De meningen ge-uit door medewerkers en studenten van de TU Delft en de commentaren die zijn gegeven reflecteren niet perse de mening(en) van de TU Delft. De TU Delft is dan ook niet verantwoordelijk voor de inhoud van hetgeen op de TU Delft weblogs zichtbaar is. Wel vindt de TU Delft het belangrijk - en ook waarde toevoegend - dat medewerkers en studenten op deze, door de TU Delft gefaciliteerde, omgeving hun mening kunnen geven.

Robot Man- Aswin Chandarr on his Thesis

My company these days in Delft mainly comprises of my
friends who are in various Master tracks at the TU Delft. This is due to the
fact that most of my peers from my own faculty and Bachelor program have gone
back home for the summers. This leads to various conversations I have with my
older friends who are mostly completing their Thesis and are in the process of

One such friend is Aswin Chandarr. He’s currently in the
process of writing his Master’s thesis and hopes to graduate soon. He has been
part of the faculty of Mechanical Engineering and is specializing in
Biorobotics. So here’s a little interview I conducted with him talking about
his Thesis and what it deals with and his graduation process. He was kind
enough to take out some time and answer my questions! Thank you Aswin J


Q. How would you describe your thesis to a layperson like
me with no background in Robotics?

A. To be short, I’d say it’s about bringing personal
robots in households. We have seen robots in science fiction films like Star
Wars etc.  But we haven’t seen robots
outside the laboratory. So the overall goal of my Thesis is to bring robots
outside the laboratory so they can be utilized practically.


Q. Don’t robots for households already exist?

A. There are some robots, say, like a dishwasher. But real
personal robots are still not there. We’re targeting at personal robots in
hospitals that will help patients in need or at airports to help lost
passengers and guide directions.


Q. So this is the general idea. What is your Thesis specifically
focussing on?

A. Object recognition. The whole group is targeting ‘perception’
as in objects, faces and sounds. My colleague’s thesis focuses on facial
recognition but mine focuses on object recognition. And this will be set in a
small indoor environment with everyday small usable objects which can be
grasped by the robots. For example if I ask the robot to grab me a can of cola
it will get me a can of cola and not a carton of milk. A lot of algorithms are
present that work only in laboratory conditions. For instance, you click a
photo of the object and then the robot will only identify that object. But my goal is to get the robot to
identify differences within similar looking objects as well. The problem with current
recognition is that it will identify the same object as two different objects
depending on what side it ‘sees’.


Q. When are you due with your Thesis?

A. Basically I’m done. I’m just writing the report right
now and my defence is on August 28.


Q. Do you hope to carry on with this research after you’re
done with you Masters here?

A. I’m starting my PhD from September and it will
basically be an extension of this current project. Right now the concept is
more robust than before but still not robust enough. So I’d like to continue to
that further.


Q. So did you guys actually make a robot?

A. Yes as a group we did and we went to Mexico for a
competition. The team comprised of four Master’s students doing their thesis on
it, three bachelor’s students and a PhD researcher leading the team.


Thank you again Aswin! It was great to get your insight into
the world of a student completing his Master’s Thesis. I’ll hopefully get a
picture of the root when it’s back from Mexico.


Aswin with his fuel- Coffee 


And there will be more of these interviews to follow!


Tot Later


Be Sociable, Share!

Leave a Reply

© 2011 TU Delft