Skip to site menu Skip to page content

TIER IV to design open source AI chip for autonomous driving 

TIER IV said the project is aimed at overcoming limits of general-purpose computing platforms such as GPUs in Level 4 driving. 

Shivam Mishra August 17 2026

TIER IV has joined a Japan Science and Technology Agency-backed semiconductor R&D programme to develop an open-source artificial intelligence (AI) chip design for Level 4 autonomous driving. 

The Tokyo-based company said today (14 August) it will work under JST’s Next-Generation Edge AI Semiconductor Research and Development Program, where a team led by Professor Yoshihiro Kawahara at the University of Tokyo is researching use-case-driven AI chip design.  

TIER IV’s role is to develop the logic design of an AI chip for end-to-end autonomous driving inference and to open source the design assets, compiler and related toolchain. 

The chip will be designed to support Autoware, TIER IV’s open-source autonomous driving software, and will be evaluated as part of a software-defined system-on-chip, or SoC. 

TIER IV founder and CEO Shinpei Kato said: “Through this initiative, we are introducing a software-defined and open approach to AI chip design that combines power efficiency, adaptability, transparency and verifiability.” 

TIER IV said the project is aimed at overcoming limits of general-purpose computing platforms such as GPUs in Level 4 driving, where AI models must run continuously under real-time, real-world constraints. 

The architecture will focus on Transformer inference, using dedicated circuits for workloads such as matrix multiplication and attention while reducing power use from external memory transfers, the group explained. 

The company also plans to use the Tensor Operator Set Architecture, or TOSA, as an intermediate layer between AI models and hardware so software updates can accommodate model changes without requiring a full chip redesign. 

Kato said traceability and verification of how AI models are transformed before execution will become increasingly important in “safety-critical environments”. 

Kawahara said GPU power consumption has been “a major bottleneck” in deploying physical AI on battery-powered devices. 

“This project aims to fundamentally overcome this constraint through a functionally differentiated chip design backward-mapped from specific use cases,” he said. 

TIER IV said the open-source approach is intended to help semiconductor makers commercialise SoCs for Level 4 vehicles. 

The move follows Toyota Motor’s June acquisition of a roughly 1% stake in TIER IV as part of a broader autonomous driving partnership. 

Its investor base also includes Sony Group, Sompo Holdings, KDDI, Suzuki Motor and Isuzu Motors. 

Uncover your next opportunity with expert reports

Steer your business strategy with key data and insights from our latest market research reports and company profiles. Not ready to buy? Start small by downloading a sample report first.

Newsletters by sectors

close

Sign up to the newsletter: In Brief

Visit our Privacy Policy for more information about our services, how we may use, process and share your personal data, including information of your rights in respect of your personal data and how you can unsubscribe from future marketing communications. Our services are intended for corporate subscribers and you warrant that the email address submitted is your corporate email address.

Thank you for subscribing

View all newsletters from across the GlobalData Media network.

close