Robostral Navigate
8B embodied navigation model for autonomous robot movement using single RGB camera and natural language instructions
Context window
N/A (vision-to-action)
Input / 1M tokens
Contact sales
Output / 1M tokens
Contact sales
Provider
Mistral AI
An 8B single-RGB-camera robot navigation model. Enterprise access only through Mistral sales; no public API, pricing, license or open weights announced. · Data verified 2026-10-08
Robostral Navigate is an 8-billion-parameter vision-language-action model for robotic navigation that enables robots to autonomously navigate complex environments using only a single RGB camera and plain-language instructions. It achieves 76.6% success on the R2R-CE benchmark without requiring LiDAR, depth sensors, or multiple cameras. The model generalizes across wheeled, legged, and flying robot platforms.
Capability index
Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.
How to access it
Contact Mistral AI sales; no public API or weights.
Strengths
- ✓Single-camera design reduces hardware costs and complexity
- ✓High performance on R2R-CE benchmark (76.6% unseen, 79.4% seen)
- ✓Generalizes across different robot types and sizes
- ✓Trained entirely in simulation for rapid iteration
- ✓Compact 8B parameters suitable for edge inference
Best for developers who...
When to choose it (and when not to)
Reach for Robostral Navigate when...
- →When deploying navigation systems with minimal sensor hardware requirements
- →For cost-sensitive robotics applications in controlled indoor environments
- →When hardware-agnostic deployment across multiple robot types is needed
Look elsewhere if...
- ✕Safety-critical outdoor autonomous systems requiring depth and range sensing
- ✕Environments with challenging visual conditions (glass, mirrors, low-light areas)
- ✕Applications where latency is critical (edge inference numbers not published)
How to use it
- ›Use clear, sequential language instructions describing the desired navigation path
- ›Break complex routes into logical waypoints in plain language
- ›Describe target locations relative to visible features in the current field of view
Quickstart
Python# Pseudo-code example from official documentation
observation = camera.read() # RGB frame
instruction = "Leave the lobby, walk through the corridor, enter the supply room"
action = model.predict(instruction, observation_history)
if action.type == "point":
robot.move_to_pixel(action.x, action.y, action.heading)
else:
robot.move_local(action.forward_m, action.left_m, action.turn_deg)Integration requires mapping model outputs to robot velocity controllers; Mistral provides reference implementations for ROS and proprietary stacks
API model id: robostral-navigate
Benchmarks
| Benchmark | Score | Notes |
|---|---|---|
| R2R-CE (Room-to-Room in Continuous Environments) - Validation Unseen | 76.6% | Outperforms best single-camera approach by 9.7 points and best multi-sensor systems by 4.5 points |
| R2R-CE (Room-to-Room in Continuous Environments) - Validation Seen | 79.4% | Performance on previously seen environments |
| R2R-CE validation unseen | 76.6% | Room-to-Room in Continuous Environments |
| R2R-CE validation seen | 79.4% | Room-to-Room in Continuous Environments |
| R2R-CE (Room-to-Room in Continuous Environments) | 76.6% | Success rate on unseen validation environments; 79.4% on seen environments |
| R2R-CE (validation unseen) | 76.6% | Room-to-Room in Continuous Environments benchmark |
| R2R-CE (validation seen) | 79.4% | Known environments |
| R2R-CE (Room-to-Room in Continuous Environments) validation unseen | 76.6% | Beats best single-camera approach by 9.7 points and best multi-sensor system by 4.5 points |
| R2R-CE (unseen) | 76.6% | Room-to-Room in Continuous Environments validation unseen |
| R2R-CE (seen) | 79.4% | Room-to-Room in Continuous Environments validation seen |
| R2R-CE | 76.6% | unseen environments |
| R2R-CE (validation-unseen) | 76.6% | Single RGB camera, 9.7pp above best single-camera approach |
| R2R-CE (validation-seen) | 79.4% | |
| R2R-CE (Room-to-Room Continuous Environments) - validation unseen | 76.6% | Outperforms best single-camera approach by 9.7 points; outperforms best multi-sensor system by 4.5 points |
| R2R-CE - validation seen | 79.4% |
Source: Mistral AI Official Announcement
Compare Robostral Navigate
Compare Robostral Navigate with any other model
Build a comparison →All model comparisons →