If robots are going to work alongside humans, the machines are going to need to swallow their pride and learn to ask for help. At least, that’s the thinking of computer scientists at the University of Washington (UW), who are working on ways for robots to crowdsource their problems when learning new tasks. If successful, this approach points the way toward future robots that are capable of asking for assistance to speed up their learning when it comes to figuring out how to carry out household tasks... Continue Reading Crowdsourcing could help robots learn new tasks faster
Section: Robotics
Tags: Crowdsource, Learning, Robotics, Robots, University of Washington
Related Articles:
Cross training helps humans and robots work better together
Who needs humans? Computers used to teach other computers
Teaching robots new tricks without programming
RoboEarth "Wikipedia for robots" demonstrated
Teaching robots to think like people
No comments:
Post a Comment
Rules for submitting comments:
1. No profanity. I maintain the pretense that this is a family-friendly site.
2. Stay on topic. A bit of straying and off-hand commenting is okay, but hijacking the discussion is right out.
3. No ad hominem attacks. Attack the subject, not the other person on the thread and keep the discussion civil.
4. No spamming or commercial endorsements. These get deleted immediately.
Tip: Beware of putting hyperlinks in your comments–especially at the end. For some reason, Blogger interprets these as spam.
Note: Due to the recent spate of anonymous spamming, registration for comments is now required.