Robots get pressure sensitive skin

Robots get pressure sensitive skin

Organic field-effect transistors have been used to fabricate pressure-sensitive skin for robots, according to an abstract published in the Proceedings of the National Academy of Sciences this week.

Why is this good news? Because all of these fancy robots you’ve been reading about have wonderful machine vision and even voice recognition, but they don’t have a good sense of touch. At present, it is not possible to manufacture large area skin with thousands of silicon-based electronic pressure sensors with good mechanical flexibility. Organic field-effect transistors and rubber pressure sensors are used to create a practical artifical skin.

Child-like intelligence created in Second Life

http://itnews.com.au/News/72057,childlike-intelligence-created-in-second-life.aspx

Child-like intelligence created in Second Life

function TextLarge() { $(“maintext”).style.fontSize = “150%”; } function TextNormal() { $(“maintext”).style.fontSize = “110%”; }

By Liz Tay
Four-year-old Eddie might behave like a typical young boy. Outside of the Second Life virtual world, however, he is anything but.

The child is a product of logic-based artificial intelligence and complex modelling techniques, and operates on what has been said to be the most powerful university-based supercomputing system in the world.

A creation of researchers from Rensselaer Polytechnic Institute, Eddie has his own set of beliefs, and the ability to reason about his beliefs to draw conclusions in a manner that matches human children his age.

This includes a partially-developed “Theory of Mind”, which allows him to understand, predict and manipulate the behaviour of other agents and of even human players, with whom researchers expect the technology to be able to one day interact with in the real, physical world.

“Second Life is remarkably easy to work with, and is very popular,”
said Selmer Bringsjord, head of Rensselaer’s Cognitive Science Department and leader of the research project.

“But our technologies can be applied to any digital environment, and indeed we are specifically aiming, with IBM, at environments in which the physical and the virtual directly interact.”

Eddie is only the first step of what Bringsjord called a “divide-and-conquer” strategy of prudent engineering.

Eventually, more advanced versions of the artificial intelligence technology will be put to use in entertainment and gaming, as well as immersive training and education scenarios.

“The apps, frankly, are endless,” Bringsjord said. “Imagine being able to step into a simulation environment in which you interact with synthetic characters as sophisticated as those seen in Star Trek’s holodeck.”

“It’s one thing to read about trauma scenarios as a first responder; it would be quite another if you could enter a simulation in which, courtesy of synthetic characters at the level we seek, you could strive to get a disaster under control, with the look and feel of the real world.”

“Or imagine a hostage situation: How do you prepare for negotiating with a terrorist holding a hostage? Now, it’s textbook and playacting. But what if you could enter the holodeck and match wits with a synthetic character that has the ability to reason in earnest about your mind, and about what you’re trying to do? This is actually a demo we’re considering trying to engineer,” he said.

Currently, the team is grappling with computational tractability issues to do with the sorting of growing amounts of knowledge that is collected as a artificially intelligent character matures.

As Eddie operates entirely on formal logic and well-defined theorems, reasoning is not automatically fast, Bringsjord said, explaining the need for clever engineering and high-performance hardware.

This research is supported by IBM and other outside sponsors, and requires the use of Rensselaer’s Computational Center for Nanotechnology Innovations (CCNI), which provides more than 100 teraflops of computing power through massively parallel Blue Gene supercomputers, POWER-based Linux clusters, and AMD Opteron processor-based clusters.

ASIMO

ASIMO (アシモ, ashimo) is a humanoid robot created by Honda Motor Company. Standing at 130 centimeters (4 feet 3 inches) and weighing 54 kilograms (119 pounds), the robot resembles a small astronaut wearing a backpack and can walk or run on two feet at speeds up to 6 km/h (3.7 mph). ASIMO was created at Honda’s Research & Development Wako Fundamental Technical Research Center in Japan. It is the current model in a line of eleven that began in 1986 with E0.

Military Robots

• US Mechatronics has produced a working automated sentry gun and is currently developing it further for commercial and military use.
• MIDARS, a four-wheeled robot outfitted with several cameras, radar, and possibly a firearm, that automatically performs random or preprogrammed patrols around a military base or other government installation. It alerts a human overseer when it detects movement in unauthorized areas, or other programmed conditions. The operator can then instruct the robot to ignore the event, or take over remote control to deal with an intruder, or to get better camera views of an emergency. The robot would also regularly scan radio frequency identification tags (RFID) placed on stored inventory as it passed and report any missing items.
• US scientists at MIT are known to be “looking into building a mechanical super-fighter … able to heal his own wounds, leap buildings, deflect bullets and even become invisible” which “won’t be ready for at least 10 years.”
• Tactical Autonomous Combatant (TAC) units, described in Project Alpha study ‘Unmanned Effects: Taking the Human out of the Loop’ – TAC robots are seen as being faster and more lethal than human soldiers, and able to work in more hazardous environments. This study, which was done in 2003, saw TACs as a reality by 2025.

Defense contractors in the USA are hard at work developing autonomous “robot soldiers”, but most current models look more like tanks than humans. There are problems with threat recognition and response; some models will not shoot cows with guerillas crouched behind them, but will fire at anything stenciled with an AK – 47 silhouette.

In December 2003, the Associated Press reported that The Pentagon had purchased several Segways, as part of a research program called “Mobile Autonomous Robot Software”, an attempt to develop more advanced military robots.

The implications of mastering and using this type of technology are wide, with the possibility of advanced artificial intelligence causing unforeseen consequences (especially if weaponized machines are ever given AI on the level of sentience), the possibility of robots being hacked into and used against the owners or the possibility of simple machine breakdown leaving soldiers defenceless if robots are relied on too much.

In literature, a play published in 1921, ‘Rossum’s Universal Robots‘ by Czech writer Karel Capek, tells the story of how people built better and better robots until they finally built robots to fight wars. In the end, the robots decide that fighting is crazy, and take over the world. This idea has since become a common staple of fiction in books, films and television. Its popularity fueled the common (but principally erroneous) belief that machinery is entirely physically superior to biology.

The Shadow Hand

The Shadow Hand

Considered to be the most advanced Dextrous Hand in the world!

The Shadow Hand is the closest robot Hand to the human Hand available. It provides 24 movements, allowing a direct mapping from a human to the robot.

The Shadow Hand has integrated sensing and position control, allowing precise control from off-board computers, or integration into your existing robot platform.

The Shadow Hand contains an integrated bank of 40 Air Muscles which make it move. The muscles are compliant, which allows the Hand to be used around soft or fragile objects.

The Shadow Hand can be fitted with touch sensing on the fingertips, offering sensitivity sufficient to detect a single small coin.

 

Action Robot to Copy Human Brain

Aberystwyth University academics are working on the machine which they hope will recognise objects and retrieve them using an arm and cameras for eyes.

However, it is unclear at present what it could be used for ultimately.

Scientists said they aimed to “unravel” how a part of the brain worked and would then use that information to develop the machine.

Led by Professor Mark Lee, the team from Aberystwyth is joined by academics from six other universities on the five-year project.

Financial backing worth some £1.9m has come from the Engineering and Physical Sciences Research Council – Aberystwyth’s share is £470,000.

Most robots are programmed to make certain decisions, but are unable to think for themselves.

According to Prof Lee, the project’s purpose was to try to “unravel” the way in which the brain worked and to then build a robot that could “think” for itself.

“Humans and animals adapt their actions according to what surrounds them, and are able to do several things at the same time and learn from their mistakes,” he said.

“With this project we hope to solve this problem of multi-tasking by using our knowledge of how the brain works.”

The robot would also be able to detect items, assess their significance and prioritise, focusing on the most important.

However, Prof Lee said that it would not look like a standard robot but be desk based with a robotic arm and cameras for eyes.

“All these capabilities will be combined within an overall control system that makes use of a central selection mechanism, just as we believe occurs in the brain,” he added.

“Our understanding of how the brain works is also key to the next stage which will involve teaching the robot how to react to things that change around it.

“For example, something which could potentially distract it from the task it has been set. It will also be able to learn from its mistakes just as humans do.

“Once the robot has been constructed we will then stand back and ask the question ‘what general features of the model gave it its ability to integrate its behaviours successfully?’

“By doing this we hope to be able to transfer our work into a wider range of robots designed for many different tasks.”

The full project team is made up of mathematicians, control engineers, computer modellers and neuroscientists from universities including Bristol, Sheffield, Oxford and Cambridge.

Air Muscles

Air Muscles

The Air Muscle is an extraordinary actuator that is small, light, simple and ‘friendly’. It is soft, has no stiction, is easily controllable and exceptionally powerful.

Advantages of the Air Muscle

Lightweight	Air Muscles weigh as little as 10 grammes – particularly useful for weight-critical applications.
Lower Cost	Air Muscles are cheaper to buy and install than other actuators and pneumatic cylinders.
Smooth	Air Muscles have no ‘stiction’ and have an immediate response. This results in smooth and natural movement.
Flexible	Air Muscles can be operated when twisted axially, bent round a corner, and need no precise aligning.
Powerful	Air Muscles produce an incredible force especially when fully stretched.
Damped	Air Muscles are self-dampening when contracting (speed of motion tends to zero), and their flexible material makes them inherently cushioned when extending.
Compliant	Being a soft actuator, Air Muscles systems are inherently compliant.

The Shadow Air Muscle is a simple yet powerful device for providing a pulling force. It behaves in a very similar way to a biological muscle. When actuated with a supply of compressed air, they contract by up to 40% of its original length. The force it provides decreases as it contracts, and the first few percent of the contraction is very powerful indeed.

The Blue Brain Project

The Blue Brain Project

The Blue Brain project is the first comprehensive attempt to reverse-engineer the mammalian brain, in order to understand brain function and dysfunction through detailed simulations.

In July 2005, EPFL and IBM announced an exciting new research initiative – a project to create a biologically accurate, functional model of the brain using IBM’s Blue Gene supercomputer. Analogous in scope to the Genome Project, the Blue Brain will provide a huge leap in our understanding of brain function and dysfunction and help us explore solutions to intractable problems in mental health and neurological disease.

At the end of 2006, the Blue Brain project had created a model of the basic functional unit of the brain, the neocortical column. At the push of a button, the model could reconstruct biologically accurate neurons based on detailed experimental data, and automatically connect them in a biological manner, a task that involves positioning around 30 million synapses in precise 3D locations.

In November, 2007, the Blue Brain project reached an important milestone and the conclusion of its first Phase, with the announcement of an entirely new data-driven process for creating, validating, and researching the neocortical column.

Milestones:

* 2002 – Henry Markram founds the Brain Mind Institute at EPFL
* June 6, 2005 – signature of agreement between EPFL and IBM, birth of the Blue Brain Project.
* April 2006, Barcelona: Cajal Centenary Conference, first public appearance & keynote at Neuroscience Conference.
* July 2006, Vienna: Forum of European Neuroscience (FENS), public presentation of toolchain (21 posters).
* Summer 2006 – 10,000 neuron NCC of the rat successfully built with simplified neurons.
* December 2006 – Completion of 10,000 neuron NCC with automatically generated, biologically accurate neurons.
* January 2007 – presentation of BBP at World Economic Forum in Davos, Switzerland .
* November 26, 2007 – announcement of the completion of Phase I of the Blue Brain Project, in Lausanne, Switzerland.