Posts tagged AI
Articles and news from the latest research reports.
Robot Learns to Pick the Sweetest, Ripest Strawberries
Richard Dudley imagines a world where strawberries grow in perfect rows and every day a robot army tastes their colors before harvesting the ripe ones. No, that isn’t LSD talking. The research scientist at the United Kingdom’s National Physical Laboratory is building a bot that uses multiple wavelengths of electromagnetic radiation to identify the sweetest, ripest fruit — then plucks it from the vine.
Science fiction comes to life in Italian lab
At Italy’s Sant’Anna university, a bionic arm commanded by the human brain or a limb extension that allows rescuers to lift rubble after earthquakes are just some of the futuristic innovations in the pipeline.
“The idea is to get robots out of factories where they have shown their worth and to transform them into household machines which can live together with humans,” says Professor Paolo Dario, director of the college’s bio-robotics department.
The university in the historic town of Pisa in Tuscany is a veritable factory of ideas.
Researchers here are working on projects ranging from a robot that can come to your door to collect your recycling to tomatoes that slow the effects of ageing and plants that survive underwater to help flood-prone regions of the world.
Roke Manor Research Ltd (Roke), a Chemring Group company, has developed the world’s first threat monitoring system for autonomous vehicles that emulates a mammal’s conditioned fear-response mechanism.
The STARTLE system uses a combination of artificial neural network and diagnostic expert systems to continually monitor and assess potential threats.
“Startle delivers local autonomy to a vehicle by providing a mechanism for machine situation awareness to efficiently detect and assess potential threats. This allows vehicle sensing and processing resources to be devoted to the assigned task, but if a threat is detected it will cue the other systems to deal with it swiftly before continuing its mission. These vital seconds could be the difference between mission failure and success.”
Source: Neuroscience News
Using piezoelectric materials, researchers have replicated the muscle motion of the human eye to control camera systems in a way designed to improve the operation of robots. This new muscle-like action could help make robotic tools safer and more effective for MRI-guided surgery and robotic rehabilitation.
Read more: Robot vision: Muscle-like action allows camera to mimic human eye movement
Charles Darwin and Alan Turing, in their different ways, both homed in on the same idea: the existence of competence without comprehension.
Some of the greatest, most revolutionary advances in science have been given their initial expression in attractively modest terms, with no fanfare.
Charles Darwin managed to compress his entire theory into a single summary paragraph that a layperson can readily follow.
Francis Crick and James Watson closed their epoch-making paper on the structure of DNA with a single deliciously diffident sentence. (“It has not escaped our notice that the specific pairing we have postulated immediately suggests a possible copying mechanism for the genetic material.”)
And Alan Turing created a new world of science and technology, setting the stage for solving one of the most baffling puzzles remaining to science, the mind-body problem, with an even shorter declarative sentence in the middle of his 1936 paper on computable numbers:
It is possible to invent a single machine which can be used to compute any computable sequence.
'A Perfect and Beautiful Machine': What Darwin's Theory of Evolution Reveals About Artificial Intelligence by Daniel C. Dennett