AssetID: 53318588
Headline: RAW VIDEO: Scientists Create AI That Can Solve Physical Marble Labyrinth In Record Time
Caption: Scientists at the ETH Zurich in Switzerland university have created an AI robot, CyberRunner, that is capable of guiding a marble through a labyrinth in record time. The labyrinth marble game is traditionally seen as a domain of human expertise as it requires subtle physical skills and intuition for a person, rather than the cold calculations of chess or the strategy game Go. However, even this task has now been conquered by the AI using deep reinforcement learning. Remarkably, the machine cost under $200 - raising hopes of the research being widely replicable for those looking to build on it. “We believe that this is the ideal testbed for research in real-world machine learning and AI,” said lead researcher Prof. Raffaello D’Andrea. “Prior to CyberRunner, only organizations with large budgets and custom-made experimental infrastructure could perform research in this area. “Now, for less than $200, anyone can engage in cutting-edge AI research, as applied to the physical world. Furthermore, once thousands of CyberRunners are out in the real-world, it will be possible to engage in large-scale experiments, where learning happens in parallel, on a global scale. The ultimate in Citizen Science!” The CyberRunner learns through experience, capturing observations and receiving rewards based on its game performance. The robot employs two knobs to control the orientation of the labyrinth board, demonstrating fine motor skills and spatial reasoning. The model-based reinforcement learning algorithm continuously refines its strategy and behaviour, with learning taking place concurrently while the robot plays the game. Remarkably, CyberRunner completed the learning process on the real-world labyrinth in just 6.06 hours, outperforming the fastest recorded time by a skilled human player by over 6%. During the learning phase, the AI robot did something even more interesting - it discovered shortcuts, prompting researchers to intervene and instruct it not to cheat by exploiting these. D’Andrea and fellow lead researcher Thomas Bi hope their creation will spark a surge in AI research, given its low cost. The research paper is available on the project's website, www.CyberRunner.ai.
Keywords: ETH Zurich,feature,photo,video,robots,ai,artificial intelligence,news,science
PersonInImage: