I am a Docent and Research Scientist at the Centre for Autonomous Systems at the Royal Institute of Technology, and the Department of Computer Science and Numerical Analysis. I was formerly a at the Massachusetts Institute of Technology. Here is a CV .
My research is concentrated on machine learning for mobile robotics, particularly for navigation. The idea is to make machines that can learn how to find their way around without the need for guidance.
To do this the robot needs to form models of the environment suitable to the task. That might be simply avoiding obstacles or, more complicated tasks like finding its way back to a location previously visited. These models need to be learned and refined based on the observations made by the robot. It is this learning that I am focused on
My background includes graduate studies in Physics at the State University of New York at Stonybrook, some work as a researcher at an electronics company in San Jose CA, and my own consulting business were I did statistical data analysis.
I have a Bachelor Degree in physics from the City University of New York. And a Masters in Computer Science from the Royal Institute of Technology in Sweden . My masters thesis was entitiled Projection of a Markov Process with Neural Networks.
I defended Doctorial thesis on October 4, 2005. Here is what the final version looks like PhD thesis .
I have designed and implemented a system for our outdoor robot, Pluto. You can read about that here pluto.pdf . Pluto can localize to a map to and goto a designated coordinate avoiding obstacles along the way. Pluto can automatically explore and map an area using a laser range scanner to located the walls of buildings. The robot can also investigate a parked car: approach it, extend its arm to position a camera to see under the car and then circle the car holding the camera always at the proper angle.
Others in the lab have integrated with my system to add road following, person following and simple arm movements. A number of nice user interfaces have also been developed. The work goes on but I am no longer directly involved.
I am part of the team developing CURE (CAS Unified Robot Environment). CURE is, so far , a collection of libraries in C++ to help people working in the lab.
I have also worked on underwater SLAM.
relatively simple robot must find its way in a confusing underwater
world. Its a task that requires careful modeling of all
uncertianties. Only then can the robot carry out its
Currently: I am teaching Applied Estimation at KTH. I
am currently researching on new methods for learning,
perception, and estimation. My latest developement is the
Antiparticle filter, (more on this to come).
Research: I am participating in an EU funded robotics project starting in 2013 called STRANDS which will investigate long term learning by robots.
Here is a movie of a robotic head I we made as part of a small project which I coordinated here at KTH: CSCHEAD.
Also: I play piano and have a patent for
music keyboard related invention.
Generated by John Folkesson, firstname.lastname@example.org Dec. 18, 2010