Behavioral AI for Autonomous Cars

Humans and robots are a useful combination, but also one where danger may lurk. A robot, such as an autonomous car, must be able to move safely around people. This means that they must be able to recognize and predict intentions, but also that they must be able to interact with people. What gestures, what posture, what facial features mean what exactly, and how should a two-ton robot be able to react accordingly on the road.

We had already presented examples of this here, such as the duck that was chased and scared away by a woman in an electric wheelchair. Or the two women at the side of the road, where the car has to understand whether they want to cross the road or not.

Or just recently, this video of Cruise having a few encounters with interesting road users in San Francisco – appropriately set to the perfect tune:

San Francisco, don’t ever change!

Thanks to our own multi-talented @whatrocks for the perfect tune pic.twitter.com/EbZV9JgdmK

— cruise (@Cruise) June 10, 2022

The London-based company Humanising Autonomy has set itself the goal of identifying precisely these behaviors and their causes and necessary reactions of the robot. In doing so, it is important that the machine does not become overconfident, but also … so that they behave ethically and safely, with humans at the center. As founder and CEO Maya Pindeus says, we should get back to the point where robots and machines help people, not replace them.

The following video is the first of four planned introductions to Behavioral AI.

This article was also published in German.

Read More

Leave a Reply

Your email address will not be published. Required fields are marked *

Generated by Feedzy