You can sort by using the menu on the right.

  • ICML 2012 Workshop on Representation Learning

    In this workshop we consider the question of how we can learn meaningful and useful representations of the data. There has been a great deal of recent work on this topic, much of it emerging from researchers interested in training deep architectures. Deep learning methods such as deep belief networks, sparse coding-based methods, convolutional networks, and deep Boltzmann machines, have shown promise as a means of learning invariant representations of data and have already been successfully applied to a variety of tasks in computer vision, audio processing, natural language processing, information retrieval, and robotics. Bayesian nonparametric methods and other hierarchical graphical model-based approaches have also been recently shown the ability to learn rich representations of data.
    By bringing together researchers with diverse expertise and perspectives but who are all interested in the question of how to learn data representations, we will explore the challenges and promising directions for future research in this area.

  • ICML 2012 Workshop on New Challenges for Exploration & Exploitation 3

    The goal of this challenge is to build an algorithm that learns efficiently a policy to serve news articles on a web site. At each iteration of the evaluation process, you will be asked to pick an article from a list given a visitor (136 binary features + a timestamp). To build a smart algorithm, you might want to balance carefully exploration and exploitation and pay close attention to the “age” of the news articles (among other things of course). A quick look on the leaderboard is enough to figure out why that last point matters. It is the overall CTR (click through rate) of your algorithm that will be taken into account to rank it on the leaderboard.

  • Conference on Learning Theory

    The 25th Conference on Learning Theory (COLT 2012) was held in Edinburgh, Scotland, on June 25–June 27, 2012. COLT is supported by the Association for Computational Learning (ACL).

  • Plenary talks from ICRA 2012

    Plenary talks presented at IEEE ICRA 2012.

  • Semantic Perception and Mapping for Knowledge-enabled Service Robotics

    Consider a robot that is to act as a household assistant in an unknown kitchen environment. This robot has to acquire and use knowledge about where the task-relevant objects, such as the dish- washer and the oven are and how the robot can act on them. A recent advent of smart devices (e.g. smart phones) and high-quality-low-cost sensors (e.g. Kinect) provides us with the a ordable resources for the robot which link sensory information to the robot's knowledge base and high-level deliberative components. Resources like this allow the general-purpose service robots to e.g. query information from world wide web, seek help from remote experts through shared autonomy interfaces and to act independently and safely in human living envi- ronments.

    In this hands-on workshop we will identify key problems and so- lutions by narrowing down the de nition of semantics, we will dis- cuss what is the representative end world model as a result of se- mantic mapping, single out the optimal sensors, consider static vs. dynamic aspects of environment modeling and nally address the life- long learning in order to leverage not only the sensor data but also from human living patterns and behaviors. The workshop will feature excellent talks from researchers from academia as well as industry, live demonstrations, poster session and a working session with an aim to standardize some fundamental concepts in semantic mapping. We plan to build upon the series of related events at previous IROS, ICRA and RSS conferences.

  • Industry-Academia collaboration in the ECHORD project: a bridge for European robotic innovation

    In order to boost the practical use of robot technology not only in industrial settings, more sophisticated robotic solutions have to be elaborated, particularly in terms of autonomy, exibility, interactiv- ity and cooperating with human, ease of use, and safety. In order to be able to develop applications on the short-term and to maintain ecient improvement of European robotics in the long term, a bet- ter cooperation and technological know-how transfer between robot manufacturers and research institutions is essential.

    ECHORD (European Clearing House for Open Robotics Devel- opment, FP7-ICT-231143, http://www.echord.info) is an innovative framework aiming at intensifying this collaboration by carrying more than 50 small sub-projects (socalled experiments with speci c research foci and scenarios) with consortia composed of academia and indus- try. The whole project is coordinated by the Technische Universitt Mnchen (Germany), University of Naples (Italy), and University of Coimbra (Portugal). This workshop is composed of two parts:

    1. A presentation session where an overview of the ECHORD exper- iments will be given by the coordinating partners of ECHORD, then (intermediate) results of the experiments targeted to an in- ternational audience will be presented, followed by discussions.
    2. An open discussion session about innovative solutions in and outside ECHORD, future impacts, new applications, limitations and possible improvements, as well as safety concepts.

  • Modular Surgical Robotics: how can we make it possible?

    Computer and Robot Assisted Surgery (CRAS) is an area receiving broad attention worldwide, because of its strong potential to achieve new levels of healthcare. Many researchers and potential users are attracted to the eld. However, the market is o ering very few prod- ucts, which cannot be enhanced with add-on components produced by other manufacturers. This inability is not only due to commercial, but also to technical reasons, since an FDA-approved or CE marked surgical device cannot be altered by adding new components.

    Motivated by these considerations, the European research project Eurosurge addresses the issues of modularity and integration of di er- ent functions into a surgical robot, with a special emphasis on the in- tegration of cognitive functions into robotassisted surgical procedures, and on the satisfaction of regulatory constraints.

    This workshop aims at presenting to the robotic community the results of the rst six months of the project and to establish a fruitful discussion with experts in the areas of integration, standards, bench- marking, architectures and cognition. The workshop will be divided into three phases: the rst summarizing the current status of Euro- surge; the second with presentations from experts outside the project; and the third with a discussion to provide suggestions and opinions about introducing modularity into robotic surgery

  • Stochastic Geometry in SLAM

    Feature based SLAM is closely related to multi-sensor, multi-target .ltering. In essence, the objective is to jointly estimate a time-varying number of targets and their states from sensor measurements with data association and detection uncertainty, clutter and noise. Its sys- tematic treatment, using random set theory, led to the mathematical tools known as Finite Set Statistics (FISST), developed for data fusion and estimation of random sets.

    Random vector based SLAM is known to be extremely fragile in the presence of feature detection and data association uncertainty. Therefore recent research which has applied the FISST framework to autonomous map representations will be the subject of this workshop.

    Workshop topics will include global localisation, Rao-Blackwellised and multi-robot SLAM which jointly consider false alarms, missed detections and spatial sensor uncertainty. Experimental results in challenging outdoor and marine environments will be demonstrated.

  • Workshop on Long-term Autonomy II

    The problem of long-term autonomy is attracting increased at- tention in the robotics research community. State-of-the-art robotic mapping and localization systems have demonstrated the ability to operate in increasingly large-scale environmentsthe DARPA Grand Challenge, Mars Exploration Rovers, Willow Garage PR2 demos, long- range visual-teach-and-repeat systems, and Atlantic-Ocean crossing AUVs are only some of the examples of the maturity of the eld. However, it remains to be seen how to extend the operation time of autonomous robotic systems from days to months or years. This goal poses new challenges related to robust long-term operation and life- long learning. What valuable lessons have we learnt from large-scale robotic experiments? What challenges need to be addressed to en- sure robust and continual operation? We invite authors to share their experience and insight at this full-day workshop.