The Kynix Blog - Robots

Has your child swallowed a small battery? In the future, a tiny robot made from pig gut could capture it and expel it.Researchers at the Massachusetts Institute of Technology are designing an ingestible robot that could patch wounds, deliver medicine or dislodge a foreign object. They call their experiment an "origami robot" because the accordion-shaped gadget gets folded up and frozen into an ice capsule."You swallow the robot, and when it gets to your stomach the ice melts and the robot unfolds," said Daniela Rus, a professor who directs MIT's Computer Science and Artificial Intelligence Laboratory. "Then, we can direct it to a very precise location."It's still a long way before the device can be deployed in a human or animal. In the meantime, the researchers have created an artificial stomach made of silicone to test it.Rus said one of the robot's most important missions could be to save the lives of children who swallow the disc-shaped button batteries that increasingly power electronic devices. If swallowed, the battery can quickly burn through the stomach lining and be fatal.The robots could seek out and capture the battery before it causes too much damage, pushing it down through the gastrointestinal tract and out of the body.The robot's flexible frame is biodegradable, made of the same dried pig intestine used for sausage casing. The researchers scoured markets in Boston's Chinatown before finding the right material to build an agile robot body that could dissolve once its mission was accomplished."They tried rice paper and sugar paper and hydrogel paper, all sorts of different materials," Rus said. "We found that sausage casing has the best properties when it comes to folding and unfolding and controllability."Embedded in its meaty body—it wouldn't be hard to make a kosher version, Rus said—is a neodymium magnet that looks like a tiny metal cube.Magnetic forces control its movement. Researchers use remote-control joysticks to change the magnetic field, allowing the robot to slip and crawl through the stomach on the way to the object it is trying to retrieve or the wound where it must deliver drugs.Would it hurt to ingest a robot? Probably not, said research team member Steven Guitron, an MIT graduate student in mechanical engineering."I'm sure if you swallowed an ice cube accidently, it's very similar," he said.MIT's team has a patent pending and presented its research at a robotics conference in Sweden this spring. Rus said medical companies have expressed interest in clinical applications, which require going through the regulatory process of conducting animal and human studies."It's a nifty idea," but it could be a decade or so before hospitals could use such a device, said William Messner, a professor of mechanical engineering at Tufts University in Massachusetts who is not involved with the project. He said it could also have promise in performing biopsies.The U.S. Food and Drug Administration "has to get involved with anything like this and they're rightfully very careful about any kind of medical instrument," Messner said. "The big problem is: What if it gets stuck? Now you've really got a problem."The multidisciplinary project fits into the growing field of soft robotics that coalesced with the 2013 founding of the peer-reviewed Soft Robotics Journal, based at Tufts. The Boston region is a hub for research into the moving machines made of flexible materials that can change shape and size, making them useful for surgery and other complex environments.   

 Inside a secretive AI nonprofit backed by Elon Musk and other Silicon Valley figures, a handful of robots designed to help out in warehouses are gradually learning how to do useful household chores.OpenAI, which was created to do basic AI research, is reprogramming robots developed by Fetch Robotics, a company that supplies warehouse automation hardware. Researchers at OpenAI are equipping the robots with software that lets them train themselves through trial and error.The effort reflects a bet that innovations in software and machine learning, rather than breakthroughs in hardware, are the way to give robotics remarkable new capabilities. Fetch makes a range of robots for warehouses, including systems that follow workers around a building, carrying items dropped into a basket. OpenAI is using a system that features a mobile base but also 3-D depth sensors, a 2-D laser scanner, and a robotic arm with seven degrees of freedom.In April, OpenAI recruited Pieter Abbeel, a professor at the University of California, Berkeley, and a leading expert on robot learning. Abbeel has shown how robots can use a machine-learning approach called deep reinforcement learning to acquire completely new skills that would be hard to program by hand, such as folding towels or retrieving items from a refrigerator. Google DeepMind, an AI subsidiary based in the U.K., uses this technique to get computers to play computer games at a superhuman level.Abbeel’s robots learn tasks from scratch, using a neural network that receives sensor input and controls physical movement. The network adjusts its parameters automatically as it inches closer to its goal. A robot might try thousands of grips, for instance, in the process of learning how to hold a certain object.“If this goal can be achieved, then there will be economic and industrial benefits,” says Marc Deisenroth, an expert on reinforcement learning at Imperial College London. “Imagine a Roomba not only cleaning your floor but also doing the dishes, ironing the shirts, cleaning the windows, preparing breakfast.”Deisenroth says using off-the-shelf robots could drive costs down. “Currently, the software seems to be the bottleneck,” he adds. “However, independent of this, better hardware could also lead to substantial improvements.” Soft manipulators and elastic feet similar to a monkey’s feet are concepts that researchers have started working on, he says.Some manufacturers, including the Japanese company Fanuc, are testing reinforcement learning as a way to train industrial robots quickly in new tasks such as learning to grasp unfamiliar objects. When many robots work in parallel, the training time required is reduced accordingly . Robot researchers at Google are testing similar learning techniques.“Moving away from having to program robots by hand by endowing robots to learn autonomously is a key element for the future of robotics,” says Jens Kober, an expert on robot learning at Delft University of Technology in the Netherlands. Kober says having robots share the information they have learned will be crucial.While robots such as those made by Fetch are finding their way into many factories and warehouses, domestic robot helpers remain the stuff of science fiction. Performing seemingly simple tasks like washing dishes or folding laundry in a messy home setting is incredibly hard for a machine. A robot programmed the conventional way can easily be thrown off by an unfamiliar object or a slight variation in lighting.OpenAI confirmed that it is working with the robots from Fetch, but it declined to comment further. Melonee Wise, the company’s founder, couldn’t be reached for comment.OpenAI was created by Musk and a handful of well-known (and well-heeled) Silicon Valley entrepreneurs, including investor Peter Thiel, Y Combinator president Sam Altman, and the incubator’s cofounder Jessica Livingston. The nonprofit’s backers have committed $1 billion in funding to the project, and it is being led by Ilya Sutskever, a prominent AI researcher who left Google to join the project, and Greg Brockman, an early employee at the high-profile digital payment company Stripe.While OpenAI has committed to making the technology it develops publicly available, it could certainly benefit companies backed by Musk and Thiel, as well as those emerging from Y Combinator.Produced by Will Knight