AImotive and ON Semiconductor Collaborate on Next Gen Sensor Fusion Platforms for Automotive Applications

about 4 weeks ago by Luke James

ON Semiconductor and AImotive have recently announced that they will collaborate to develop prototype sensor fusion platforms for use in the automotive space.

The collaboration between AImotive, one of the largest independent teams globally working on automated driving technologies. and ON Semiconductor, a leading supplier of semiconductor-based solutions, will help their customers access integrated solutions for the next generation of sensor data conditioning hardware platforms. It will also allow the 2 companies to explore new levels of integration for advanced heterogeneous sensor fusion for AVs.

 

Industry Leaders Combine Their Expertise

Davide Santo, senior director and general manager, Automotive Radar Sensing Solutions at ON Semiconductor, said:

“Our customers have been asking us to help them deliver better performance by combining different sensors. When undertaking such challenges, AI and simulation are key technologies to help build future-proof products and development processes.

“We recognise AImotive's considerable expertise and industry recognition in these technologies and more for autonomous driving. We believe the results of this collaboration will enable both companies to help customers deliver more advanced sensor fusion solutions to OEMs and Tier1s.”

 

Almotive self-driving car.

An Almotive self-driving car. Image Credit: Almotive.

 

What This Means for Automotive Sensor Data Hardware

The partnership between ON Semiconductor and AImotive is set to lead to more highly-integrated sensor fusion solutions that achieve superior performance—while also being highly cost-effective and practical, i.e. capable of being produced easily at volume.

By utilising real-time AI-based sensor fusion and AImotive's aiWare hardware neural network acceleration IP, ON Semiconductor and AImotive hope to showcase an FPGA-based sensor fusion platform that features superior accuracy, low latency, and enough robustness and reliability to be deployed at scale.

Comments