About
some random stuff I find interesting today ....
Accounts
Click here to check if anything new just came in.
March 20 2012
Prospecting a Prospectus
Today it is exactly 13 months since I enrolled as a PhD student here in Lugano, at the Università della Svizzera Italiana (USI). It's time to write my research prospectus, or at least try to find out what that is *uhm*
Although I am working for over a year here at IDSIA I have not yet a clear idea what I will do, but I heard that is normal in graduate school. So finally I set down and wrote up some ideas of what I want/can do in the next years to get my doctorate.
There are some rough ideas that I have, mainly just stuff floating around in my brain, but I am pretty sure those are not yet concrete enough for a thesis topic. As I was heavily involved in making the iCub see recently I though that might be of a good start for the work. One of the ideas behind the iCub was to build a robot that can be used to investigate human development and cognition and how to transfer it to robots (see Metta et al).
The platform is particularly well suited for research into object manipulation and interaction. Recently also IIT has posted some positions investigating grasping and transfer or knowledge from humans to robots and maybe the other way around too.
I am currently looking into visually guided grasping for the iCub. Much work has been done on force/touch guided grasping. In our robot though the readout of the force sensor in the fingertips seems to be rather noise and more or less useless (unless you have a nice metallic object). Approaches taken from the (partly overlapping fields of) cognitive robotics, developmental robotics and evolutionary robotics seem to be the most interesting to try and build a sensorimotor representation for reaching and grasping. I think this might be interesting and novel enough, we will see what happens when I try to write this down ...
February 19 2012
Vision-eering
Recently I have been working a lot on trying to make the iCub see things. A fully integrated computer vision or robotic vision system is a quite tricky mathematical and engineering problem. Here at IDSIA we were trying to develop an easy to use system that would allow to rapid prototyping (offline) vision modules for the iCub, mainly to detect and localise objects the robot is in later stages supposed to manipulate and interact with.
Over the last 6 months, I developed the icVision framework, which allows to do just that. It is a modular system based on YARP and openCV. A video is probably the easiest way of showing the capabilities of icVision.
The main modules involved here are the icVision Core module, as well as, the icVision filter modules.
The Core handles the connection with the hardware and provides housekeeping functionality (e.g., extra information about the modules started and methods to stop them). Other modules can attach to the icVision Core and can therefore provide functionality by using standardized interfaces. Currently implemented modules include object detection, 3D localisation and saliency maps.
Some modules also expose their functionality by HTTP (e.g. an image can be grabbed from the HTTP instead of YARP, which increases the number of people that can work with the iCub images in our lab by A LOT).
Most recently we were working on learning how to detect objects and creating filters for specific objects. The teabox filter used in the video is an example of this. This is done using Genetic Programming and is enabled by the very easy way to add new filters. The following is the code for a fully working filter using the framework:
// Author: Juxi Leitner <juxi.leitner@gmail.com> #include <icVision/icFilterModule.h> class RedDetector : public icFilterModule { protected: void setUsedInputs() { usedInputs.Add(1); } public: RedDetector() { setName("RedDetector"); } icImage* runFilter() { icImage* in = InputImages[1]; // red icImage* out = in->threshold(64); // cvThreshold return out; } };
There will be a poster presentation and demonstration of icVision during this year's Cognitive Systems conference in Vienna.
The other area we are currently working on is to learn to localise objects in 3D space. This is a bit more tricky. More on this later :)
September 21 2011
Summer School 2011
Also this year I had the chance to attend a summer school, after ISRIS in 2009 and 2010 school at JAIST, I was going to this year's Hands On Summer School on Neural Dynamics Approaches to Cognitive Robotics in Guimaraes, Portugal.
This school focused on the idea of Dynamic Neural Fields (similar but according to the presentations more powerful than Neural Network approaches) and how to use them in various robotic systems. The presentations, mainly given by researchers from the University of Bochum and Minho, ranged from computer science to neuroscience and included various applications, such as on mobile and humanoid robots (including the Nao and ARoS, a humanoid (upper body) robot built at Minho). The school ended with a project to be implemented (and yes there is a video of ARoS after the jump).
The summer school was held at the University of Minho, which is situated in Guimaraes, the first capital of Portugal, set in a scenic landscape with rolling hills. For a full week we, about 50 students and instructors, were there to learn about NeuroDynamic Fields and robots. After the morning classes and lunch, exercises were held to use the theory in practice, and for the end of the school we were grouped and started working on different robotic projects.
ARoS Robotic Platform
Together with Martin Stoelen, I worked on the ARoS robot platform available to us at Minho. ARoS is an anthropomorphic robot, which consists of a 7DOF arm and a Barrett 3Finger hand attached as end-effector. It uses 2 FW cameras for computer vision and is aimed to be used in Human-Robot-Interaction research tasks.
In our project a joint construction task was used in which the human and the robot need to work together to construct a small toy. The interaction is forced by placing the wheels only within the humans reach and the nuts only within the robots workspace. Therefore to finish the construction the human and the robot need to hand over pieces to their counterpart. DNF were used in layers to represent a cognitive architecture somewhat human-brain-inspired to decide on the current state of the construction task, the workspace, the human's intention and the action to be performed by the robot. Here you can see the robot in action:
There is also a screencast about the activation of the neural fields, have a look at it but it might not make too much sense without further explanation. If you wanna know more just drop me an email.
August 31 2011
Some Coding
Finally I wanna put some info online about what I actually do here at IDSIA. Right now I am mainly working on the iCub robot and I am currently looking into some computer vision related problems, like image segmentation and object detection (for object manipulation later on). Here is a small teaser of what we are currently working on....
We recently started looking into getting some position data out of the 2D images and the kinematic chain of the robot, but we are not really happy with the results. To gather some data I worked on some piece of code to automatically do just that. To use this data as either training of test set for our approach (as well as a benchmarking) related to the object placement. Hopefully we get it working on the real HW soon too..
More info to come at a later stage ...
December 06 2009
A biologically-inspired vision system
If you don't want to read the paper, then you should at least watch the below video in its entirety. In the video, lead researcher David Cox explains at a high level how biological vision works and how their computational system mimics it to achieve the results presented in the paper.
July 04 2007
Hello Lisboa!
After arriving at the airport and explaining the cab driver what and WHERE IST is
I explained to him ISR and what I am going to do...
Well so what am I doing?
Basically I do something with Humanoid Robots (well okay you maybe knew that), my part is programming Computer Vision for them (okay so what is the real deal!?). The real deal is:
"Project Title: Disparity Based Depth Perception for Humanoid Robots" (find more if you click on it)
So how is Lisbon you ask? It is amazing
25°, blue skies....since i forgot my camera's USB cable the pictures will follow later...
here they are:
Maybe Soup is currently being updated? I'll try again automatically in a few seconds...
