Sign up for our weekly emails to stay up to date on the latest news!
TIER IV and the Matsuo Institute have launched a generative AI project to advance Level 4 autonomous driving by creating large-scale world models. This collaboration aims to expand the operational design domains (ODDs) of autonomous driving and make these models available as open source. By integrating generative AI and traditional robotics approaches, the project seeks to enhance the adaptability of autonomous driving across diverse environments and vehicle types.
Key Highlights
- Development of large-scale world models for Level 4 autonomous driving.
- Combination of generative AI and robotics approaches for a hybrid framework.
- Project outcomes to be released as open source.
- Focus on developing a versatile autonomous driving software for various vehicle types and environments.
The generative AI project by TIER IV and the Matsuo Institute aims to address the limitations of the traditional Level 4 autonomous driving architecture, often referred to as Autonomy 1.0. The new approach, Autonomy 2.0, seeks to replace or coexist with conventional methods by integrating various functional modules such as sensing, localization, perception, and control into a single end-to-end AI model. This innovative model can expand ODDs by learning from vast volumes of driving data and imitating human driving behavior.
The Matsuo Institute will build upon foundational research by the University of Tokyo’s Matsuo-Iwasawa Laboratory. Since 2020, TIER IV and the Matsuo Institute have led the development of both generative AI and robotics approaches, laying the groundwork for Autonomy 2.0. The new initiative will focus on key components, including a neural simulator to train AI, cooperative machine learning for handling large-scale data, and CT3 (Cars That Think and Talk) to explain the AI’s decision-making processes.
TIER IV envisions combining generative AI with the detailed rule-based robotics approach for a hybrid Autonomy 2.0 framework. This combination aims to enhance adaptability in complex driving scenarios while maintaining safety standards. By 2025, the company plans to incorporate these technologies into its Autoware platform and release them as open-source tools.
Shinpei Kato, founder and CEO of TIER IV, stated: “The extraordinary advancement of generative AI is proving to be a pivotal force in driving the realization of Autonomy 2.0. By combining the AI development expertise of the Matsuo Institute with TIER IV’s leadership in autonomous driving technology, I am confident that we can accelerate the rollout of autonomous driving, starting with robotaxis. As the company leading the development of Autoware, we are committed to making these cutting-edge innovations open and accessible to the global community, fostering a world where technology development is driven collectively.”
Yutaka Matsuo, technical advisor of the Matsuo Institute, added: “World models represent a technology that mirrors human cognitive abilities to understand the external environment, making them a crucial component for ensuring safe mobility in complex real-world settings. Through this project, we aim to contribute to the realization of autonomous driving that offers both safety and comfort, ultimately improving the quality of mobility for all.”
About TIER IV
TIER IV is a deep tech innovator behind Autoware, the first open-source software for autonomous driving. As a founding member of the Autoware Foundation, TIER IV builds scalable platforms and offers comprehensive solutions for software, vehicle manufacturing, and service operations.
About Matsuo Institute
Matsuo Institute fosters an innovation ecosystem centered around the Matsuo-Iwasawa Laboratory at the University of Tokyo. It develops and implements research from the laboratory to promote industrial competitiveness and societal adoption of emerging technologies.
Sign up for our weekly emails to stay up to date on the latest news!
