Driverless cars for small change?

Driverless cars for small change?
External sensor suite and processing: Raspberry Pi, power bank, Pi camera and Photon Cannon… or torch.

After stumbling across a YouTube video of a toy car made into a driverless vehicle, I contacted the creator, Ran Zhao, to ask him a little more about how he did it…

Ran built the car and developed a small convoluted neural network running on a Raspberry Pi computer, trained using about 200 labelled grey-scale images.

Road sign recognition working in poor light conditions at only 10fps
Path following, showing footage from the on-board Raspberry Pi camera in the top-right.

“The data has been extended so the network can handle never-before-seen road conditions and even drive in the dark. I got slightly less than 10 fps with both neural network and traffic sign classifier running at the same time.”

The video contains four scene types, driving to follow two variations of a marked path, and again using only torchlight, and stop sign recognition in daylight and torchlight as well.

“The play speed of the first scene is adjusted to be 3% faster just to synchronize the two videos. The rest scenes are of normal play speed.”

Do you have any training in this area, or is it part of your job?

“I just did it for fun. This is not exactly what I do for a living. My training is mostly done on YouTube and Google search.”

Tell us about the hardware and software…

Under the hood: Interfacing with the steering actuator and motor control

“The hardware is very simple, a toy car, a Raspberry Pi, a camera, a DC motor drive, a USB power bank and a 9v battery.  Tensorflow and OpenCV are the most popular tools for deep learning and computer vision. The alternatives would be software like Caffe or Theano.”

You’ve managed to keep the cost low for the project, how many hours did it take?

“The Pi and Pi camera cost about $45, the car was $10 and the USB power bank was about $8, so the overall cost is more like $80.

Road sign recognition in daylight

I built everything including hardware modifications and software coding in about three weekends. Most codes are from my old projects and I just reassembled and slightly optimized them so they didn’t overload the Pi.”

Are you planning a Mark 2?

“I am actually planning on Mark 2 which would be a self-driving and obstacle avoiding vehicle using deep reinforcement learning.”

What advice would you give other people learning about this technology?

“My advice to people who are interested in this technology would be ‘get your hands dirty’. The whole ‘deep learning’ may have been a mystery to many people but they are actually incredibly simple. From my perspective, the only way to learn and master would be to practice because that is what deep learning is all about. ”

Watch the video