The previous product line
Until 2026 NADIR sold real-time ADAS sensor-drift detection: scoring fleet vehicles for camera and radar miscalibration from telematics, in Pulse, Meridian and Apex tiers, with a Console, the HORIZON view and a calibration lab.
Why it was retired
A review of the product found two problems that could not be fixed by more engineering. First, the fleet telematics signal the product depended on cannot detect camera drift: the residual channel the detectors assumed is not something telematics actually provides. Second, all of the evidence for the product was synthetic — a simulated fleet of 24 vehicles and simulator studies — with no field validation. We would rather say that plainly than keep selling it.
What carried forward
- The dashcam perception stack (detection, monocular depth, lane geometry, planar ground).
- SE(3) residual math and factor-graph estimation code.
- Bayesian online changepoint detection, now aimed at braking onset.
- Evidence hashing, custody chains and signed manifests.
- The observable-output method from the Mobileye overlay study.
- The rule we learned the hard way: no claim ahead of a real benchmark.
Archived site
The old site is preserved as it was, with an archive banner on every page and excluded from search indexing. Its numbers come from synthetic data.
- Previous home page
- Platform: Monitor, Operate, Prove, Resolve
- Technology: sensing, calibration geometry, scoring, validation
- Industries: fleets, collision networks, insurance, OEM
- Company pages
- Pricing (Pulse, Meridian, Apex tiers)
Archived reports
-
Continuous Extrinsic-Miscalibration Monitoring Above a Fleet-Visible EyeCAN Flag Baseline
Simulation study comparing NADIR's former drift-monitoring tiers against an observable EyeCAN-style binary flag baseline. Prior product line; every result comes from a simulator, not from field data.
-
Distribution-Free Fleet Monitoring of Post-Repair ADAS Extrinsic Drift Under Sparse Telemetry Proxies
Formalises post-repair drift monitoring from CAN and telematics proxies and evaluates robust-Mahalanobis, conformal, CUSUM and BOCPD detectors on a synthetic benchmark, including negative results. Prior product line; synthetic evaluation only.
Product surfaces from that line (console, calibration lab, demo pages) remain online at their existing addresses for reference and are not maintained.