Spatial intelligence
for hardware AI.

One API to give your drones, robots, and autonomous systems the ability to reconstruct, understand, and simulate the physical world in real time.

Read the Docs →Get API Key

From sensor to spatial intelligence in 10 lines.

Our Python SDK handles the full pipeline — reconstruct from any source, build a queryable scene graph, and run physics simulations. All with a single API key.

[python][typescript][rest-api][grpc]
pipeline.py
import percept

# Initialize with your API key
client = percept.Client(api_key="pk_live_...")

# Reconstruct from drone video
scene = client.reconstruct(
  source="drone_capture.mp4",
  mode="metric_3d",
  coordinate_system="EPSG:4326"
)

# Query the scene graph
defects = scene.query(
  type="structural_defect",
  severity="critical",
  within=scene.bounds(lat=37.87, lon=-122.26, radius=500)
)

# Run physics simulation
result = scene.simulate(
  scenario="fire_spread",
  duration=4,
  wind_speed=12.5,
  wind_direction=225
)

# Stream results
for frame in result.frames():
    print(f"t={frame.time}s  burned={frame.area_m2}m²")

# → 2.4M vertices · 12 defects · 96.2% confidence

Everything you need to build spatial AI.

01

Reconstruction

percept.reconstruct(source, mode="metric_3d")

Turn any video or sensor stream into metrically accurate 3D. Supports phone cameras, drones, LiDAR, and satellite.

02

Scene Queries

scene.query(type="defect", severity="critical")

Query the physical world like a database. Filter by object type, material, spatial region, or semantic label.

03

Physics Simulation

scene.simulate(scenario="fire_spread", duration=4)

Run real physics on real geometry. Fire, flood, structural failure — all on actual terrain data.

04

Streaming Ingest

percept.stream(feed=camera_array, fps=30)

Real-time processing of live sensor feeds. Continuously update the scene graph as new data arrives.

05

Export & Integrate

scene.export(format="gltf", crs="EPSG:4326")

Export to standard formats. Integrate with GIS systems, game engines, CAD tools, or your own pipeline.

06

Webhooks & Events

percept.on("defect_detected", callback)

Event-driven architecture. Get notified when objects change, defects appear, or simulation thresholds trigger.

Built for the hardware AI ecosystem.

Integrate Percept directly into your drone, robot, or autonomous system. Our SDK runs on edge devices with real-time performance.

Drone Manufacturer
Robotics Company
Autonomous Vehicles
Satellite Provider
Sensor OEM
Edge AI Platform