Swedish autonomous driving software company Zenuity is teaming up with CERN, the European Organization for Nuclear Research, to develop fast machine learning for autonomous vehicles.
Zenuity hopes the collaboration with CERN will help it to develop technology that enables autonomous vehicles to reach decisions and make predictions more quickly, thus avoiding accidents.
It plans to this by using Field-Programmable Gate Arrays (FPGAs), a hardware solution that can execute complex decision-taking algorithms in micro-seconds, to further research of so-called ‘deep learning’, a class of machine learning algorithms.
The two organisations will utilise this technology to reduce the runtime and memory footprint of relevant deep learning algorithms without reducing accuracy, while simultaneously minimising energy consumption and cost.
Dennis Nobelius, Zenuity’s chief executive, said: “I think it says something important about the collaborative nature of science that an organisation like CERN, which conducts high-energy particle collisions, can work with a company that is dedicated to completely eliminating collisions… in traffic.”
