IIT has recently released their Call for Participation for this year's (already the seventh!) summer school focused on developing software for the iCub humanoid robot. It will be a great 10 days, at an awesome location, with a very cool robot and enough time to get your hands dirty. If everything goes right IDSIAni will be there too to show what we are working on here ...

We will show what we are working on with our iCub, mainly computer vision, control and planning (with a cool self-collision avoidance suite).

From their call:

The school is a hackathon for robotics researchers interested in any combination of humanoids, free software, open-source hardware, and Italian beaches. Those who would like to participate should email their name, affiliation, and a CV (or relevant website URL) to: vvv12-admin@icub.org
no later than: May 13th, 2012

The aim of the yearly iCub Summer School, with the official title "Veni Vidi Vici", "serves to consolidate and disseminate skills in software engineering for humanoid robots." (from the webpage). It is setup in peer-to-peer fashion with no lectures, and no strict division of instructors and students. The school is organized flexibly around informal tutorials from participants on modules they are working on or interested in. A series of hands-on practical laboratory sessions are the main parts of the 10 days.

Topics of interest are: Motor control, robot design, image processing, software engineering, communication, machine learning, free software, open-source hardware.

This year the school will be hosted at the Mediaterraneo Foundation in Sestri Levante, Liguria, Italy. See the school website for venue details: http://eris.liralab.it/summerschool2012/

UPDATE: I found a video from VVV 2010.

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 :)

This is my old laptop bag after five years of using it.

Lucky (for me) GearZap.com offered me to send one to me for free, so I took the chance. They have a big selection of MacBook Pro 13" cases and bags and I was first thinking of getting the Quiksilver one, but was not sure. So I was checking out more of their MacBook Pro cases on their webpage.

The awesome Japanese description of my the ZeroShock bag!

I then decided to go with the ZeroShok bag, and it's really cool! Apart from all the Japanese salesmanship, it's fits the laptop quite nicely, has a small extra compartment (which I probably won't need) and supposedly can withstand quite large shocks. Though I have not tested that yet it's definitely nice to get a new bag :)

For IDSIA we did not get a webcam, but we nevertheless uploaded a movie about us and our current activities. Enjoy the film after the jump.

About the mission: MAVEN is set to launch in 2013 and will explore Mars’ upper atmosphere, ionosphere and interactions with the sun and solar wind. Scientists will use MAVEN data to determine the role that loss of volatile compounds, such as CO2, NO2, and H2O, from the Mars atmosphere to space has played through time, giving insight into the history of Mars atmosphere and climate, liquid water, and planetary habitability.

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.

iCub Dancing Rave
How cool is that?! This is the simulator with a changed dome and some nifty floor tiling. Okay the sunglasses I think is scripted but the rest is using a beat detector which sends the commands via YARP to the simulator.

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 ...

The iCub's shoulder, how it should not look

So the last two days we had the IM-CLeVeR Review Meeting here in Lugano and I helped showing some of the demos to the roughly 50 people involved in the project. As usual with robotics demonstration everything that could went wrong, and while reseting the software and homing the iCub, its shoulder decided to pop, as you can see on the picture.

Broken Shoulder in Detail

Luckily it seems like just the tendons are popped out of their places on the shoulder, so no ripping of a cables or breaking of the hardware. So now we are back to cleaning up and repairing the robot.