Robots could mimic human forgetfulness to filter out less useful information.
By Kristina Grifantini
We are constantly inundated with
new information, and to manage it effectively it's sometimes necessary to forget old, irrelevant memories.
Researchers at Vanderbilt
University have now developed an algorithm that mimics this kind of forgetfulness
in robots, as a way to filter out less useful information.
"Forgetting is a critical
capability when operating in dynamic environments," says PhD student Sanford
Freedman, who presented
the group's data filtering-software, called ActSimple, in a paper published at
the IASTED Robotics and Applications conference held
this week in Cambridge,
MA.
ActSimple draws on two facets of human
memory: time-based decay, or the way that memories disappear over time,
and interference, which is the failure to recall information due to other memories competing
for attention. ActSimple assigns different pieces of data values
depending on how often they are used, and how similar it is to other pieces
of information.
To test the software, the
researchers used it to control a simulated robot that measured the strength of
WiFi signals in a virtual environment. The robot recorded WiFi readings on a scale
of 1-100, as it moved through the virtual setting and these WiFi readings also had different levels of noise (errors) associated with them. At intervals, the robot relied on its memory to create an estimated WiFi signal map by
recalling signal strength information it had gathered and stored. The
researchers tested ActSimple against four other algorithms,
including one that strictly disregarded the oldest information, and another
that out filtered random information.
The Team found that on average,
ActSimple created the most reliable estimated WiFi map. Interestingly, when the robot "remembered"
everything--that is, used all of its gathered information (errors and all)--it generated
the least accurate map overall.
This bipedal bot walks on two legs and can recover from a push,
using the same balancing technology that allows BigDog to recover from a kick
or keep its balance when walking on ice.
While BigDog was designed to carry payloads for soldiers in the
field, Petman will be used for military chemical suit research. In the final
version, which should be ready in 2011, Petman will have a range of motions. According to the company:
Unlike previous suit
testers, which had to be supported mechanically and had a limited repertoire of
motion, PETMAN will balance itself and move freely; walking, crawling and doing
a variety of suit-stressing calisthenics during exposure to chemical warfare
agents.
The finished Petman will also mimic human physiology, for example sweating
in response to temperature and humidity changes, to make it a realistic testing
device for the suits.
According to the IEEE's Automaton
blog, the prototype currently has a top speed of 3.2 mph. Watch a video of Petman
striding smoothly along a treadmill track below.
Surveillance bots could be turned against their users, researchers say.
By Kristina Grifantini
A paper published recently by researchers at the University of Washington shows that several commercial
home robots--essentially small, wheeled bots with cameras, microphones and other
audio-visual surveillance features--are not as secure as their owners might think. The researchers studied 2008
models of the Erector
Spykee, and WowWee's RoboSapien
and Rovio robots and found security holes that include unencrypted audio-visual streams, unencrypted usernames and passwords
for accessing and controlling the bots, and tricks for taking over the robots remotely.
[These vulnerabilities] mean that someone might be able to
drive your robot around your home, look around the house, listen in on
conversations, and knock over small objects.
Since few people have personal robots it's hardly a major threat. But the researchers point out that better security and privacy safety measures will need to be taken as home robots become more common. To stay protected, they recommend keeping networks
and robot control encrypted, avoiding remote access, and turning off the robots
when they're not in use.
Massachusetts Institute of Technology