You are here
Researchers have developed algorithms that enable robots to learn motor tasks through trial and error using a process that more closely approximates the way humans learn, marking a major milestone in the field of artificial intelligence.
Through a clinical collaboration between Caltech, Keck Medicine of USC and Rancho Los Amigos National Rehabilitation Center, a 34-year-old paralyzed man is the first person in the world to have a neural prosthetic device implanted in a region of the brain where intentions are made, giving him the ability to perform a fluid hand-shaking gesture, drink a beverage, and even play 'rock, paper, scissors,' using a robotic arm.
Engineers have developed an ultracompact beamsplitter -- the smallest on record -- for dividing light waves into two separate channels of information. The device brings researchers closer to producing silicon photonic chips that compute and shuttle data with light instead of electrons.
A wearable FES-robot hybrid training system has been designed for multi-joint upper limb rehabilitation. With successful combination of the two technologies' advantages, recovery achieved by the hybrid system was more prominent than using either technology alone in pilot clinical trials.
A novel computer-aided detection system has been developed for acute stroke using computer intelligence technology. The detection accuracy is 90 percent, which is as high as that conducted by specialists, but at a much reduced time from 10-15 minutes to three minutes. The new system serves as a second opinion for frontline medical doctors, enabling timely and appropriate treatment for stroke patients.
New theories on game intelligence could change the world of team sports forever. Game intelligence is not necessarily something you are born with but something you can learn, according to new research.
Medical researchers have developed a novel computer-aided detection system for acute stroke using computer intelligence technology. The detection accuracy is 90%, which is as high as that conducted by specialists, but at a much reduced time from 10-15 minutes to 3 minutes.
When ants go exploring in search of food they end up choosing collective routes that fit statistical distributions of probability. This has been demonstrated by a team of mathematicians after analyzing the trails of a species of Argentine ant. Studies like this could be applied to coordinate the movement of micro-robots in cleaning contaminated areas for example.
Using a smart tablet and a red beam of light, researchers have created a system that allows people to control a fleet of robots with the swipe of a finger.
A circuit implementing the rudimentary artificial neural network successfully classified three letters by their images.
Researchers have successfully demonstrated pattern recognition using a magnonic holographic memory device, a development that could greatly improve speech and image recognition hardware.
Robotic dogs are likely to replace the real thing in households worldwide in as little as a decade, as our infatuation with technology grows and more people migrate to high-density city living.
Object recognition -- determining what objects are where in a digital image -- is a central research topic in computer vision. Researchers have now demonstrated that, en route to learning how to recognize scenes, a new computer system also learned how to recognize objects.
For the last decade, scientists have deployed increasingly capable underwater robots to map and monitor pockets of the ocean to track the health of fisheries, and survey marine habitats and species. In general, such robots are effective at carrying out low-level tasks, specifically assigned to them by human engineers -- a tedious and time-consuming process for the engineers. Now a new programming approach gives robots more "cognitive" capabilities, enabling humans to specify high-level goals, while a robot performs high-level decision-making to figure out how to achieve these goals.
How safe is that robot doing your surgery? Researchers easily hacked a next generation teleoperated surgical robot to test how easily a malicious attack could hijack remotely-controlled operations in the future and to offer security solutions.
What if a new material would allow for development of a 'soft robot' that could reconfigure its own shape and move using its own internally generated power?
Computer scientists have combined sophisticated computer vision algorithms and a brain-computer interface to find mines in sonar images of the ocean floor. The study shows that the new method speeds detection up considerably, when compared to existing methods -- mainly visual inspection by a mine detection expert.
In a rolling, outdoor field, full of lumps, bumps and uneven terrain, researchers have successfully field-tested for the first time the locomotion abilities of a two-legged robot with technology that they believe heralds the running robots of the future.
Most people are naturally adept at reading facial expressions -- from smiling and frowning to brow-furrowing and eye-rolling -- to tell what others are feeling. Now scientists have developed ultra-sensitive, wearable sensors that can do the same thing. Their technology could help robot developers make their machines more human.
How is it possible to create computer memory that is both faster and consumes less energy? Researchers have unlocked the physical mechanisms involved in new-generation magnetic memory, and have shown that these mechanisms could be used as "synapses" in a new type of neuro-inspired system, able to learn how to store and retrieve information.