BADAS 2.0

Nexar's collision-prediction model. It anticipates likely crashes from live driving video before they happen, trained on millions of real-world driving clips.

Nexar APEX

A real-world credibility test (a "driver's license") for autonomous vehicles, validating an AV stack against billions of miles of ground-truth human driving data rather than simulation alone.

Nexar Atlas

Nexar's platform that converts billions of miles of crowdsourced driving video into AI-ready datasets and intelligence for model training and simulation.

Nexar APEX

A real-world credibility test (a "driver's license") for autonomous vehicles, validating an AV stack against billions of miles of ground-truth human driving data rather than simulation alone.

The City AV Index

Nexar's measure of how ready each U.S. city is for autonomous driving, based on real-world driving behavior, monthly data freshness, and block-level risk signals.

Physical AI

AI systems that perceive and act in the physical world, such as vehicles and robots, rather than purely digital tasks.

Real-world AV training data

Driving data captured from actual roads (not simulated), used to train autonomous-vehicle and ADAS models.

Collision prediction model

An AI model that estimates the likelihood of an imminent crash from video or sensor input, enabling earlier warnings than reactive systems.

Edge case

A rare, unusual, or hard-to-predict driving situation that standard models struggle with and that simulators rarely reproduce.