This website will give you more information about me, Jacqueline Heinerman, PhD student, and the activities regarding Evolutionary Robotics within the Computational Intelligence group of the department of Artificial Intelligence at the VU University Amsterdam.
September 27, 2016
Last week the PPSN conference was held in Edinburgh with a view on Arthur’s Seat. Our tutorial on “Evolutionary robotics – a practical guide to experiment with real hardware” was part of the schedule. Check out the slides!
Writing a scientific article: great course!
Just finished the intensive summer writing course of VU Taalcentrum to improve my paper writing skills. I learned a lot and recommend the course to all starting PhD students.
New colleague & roommate!
April 20, 2016
Alessandro Zonta started his PhD last week within our group on the topic of Situational Analytics.
The aim of his PhD project is to develop methods and technologies to filter, combine and interpret the vast amounts of information coming from various sources, such as (autonomous) sensors, in order to continuously provide up to date situational awareness tailored to the context of the person/role/organization at hand.
He already proved to be a good researcher during his master thesis which resulted in a joint publication with the Thymio robots.
I’m happy you are back again!
Robot heads arrived
March 9, 2016
The robot heads arrived that are specially made for our 3D printed robots. The heads integrate all needed electronics for connecting servos, power supply, independent recharging, and more nerdy stuff. Milan, another PhD at our department, and Matteo, a master student doing his thesis on the topic, made it work today on the robot. Interested? Stop by at the robot lab anytime (P437 W&N building VU).
DREAM review meeting in Paris
March 8, 2016
Just back from the DREAM review meeting. At UPMC, we presented our results of the first year with a beautiful 360 view of Paris! We also showed demonstrations with the Thymio, Crustcrawler and Baxter robot.
Paper accepted @ Evostar conference!
January 22, 2016
Just submitted the camera-ready copy of our paper on “On-line Evolution of Foraging Behaviour in a Population of Real Robots“.
Abstract: This paper describes a study in evolutionary robotics conducted completely in hardware without using simulations. The experiments employ on-line evolution, where robot controllers evolve on-the-fly in the robots’ environment as the robots perform their tasks. The main issue we consider is the feasibility of tackling a non-trivial task in a realistic timeframe. In particular, we investigate whether a population of six robots can evolve foraging behaviour in one hour. The experiments demonstrate that this is possible and they also shed light on some of the important features of our evolutionary system. Further to the specific results we also advocate the system itself. It provides an example of a replicable and affordable experimental set-up for other researchers to engage in research into on-line evolution in a population of real robots.
You can already read the full paper or wait for the poster presentation session at the Evostar conference at the end of March in Porto, Portugal.
Responsible Robotics Foundation
January 18, 2016
After meeting Aimee van Wynsberghe last week, she invited me to join her Responsible Robotics Foundation. The mission of the foundation is the following:
To promote the responsible design, development, implementation, and policy of robots embedded in our society. Our goal is to influence the future development and application of robotics such that it embeds the standards, methods, principles, capabilities, and policy points, as they relate to the responsible design and deployment of robotic systems. We see both the definition of responsible robotics and the means for achieving it as on-going tasks that will evolve alongside the technology of robotics. Of great significance is that the FRR aims to be proactive and assistive to the robotics industry in a way that allows for the ethical, legal, and societal issues to be incorporated into design, development, and policy.
Become a member of the foundation via the website and join a working group of your interest.
Second place best student paper award!
January 12, 2016
We are proud to tell that our paper “Evolution, Individual Learning, and Social Learning in a Swarm of Real Robots”, presented in Capetown South Africa, got a Best Student Paper Award (second place)! read paper
Dream meeting in London
November 18, 2015
In the beginning of November, we had a very inspiring meeting with the members of the DREAM project (http://robotsthatdream.eu/). We presented our own work on on-line evolution of foraging behaviour in a population of Thymio II robots and we heard new ideas from the other Universities, that we start to implement now too.
But luckily, there was also time to see London and eat at the new restaurant of Ottolenghi: NOPI!
Discovery Festival @ NEMO
October 1, 2015
At the Discovery festival at NEMO last Friday, we presented our evolving robots for the first time to the public.
Thank you all for the enthusiastic reactions! For the ones who missed it: the robots will still be available this whole week at the EXPO room @ NEMO.
Photo’s and video’s of the event can be found at: https://www.facebook.com/discoveryfestival?fref=ts.
Blog about our research written by the Discovery Festival
September 18, 2015
Massimiliano talking to the Thymio robots
Paper accepted on the 2015 IEEE Symposium Series on Computational Intelligence!
September 15, 2015
We are really happy to tell that we got a paper accepted on the 2015 IEEE Symposium Series on Computational Intelligence! Capetown: here we come!
The paper is called: “Evolution, Individual Learning, and Social Learning in a Swarm of Real Robots”.
Abstract: We investigate a novel adaptive system based on evolution, individual learning, and social learning in a swarm of physical Thymio II robots. The system is based on distinguishing inheritable and learnable features in the robots and defining appropriate operators for both categories. In this study we choose to make the sensory layout of the robots inheritable, thus evolvable, and the robot controllers learnable. We run tests with a basic system that employs only evolution and individual learning and compare this with an extended system where robots can disseminate their learned controllers. Results show that social learning increases the learning speed and leads to better controllers.
Thanks Massimiliano for all your help! See you in Capetown.
My name Jacqueline Heinerman, 2nd year PhD student in the field of Evolutionary Robotics at the VU University in Amsterdam. Evolutionary Robotics aims to evolve the controllers, the morphologies, or both, for real and/or simulated autonomous robots with use of Evolutionary Algorithms.