Using Ogma Corp’s EOgmaNeo machine learning library, we created a tiny vision-based self-driving car(SDC), powered by a Raspberry Pi Zero and weighing 102g. It learns online from the user in real-time, and then drives on its own with the flick of a switch!

Ogma is building new AI technology based on a multidisciplinary approach, combining the latest developments in machine learning, the applied mathematics of dynamical systems, and computational neuroscience. Systems matching the power of state-of-the-art Deep Learning algorithms can be built with the self-organising structure, flexibility and efficiency found in the human brain. Our SDCs and software differ for other alternatives and similar SDCs, by performing all machine learning and inference/prediction on a small board computer (SBC), e.g. a Raspberry Pi3 / Zero boards. Alternatives rely on offloading learning onto more powerful computers (GPUs, server farms, etc.), and then only doing inference/prediction on a SBC. We use faster ‘online unsupervised learning’ techniques, compared to alternative ‘offline supervised learning’ techniques, to be able to perform all computation on smaller compute devices.