IDSIA Robotics Lab, Dalle Molle Institute for Artificial Intelligence Research, Manno-Lugano, Switzerland


Improving Robot Vision Models for Object Detection Through Interaction (IJCNN 2014 Submission)

Published on Feb 5, 2014

Video Attachment to the IJCNN 2014 Conference Submission

Improving Robot Vision Models for Object Detection Through Interaction
created by Juxi Leitner, Alexander Forster, Jurgen Schmidhuber
 

Uploaded on Nov 29, 2011

Presentation of the IDSIA Robotics Lab for the EU Robotics Week 2011.

IDSIA (Istituto Dalle Molle di Studi sull'Intelligenza Artificiale) is a non-profit oriented research institute for artificial intelligence, affiliated with both the Faculty of Informatics of the University of Lugano and the Department of Innovative Technologies of SUPSI, the University of Applied Sciences of Southern Switzerland. We focus on machine learning (artificial neural networks, reinforcement learning), optimal universal artificial intelligence and optimal rational agents, operations research, complexity theory, and robotics. IDSIA is situated near Lugano, a lakeside city in the Italian-speaking canton of Ticino, a region of Switzerland well known for its warm climate and outstanding scenery.
 

Reactive Reaching and Grasping on a Humanoid

Published on Jun 2, 2014

Video using our MoBeE and icVision frameworks to allow for reactive grasping and obstacle avoidance on the iCub.

Abstract:
We propose a system incorporating a tight integration between computer vision and robot control modules on a complex, high-DOF humanoid robot. Its functionality is showcased by having our iCub humanoid robot pick-up objects from a table in front of it. An important feature is that the system can avoid obstacles -- other objects detected in the visual stream -- while reaching for the intended target object. Our integration also allows for non-static environments, i.e. the reaching is adapted on-the-fly from the visual feedback received, e.g. when an obstacle is moved into the trajectory. Furthermore we show that this system can be used both in autonomous and tele-operation scenarios.
 

Toward Intelligent Humanoids | iCub 2012
October 8, 2012

Director / Screenwriter / Voice Over: Mikhail Frank
Co-Director / Cinematographer / Editor: Tomas Donoso (tomasdonoso.com)
Music: Magnus Birgersson aka Solar Fields (solarfields.com) Ultimae Records (ultimae.com)

Principal Researchers (alphabetical):

Mikhail Frank -
Robotics (Planning and Control)
M.S. and B.S. Mechanical Engineering, University of Connecticut, USA
B.S. German Language, University of Connecticut, USA

Simon Harding -
Machine Learning and Vision
Ph.D. Electronics, University of York, UK
B.Sc. AI and Computer Science, Birmingham University, UK

Varun Kompella -
Pattern Recognition and Reinforcement Learning
M.S. Informatics, Institut Nationale Polytechnique de Grenoble, France
M.S. and B.E. Electronics and Communication Engineering,
Ramaiah Institute of Technology, Bangalore, India

Jurgen Leitner -
Robotics (Computer Vision and Control)
M.Sc. Space Science and Technology, Lulea Technical University, Sweden
M.Sc. Space Robotics and Automation, Aalto University (TKK), Finland
B.Sc. Software and Information Engineering, TU Vienna, Austria

Hung Ngo -
Reinforcement Learning
M.Sc. Computer Engineering, KyungHee University, Korea.
B.E. Electronics and Telecom, HCMC University of Technology, Vietnam

Leo Pape -
Reinforcement Learning
Ph.D. Physical Geography, Utrecht University, Netherlands
M.Sc. Cognitive Artificial Intelligence, Utrecht University, Netherlands

Marijn Stollenga -
Artificial Intelligence, Optimization
M.Sc. Artficial Intelligence, University of Groningen, Netherlands
B.Sc. Artficial Intelligence, University of Groningen, Netherlands

Supervising Researchers:

Alexander Forster -
Director of IDSIA Robotics Lab
Lecturer, Universita della Svizzera italiana

Jurgen Schmidhuber - Director of IDSIA
Professor of Artificial Intelligence, Universita della Svizzera italiana
Professor, Scuola universitaria professionale della Svizzera italiana

We support the following open-source projects:

The RobotCub Project
Yet Another Robot Platform (YARP)
...and the iCub Cartesian Interface
The Boost Graph Library (BGL)
Computational Geometry Algorithms Library (CGAL)
The Software Library for Interference Detection (FreeSOLID)
Cross-Platform Make (CMAKE)
The Qt Application Framework

The authors would also like to thank:

The Italian Institute of Technology (IIT) for developing the iCub, the first
open-source, humanoid robot.

Gregor Kaufmann and Tobias Glasmachers for their valuable
contributions to the MoBeE code base.

No researchers or robot-babies were harmed during the making of this film.
 

Quadcopter navigation in the forest using deep neural networks

Published on Feb 1, 2016

Alessandro Giusti, Jerome Guzzi, Dan Ciresan, Fang-Lin He, Juan Pablo Rodr?guez G?mez, Gianni Di Caro, J?rgen Schmidhuber, Luca M. Gambardella, Flavio Fontana, Matthias Faessler, Christian Forster, Davide Scaramuzza

IDSIA - Dalle Molle Institute for Artificial Intelligence, USI-SUPSI, Lugano, Switzerland
RPG - Robotics and Perception Group, Department of Informatics, University of Zurich, Switzerland
 
Back
Top