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.
Read more . . .
The Latest on: Robot learning
[google_news title=”” keyword=”Robot learning” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Robot learning
- Underwater cleaning robots. Ultraviolet disinfectant. Accelerator boosts NJ tech startupson April 30, 2024 at 2:01 pm
Underwater cleaning robots. Ultraviolet disinfectant ... compressing years’ worth of learning-by-doing into just a few months,” said Ian Hathaway in a 2016 Harvard Business Review article. HAX, a ...
- Trotting robots reveal emergence of animal gait transitionson April 30, 2024 at 6:23 am
A four-legged robot trained with machine learning by EPFL researchers has learned to avoid falls by spontaneously switching between walking, trotting, and pronking—a milestone for roboticists as well ...
- MIT Technology Reviewon April 30, 2024 at 2:00 am
AI is upending the way robots learn, leaving companies and researchers with a need for more data. Getting it means wrestling with a host of ethical and legal questions.
- Watch Boston Dynamics’ dog-like robot don a dog suit and danceon April 29, 2024 at 11:15 pm
To mark International Dance Day, Boston Dynamics has shared a video showing its Spot robot dressed as a dog and pulling some moves.The Latest Tech News, Delivered to Your Inbox ...
- FDA-approved surgical robots trend toward autonomy, study findson April 29, 2024 at 6:24 pm
A systematic review in npj Digital Medicine categorizes FDA-approved surgical robots by their levels of autonomy, highlighting a need for standardized definitions and greater regulatory clarity as ...
- Researchers use ChatGPT for choreographies with flying robotson April 29, 2024 at 11:57 am
Prof. Angela Schoellig from the Technical University of Munich (TUM) uses ChatGPT to develop choreographies for swarms of drones to perform along to music. An additional safety filter prevents mid-air ...
- This is the first humanoid electric robot that can run at 6km/hon April 29, 2024 at 4:34 am
China has recently unveiled the first ever fully electric humanoid robot called 'Tiangong' which is capable of running at a speed of 6 km/hr.
- Humanoid robots are learning to fall wellon April 28, 2024 at 1:15 pm
The savvy marketers at Boston Dynamics produced two major robotics news cycles last week. As I write this, the sub-40 second video is steadily approaching five million views. The accompanying video ...
- Europe taps deep learning to make industrial robots safer colleagueson April 26, 2024 at 1:07 am
European researchers have launched the RoboSAPIENS project to make adaptive industrial robots more efficient and safer to work with humans.
- Sanctuary’s new humanoid robot learns faster and costs lesson April 24, 2024 at 5:00 pm
While “general intelligence” is one of those big, abstract terms, the consensus among many roboticists is that we’re still five-10 years out from robots that are capable of learning new tasks in a ...
via Bing News