Speaker: Raquel Urtasun. Assistant Professor at the Toyota Technological Institute at Chicago.

Talk: 3D Urban Scene Understanding from Movable Platforms

Date: 19th of December, 2011, 15:00 h

Place: Sala de Grados del Edificio Politécnico. Zona Este. Primera planta



Developing autonomous systems that are able to assist humans in everyday’s tasks is one of the grand challenges in modern computer science. Notable examples are personal robotics for the elderly and people with disabilities, as well as autonomous driving systems which can help decrease fatalities caused by traffic accidents. In order to perform tasks such as navigation, recognition and manipulation of objects, these systems should be able to efficiently extract 3D knowledge of their environment. While a variety of novel sensors have been developed in the past few years, in this work we focus on the extraction of this knowledge from visual information alone. Unfortunately, existing approaches to 3D scene understanding either produce a mild level of understanding, e.g., segmentation, object detection, or are not accurate enough for these applications, e.g., 3D pop-ups. In this talk I will show generative models of 3D urban scenes that take into account dependencies between static and dynamic features, and are able to infer the geometric (e.g., street orientation) and topological (e.g., number of intersecting streets) properties of the scene layout, as well as the semantic activities occurring in the scene, e.g., traffic situations at an intersection, from monocular and stereo imagery. Furthermore, I will show that this global level of understanding provides the context necessary to disambiguate current state-of-the-art detectors. This is joint work with Andreas Geiger, Martin Lauer and Christian Wojek.


Raquel Urtasun is an Assistant Professor at TTI-Chicago a philanthropically endowed academic institute located in the campus of the University of Chicago. She was a visiting professor at ETH Zurich during the spring semester of 2010. Previously, she was a postdoctoral research scientist at UC Berkeley and ICSI. Before that, she was a postdoctoral associate at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, where she worked with Prof. Trevor Darrell. Raquel Urtasun completed her PhD at the Computer Vision Laboratory, at EPFL, Switzerland in 2006 working with Pascal Fua and David Fleet at the University of Toronto. She has been area chair of NIPS multiple times, and served in the committee of numerous international computer vision and machine learning conferences (e.g., CVPR, ICCV, ECCV, ICML, NIPS). Her major interests are statistical learning and computer vision, with a particular interest in non-parametric Bayesian statistics, latent variable models, structured prediction and their application to 3D scene understanding and human pose estimation.


This workshop presents the tenth Workshop of the RoboCity2030 project, supported by the PADIR program of the Community of Madrid. The RoboCity2030 consortium is formed by the research groups of the University Carlos III of Madrid, the Centre for Automation and Robotics of CSIC, the Polytechnic University of Madrid, the University of Alcalá, the University Rey Juan Carlos and the UNED. The workshop will be held on the first day of the IEEE Intelligent Vehicles Conference, June 3rd, 2012.

This workshop is looking for original research works on perception in robotics area carried out by the most important international groups that are working in this subject. Topics of interest include, but are not limited to:

•    Sensor-based mobile robot localization
•    Multisensor fusion and integration
•    Sensor-based robot control
•    Distributed sensor networks
•    Simultaneous Localization and Mapping
•    Computer vision in robotics
•    3D reconstruction
•    Cooperative perception in robotics
•    New sensing devices
•    Human-Robot interaction




Registration online is open.






When Joseph Engelberger, an industrial robotics pioneer, once remarked "I can't define a robot, but I know one when I see one” it was patent how heterogeneous is the robotics matter. In this summer course we focus in the main task that are needed when we work on mobile robotics (navigation, localization, cognitive process) and how can be improved using Soft Computing techniques. Summer course begins with an introduction to robotics and Soft Computing, and then we will progress in the study of more complex algorithms and systems like Simultaneous Localization And Mapping and swarm robotics. Finally, at each phase of the course, we will do some practical works with robotics platforms (simulators and real robots).

Important dates: from 11th to 15th of July
Schedule: from 9:00am to 1:00pm and from 2:30pm to 4:30pm (with lunching time from 1:00pm to 2:30pm)*
* Lunch is included in the price
Teaching hours: 30
Credits: 2 Credits or 1 ECTS
Place: Escuela Politécnica Superior (Lab Oeste-L5)
Price: Regular: 200 €, University Students: 150 €
Number of alumns: min: 12 – max: 24

More information



Organized by:  Suported by:


Within the activities of RoboCity2030-II members:


Luis Miguel Bergasa 
Robesafe Director
This email address is being protected from spambots. You need JavaScript enabled to view it.
Tlf:      +34 918856569
Fax:   +34 918856590


Polytechnic School

University of Alcalá

Av. Jesuitas s/n.

Alcalá de Henares, 28871

Madrid, Spain

Sarbot Team