% and 75.1% success rates, respectively.

Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployment cost. We introduce Robostral Navigate, an 8B vision-language model built around this scalability objective. The model consumes only a stream of monocular RGB images - the most ubiquitous sensor across robotic platforms and predicts waypoints by pointing to the next target location in the current camera view. Operating purely in image space, rather than robot-specific coordinates, makes the policy naturally robust to changes in camera intrinsics and scene scale, enabling deployment across wheeled, legged, and aerial robots without recalibration. We generate 2.4 million trajectories across 350k simulated scenes to reduce the reliance on real-world data collection and scale easily. We further introduce a prefix-caching training recipe that packs entire episodes into single training sequences, reducing training tokens by 22x and cutting training time from months to days. A tree-based attention mask prevents conditioning on previous ground-truth actions, encouraging visually grounded action prediction, and reinforcement learning is used to further improve exploration and recovery capabilities. On the Room-to-Room and Room-Across-Room in Continuous Environments (R2R-CE and RxR-CE) benchmarks, Robostral Navigate sets a new state of the art. On R2R-CE, it achieves a 77.4% success rate, surpassing the best monocular method by 10.5 points and the strongest depth- or multi-camera system by 5.3 points despite using only a single RGB camera. On RxR-CE, it reaches 75.1% success rate, outperforming all monocular baselines.
Original Article
View Cached Full Text

Cached at: 07/24/26, 05:06 AM

Paper page - Robostral Navigate

Source: https://huggingface.co/papers/2607.20785 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Deployingnavigationsystemsatscalerequiresarecipethatminimizessensorassumptions,generalizesacrossrobotembodiments,andtrainsefficiently.Yet,today’sbestsystemsdependondepthsensors,multi-camerarigs,orpre-builtmaps,limitingthehardwaretheysupportandincreasingdeploymentcost.WeintroduceRobostralNavigate,an8Bvision-languagemodelbuiltaroundthisscalabilityobjective.ThemodelconsumesonlyastreamofmonocularRGBimages-themostubiquitoussensoracrossroboticplatformsandpredictswaypointsbypointingtothenexttargetlocationinthecurrentcameraview.Operatingpurelyinimagespace,ratherthanrobot-specificcoordinates,makesthepolicynaturallyrobusttochangesincameraintrinsicsandscenescale,enablingdeploymentacrosswheeled,legged,andaerialrobotswithoutrecalibration.Wegenerate2.4milliontrajectoriesacross350ksimulatedscenestoreducetherelianceonreal-worlddatacollectionandscaleeasily.Wefurtherintroduceaprefix-cachingtrainingrecipethatpacksentireepisodesintosingletrainingsequences,reducingtrainingtokensby22xandcuttingtrainingtimefrommonthstodays.Atree-basedattentionmaskpreventsconditioningonpreviousground-truthactions,encouragingvisuallygroundedactionprediction,andreinforcementlearningisusedtofurtherimproveexplorationandrecoverycapabilities.OntheRoom-to-RoomandRoom-Across-RoominContinuousEnvironments(R2R-CEandRxR-CE)benchmarks,RobostralNavigatesetsanewstateoftheart.OnR2R-CE,itachievesa77.4%successrate,surpassingthebestmonocularmethodby10.5pointsandthestrongestdepth-ormulti-camerasystemby5.3pointsdespiteusingonlyasingleRGBcamera.OnRxR-CE,itreaches75.1%successrate,outperformingallmonocularbaselines.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.20785

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.20785 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.20785 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.20785 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles