tactile Simultaneous Localization and Mapping using Whiskers

There are few ways of learning. Based upon the methods the learners are classified as:

• visual learners;
• auditory learners;
• kinesthetic learners or tactile learners

In robotics, we have seen examples of using audio and visual sensors to learn the surroundings. I came across this tactile learners called Shrewbots (Or may I call them the whisker-bots). Shrewbots use the technique called tSLAM (tactile Simultaneous Localization and Mapping) to sense its environments by using few actuated whiskers. See the video:


Below you can see the tSLAM at work!

Read more:
“Simultaneous Localization and Mapping on a Multi-Degree of Freedom Biomimetic Whiskered Robot,” by Martin J. Pearson, Charles Fox, J. Charles Sullivan, Tony J. Prescott, Tony Pipe, and Ben Mitchinson from the Bristol Robotics Laboratory and Sheffield University's Adaptive Behaviour Research Group, was presented this week at ICRA 2013 in Germany. via ieeeSpectrum
http://spectrum.ieee.org/automaton/robotics/robotics-hardware/shrewbot-whiskered-robot-tslam

Plus, you should follow BotJunkie to see some weird and interesting stuffs:
http://www.youtube.com/user/GerbilGod7?feature=watch

-->

#NASA's @AstroRobonaut Challenge

Here is the challenge:
Improve the vision algorithms of  @AstroRobonaut, and win some money. http://t.co/ccwbDOTUNi

A Robonaut is a dexterous humanoid robot built and designed at NASA Johnson Space Center in Houston, Texas. You can join him on facebook:
https://www.facebook.com/NASArobonaut
-->

Rock paper scissors, wait there is more...

You can win the game (or battle) with few methods: with intelligence/tactics, and/or with speed (assuming equally powerful players).
The field of Machine learning can use both! :)
So, fasten your seatbelt and think!
Recently I saw a video showing robot system with 100% winning rate "as one example of human-machine cooperation systems". The key was the speed. http://www.k2.t.u-tokyo.ac.jp/fusion/Janken/index-e.html

On the lighter note to the post, because of limited outcomes of the Rock-paper-scissors, there might be draws. So there is more to the game, if you are willing to add the options. As BBT suggests: "Rock-paper-scissors-lizard-spock".

Boston Dynamics and Cheetah, the running robot

Boston Dynamics has produced a bio-inspired running prototype, called Cheetah, which I am sure will be running outdoors soon.
Funded by DARPA's Maximum Mobility and Manipulation program, it might be the fastest running 4-legged robot to date running at 18 miles per hour. (Homework: convert it into km/hr :P)

You probably remember their alpha dog:

which could stand up in couple of seconds, and their field robot called big dog, and little dog.

>

Swarm of Helicopters playing James Bond and other neat tricks

In this post, I will be presenting two interesting videos. These two nice examples illustrate how one could automate the process by assigning the task to the individuals, and allow them to act as a swarm.

1. In the video shown, small fleet of flying robot quadrotors perform the James Bond Theme. Each of them are assigned tasks such as playing keyboard, drums and maracas etc.  These flying quadrotors are completely autonomous, meaning humans are not controlling them; rather they are controlled by a computer programed with instructions to play the instruments.

2. Second is an example of swarm of nano robots performing some neat tricks. Courtesy of GRASP Lab, University of Pennsylvania.

The TED talk:

AstroRobonaut@Space

Humans in International Space Station has a new companion: A Robonaut (R2B). R2 is the first humanoid robot in space. It will go thru extensive tests after which it will serve side by side with human missions in ISS and beyond.
From: http://robonaut.jsc.nasa.gov/default.asp

There are currently four Robonauts, with others currently in development. This allows us to study various types of mobility, control methods, and task applications. The value of a humanoid over other designs is the ability to use the same workspace and tools - not only does this improve efficiency in the types of tools, but also removes the need for specialized robotic connectors. Robonauts are essential to NASA's future as we go beyond low earth orbit and continue to explore the vast wonder that is space. 

See the preparation on time lapse:


Twitter Follow:
http://twitter.com/AstroRobonaut
Facebook:
http://www.facebook.com/NASArobonaut

Just imagine a humanoid-robotic hand picking the martian dust!

Arduino The Documentary

Arduino is one of the success stories of hard work and the power of collaboration in open source projects.
For curious minds who have wanted to try something  Arduino makes the way. The best part being the accessible budget in the involved projects.

Arduino is an open-source electronics prototyping platform based on flexible, easy-to-use hardware and software. It's intended for artists, designers, hobbyists, and anyone interested in creating interactive objects or environments.

Quoted from: http://www.arduino.cc/

 

Arduino The Documentary 2010

Seaswarm: Autonomous Oil absorbing robot

When the Gulf oil spill occured, attempts were made to clean it manually. It required deploying thousands of workers and still only few percentage of the spill was collected.  The spill had very bad effects on the environment. Just google gulf oil spill in pictures.
Now researchers at MIT have come up with an autonomous robot to collect the oil from such spill. The video below shows how swarm of networked robots can be used to collect such spill.
The idea is nice because it does not need human intervention. Once left on the spill site, it can work spontaneously.



http://web.mit.edu/press/2010/seaswarm.html

Adaptive Evolution and Darwinian Selection in Robots

Natural selection: is it the law or consequence due to the constraints provided in the situation?
It is "the law" if you think nature as an agent at work and that requires some law to work on. On the other hand it is the consequence if  you view it with the concept of "natural process". The difference is subtle: do you conceive it as a work done by an agent or a continuous process?
Whatever it is, one thing is sure that Darwinian theory of natural selection is true for agents in the play ground. Be it living beings, or robots.
The understanding of nature and appreciation to it becomes rather huge once you have the capacity to build and mimic "natural behavior".
Scientists have been working on adaptive and evolutionary robots with capabilities to learn and hence are able to realize the Darwinian selection rule in such robotic agents as the consequence of such learning and adaptive behavior.
See some video...





Evolution of Adaptive Behaviour in Robots by Means of Darwinian Selection

• http://www.plosbiology.org/article/info%3Adoi%2F10.1371%2Fjournal.pbio.1000292
• http://spectrum.ieee.org/automaton/robotics/robotics-software/evolution-of-adaptive-behaviour-in-robots-by-means-of-darwinian-selection

Read more interesting stuffs...

• http://www.popsci.com/science/article/2010-01/robots-display-predator-prey-co-evolution-evolve-better-homing-techniques
• http://www.npr.org/blogs/alltechconsidered/2010/02/evolving_robots.html
• http://www.botjunkie.com/2010/02/02/robots-evolve-cooperative-behaviors-learn-to-hunt-and-be-hunted
• http://news.cnet.com/8301-17938_105-10432608-1.html
• http://www.physorg.com/news184228204.html

A Robot Conductor in Stage!

I know, it is all about pre-programmed robot in the video below.
But we all go into training to get ourselves into some familiar sequence of nice notes. That is also a kind of programming. I found a video in which the robot Asimo directing people as a conductor in a nice stage program.

Many people may find trouble to work under robot.
Oh, actually you can find humans working as robots whenever you call to the 1-800 numbers which are usually equipped with real people trained to behave as robot.
The debate on whether robots are going to outsmart people will continue.
Enjoy the video.