Ultra-Low Power Event-Based Camera for Autonomous Vehicle

As vision systems based on artificial intelligence are becoming increasingly popular, the most attractive, promising and practical application field currently remains the efficient provision of driving assistance to users and the manufacture of fully-autonomous vehicles. It is however vital to design systems requiring a reduced energy consumption, not only because of their combination with other numerous embarked systems in autonomous vehicles, but also with regard to environmental sustainability as a whole. By means of processing data closest to the sensor, low-power advanced vision applications can process information with minimal energy consumption, thus enhancing and extending their performance duration. Consequently, less information is needed, which translates into lower power consumption. In fact, lower power consumption accommodates a power-limited environment within the car. In his context, the Ultra-Low Power Event-Based Camera (ULPEC) research project, funded since 2017 through the 'Smart System Integration' (SSI) scheme from the European Commission's Horizon 2020 framework programme, aims to develop advanced vision applications with ultra-low power requirements and ultra-low latency, relying on the design of a brain-inspired technology.