AI startup will train self-driving cars


What do you think will be the biggest challenge for you if you were to drive a car in a busy city? Deciphering the body language of pedestrians as they can wander in any direction with little warning. Right? Now, think about self-driving cars. They lack this critical ability to read human intentions altogether.

A new startup called Perceptive Automata asked companies building automated vehicles how they were approaching the problem. What they learned was that none of them had figured out a way to address it. So Perceptive Automata decided to solve this problem to help with the meaningful real-world deployment of self-driving vehicles.

“We felt that human intuition could be cracked with the right combination of talent, tech, and out-of-the-box thinking, and we felt the problem was too urgent to wait around for someone else to try to figure it out,” said Sam Anthony, co-founder and chief technology officer at Perceptive Automata.

They have designed a model that can use the whole spectrum of subtle, unconscious insights that we, as humans, use to make incredibly sophisticated judgments about what’s going on in someone else’s head.

“Once trained, our deep learning models allow self-driving cars to understand and predict human behavior and, subsequently, react with human-like behaviors. This has huge implications for safety, rider experience, and practical utility in the self-driving car industry,” he added.

Today, Perceptive Automata’s human intuition AI module is already up and running in the vehicles of self-driving car companies around the world. The company, however, didn’t reveal the names of its customers.

Using deep learning techniques, all it’s aiming to change is that the vehicles they are building should be safe, easy to interact with, and good citizens of the road.

Don't miss out great stories, subscribe to our newsletter.

Robotics Petting Zoo engages young minds in programming

Previous article

PowerShell now available for Linux as a Snap

Next article
Login/Sign up