Current national collaborations

ANR national projects

ANR Contint Prosit project

This project is a multidisciplinary industrial research type project led by the Prisme lab (previously called LVR) in Bourges. It is just starting in collaboration with Lirmm in Montpellier, LMS in Poitiers, CHU of Tours, and the Robosoft company. The object of this project is to develop an interactive master-slave robotic platform for a medical diagnosis application (tele-echography) and to develop a cluster of interactive functionalities combining: visual servoing, force control, haptic feedback, virtual human interface, 3D representation of organs. Within this project, we will study and develop autonomous control modes that directly make use of visual data provided by a camera observing the patient and information contained in the ultrasound image to move the ultrasound probe.

ANR Contint USComp project

This project, led by Alexandre Krupa, has just started. It involves a collaboration with the Visages team in Rennes, LSIIT in Strasbourg and Lirmm in Montpellier. Its goal is to provide methodological solutions for real-time compensation of soft tissues motion during ultrasound imaging. The approach will consist in synchronizing the displacement of a 2D or 3D ultrasound transducer to stabilize the observed image by the use of a robotic arm actuating the ultrasound probe. The problematic concerns more specifically the use in the control scheme of the peroperative ultrasound image, the interaction force between the probe and the soft tissues and the measurements of external signals providing the breathing state of the patient.

ANR Psirob RobM@rket project

This project started in March 2008. It is realized in collaboration with BA Systèmes, CEA List, and Université de Caen. RobM@rket project aims at developing automated applications for order picking in a fast-expanding business which mainly includes manual tasks. The system would apply to packaging before dispatching items ordered on a website through an online catalogue including more than 1000 references or to order picking with orders dedicated to kitting. The robotic system will be made of a PLC mobile platform of AGV type (Automatic Guided Vehicles, by BA Systèmes) and of an industrial robot arm. This platform will be used to integrate several algorithms allowing picking up selected items in a warehouse through a command file and bringing them back for dispatching or assembling them. The items could be either methodically stored or jumbled in the boxes. Our current work consists in developing vision-based objects localization techniques for grasping them.

ANR Tosa CityVIP project

This project, managed by Lasmea, started in July 2008. It involves eight partners, including Lagadic. The project consists of enhancing the autonomy of urban vehicles by integrating sensor-based techniques with a geographical database. Within CityVIP, Lagadic will provide its expertise in the fields of vision-based localization and vision-based navigation, including safe navigation in the presence of obstacles.

ANR AM Gamme project

This project started in March 2008. It is realized in collaboration with Orange Labs, CEA Leti, Movea, Polymorph, and the Museum of fine arts in Rennes. The Augmented Reality (AR) concept aims to enhance our real world perception, combining it with fictitious elements. AR research is concerned with the different methods used to augment live video imagery with coherent computer generated graphics. The combination of mobile technologies and AR will allow the design of a video rendering system with an augmentation of the real world depending on user localisation and orientation. In this project we propose to focus on indoor environments having as a main objective the implementation of AR technologies on mobile devices. The experimental field proposed is the Museum, a controlled environment (constant lightening and location of objects) without some of the perturbations of outdoor environments. We do estimate that a successful museum prototype could be used as the backbone of many other indoor and outdoor AR applications. Within this project we are involved in tracking and sensor fusion parts of the AR process.

ANR Psirob Scuav project

This project, led by Tarek Hamel from I3S, started in June 2007. It is realized in collaboration with I3S, the EPI ARobAS at Inria Sophia Antipolis-Méditerranée, Heudiasyc in Compiègne, the CEA-List and the Bertin company. It is devoted to the sensor-based control of small helicopters for various applications (stabilization landing, target tracking, etc.).

DGA project

PEA Tarot

This project is a large project realized for the DGA through a consortium led by Thales Optronics. We work in close collaboration with the ARobAS team at Inria Sophia Antipolis-Méditerranée. This project is about the development of tracking algorithms and the control of non-holonomic vehicles. Within this project, our work consists in developing 2D image-based tracking algorithms in complex outdoor scenes. The algorithms provided last year using points of interest were improved, new functionalities were added and our contribution was ported to the DGA's autonomous military terrestrial vehicle dedicated to survey missions.

Past national collaborations

CNRS ROBEA Projects

Parknav project

This three years project, which began in october 2002 and financed by CNRS within the ROBEA framework is a collaboration between INRIA Grenoble (Sharp, Movi, PRIMA), the LAAS (RIA) and the VISTA project. The objective of this project is the automation of the control of a vehicle in road environment.

Omnibot project

This two years project started in October 2002. The aim of this project is to develop robot navigation schemes using a panoramic vision sensor. It is realized through a collaboration between Lasmea in Clermont-Ferrand, Lirmm in Montpellier, Crea in Amiens and our group. This year, we have determined the analytical form of the interaction matrix related to image moments using the very particular geometrical models of panoramic sensors. A visual servoing control law has then been developed from this modeling step. A project meeting has been organized at Irisa in November 2003.

Tasks sequencing project

This three years project started in September 2003. The aim of this project is to develop tasks sequencing schemes to realize high level robotics tasks from local sensor-based control techniques. Comparison between vision-based control and human beings for gaze control is also considered. It is realized through a collaboration between Laas, Cerco and Enit, all located in Toulouse, and our group.

Bodega project

This two years project started in November 2003. Its aims is to develop vision-based and sensor-based methods for the autonomous navigation of mobile vehicles moving around an urban environments. It is realized through a collaboration between Ensil in Limoges, UTC in Compiègne, Lasmea in Clermont-Ferrand, the Icare group of Inria Sophia-Antipolis, and our group. A project meeting has been organized at Irisa in November 2003.

Robvolint project

This two years project started in November 2003. Its aims is to develop vision-based localization techniques and visual servoing schemes for small helicopters moving around an indoor environment. It is realized through a collaboration between I3S in Nice, Cea in Fontenay-aux-Roses, and our group.

CNRS DSTIC specific actions

AS real-time augmented reality

This action, leaded by M.-O. Berger, is concerned with augmented reality. A. Comport and E. Marchand have presented their work in this area during a workshop in Paris in September 2003. Eric Marchand participated to the IEEE Int. Symp. on Mixed and Augmented Reality thanks to this action.

National projects

Predit Mobivip project

This project is a large project headed by Inria Sophia Antipolis. It is concerned with the navigation of mobile vehicles in urban environments. Within this project, our work consists in designing autonomous vision-based navigation techniques using an image database of the environment. As for scientific aspects, this project is closely related to the Robea Bodega project.

Sora RIAM Project

The goal of the SORA project (Objects tracking for augmented reality) is the developpement of tracking algorithm for augmented reality application. Our partners are Total-Immersion and VideoMage. Augmented Reality has now progressed to the point where real-time applications are being considered and needed. At the same time it is important that synthetic elements are rendered and aligned in the scene in an accurate and visually acceptable way. In order to address these issues a real-time, robust and efficient 3D model-based tracking algorithm is proposed for a 'video see through' monocular vision system. Virtual objects can then be projected into the scene using the pose. The tracking rate is 50Hz.