Sign up for our weekly emails to stay up to date on the latest news!
TIER IV, a leading company in autonomous driving technology, has been selected for a significant Japanese government project aimed at enhancing autonomous driving services to tackle local mobility issues. The initiative focuses on developing standards for Level 4+ autonomous driving and creating an open dataset to support the advancement of AI in this field.
Key Highlights
- TIER IV selected for Japanese government project on autonomous driving.
- Focus on developing standards for Level 4+ autonomous driving.
- Creation of an open dataset integrating real-world and synthetic data.
- Collaboration with Carnegie Mellon University for hybrid architecture.
- Efforts to establish profitable autonomous taxi services in Japan.
Under this project, TIER IV will collaborate with consortium members to establish industry-leading standards for autonomous driving, with automotive manufacturers playing a pivotal role. This collaboration aims to facilitate the deployment of new autonomous driving services across Japan and explore global market opportunities, particularly in regions facing similar mobility and urban development challenges.
A significant aspect of the project is the development of an open dataset that combines real-world data with data generated by AI. This dataset will enable the creation of simulation environments replicating diverse traffic scenarios, which are crucial for evaluating the safety and performance of autonomous driving systems.
TIER IV’s recent collaboration with Carnegie Mellon University has led to the development of a hybrid architecture that merges data-centric AI approaches with best practices in robotics. This architecture is designed to realize a next-generation Level 4+ autonomy concept. Leveraging insights from this collaboration, TIER IV will advance the development of autonomous driving standards and provide an open dataset to ensure transparency and traceability in AI decision-making processes.
The project’s focus areas include integrating multiple end-to-end generative AI models into autonomous driving systems and conducting scenario-based evaluations to compare their characteristics. Additionally, a framework for evaluating and validating these AI models will be developed, along with a roadmap for their real-world deployment. Safety evaluation techniques will also be applied to robotaxi services, drawing on findings from proof-of-concept tests to support safe service design.
For the open dataset, TIER IV will collect driving data using Level 4+ vehicles in and around Tokyo. This data will be combined with synthetic data to create a large, diverse dataset for evaluating autonomous driving systems in complex environments. Varied driving scenarios will be generated using different generative AI architectures, reflecting a wide range of behaviors, traffic participants, and environmental conditions. The synthetic output will be compared with real-world data to address challenges such as errors and hallucinations, ensuring the reliability of the AI models.
The Japanese government’s Mobility DX Strategy aims to establish profitable autonomous taxi services in the near term. TIER IV’s participation in this project not only contributes to this goal but also sets the stage for applying autonomous driving technologies to passenger vehicles, thereby enhancing the global competitiveness of Japan’s automotive industry. Through this initiative, TIER IV is poised to make significant contributions to the advancement of autonomous driving technology, both in Japan and globally.
Sign up for our weekly emails to stay up to date on the latest news!
