Aircraft-carrier crew use a set of standard hand gestures to guide planes on the carrier deck. But as robot planes are increasingly used for routine air missions, researchers at Massachusetts Institute of Technology are working on a system that would enable them to follow the same types of gestures.
Robots could one day navigate through constantly changing surroundings with virtually no input from humans, thanks to a system developed at the Massachusetts Institute of Technology that allows them to build and continuously update a 3D map of their environment using a low-cost camera such as Microsoft's Kinect.
Givaudan has turned to researchers in the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory (CSAIL) for help analyzing taste-test results. To analyze taste-test results, the CSAIL researchers are using genetic programming, in which mathematical models compete with each other to fit the available data and then cross-pollinate to produce models that are more accurate.
A group of Massachusetts Institute of Technology researchers have developed a new algorithm that, in a large range of practically important cases, improves on the fast Fourier transform—an algorithm that was devised in the mid-1960s that made it practical to calculate Fourier transforms on the fly. Under some circumstances, the improvement can be dramatic—a tenfold increase in speed.
A new technique, developed by researchers at the Massachusetts Institute of Technology, for finding relationships between variables in large datasets makes no prior assumptions about what those relationships might be.
Designers of mobile devices need to think hard about which functions to implement in hardware and which in software. A new programming language, developed at the Massachusetts Institute of Technology, makes that much easier.
Kilobots scuttle around autonomously on three toothpick-like legs, but their real power is the ability to coordinate behavior and swarm with other Kilobots. Created by engineers at Harvard University, the quarter-sized bots have been licensed by a Swiss manufacturer, allowing researchers and robotics enthusiasts to build their own swarms.
In an effort to show that Asimo is more than a toy-like showcase for the Honda Motor Co. brand, the company recently demonstrated a revamped robot that can run faster, balance itself, hop on one foot, and pour a drink. It may even help with clean-up at the damaged Fukushima nuclear plant.
Since the 1970s, when early autonomous underwater vehicles (AUVs) were developed at the Massachusetts Institute of Technology, scientists there have tackled various barriers to the design of robots that can travel autonomously in the deep ocean. Part two of the four-part series examines how advanced mathematical techniques enable AUVs to survey large, complex, and cluttered seascapes.
Since the 1970s, when early autonomous underwater vehicles (AUVs) were developed at the Massachusetts Institute of Technology (MIT), Institute scientists have tackled various barriers to robots that can travel autonomously in the deep ocean. This four-part series examines current MIT efforts to refine AUVs’ artificial intelligence, navigation, stability, and tenacity.
John McCarthy, a pioneer in artificial intelligence technology and creator of the computer programming language often used in that field, died this week at age 84. He was a leader in the field, coining the term in a 1955 research proposal and going on to create influential laboratories at both Stanford University and Massachusetts Institute of Technology.
First it was chess. Then it was Jeopardy. Now computers are at it again, but this time they are trying to automate the scientific process itself. An interdisciplinary team of scientists at Vanderbilt University, Cornell University, and CFD Research Corporation Inc., has taken a major step toward this goal by demonstrating that a computer can analyze raw experimental data from a biological system and derive the basic mathematical equations that describe the way the system operates.
Robots for everyone. That's James McLurkin's dream, and as the director of a Rice University robotics laboratory, he's creating an inexpensive and sophisticated robot called the "R-one" to make the dream a reality.
Since 2000, R&D Magazine has annually honored an individual whose research has greatly contributed to the advance of high technology, and whose achievements have helped change society. In 2011, for the first time, the editors recognize the teamwork involved in making possible the most advanced computer-supported intelligence system yet: Watson.
University of Texas at Austin researchers have discovered how to extract and use information in an individual image to determine how far objects are from the focus distance, a feat only accomplished by human and animal visual systems until now.
By combining two innovative algorithms developed at the Massachusetts Institute of Technology, researchers have built a new robotic motion-planning system that calculates much more efficient trajectories through free space. This will allow robots to execute tasks more efficiently and move more predictably.
University of Exeter engineers have pioneered new methods for detecting leaky pipes and identifying flood risks with technologies normally used for computer game graphics and artificial intelligence. These techniques could help to identify water supply and flooding problems more quickly than ever before, potentially saving people from the traumatic experience of flooding or not having water on tap.
Ground controllers turned Robonaut on Monday for the first time since it was delivered to the International Space Station in February. The test involved sending power to all of Robonaut's systems. The robot was not commanded to move; that will happen next week. It is, however, tweeting now.
Computer scientists in the field of artificial intelligence have made an important advance that blends computer vision, machine learning, and automated planning, and created a new system that may improve everything from factory efficiency to airport operation or nursing care. It is based on watching football.
Today, IBM researchers unveiled the company’s first neurosynaptic computing chips, which are designed to emulate the phenomena between spiking neurons and synapses in biological systems, such as the brain, through advanced algorithms and silicon circuitry.
A robot in a University of Michigan lab can run like a human—a feat that represents the height of agility and efficiency for a two-legged machine. With a peak pace of 6.8 miles per hour, MABEL is believed to be the world's fastest bipedal robot with knees.
The editors of R&D Magazine have opened the nominations for the 2012 R&D 100 Awards competition, which will celebrate the 50th anniversary of the awards. If your organization introduced a new product this year, or is planning to, you can begin the entry process now.
Researchers at Caltech have taken a major step toward creating artificial intelligence—not in a robot or a silicon chip, but in a test tube. The researchers are the first to have made an artificial neural network out of DNA, creating a circuit of interacting molecules that can recall memories based on incomplete patterns, just as a brain can.
In a nod to Sandia National Laboratories' contributions to the field of robotics, the Smithsonian Institution has obtained nine of Sandia's historically significant robots for its permanent collection at the National Museum of American History.
Researchers at the Stanford School of Engineering have made a nanoelectronic synapse that might drive a new class of microchips that can learn, adapt, and make probability-based decisions in complex environments. The device emulates synaptic plasticity using phase-change material, and makes a leap past two-state transistors by demonstrating the ability to convey at least 100 values from each synapse.