Not established from the available sources.
MISTRAL AI · MODEL RELEASE TRACKER
Robostral Navigate
Robostral Navigate (announced 2026-07-08) is an 8B model for embodied navigation that uses a single RGB camera and plain-language instructions to autonomously move robots through complex, real-world environments, generalizing across robot types.CURRENT SNAPSHOT2/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
Input modalitiesOperates from a single ordinary RGB camera and plain-language instructions; does not use LiDAR or depth sensors.
R2R-CE benchmark performance76.6% success on R2R-CE validation (unseen); 79.4% success on validation (seen). Reportedly outperforms the best single-camera approach by 9.7 percentage points and the best depth/multi-camera system by 4.5 points.
Not established from the available sources.
VERIFIABLE FACTS
Every value stays attached to a source and date.
RELEASE · Release dateDEVELOPER CLAIM
Published/announced on 2026-07-08 (source page publish date).
CAPABILITIES · Primary capabilityDEVELOPER CLAIM
Autonomous embodied navigation: given a plain-language instruction and a history of observations, predicts navigation actions (pointing) to move a robot through an environment and complete long-horizon tasks, adapting to unseen obstacles.
MODALITIES · Input modalitiesDEVELOPER CLAIM
Operates from a single ordinary RGB camera and plain-language instructions; does not use LiDAR or depth sensors.
BENCHMARKS · R2R-CE benchmark performanceDEVELOPER CLAIM
76.6% success on R2R-CE validation (unseen); 79.4% success on validation (seen). Reportedly outperforms the best single-camera approach by 9.7 percentage points and the best depth/multi-camera system by 4.5 points.
RELEASE · Development and trainingDEVELOPER CLAIM
Built entirely in-house and trained entirely in simulation using token-efficient techniques.
CAPABILITIES · Robot compatibilityDEVELOPER CLAIM
Runs on wheeled, legged, and flying robots and generalizes across robot sizes.
CAPABILITIES · Navigation methodDEVELOPER CLAIM
Combines pointing-based navigation with reinforcement learning for continuous improvement.
WHAT CHANGED