is a Budapest-based software company, developing a full-stack software suite for fully autonomous self-driving cars. Established on the idea that self-driving cars should mimic human behavior, AImotive’s algorithms rely on cameras as primary sensors for accomplishing the tasks of object recognition and classification, localization, decision making, trajectory planning and vehicle control. Development and operation processes follow the current automotive standards, providing a hardware-agnostic, yet scalable solution. The software engine components are aided by an extensive toolkit to accelerate the training and verification, including calibration, data collection and augmented data generation, semi-supervised annotation, and a real-time, photorealistic simulation environment. Addressing the growing need for hardware accelerators that are optimized specifically for artificial intelligence, AImotive designs a power efficient, high performance neural network hardware IP for automotive embedded solutions. The reference design helps chip companies build the optimal hardware to support the performance requirements of the AI-based software suite.
The AImotive office is in a small converted house at the end of a quiet residential street in sunny Mountain View, spitting distance from Google’s headquarters. Outside is a branded Toyota Prius covered in cameras, one of three autonomous cars the Hungarian company is testing in the sleepy neighbourhood. It’s a popular testing ground: one of Google’s driverless cars, now operating under spin-out company Waymo, zips past the office each lunchtime.