BADGR successfully reached its goal while avoiding collisions and bumpy terrain, unlike a geometry-based policy. Source: Greg Kahn, BAIR
A geometric approach to mobile robot navigation and obstacle avoidance may be sufficient for environments such as warehouses, but it might not be enough for dynamic settings outdoors. Researchers at the University of California, Berkeley, said they have developed BADGR, “an end-to-end, learning-based mobile robot navigation system that can be trained with self-supervised, off-policy data gathered in real-world environments, without any simulation or human supervision.”
The post BADGR mobile robot learns to navigate on its own appeared first on The Robot Report.
Article From: "Eugene Demaitre" Read full article »
Hire with PACE
The PACE robotics team specializes in placement for robotics, autonomous systems and industrial automation. Contact us today and let PACE find the talent to take your organization to the next level.
Talented Engineers Wanted
PACE aligns elite companies with the best and brightest, and we are always finding new opportunities for technical talent in Boston, Massachusetts, and New England. Submit your resume and let PACE start working for you.
