Vous êtes ici
Agrégateur de flux
A mechanical engineer and his team have developed a computer-controlled camera that enables their robotic ankle to see where it is going.
Researchers have come up with a more accurate way than currently possible to train computers to be able to digest data that comes in the form of images and extract the emotions they convey.
People typically consider doing the laundry to be a boring chore. But laundry is far from boring for artificial intelligence researchers. To AI experts, programming a robot to do the laundry represents a challenging planning problem because current sensing and manipulation technology is not good enough to identify precisely the number of clothing pieces that are in a pile and the number that are picked up with each grasp. People can easily cope with this type of uncertainty and come up with a simple plan. But roboticists for decades have struggled to design an autonomous system able to do what we do so casually--clean our clothes.
Researchers have developed a prototype of a social robot which supports independent living for the elderly, working in partnership with their relatives or carers.
Scientists have developed an octopus-like robot, which can zoom through water with ultra-fast propulsion and acceleration never before seen in human-made underwater vehicles. Most fast aquatic animals are sleek and slender to help them move easily through the water but cephalopods, such as the octopus, are capable of high-speed escapes by filling their bodies with water and then quickly expelling it to dart away. Inspired by this, scientists built a deformable octopus-like robot with a 3D printed skeleton with no moving parts and no energy storage device, other than a thin elastic outer hull.
For decades, researchers in artificial intelligence, or AI, worked on specialized problems, developing theoretical concepts and workable algorithms for various aspects of the field. Computer vision, planning and reasoning experts all struggled independently in areas that many thought would be easy to solve, but which proved incredibly difficult.
Eve, an artificially intelligent 'robot scientist' could make drug discovery faster and much cheaper, say researchers writing in the Royal Society journal Interface. The team has demonstrated the success of the approach as Eve discovered that a compound shown to have anti-cancer properties might also be used in the fight against malaria.
Computers are able to use monkey facial patterns not only to correctly identify species, but also distinguish individuals within species, a team of scientists has found. Their findings, which rely on computer algorithms to identify guenon monkeys, suggest that machine learning can be a tool in studying evolution and help to identify the factors that have led to facial differentiation in monkey evolution.
Little animations trying to master a computer game are teaching neuroscience researchers how the brain evolves when faced with difficult tasks. Neuroscientists have programmed animated critters that they call 'animats.' The critters have a rudimentary neural system made of eight nodes: two sensors, two motors, and four internal computers that coordinate sensation, movement and memory.
An innovative approach to turn any computer or smartphone with a camera into a personal mental health monitoring device has been created by researchers. The computer program can analyze "selfie" videos recorded by a webcam as the person engages with social media, to extract a number of "clues," such as heart rate, blinking rate, eye pupil radius, and head movement rate.
Agricultural researchers and computer scientists are working on the development of an unmanned robot, equipped with non-invasive advanced sensors and artificial intelligence systems, which will help manage vineyards. This robot will provide reliable, fast and objective information on the state of the vineyards to grapegrowers, such as vegetative development, water status, production and grape composition.
The interactions of cancer cells may be explained by using game theory. The Public Goods Game is part of game theory and is used in economics as a model to analyze the provision of common goods. There is an imbalance in the consumption of these goods between those that provide them and pay the production costs and those that do not pay but consume anyway -- a situation that is known in economics as the free rider problem. The researchers now applied this model to the cooperation between producing and non-producing members of a cancer cell population, in order to examine if the model is also applicable to biological processes, such as carcinogenesis.
NASA and Microsoft have teamed up to develop software called OnSight, a new technology that will enable scientists to work virtually on Mars using wearable technology called Microsoft HoloLens.
Optimizing optimization algorithms: Getting best results when approximating solutions to complex engineering problems
Optimization algorithms, which try to find the minimum values of mathematical functions, are everywhere in engineering. Among other things, they're used to evaluate design tradeoffs, to assess control systems, and to find patterns in data. Scientists have come up with a way to generate a sequence of simplified functions that guarantees the best approximation that the method can offer.
Often enough, it is human nature to conform. This tendency makes us follow the lead of computers, even if the machines give us the wrong advice. This is the finding of a study that investigates how people make judgment calls after playing role-playing video games. Real-life encounters and face-to-face contact with other people are on the decline in a world that is becoming increasingly computerized. Many routine tasks are delegated to virtual characters. People spend hours role-playing through virtual-reality video games by taking on the persona of a virtual character or avatar.
Robotic systems that are able to teach themselves have been developed by researchers. Specifically, these robots are able to learn the intricate grasping and manipulation movements required for cooking by watching online cooking videos. The key breakthrough is that the robots can 'think' for themselves, determining the best combination of observed motions that will allow them to efficiently accomplish a given task.
For household robots ever to be practical, they'll need to be able to recognize the objects they're supposed to manipulate. But while object recognition is one of the most widely studied topics in artificial intelligence, even the best object detectors still fail much of the time. A new algorithm could enable household robots to better identify objects in cluttered environments.
For over a half-century, games have been test beds for new ideas in Artificial Intelligence and the resulting successes have marked significant milestones: Deep Blue defeated Kasparov in chess, and Watson defeated Jennings and Rutter on Jeopardy! However, defeating top human players is not the same as actually solving a game, and for the first time researchers have essentially solved heads-up limit hold 'em poker.
Researchers are closer to creating underwater robotic creatures with a brain of their own -- besides behaving like the real thing. In the near future, it would not be too tall an order for the team to produce a swarm of autonomous tiny robotic sea turtles and fishes for example, to perform hazardous missions such as detecting nuclear wastes underwater or other tasks too dangerous for humans.
For decades, neuroscientists have been trying to design computer networks that can mimic visual skills such as recognizing objects, which the human brain does very accurately and quickly. Until now, no computer model has been able to match the primate brain at visual object recognition during a brief glance. Now neuroscientists have found that one of the latest generation of 'deep neural networks' matches the primate brain.