TIER IV Details Five Open-Source Models for Autonomous Driving

Unite.AI
Read full story· 5 min
TIER IV released five open-source end-to-end autonomous driving AI models for Autoware, supporting various sensor setups including camera-only and combinations with LiDAR and radar. The models vary in size, sensor requirements, and integration readiness, aiming to facilitate commercial adoption across vehicle types.

What happened

On November 11, 2026, TIER IV released five open-source AI models for autonomous driving, designed for use with the Autoware platform. The models support a range of sensor setups, from camera-only systems to those combining LiDAR, radar, and high-definition maps. Each model differs in size, sensor requirements, and level of integration with Autoware, with some already integrated and others still in development. The release aims to give automakers and technology partners flexible options for integrating autonomous driving capabilities into various vehicles.

Key details

  • The five models are named NVIDIA Alpamayo 2 Edge, AutoE2E, METEOR, OnePlanner, and LatentDrive.
  • Alpamayo 2 Edge has 2 billion parameters and is fully integrated with Autoware, while Alpamayo 2 Super has 34 billion parameters.
  • AutoE2E v1.0 was released under the Apache 2.0 license and achieved an average displacement error of 0.744 meters over three seconds in validation tests.
  • METEOR has 16 million parameters, supports up to eight cameras, and can run on NVIDIA and Renesas platforms.
  • Some models, like LatentDrive, do not require high-definition maps and are still undergoing integration and validation.

Why it matters

Automakers, technology partners, and component suppliers now have access to a range of open-source AI models that can be adapted for different vehicle types and sensor configurations. This release allows these groups to optimize and integrate autonomous driving technology without being tied to a single AI model or hardware platform. The models' open-source nature and varying integration readiness give companies more flexibility in development, but some models still require further testing and adaptation before commercial deployment.


More in Automotive