Skip to main content
LivestreamHear more about how Niantic Spatial is working with NVIDIA and Flexion to close the Sim-to-Real gap!Watch now
Scaniverse appCapture and reconstruct real places.PricingPlans for teams and enterprises.
Contact sales
Industries

Where people and machines work in the real world.

Field operator at a refineryOil and gasIntelligent field operations. Aerial view of a coastal site, measured from drone imageryDefense and intelligenceMission rehearsal and GPS-denied operations. Robots in a real-to-sim workshopEmbodied AIReal-to-sim training for robots.
Company

The team, partners and resources behind Niantic Spatial.

About
About usEventsCareers
Partners
Developer partner programAcademic and community partnersPartner with us
Guides and support
Scaniverse FAQNiantic Spatial SDK docsDeveloper forums
NewsResearch
A family of foundation models, trained on real-world data to establish ground truth for physical AI.
ReconstructionMetric-scale splats and aligned meshes of real places, from a single room to city-scale.LocalizationPrecise vision-based positioning, even where GPS doesn’t work.UnderstandingObjects, change over time and answers at every 3D point of a real place.
Where people and machines work in the real world.
Oil and gasIntelligent field operations.Defense and intelligenceMission rehearsal and GPS-denied operations.Embodied AIReal-to-sim training for robots.
The team, partners and resources behind Niantic Spatial.
About
About usEventsCareers
Partners
Developer partner programAcademic and community partnersPartner with us
Guides and support
Scaniverse FAQNiantic Spatial SDK docsDeveloper forums
Scaniverse appCapture and reconstruct real places.PricingPlans for teams and enterprises.
Contact sales

Precise visual-based positioning anywhere in the world.

Our Visual Positioning System (VPS) turns standard cameras into precise 3DOF or 6DOF positioning sensors, combining global vision-based positioning with customers’ mapped data for seamless indoor and outdoor operation by people and machines.

Contact salesAccess developer docs

Deliver assured localization across contested, robotic, and mobile applications, on hardware already in the field and even when GPS is denied.

CameraAny standard camera
Ground mapsFrom captures and reconstructions
Aerial mapsDrone-captured
SatelliteWhen no local map exists
Localization
WorksIndoors, outdoors, GPS-denied
DeploymentOn device, edge container or cloud, online or offline
IntegrationFuses with GPS and your navigation stack
3DoFPosition and heading
6DoFFull pose (latitude/longitude, altitude, heading, pitch, roll)
Private mapsPrecise positioning on your sites with access you control

Watch a robot localize

A simulation of our Visual Positioning System: a moving robot matches what its camera sees against a 3D model to stay precisely located.

Maps for machines demo

Adaptive VPS for GPS-denied and disconnected environments

  1. Ground-to-air localization
    Localize ground devices against drone-captured maps, covering large areas without mapping every route on foot. VPS can localize ground actors against aerial imagery to within 0.5m and 0.5° of ground truth, even in GPS-denied DDIL environments.
  2. Satellite fallback
    When no local map exists, orient against satellite imagery through our partnership with Vantor.
  3. Private maps
    Enhance global vision-based positioning with your own site maps and keep localization current as environments change.

Fits in your stack and keeps you in control.

Integrate with your navigation stackA passive, vision-based positioning layer feeds pose estimates into the navigation system your vehicle or device already uses.
Private by default. Own your data and control accessRetain ownership of your spatial data with encrypted storage and control over who can localize where.

Industries we support

Oil and GasPositioning for field teams, inspection drones and robots across large, changing plants.Explore oil and gas Defense and IntelligenceAbsolute position for people and autonomous systems when GPS is denied or degraded.Explore defense Embodied AIContinuous positioning so robots navigate complex spaces safely, indoors and out.Explore embodied AI

Related

CaptureCapture real-world environments using smartphones, 360° cameras, drones, LiDAR, and satellite imagery. Capture is the entry into our Niantic Spatial models including reconstruction, localization, and understanding.ReconstructionReconstruct the real world from multi-sensor data including off the shelf cameras as geometrically accurate, georeferenced 3D meshes and Gaussian splats for measurement, visualization, simulation, and spatial understanding.

Frequently Asked Questions

What is VPS, and how does it work?

Niantic Spatial’s Visual Positioning System (VPS) uses camera imagery to determine position and orientation. By matching what a camera sees against spatial data, VPS gives robots, vehicles, and field teams a shared reference for where they are and where they’re looking.

Can VPS work without GPS or network connectivity?

VPS can localize using visual data when GPS is degraded or denied. Cloud localization requires connectivity; network-denied operation requires an appropriate on-device or edge configuration, with deployment requirements defined for your application.

Do I need to map a site before using VPS?

Not every area requires a site-specific scan. VPS can use broader map and imagery sources for position and heading estimates, while detailed site maps enable precise 6DOF localization. Customers can add their own mapped data, and ground devices can localize against drone-captured maps.

How accurate is VPS?

Accuracy depends on the localization method, map quality, and operating conditions. In ground-to-air testing, VPS localized ground actors within 0.5 meters and 0.5 degrees of ground truth in GPS-denied environments. These results describe tested conditions, not a universal accuracy guarantee.

Does VPS require dedicated positioning hardware or a new navigation stack?

VPS uses standard cameras rather than dedicated positioning hardware or installed beacons. Available through the Niantic Spatial Development Kit (NSDK), it feeds position and orientation estimates into the navigation system your vehicle or device already uses.