首页|Investigators at Imperial College London Report Findings in Robotics (A Robot We b for Distributed Many-device Localization)

Investigators at Imperial College London Report Findings in Robotics (A Robot We b for Distributed Many-device Localization)

扫码查看
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Robotics is the subjec t of a report. According to news reporting out of London, United Kingdom, by New sRx editors, research stated, "We show that a distributed network of robots or o ther devices which make measurements of each other can collaborate to globally l ocalize via efficient ad hoc peer-to-peer communication. Our Robot Web solution is based on Gaussian belief propagation £ on the fundamental nonlinear factor gr aph describing the probabilistic structure of all of the observations robots mak e internally or of each other, and is flexible for any type of robot, motion or sensor." Financial support for this research came from Engineering & Physic al Sciences Research Council (EPSRC). Our news journalists obtained a quote from the research from Imperial College Lo ndon, "We define a simple and efficient communication protocol which can be impl emented by the publishing and reading of web pages or other asynchronous communi cation technologies. We show in simulations with up to 1000 robots interacting i n arbitrary patterns that our solution convergently achieves global accuracy as accurate as a centralized nonlinear factor graph solver while operating with hig h distributed efficiency of computation and communication. Via the use of robust factors in GBP, our method is tolerant to a high percentage of faulty sensor me asurements or dropped communication packets."

LondonUnited KingdomEuropeEmerging TechnologiesMachine LearningNano-robotRobotRoboticsImperial College L ondon

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Apr.1)