[Impressions from ECAL 2013]

Multi-agent systems Robots Added on 17/09/2013

Taormina

I recently returned from Taormina, Sicily where I attended the ECAL 2013 conference. It was so amazing that I felt I had to share my experience from it on this blog.

The conference started with a number of workshops ran in parallel, and although I was quite interested in a workshop about swarm robotics, I chose to go to TRUCE, a meetup of scientists and creative writers. Being one of the 'scientists', I submitted my idea about how the world would look like in 2070 should my research be successful and a writer Robin Yassin-Kassab offered to write a story based on my vision of an evil government using insect-like robots and nanobots to spy on people and to kill them silently. Robin and me worked on the story that day and had amazing talks about many other things, like the current conflict in the Middle East, buddhism and the origin of the Universe. It was a really great start to the conference for me. The story will be published in a book with others from TRUCE sometimes next year, with my afterword next to it.

The following three days were full of interesting talks, at least half of them being about robotics. Sometimes I felt like I should split myself to pieces and send each piece to a different room in order to absorb everything. Well, unfortunatelly that was not possible, so I was stuck with carefully choosing the people to see. I was lucky enough to meet with Roman Miletitch from the Brussels university, who does his PhD on foraging robots, simulating them in ARGoS, a platform that I am seriously considering for my PhD as well. We had an evening of talking about swarms over drinks of Martini, and we couldn't believe how researchers can become isolated without knowing about each other's work.

My own talk on Controlling Ant-Based Construction went quite well, actually much better than I expected. Of course, the flow of the presentation that my supervisor Seth helped me perfect was a big part of the success. I don't know if it was the exhaustion and the lack of sleep, or the general mood of the conference, but for the first time ever I felt good presenting in front of a room full of people. Like I was supposed to be there.

There were some interesting keynote speakers as well, a talk about nanobots or intelligent playware is always welcome after a nice Sicilian lunch. By the way, the food everywhere was amazing, the coffee was even better, the wine tasted like it was made with care and don't even let me start about the Italian ice-cream! Most importantly, the people seemed truly interested in making you feel welcome, which was a nice change from the fake interest and smiles so often experienced in the UK. In general, I very much enjoyed my time there and the conference gave me a lot of perspective into what I am doing with my PhD. Thank you Southampton DTC for enabling me the trip!

Comments

Lenka
[17/09/2013]


Yes indeed Ra, thanks for making TRUCE happen!
Ra
[17/09/2013]
:: [WEB]
It was awesome wasn't it!!


{Please enable JavaScript in order to post comments}

Impressions from ALIFE 14 New York

This summer, I attended the Artificial Life conference in New York. There were some interesting and not-so-interesting talks, but generally I am very glad I went. I had a chance to meet some great people and more importantly, to get much needed feedback on my own research. I also got offered to try out real robots in my research.

Accepted to the ECAL 2013 A-Life conference

The paper 'Controling Ant-Based Construction' that I recently wrote in cooperation with my supervisor Seth Bullock has now been accepted to the ECAL 2013 conference. The work is about a simulation of 2D ant nest building, where different nest shapes are made...

Controlling Ant-Based Construction

Stigmergy allows insect colonies to collectively build structures that no single individual is fully aware of. Since relatively minimal sensory and reasoning capabilities are required of the agents, such building activity could be utilised by robotic swarms if we could learn how to control the shape of the final structures.

Foraging Strategies in Nature and Their Application to Swarm Robotics

While foraging is a task often experimented with in swarm robotics, it is often the case that foraging strategies inspired by nature are chosen without careful consideration. Foraging strategies including solitary foraging, behavioural matching, stigmergy, signaling to guide others and coordinated and cooperative hunting are identified and their implementation costs in robots, as well as their suitability for different scenarios is discussed.

Starting my PhD Next Week

I have finally finished making my studio in Southmapton at least decently homey as I am starting my PhD programme on Tuesday. I met some of my classmates yesterday (Saturday) during a barbeque and I am very excited about our future discussions and beer drinking.

pyCreeper

The main purpose of pyCreeper is to wrap tens of lines of python code, required to produce graphs that look good for a publication, into functions. It takes away your need to understand various quirks of matplotlib and gives you back ready-to-use and well-documented code.