Skip to content

Wave 1 segment

Evaluation-ready capture for robotics teams that care about sim-to-real delivery, not visual theater.

Roam helps robotics teams assess whether a capture program can produce usable scene assets, metadata, and review artifacts before opening a field deployment.

Likely buyer teams

Robotics foundation modelsSimulation and digital twin leadsEmbodied AI teams

What teams usually need to confirm

  • OpenUSD and simulation-asset expectations
  • Metadata and acceptance criteria examples
  • Clear caveats around preview versus production-ready outputs

First pains to address

Scene diversity and refresh cadence are hard to source internally.

Sim-ready assets need more than screenshots or meshes.

Buyers need clarity on what is authoritative for measurement versus preview.

Example program shapes

Facility twins for manipulation and navigation

Home and retail scene libraries for embodied evaluation

Logistics environment capture with refresh cadence

Deliverable fit

Output families that fit this workflow.

Open full deliverables matrix

Point clouds

Structured geometry for measurement, mapping, simulation prep, and change review.

Authoritative for
Measurement-adjacent review, geometry QA, GIS intake, and reconstruction baselines.
Preview use
Subset exploration, coverage checks, and visual inspection.
LAZ / LASCOPCE57PLY

Meshes and reconstructions

Reconstructed surfaces for visualization, facility understanding, and downstream asset generation.

Authoritative for
Operational context and geometry-aware visualization when the engagement calls for reconstructed surfaces.
Preview use
Fast review, stakeholder walkthroughs, and scene understanding.
OBJ / MTLglTF / GLBFBX

OpenUSD scenes

Scene-graph packaging for simulation, twin ingestion, and composition-aware workflows.

Authoritative for
Simulation and scene composition where OpenUSD is the agreed delivery container.
Preview use
Scene inspection, layer review, and asset organization checks.
USDA / USDC / USDZLayer manifests

Simulation assets

Scene assets, semantic layers, and environment packages shaped for evaluation and sim-to-real workflows.

Authoritative for
Simulation setup, evaluation libraries, and digital twin seeding.
Preview use
Pipeline fit validation and asset-family review.
OpenUSD scene layersSemantic labelsAsset bundles

Materials you can review now

public exampleOpen asset

Sample delivery packet

Public outline of a delivery packet with manifests, QA, artifact references, and caveats.

Why review it: Roam thinks in terms of delivery packets rather than isolated media files.

Boundary: Commercial terms, sensitive handling rules, and customer-specific destinations stay under NDA.

public exampleOpen asset

Acceptance criteria outline

Example definition-of-done checklist for coverage, metadata, and artifact integrity.

Why review it: Roam can frame output acceptance criteria in operational terms.

Boundary: Thresholds are illustrative and must be set in the actual engagement.

demo-onlyOpen asset

Sample dataset catalog

Live demo datasets, manifests, and gated artifact downloads.

Why review it: The public demo routes are real and runnable today.

Boundary: Demo subsets are not equivalent to a production program or customer packet.

demo-onlyOpen asset

Sandbox and readiness APIs

Short-lived demo keys, sample dataset listing, and readiness scoring.

Why review it: Technical evaluators can verify endpoint behavior and sample shapes now.

Boundary: Not a production API commitment.

Likely objections

Will this fit our simulation workflow?

Roam publishes output families, metadata, QA expectations, and example artifacts so you can judge fit against your workflow.

We need repeatable environments, not just one scan.

Programs can be scoped around refresh cadence and repeatable environment libraries instead of one-time scans.

Ways to engage

Technical evaluation

Start with docs, sample data, format references, and the sandbox before opening a live program.

Audience: ML engineers, simulation leads, GIS analysts, platform teams

Available now: Public and available now through developer docs, sandbox APIs, and sample-data examples.

Validate technical fit

Live program scoping

Scope environments, outputs, review constraints, and timeline through an intent-first intake path.

Audience: Founders, VPs, robotics PMs, autonomy leads, operations buyers

Available now: Public intake is available now; commercial and operational specifics are finalized in the engagement.

Start program scoping

Security, privacy, and legal diligence

Bring data handling, deletion, privacy-sensitive capture, and diligence questions in early.

Audience: Security reviewers, privacy counsel, legal, procurement

Available now: Public diligence materials are available now; customer-specific review expands under NDA when needed.

Start diligence review

From evaluation to scoping

Validate technical fit

Start with docs, the sandbox, and sample artifacts.

Raise NDA, security, privacy, and delivery constraints in the first conversation instead of after procurement restarts the process.

Need immediate scheduling? Use the programs inbox.