Please tell us about yourself

Aswin Chandarr is 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

Original Link:

http://haiderhussain.weblog.tudelft.nl/2012/07/22/robot-man-aswin-chandarr-on-his-thesis/

What is your educational background?

I did my Bachelor’s Degree in Electrical and Electronics Engineering from National Institute of Technology, Tiruchirappalli and Master’s Degree in Robotics from Technische Universiteit Delft / Delft University of Technology

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

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.

 Don’t robots for households already exist?

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.

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

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’.

 When are you due with your Thesis?

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

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

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.

 So did you guys actually make a robot?

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.