Pour a robot a glass of water, and you quench its thirst for a day. But teach a robot to pour a cup of water and you are somewhere on par with researchers at Tokyo Institute of Technology’s Hasegawa Group. Roboticists and software engineers there have implemented a kind of self-replicating neural technology into their robot that enables it not only to perform tasks but also to learn as it goes, integrating prior knowledge into new tasks and environments.
Well, we’ve seen this movie before (literally speaking). A group of robotics engineers at the University of Technology in Eindhoven are developing an Internet for robots; a kind of online database from which robots can download instructions and to which they can upload “experience.” According to its creators, their RoboEarth system will allow robots to share information and learn from each other, allowing the benefits of machine cognition and learning to proliferate through a network of bots. Cue the SkyNet comparisons.
Artificial intelligence has long been the overarching vision of computing, always the goal but never within reach. But using memristors from HP and steady funding from DARPA, computer scientists at Boston University are on a quest to build the electronic analog to a human brain. The software they are developing – called MoNETA for Modular Neural Exploring Traveling Agent – should be able to function more like a mammalian brain than a conventional computer.