Covering Disruptive Technology Powering Business in The Digital Age

TIER IV, a pioneer in open-source autonomous driving (AD) technology, has successfully partnered with  Axell Corporation, a Japan-based computer hardware company, to conduct a collaborative research project aimed at creating a new application-specific system-on-chip (SoC) and software platform for autonomous vehicles.

The project culminated in a demonstration, showcasing the power and performance advantages of the Autoware Accelerators. These hardware accelerators are custom-designed specifically for the Autoware architecture. Autoware is the world’s first open-source autonomous driving (AD) software developed by Tier IV. The company is the forefront of the research and development of AD technology.

The company provides cutting-edge technology solutions, including software and hardware across multiple platforms, that enable the safe and efficient development of autonomous driving. It also is committed to the societal implementation of AD technology, driven by their vision of “the art of open source—reimagine intelligent vehicles”.

These collaborative research efforts were funded by the “Innovative AI Chip and Next-Generation Computing Technology Development” project, sponsored by the New Energy and Industrial Technology Development Organization (NEDO).

An Optimised Solution Ready for Integration

The new SoC has been specifically optimised to integrate with Autoware, a widely acclaimed open-source software for autonomous driving championed by TIER IV. Designed to execute a diverse range of AD algorithms with exceptional efficiency, the SoC sets the stage for the development of a complete Robo-Taxi system with an estimated power consumption of less than 150W (utilising the latest state-of-the-art semiconductor process).

Additionally, the system features hardware accelerators that expertly manage high-load sensor data processing, achieving close to a tenfold reduction in power consumption compared to existing environments. To ensure seamless execution of control system processing, a dedicated real-time operating system (RTOS) is seamlessly integrated with many-core processors, effectively mitigating fluctuations in execution time.

With its focus on AI edge computing, the SoC aims to provide more efficient and reliable AD functions.

(0)(0)