Using Ogma Corp’s EOgmaNeo machine learning library, we created a tiny vision-based self-driving car, powered by a Raspberry Pi Zero.

This SDC was featured in an article in the first issue of a new magazine called HackSpace. A free PDF can be found by clicking the cover below:



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.

Project Details

CAD Design: Provided by Eric Laukien
Material: SLS Nylon
Polishing: NO
Dyeing: YES
Finishing: N/A
Dimensions(mm): Largest part: 81 x 48 x 13.50mm
Project cost: 3 Custom Parts Total £49.68+ vat

The car uses a fish eye camera, which presents an EOgmaNeo hierarchy with grey scale pixel data(pictured left). From that, the steering angle is predicted.

Click here for the full project details and part downloads

This work is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Contact Ogma via to discuss commercial use and licensing options.

“For our first foray into using a 3D printing service, my expectations were far surpassed. We required certain 3D print accuracy and material qualities with the micro self-driving car parts, and 3D Print UK managed to match that on the first print run. The online ordering interface, production run feedback and progress reporting, fast turnaround, and excellent quality made this experience a real pleasure.”

Richard Crowder, Research Engineer
Ogma Intelligent Systems Corp.

No part of the larger SDC featured in this video was 3D printed.