University of California, Berkeley (UC Berkeley) researchers have developed a robot learning system that can learn about physical attributes of the environment through its own experiences in the real world, without the need for simulations or human supervision.
BADGR: the Berkeley Autonomous Driving Ground Robot autonomously collects data and automatically labels it.
The system uses that data to train an image-based neural network predictive model, and applies that model to plan and execute actions that will lead the robot to accomplish a desired navigational task.
UC Berkeley’s Gregory Kahn wrote, “The key insight behind BADGR is that by autonomously learning from experience directly in the real world, BADGR can learn about navigational affordances, improve as it gathers more data, and generalize to unseen environments."
From IEEE Spectrum
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found