Robot Fish Powered by Synthetic Blood Just Keeps Swimming

A liquid battery that doubles as hydraulic fluid helps this robot swim for up to 36 hours Living things are stupendously complicated, and when we make robots (even bio-inspired robots), we mostly just try and do the best we can to match the functionality of animals, rather than the details of their structure. One exception to this is hydraulic robots, which operate on the same principle as spiders do, by pumping pressurized fluid around to move limbs. This is more of a side effect than actual bio-inspiration, though, as spiders still beat robots in that they use their blood as both a hydraulic fluid and to do everything else that blood does, like transporting nutrients and oxygen where it’s needed. In a paper published in Nature this week, researchers from Cornell and the University of Pennsylvania are presenting a robotic fish that uses synthetic blood pumped through an artificial circulatory Continue reading Robot Fish Powered by Synthetic Blood Just Keeps Swimming

From one brain scan, more information for medical artificial intelligence

MIT researchers have devised a novel method to glean more information from images used to train machine-learning models, including those that can analyze medical scans to help diagnose and treat brain conditions. An active new area in medicine involves training deep-learning models to detect structural patterns in brain scans associated with neurological diseases and disorders, such as Alzheimer’s disease and multiple sclerosis. But collecting the training data is laborious: All anatomical structures in each scan must be separately outlined or hand-labeled by neurological experts. And, in some cases, such as for rare brain conditions in children, only a few scans may be available in the first place. In a paper presented at the recent Conference on Computer Vision and Pattern Recognition, the MIT researchers describe a system that uses a single labeled scan, along with unlabeled scans, to automatically synthesize a massive dataset of distinct training examples. The dataset can Continue reading From one brain scan, more information for medical artificial intelligence