Anduril operates on a clear premise: test volume drives capability. More tests means more learning. More learning means faster iteration. This philosophy extends across all domains: air, land, sea, and space.
Thanks for reading Nominal’s Substack! Subscribe for free to receive new posts and support my work.
Subscribe
But test volume creates a constraint: analysis infrastructure. The ability to manage and process test data is a limiting factor at-scale.
High-tempo testing across Anduril’s vehicle programs produces massive data volumes: high-frequency telemetry at 1-10 kHz across thousands of channels, onboard video from multiple cameras, logs capturing autonomy decisions, and operator annotations tracking failures and configurations.
Before Nominal, this data landed in dozens of different storage systems and analysis tools spanning test sites and customer operations worldwide. Each program and team had evolved their own stack for operationalizing test data. Sharing insight required manual exports, screenshots over Slack, or learning another team’s bespoke analysis workflow. Test tempo accelerated but the ability to run analysis did not.
Anduril adopted Nominal as the analysis platform underpinning its test and evaluation workflows across a number of Anduril programs, a unified solution where every signal from multiple products could be captured, synchronized, and understood.
Nominal Core ingests multimodal data from every source, automatically collates and aligns it, and makes it rapidly queryable by engineers and operators of all stripes.
A test engineer at headquarters, mission operator at a remote range, and software lead at a development facility all work from the same organized catalog of Runs and Assets.
Flight test engineers build Workbook templates for post-flight analysis: motor performance, battery discharge, control loop stability, perception accuracy. Specialists define the logic once (which derivatives, which comparisons, which metrics) and save it as a template that any engineer or operator can utilize.