rFabric

Documentation

Build Sequence

The target architecture does not change as rFabric expands. What changes is how much depth exists inside each backbone plane and product component. The sequence below shows how the platform compounds from the current wedge outward.

Phased Expansion

Phase 1 - Data foundation wedge

Establish the system-of-record position around robot data intake, labeling, and dataset preparation.

  • Data Ingestion & Preprocessing
  • Annotation & Labeling
  • Dataset Curation & Versioning at baseline depth
  • Unified Data Model & Traceability for core data entities
  • Platform API, CLI & SDKs for data operations
  • Identity & Access and Governance & Tenancy at baseline depth

Phase 2 - Dataset quality depth

Deepen the highest-leverage surface in robot learning: dataset quality, curation ruleset, and review rigor.

  • Automated quality scoring and policy-driven selection
  • Multi-operator coordination and correction loops
  • Orchestration for data-to-dataset automation
  • Governance policy depth for retention, regions, and approval paths
  • Metering & Billing for storage and media-processing economics

Phase 3 - Model development

Extend trust from governed datasets into reproducible training runs, evaluation results, and promoted model identity.

  • Model Training & Evaluation
  • Model Registry
  • Training lineage inside the shared data model
  • Orchestration for dataset-to-model workflows
  • Compute visibility through Metering & Billing

Phase 4 - Release management

Turn approved models into governed production artifacts and controlled rollout flows.

  • Release Packaging
  • Deployment & Updates
  • Environment progression and deployment approvals
  • Release and deployment entities added to the shared graph
  • Promotion, rollout, and rollback flows orchestrated end-to-end

Phase 5 - Live operations

Complete the closed loop from deployed fleets back to data, evaluation, and better future releases.

  • Fleet Management
  • Monitoring, Alerting & Maintenance
  • Human Intervention & Robot Control
  • Operations lineage across telemetry, incidents, maintenance, and interventions
  • Full lifecycle orchestration and operations-aware metering

How The Backbone Deepens

Unified Data Model & Traceability

It expands from datasets and episodes into training runs, promoted models, artifacts, deployments, telemetry, interventions, and financial accountability.

Orchestration

It starts with data-to-dataset automation and grows into promotion, rollout, rollback, maintenance, and human intervention workflows.

Governance & Tenancy

It deepens from workspace isolation into region policy, environment promotion rules, operational approvals, and regulated deployment controls.

Metering & Billing

It becomes more valuable as the platform adds storage, compute, media processing, rollout, and fleet operations that need cost visibility.

Why The Sequence Works

It follows real pain

The first wedge targets the data-to-training bottleneck where robotics teams already feel the infrastructure burden most acutely.

It preserves one architecture

Each phase deepens the same backbone and component map instead of inventing a new platform taxonomy at every stage.

It compounds adoption

Every additional phase enriches the same system of record, which makes the already-adopted parts of the platform more valuable.

It keeps roadmap promises grounded

Expansion follows proven usage and deeper trust, not speculative feature sprawl disconnected from the wedge that wins first.