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
- Robot chef uses machine learning to perfect its omelette-making skillson June 2, 2020 at 11:57 pm
From robots that flip burgers in California to ones that serve up bratwursts in Berlin, we are starting to see how machines can play sous-chef in kitchens around the world. But scientists at the ...
- GE Appliances Deploys Autonomous Mobile Robotson June 2, 2020 at 3:54 pm
GE Appliances implemented of autonomous mobile robots (AMRs) from Agilox. AMRs lend themselves to low cost pilots. After a successful pilot, GE Appliances is scaling their use of this technology.
- American workers fear losing job to robotson June 2, 2020 at 3:05 pm
A quarter of U.S. workers fear they will lose their jobs to robots that can do tasks previously performed by humans.
- Spin-Off Company Teases Unannounced Robotics for Policeon June 2, 2020 at 11:12 am
Company Six’s founders are mum on details, but they say they’re making advanced technology more affordable and user-friendly, and giving officers more information to make decisions.
- Service Robotics Market Industry Size, Growth Factors and Major Segments, Forecast Research Reporton June 2, 2020 at 8:41 am
The overall service robotics market is expected to grow from USD 11.25 Billion in 2018 to USD 46.13 Billion by 2026 at ...
- Watch a robot make a prettier omelet than you canon June 1, 2020 at 12:07 pm
That's why I'm ready to welcome a robot cooking overlord into my kitchen to handle breakfast duties. I just need to go to the University of Cambridge in the UK and beg them to give me their robot.
- A good egg: Robot chef trained to make omeletteson June 1, 2020 at 8:43 am
A team of engineers have trained a robot to prepare an omelette, all the way from cracking the eggs to plating the finished dish, and refined the 'chef's' culinary skills to produce a reliable dish ...
- Demand for Enterprise Robots Drives Momentum in the Robotic Components Market as Automation and Artificial Intelligence Propel Revenue to $126.3 Billion by 2025, According to Omdiaon June 1, 2020 at 5:27 am
Demand for robotic components will grow rapidly as more companies realize the benefits of automation, robots, and cobots and increase adoption rates ...
- MIT gives soft robots a better sense of touch and spatial awarenesson June 1, 2020 at 5:10 am
In order to do that, they need tactile sensing and proprioception -- an awareness of where they are in space. This kind of sensing has been absent in most soft robots, but now two teams from MIT have ...
- Robots Writing The News: Why Not?on May 31, 2020 at 4:59 am
Microsoft has laid off 27 journalists tasked with writing MSN News, outsourced to PA Media, and replaced them with a series of machine learning algorithms. I wonder if anybody will notice.
via Bing News