Algorithm lets independent agents collectively produce a machine-learning model without aggregating data.
Machine learning, in which computers learn new skills by looking for patterns in training data, is the basis of most recent advances in artificial intelligence, from voice-recognition systems to self-parking cars. It’s also the technique that autonomous robots typically use to build models of their environments.
That type of model-building gets complicated, however, in cases in which clusters of robots work as teams. The robots may have gathered information that, collectively, would produce a good model but which, individually, is almost useless. If constraints on power, communication, or computation mean that the robots can’t pool their data at one location, how can they collectively build a model?
At the Uncertainty in Artificial Intelligence conference in July, researchers from MIT’s Laboratory for Information and Decision Systems will answer that question. They present an algorithm in which distributed agents — such as robots exploring a building — collect data and analyze it independently. Pairs of agents, such as robots passing each other in the hall, then exchange analyses.
In experiments involving several different data sets, the researchers’ distributed algorithm actually outperformed a standard algorithm that works on data aggregated at a single location.
The Latest on: Robot learning
via Google News
The Latest on: Robot learning
- Meet 13 robotics startups in Denmark’s Beyond Betaon May 23, 2022 at 9:29 am
The startups will receive coaching and mentoring from robotics experts and exposure through Odense Robotics during the Beyond Beta program.
- Love, Death and Robots: Vol. 3 Reviewon May 23, 2022 at 9:21 am
Love, Death and Robots Vol. 3 is available now on Netflix. Netflix’s ongoing animation anthology Love, Death and Robots returns for a third volume of brand-new shorts with the unofficial mandate of ...
- FogROS brings robotic cloud computing to the Robot Operating Systemon May 23, 2022 at 8:03 am
On a recent trip to the Bay Area, I took a few hours to pay a visit to Berkeley Artificial Intelligence Research Lab (BAIR). Professor Ken Goldberg walked me around the lab and introduced me to a ...
- Can Robots Learn Law? Scientists and Theologians Discuss the Future of AIon May 23, 2022 at 6:17 am
The conference was organized in three parts around the concepts of expressing, defining, and understanding intelligence.
- Love, Death & Robots Season 3 Features A Sequelon May 22, 2022 at 3:45 pm
Love, Death & Robots' third season kicks off with a sequel to the popular episode "Three Robots." Here's what the robots have been up to.
- BHS robotics team showcases workon May 22, 2022 at 9:26 am
This year was the second time in the team’s 15-year history that students made it to state, placing 31st and learning valuable lessons along the way. Students on the Warriors robotics team spent the ...
- New deep learning technique paves path to pizza-making robotson May 22, 2022 at 7:00 am
A new deep learning technique developed by researchers shows promise to make robotics systems more stable in handling deformable objects.
- Primrose Schools® Introduces New Junior Robotics Challenge To Engage Children In STEM-Based Learning'on May 18, 2022 at 9:39 am
New 'Ready, Set, Robotics!' curriculum further integrates STEM learning and strengthens social-emotional competenciesATLANTA, May 18, 2022 ...
- Researchers design 'socially aware' robots that can anticipate and safely avoid people on the moveon May 18, 2022 at 8:14 am
A team of researchers led by University of Toronto Professor Tim Barfoot is using a new strategy that allows robots to avoid colliding with people by predicting the future locations of dynamic ...
- Robots coded for fun and learning in the Mountain Stateon May 16, 2022 at 9:01 pm
Angelo Ferrell, in effect, was biting the hand that fed him Monday morning. Or the toes that taught him. Something like that, anyway. At least his instructor was amused. "Look at this, " Rebecca ...
via Bing News