Why we train every skill in the twin first
Practical notes on building, validating, and scaling physical-AI fleets.
Blog
Notes on building physical AI
Research, engineering, and product writing from the team teaching and coordinating the world’s robot fleets.
Deploys on your robots Validated in NVIDIA simulation No hardware at risk
Read by teams building physical AI
NORTHFORGE Vantek MERIDIAN 3PL AxisWorks Polaris CPG Cobalt Robotics
Latest
Recent posts
What we’ve been writing.
Closing the reality gap with domain randomization
Practical notes on building, validating, and scaling physical-AI fleets.
Designing an agentic planner for the factory floor
Practical notes on building, validating, and scaling physical-AI fleets.
What a safety gate actually checks
Practical notes on building, validating, and scaling physical-AI fleets.
Using world-model rollouts for synthetic scenarios
Practical notes on building, validating, and scaling physical-AI fleets.
Real-time policy inference on Jetson Thor
Practical notes on building, validating, and scaling physical-AI fleets.
Series
Deep dives
Multi-part explorations.
The data flywheel, part 1
Practical notes on building, validating, and scaling physical-AI fleets.
The data flywheel, part 2
Practical notes on building, validating, and scaling physical-AI fleets.
Cross-embodiment skills, part 1
Practical notes on building, validating, and scaling physical-AI fleets.
Enterprise
Built for the plant and the boardroom
Land on one cell, expand to the line, then every site, with the controls IT and operations require.
Deploy your way
Cloud, VPC, or fully on-prem with NVIDIA AI Enterprise support.
SSO & RBAC
SAML/OIDC, SCIM provisioning, granular per-site roles.
SLAs & support
99.9% control-plane uptime, dedicated solutions engineering.
Integrator channel
Certified partners to stand up sites fast.
Safety certification
Documented validation trail for every deployed skill.
ROI reporting
Throughput, uptime, and cost-per-task dashboards for finance.
Topics
What we cover
6
core topics
30+
articles
4
GPU-essential stages
2
posts a month
Readers
What people take away
“The sim-to-real posts changed how our team validates skills.”
“Clear, honest engineering writing. Rare in robotics.”
“The data flywheel series finally made the strategy click for us.”
Integrations
Works with the stack on your floor
Vendor-agnostic across robots, controllers, and systems of record.
Robots & arms
Universal RobotsFANUCKUKAABBFetchBoston Dynamics
AMRs & humanoids
MiROTTOLocusAgilityApptronikFigure
Controllers & sensors
ROS 2PLCs / OPC-UAIntel RealSenseZividSICKCognex
Systems of record
SAPManhattan WMSBlue YonderNetSuiteSnowflakeDatabricks
Security & safety
Enterprise-grade, safety-first by design
Robots act in the physical world, so every skill is validated before it ever touches hardware.
SOC 2 Type II ISO 27001 GDPR ISO 10218 / RIA R15.06 SSO / SAML Audit logs
Safety gates
Every policy must pass success + collision + force limits in sim before deploy.
Encryption everywhere
AES-256 at rest, TLS 1.3 in transit, per-site key isolation.
Data residency
Run in your VPC or on-prem; telemetry never leaves your boundary.
SSO, SCIM & RBAC
SAML/OIDC, provisioning, and role-based access down to the cell.
Get started
Get the next post
Subscribe for research and engineering notes on physical AI.