EKOO TECH WORLD

The Roomba Now Sees and Maps a Home

Unknown

Link Author

Title: The Roomba Now Sees and Maps a Home
Author: Unknown
Rating 5 of 5 Des:

The Roomba 980 vacuum builds a map of its surroundi...

<section class="body"><aside class="img-left">
  <img alt="" height="640" src="http://www.technologyreview.com/sites/default/files/images/iRobot_Newsx299.gif" width="640" />  </aside>
    <aside class="caption-left">
            The Roomba 980 vacuum builds a map of its surroundings as it cleans a house (shown here at high speed).<br />

</aside>
  
The world’s most successful home robot, the Roomba, is getting some 
new skills. The robotic vacuum cleaner is gaining a camera and 
image-processing software that will let it find its way around an area 
as it cleans.<br />

Up until now, the device from <a href="https://www.blogger.com/null" target="0">iRobot</a>
 has relied on a rather simple approach to navigation. It moved more or 
less randomly, using sensors to change direction whenever faced with an 
obstacle or the top of a set of steps. This gets the job done, but it’s 
hardly very efficient or intelligent.<br />

The Roomba 980, announced by iRobot CEO Colin Angle at an event in 
New York today, follows a new approach. It comes with a camera that 
captures images of a room, and software that compares these images to 
gradually build up a map of the robot’s surroundings and determine its 
location.<br />

The 980’s new vision and navigation capabilities allow the robot to 
cover a carpet more efficiently, but they also lay the groundwork for 
more advanced features in future models. Right now the Roomba 980 uses 
its map only to make sure it’s cleaned a room properly; it cannot 
recognize objects or classify different rooms, for example. But such 
abilities are likely in the pipeline.<br />

“Being able to localize in the environment is a foundational 
capability,” says Chris Jones, director of strategic technology 
development at iRobot.<em> “</em>You can imagine the day when a robot in
 the home can perceive and understand salient objects in the 
environment—that’s a couch, that’s my oven—that type of thing.”<br />

The navigation approach used by the 980 is known as simultaneous 
location and mapping, or SLAM, which means it builds a map as it goes 
along and refers back to it. SLAM has been studied in academia for 
decades, but it has recently found its way into commercial research 
efforts and products. Traditionally, however, SLAM has required a 
significant amount of computing power. Getting SLAM to work in a small 
embedded computer system required significant effort to refine and 
optimize the algorithms used.<br />

<div class="story-img">
  <img alt="" height="260" src="http://www.technologyreview.com/sites/default/files/images/iRobot_Newsx519.gif" width="519" />        The Roomba now covers an area methodically, rather than randomly.<br />

</div>
John Leonard,
 a professor at MIT who has done pioneering work on SLAM, says the 
technique is rapidly becoming a valuable commercial tool. Many of the 
automated cars currently being developed by carmakers as well as by 
Google and perhaps Apple use approaches based on SLAM for navigation. 
The technique is also used to help drones navigate, he notes. “It’s an 
exciting time for SLAM researchers,” Leonard says. “iRobot bringing a 
SLAM-based product to market is just further evidence of that.”<br />

The Roomba 980 also performs what’s known as “sensor fusion,” meaning
 it combines data from its various proximity sensors with imagery from 
its camera. This means that it can still navigate if the camera is 
obscured by, say, a cat riding on top of the robot—a <a href="https://www.blogger.com/null" target="0">surprisingly common occurrence</a>.<br />

Besides the new sensing and mapping abilities, the new Roomba 
features an improved cleaning system and roughly double the battery 
life. It can also be controlled via a smartphone app for the first time.
 The 980 costs $899, which is $200 more than the current top-of-the-line
 model.<br />

iRobot is conscious of the security and privacy concerns that the new
 camera and connectivity may introduce. A representative explains that 
the maps are not transmitted from Roomba, and they are deleted after the
 robot finishes cleaning a room.<br />

iRobot was founded in 1990 by researchers from MIT’s Computer Science
 and Artificial Intelligence Lab. The company’s first product was a 
remote-controlled machine for the military capable of bomb disposal and 
other tasks. The company got into home robots with the Roomba in 2002. 
Several generations of vacuum cleaner have followed, as well as robots 
for mopping and washing floors and cleaning gutters and pools.<br />

Other companies have introduced competitive products within the robot vacuuming space. Last year the British appliance-maker <a href="https://www.blogger.com/null" target="0">Dyson</a>
 demonstrated an automated vacuuming device that also uses cameras to 
navigate, but it hasn’t been released yet. And this year a startup 
called <a href="https://www.blogger.com/null" target="0">Neato Robotics</a> began selling a robot vacuum that performs laser mapping as it moves around.<br />

As competition heats up, home robots could become much more capable. 
Jones even hints that we might eventually see a Roomba capable of 
picking up your socks.<em> “</em>Another area on our roadmap is 
manipulation,” he says. “For that you need dense 3-D maps and models of 
the space around a robot, which is similar to the mapping you’re seeing 
here.”</section>

The Roomba Now Sees and Maps a Home

The Roomba 980 vacuum builds a map of its surroundi...

Remote-controlled robot has human-like reflexes

Unknown

Link Author

Title: Remote-controlled robot has human-like reflexes
Author: Unknown
Rating 5 of 5 Des:

Robotics research is moving along at such a fast pace that it can be difficult to spot the major milestones of innovation in the technolo...

<div class="separator" style="clear: both; text-align: center;">
<img border="0" height="358" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh4KZaA9ThWnC6E7XCUCJEreJdHp89xepiRqv1zFGiMmkaT3VMjNOFTlpliSIuVIwcdGi8yeO0iNKdmGhmI4unSbm1ddlvH6klKp4Jj4pCTMEPR0_OD80dilVhkMkmsxLt3xnq_WjjxUAU/s640/mit-hermes-robot%25402x.jpg" width="640" /></div>
Robotics research is moving along at such a fast pace that it can be 
difficult to spot the major milestones of innovation in the technology 
as they go by. One significant step forward is in evidence at MIT in the
 form of Hermes. Physically it's all robot, but its actions and reflexes
 are controlled by a human being.<br />

<div class="separator" style="clear: both; text-align: center;">
<img alt="Two joysticks control Hermes' three-fingered hands" border="0" src="http://images.gizmag.com/gallery_tn/mit-hermes-robot-4.jpg" style="cursor: move;" title="Two joysticks control Hermes' three-fingered hands" /><img alt="Hermes is built like a robot but controlled by a human" border="0" src="http://images.gizmag.com/gallery_tn/mit-hermes-robot-1.jpg" title="Hermes is built like a robot but controlled by a human" /><img alt="Even pouring a cup of coffee is no problem for Hermes" border="0" src="http://images.gizmag.com/gallery_tn/mit-hermes-robot-5.jpg" title="Even pouring a cup of coffee is no problem for Hermes" /><img alt="The robot is much stronger than its human controller" border="0" src="http://images.gizmag.com/gallery_tn/mit-hermes-robot-2.jpg" title="The robot is much stronger than its human controller" /></div>
The robot feeds back information about its balance and 
positioning in real-time, so the human operator is able to adjust his or
 her feet and body accordingly. It addresses one of the major problems <a href="https://www.blogger.com/null" target="_blank">for humanoid robots</a>
 – keeping upright on two feet. In other words, the reflexes of the 
robot to changing terrain or from a shove in the back can be almost as 
good as those of a human.<br />

Also of note are the hands of Hermes, three-fingered 
claws that can pick up power tools, crush a soda can or even pour out a 
coffee. Using joysticks rigged up to the main exoskeleton, the human 
operator is able to pick up objects and interact with the surroundings 
with more precision than a robot of this type would usually have.<br />

There are plenty of advantages to having a human operator
 control a robot in the field, because the machine benefits from 
thousands of years of brain evolution and the human being benefits from 
being able to stay out of harm's way (in the event of a natural disaster
 or in the case of a walk across an uninhabitable planet). The robot is 
able to directly benefit from some of the things humans can still do 
better, from keeping their balance to tightening a grip on an object.<br />

<div class="inline-item">
    
        <img alt="" src="http://images.gizmag.com/inline/mit-hermes-robot-5@2x.jpg" />
    
	
	<div class="caption caption--inline">
	    Even pouring a cup of coffee is no problem for Hermes<br />

</div>
</div>
The final piece of the jigsaw is a pair of vision goggles
 that enable the human controller to see whatever is ahead of Hermes. 
Whether trying to navigate through a series of rooms or attempting to 
pick up an object from the floor, it gives the operator a greater sense 
of awareness of the robot's surroundings.<br />

PhD students Joao Ramos and Albert Wang of the MIT 
Department of Mechanical Engineering are behind the project, and they 
eventually envisage more robotic intelligence being added to the design.<br />

"The human's still going to provide that creativity, that
 problem-solving and that large-scale coordination of all the joints, 
but we've designed the robot to be stronger than a person, so we'd 
imagine that in the future we want to merge some level of autonomous 
control along with the human's intelligence," explains Wang.

Remote-controlled robot has human-like reflexes

Robotics research is moving along at such a fast pace that it can be difficult to spot the major milestones of innovation in the technolo...

A new car interface aims to minimize driver distraction while a car is in self-driving mode.

Unknown

Link Author

Title: A new car interface aims to minimize driver distraction while a car is in self-driving mode.
Author: Unknown
Rating 5 of 5 Des:

How do you make sure a driver doesn’t get too distracted when his or her car is doing the driving? A new interface for cars, developed ...

<div class="separator" style="clear: both; text-align: center;">
<img border="0" height="446" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEidFGMlpEa53Um3z2Y4-akR68f7UuUUwaS0Jrg2jQMlrpQPNrZEWbipjJ0nN9GKw_67vHXzOeJBUjqPh_Hnp5tCSjAVFefWyqy3GjcnEoXIfNPTVOHremyrnGQstHzDoB5VEci92blyQbw/s640/displayx519_0.jpg" width="640" /></div>
How do you make sure a driver doesn’t get too distracted when his or her car is doing the driving?<br />

A new interface for cars, developed by the French automotive hardware supplier called <a href="https://www.blogger.com/null" target="0">Valeo</a>,
 tries to answer this question with a new dashboard interface that spans
 a vehicle’s steering wheel and its instrument display and shows 
information from a user’s smartphone. The company says that recent user 
testing showed it could be a safer way of transitioning from automated 
driving back to human control.<br />

Driver distraction is already a huge problem on the road, and 
smartphone use is implicated in more than 25 percent of all traffic 
accidents. This is why many carmakers are already allowing smartphone 
makers access to the entertainment consoles in cars (see “<a href="https://www.blogger.com/null" target="0">Rebooting the Automobile</a>”).
 But the issue of driver distraction is likely to get more complicated 
as carmakers make it possible for cars to drive themselves some of the 
time, with research showing that it can take drivers more than 10 
seconds to regain control of a vehicle in an emergency if they are fully
 distracted (see “<a href="https://www.blogger.com/null" target="0">Proceed with Caution toward the Self Driving Car</a>”).<br />

Carmakers are acutely aware of this issue, even as they tout the 
automated capabilities they are developing, and Valeo’s interface, 
called Mobius, offers a possible solution.<br />

Once a car has entered automated driving mode, the display shows 
information from the driver’s own smartphone, but it combines that with 
information such as current speed and the direction of the next turn. 
The idea is that, because the display is also close to the driver’s view
 of the road, he or she should find it easier to retake control of the 
wheel when necessary.<br />

“You can access the weather, the news, you can even play [games],” 
said Patrice Reilhac, director of innovation and collaborative research 
at Valeo, at an industry event. “At the same time, we keep some kind of 
situational awareness. And given that the screen is placed close to the 
road, people keep the road in their peripheral vision.”<br />

The company recently tested the interface with 41 people at the 
Vehicle Interaction Lab at the Fraunhofer Institute in Germany. “What we
 found was astonishing,” Reilhac added. “The reaction time was below two
 seconds. Our idea, that people keep situational awareness through their
 peripheral vision, seems to be confirmed.”<br />

Gregory Fitch,
 a research scientist specializing in user experiences at Virginia 
Tech’s Center for Automated Vehicles, says regaining control from a 
partially automated vehicle is a big challenge within the auto industry.
 His group recently conducted research with GM and Google that showed 
how easily drivers can misjudge what an automated vehicle is doing.<br />

Mobius would also check to see if the driver’s eyes are on the road 
before handing control back to them. Other experts say this could also 
be a very important part of future vehicle interfaces.<br />

Bryan Reimer,
 a researcher at the MIT Age Lab who studies vehicle interfaces, says 
driver monitoring is likely to become much more common, and also a 
crucial part of the interface. “Based upon the driver’s state, adaptive 
warnings can be more appropriately deployed,” he says. This could help 
minimize potentially dangerous confusion, Reimer suggests.

A new car interface aims to minimize driver distraction while a car is in self-driving mode.

How do you make sure a driver doesn’t get too distracted when his or her car is doing the driving? A new interface for cars, developed ...

Military Robots: Armed, but How Dangerous?

Unknown

Link Author

Title: Military Robots: Armed, but How Dangerous?
Author: Unknown
Rating 5 of 5 Des:

An open letter calling for a ban on lethal weapons controlled by artificially intelligent machines was signed last week by thousands of...

<div class="separator" style="clear: both; text-align: center;">
<img border="0" height="640" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg8gcxzdohCahlD6ziEVIOVjpkkcOMV4zQruk-kW3fQ7JCtbXocMWbiqr5RFXljBPMZWZYuDdzmoXLEHYX5wgTDnw6xbnaNcEGQ_tuvhpX_DRBucMl0lN3Mk3sMztgerW-C5xSNahnGpYw/s640/ai.weaponsx299.jpg" width="640" /></div>
An <a href="https://www.blogger.com/null" target="0">open letter</a>
 calling for a ban on lethal weapons controlled by artificially 
intelligent machines was signed last week by thousands of scientists and
 technologists, reflecting growing concern that swift progress in 
artificial intelligence could be harnessed to make killing machines more
 efficient, and less accountable, both on the battlefield and off. But 
experts are more divided on the issue of robot killing machines than you
 might expect.<br />

The letter, presented at the <a href="https://www.blogger.com/null" target="0">International Joint Conference on Artificial Intelligence</a>
 in Buenos Aires, Argentina, was signed by many leading AI researchers 
as well as prominent scientists and entrepreneurs including Elon Musk, 
Stephen Hawking, and Steve Wozniak. The letter states:<br />

<em>“Artificial Intelligence (AI) technology has reached a point 
where the deployment of such systems is—practically if not 
legally—feasible within years not decades, and the stakes are high: 
autonomous weapons have been described as the third revolution in 
warfare, after gunpowder and nuclear arms.”</em><br />

Rapid advances have indeed been made in artificial intelligence in 
recent years, especially within the field of machine learning, which 
involves teaching computers to recognize often complex or subtle 
patterns in large quantities of data. And this is leading to ethical 
questions about real-world applications of the technology (see “<a href="https://www.blogger.com/null" target="0">How to Make Self-Driving Cars Make Ethical Decisions</a>”).<br />

Meanwhile, military technology has advanced to allow actions to be 
taken remotely, for example using drone aircraft or bomb disposal 
robots, raising the prospect that those actions could be automated.<br />

The issue of automating lethal weapons has been a concern for 
scientists as well as military and policy experts for some time. In 
2012, the U.S. Department of Defense issued a <a href="https://www.blogger.com/null" target="0">directive</a>
 banning the development and use of “autonomous and semi-autonomous” 
weapons for 10 years. Earlier this year the United Nations held a 
meeting to discuss the issue of lethal automated weapons, and the 
possibility of such a ban.<br />

But while military drones or robots could well become more automated,
 some say the idea of fully independent machines capable carrying out 
lethal missions without human assistance is more fanciful. With many 
fundamental challenges still remaining in the field of artificial 
intelligence, however, it’s far from clear when the technology needed 
for fully autonomous weapons might actually arrive.<br />

“We’re pushing new frontiers in artificial intelligence,” says <a href="https://www.blogger.com/null" target="0">Patrick Lin</a>,
 a professor of philosophy at California Polytechnic State University. 
“And a lot of people are rightly skeptical that it would ever advance to
 the point where it has anything called full autonomy. No one is really 
an expert on predicting the future.”<br />

Lin, who gave evidence at the recent U.N. meeting, adds that the 
letter does not touch on the complex ethical debate behind the use of 
automation in weapons systems. “The letter is useful in raising 
awareness,” he says,  “but it isn’t so much calling for debate; it’s 
trying to end the debate, saying ‘We’ve figured it out and you all need 
to go along.’”<br />

Stuart Russell,
 a leading AI researcher and a professor at the University of 
California, Berkeley, dismisses this idea. “It’s simply not true that 
there has been no debate,” he says. “But it is true that the AI and 
robotics communities have been mostly blissfully ignorant of this issue,
 maybe because their professional societies have ignored it.”<br />

One issue of debate, which the letter does acknowledge, is that 
automated weapons could conceivably help reduce unwanted casualties in 
some situations, since they would be less prone to error, fatigue, or 
emotion than human combatants.<br />

Those behind the letter have little time for this argument, however.<br />

Max Tegmark, an MIT physicist and founder member of the <a href="https://www.blogger.com/null" target="0">Future of Life Institute</a>,
 which co ördinated the letter signing, says the idea of ethical 
automated weapons is a red herring. “I think it’s rather irrelevant, 
frankly,” he says. “It’s missing the big point about what is this going 
to lead to if one starts this AI arms race. If you make the assumption 
that only the U.S. is going to build these weapons, and the number of 
conflicts will stay exactly the same, then it would be relevant.”<br />

The Future of Life Institute has issued a more general warning about 
the long-term risks posed by unfettered AI, cautioning that it could 
pose serious dangers in the future.<br />

“This is quite a different issue,” Russell says. “Although there is a
 connection, in that if one is worried about losing control over AI 
systems as they become smarter, maybe it’s not a good idea to turn over 
our defense systems to them.”<br />

While many AI experts seem to share this broad concern, some see it as a little misplaced. For example, <a href="https://www.blogger.com/null" target="0">Gary Marcus</a>, a cognitive scientist and artificial intelligence researcher at New York University, has <a href="https://www.blogger.com/null" target="0">argued</a>
 that computers do not need to become artificially intelligent in order 
to pose many other serious risks, to financial markets or air-traffic 
systems, for example.<br />

Lin says that while the concept of unchecked killer robots is 
obviously worrying, the issue of automated weapons deserves a more 
nuanced discussion. “Emotionally, it’s a pretty straightforward case,” 
says Lin. “Intellectually I think they need to do more work.”

Military Robots: Armed, but How Dangerous?

An open letter calling for a ban on lethal weapons controlled by artificially intelligent machines was signed last week by thousands of...

The Roomba Now Sees and Maps a Home

Remote-controlled robot has human-like reflexes

A new car interface aims to minimize driver distraction while a car is in self-driving mode.

Military Robots: Armed, but How Dangerous?

Contact Form