TIER IV unveils AI-based Level 4 autonomous driving, accelerating global platform expansion

Open-source software stacks aim to expand operational design domains for autonomous vehicles across Japan, U.S. and Europe

Mar. 16, 2026 at 6:00am

Got story updates? Submit your updates here. ›

TIER IV, the company behind the open-source Autoware software for autonomous driving, has developed new AI-powered software stacks for Level 4 autonomous driving. The stacks are designed to be hardware-agnostic and support various system-on-chip and sensor configurations. TIER IV is collaborating with universities in Tokyo, Pittsburgh, and Munich to test the technology in diverse driving environments and contribute to the open-source Autoware ecosystem.

Why it matters

The release of these AI-powered software stacks for Level 4 autonomous driving is a significant step towards making self-driving technology more practical and accessible. By leveraging open-source software and collaborating with academic and industry partners across multiple regions, TIER IV aims to establish AI-based Level 4 autonomy as an industry standard and drive the sustainable evolution of autonomous driving technology.

The details

The newly developed software stacks from TIER IV include two main systems: a hybrid system that uses diffusion models to capture temporal changes in the surroundings and combine it with environment perception, and an end-to-end (E2E) system that treats the surroundings and driving status as vector representations and integrates perception, planning, and control into a single learning process. These software stacks are available on GitHub within the Autoware repositories, and TIER IV is working with the Autoware Foundation to foster a framework for academia, industry, and the developer community to collectively improve the open-source software.

  • TIER IV launched a Level 4+ initiative in March 2026 to expand fully autonomous driving into more complex environments.
  • The data-centric AI technology at the core of the new software stacks was released in July 2025 as part of the end-to-end (E2E) architecture for Autoware.

The players

TIER IV

A pioneering force behind open-source software for autonomous driving, developing platforms and services around the Autoware ecosystem.

Autoware Foundation

A global organization that collaborates with researchers, corporations, and developers to advance autonomous driving software through the open-source Autoware platform.

University of Tokyo

A partner institution collaborating with TIER IV on testing the new autonomous driving technology in Tokyo's urban environments.

Carnegie Mellon University (CMU)

A partner institution collaborating with TIER IV on robotaxi tests in urban areas of Pittsburgh, including routes between the airport and CMU.

Technical University of Munich

A partner institution collaborating with TIER IV on safety evaluations of the autonomous driving technology across various urban driving scenarios in and around Munich.

Got photos? Submit your photos here. ›

What they’re saying

“To achieve Level 4+ autonomy, we need technology that evolves autonomously alongside the environments it serves. Our new data-centric AI models and collaborative MLOps platform provide a common language and a shared foundation for the entire industry.”

— Shinpei Kato, Founder and CEO of TIER IV

“Autoware serves as the global foundation where researchers, corporations and developers collaborate to advance autonomous driving software. Our collaboration with TIER IV strengthens the international framework for validating and refining E2E autonomous driving through real-world deployment.”

— Yang Zhang, Chairman of the Autoware Foundation's board of directors

“The release of these software stacks and MLOps platform is a vital step toward deploying advanced AI models in industrial applications. By accumulating data from Japan's distinctive traffic environments through our Tokyo testing and contributing those insights back to Autoware, we aim to further bridge the gap between academic research and real-world deployment.”

— Yutaka Matsuo, Professor at the University of Tokyo, Graduate School of Engineering

“Autoware is a foundational technology for shaping the Level 4+ autonomy concept. Our Pittsburgh testing will validate the effectiveness of this technology under unique urban traffic conditions. It is essential for the global advancement of autonomous driving that academia and industry continue to collaborate and share results through the Autoware ecosystem.”

— Raj Rajkumar, George Westinghouse Professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University

“This initiative provides a valuable opportunity to evaluate technologies at the Level 4 autonomous driving standard within European urban environments and verify their effectiveness from multiple perspectives. We expect that this framework—improving AI models using region-specific datasets through Autoware-based collaboration—will significantly contribute to the development of highly practical autonomous technology.”

— Johannes Betz, Professor of Autonomous Vehicle Systems at the Technical University of Munich

What’s next

Through an international framework built on the open-source Autoware ecosystem, TIER IV is committed to driving the deployment and sustainable evolution of Level 4 autonomous driving by continuously improving AI model performance using large-scale driving data and various MLOps capabilities.

The takeaway

TIER IV's release of AI-powered software stacks for Level 4 autonomous driving, combined with its collaborative approach across academia and industry partners in key global hubs, represents a significant step towards making self-driving technology more practical and accessible through open-source innovation.