Episode Details
Back to Episodes
Self-Driving Cars Get Explainable | Tech News
Description
Self-driving cars are getting a major transparency boost with Motional’s new CW-Net system, which translates AI decisions into real-time human-understandable concepts like “Approaching Stopped Vehicle” or “Close to Cyclist.” Designed to be causally faithful, it reveals the actual reasons behind maneuvers—not just guesses after the fact. Tested on public roads in Las Vegas, it uncovered quirks like AI hallucinating stopped vehicles and safety systems triggering stops for cyclists. The tech boosts trust, speeds up diagnostics, and barely impacts performance—less than 1%—making it vital not just for cars but also drones and robotic surgery.
Listen in comfort:
Get a discount on a Soli Pillow: http://solipillow.com/discount/dnn.
Advertise on DNN:
advertise@thednn.ai
This is an automated, high-level news summary based on public reporting.
Report issues to feedback@thednn.ai.
View sources & latest updates:
https://sources.thednn.ai/0af2833a165a5247