Home

Langues

Mobilité Innovante
des personnes, des biens et des machines

SIDO2019

The Showroom of the Internet of Things connected (SIDO) took place on 10 and 11 April 2019 in Lyon. This is the national meeting where manufacturers, technology providers, digital players, research laboratories, startups, investors, designers, entrepreneurs, local authorities and the media meet to explore and make the Internet of Things, the new economy .

The opportunity for participants to discover the most recent and most important advances in the field of connected objects and of course to present their research, as did some IMobS³ actors.

Clermont Innovation Week 2019

As part of the Clermont Innovation Week 2019 at the initiative of ViaMéca, the Institut Pascal and Irstea, gathered in the framework of the IMobS³ LabEx and the Challenge 2 of CAP 20-25, proposed a demonstration of mobile robotics for high school students on the PAVIN VU platform.

LabEx IMobS3 extension for 5 years

Frédérique Vidal, Minister of Higher Education, Research and Innovation and Guillaume Boudy, Secretary General for Investment, announced on February 8, 2019 the list of the 103 laboratories of excellence (LabEx) that the Prime Minister Edouard Philippe has decided to extend for 5 years following the positive evaluation carried out by an international jury.

Among them is the LabEx IMobS³!!!

Cooperative robotics for transit

The LabEx IMobS³, the ViaMéca competitiveness cluster, the I-SITE CAP 20-25 and the Coboteam regional cluster have dedicated this year their event to innovative robotic solutions in the service of transit.

What is the Mobility DOMEX?

The Excellence Area "Mobility and Intelligent Transport Systems" movie of the Auvergne-Rhône-Alpes Region is online! Michel Dhome explains the implication of LabEx IMobS³ in this DOMEX.

Let's have a look here.

The IMobS3 Labex

The IMobS³ "Laboratoire d'Excellence" (for "Innovative Mobility : Smart and Sustainable Solutions") aims to develop efficient and environmentally aware technological bricks for an innovative mobility of people, goods and machines by playing on the triptych "Research - Education - Promotion".

The IMobS³ LabEx is supported by 5 establishments present in Clermont site (Clermont Auvergne University - project leader, SIGMA Clermont engineering school, CNRS, Irstea and Cerema. It is based on the multidisciplinary and complementary skills of eight laboratories (ACTé, DLCF-Cerema, LAPSCO, LIMOS, LMBP, ICCF, Pascal Institute, TSCF-Irstea) placed under the supervision of these institutions often in the form of mixed research units.

In February 2017, the Clermont University community obtained the label I-Site "Initiatives - Science - Innovation - Territories - Economy" with the project CAP 20-25. This label aims to structure the University thanks to the successes acquired during the Future Investment Programmes first call. LabEx IMobS³ is proving to be the Challenge 2 "Innovative systems and services for the production and the transports" cornerstone.

Futur events

24/05/19 : PhD Defense - Jose Sanchez Loza

On Friday 24^th May at 10:00am, Mr. Jose Sanchez Loza will publicly support his doctoral thesis entitled:

"Shape Sensing of Deformable Objects for Robot Manipulation"

Place: Amphi Recherche - EUPI, Campus des Cézeaux, 63170 AUBIERE

RESUME

Deformable objects are ubiquitous in our daily lives. On a given day, we manipulate clothes into uncountable congurations to dress ourselves, tie the shoelaces on our shoes, pick up fruits and vegetables without damaging them for our consumption and fold receipts into our wallets. All these tasks involve manipulating deformable objects and can be performed by an able person without any trouble, however robots have yet to reach the same level of dexterity. Unlike rigid objects, where robots are now capable of handling objects with close to human performance in some tasks; deformable objects must be controlled not only to account for their pose but also their shape. This extra constraint, to control an object's shape, renders techniques used for rigid objects mainly innapplicable to deformable objects. Furthermore, the behavior of deformable objects widely diers among them, e.g. the shape of a cable and clothes are signicantly aected by gravity while it might not aect the conguration of other deformable objects such as food products. Thus, dierent approaches have been designed for specic classes of deformable objects.

In this thesis we seek to address these shortcomings by proposing a modular approach to sense the shape of an object while it is manipulated by a robot. The modularity of the approach is inspired by a programming paradigm that has been increasingly been applied to software development in robotics and aims to achieve more general solutions by separating functionalities into components. These components can then be interchanged based on the specic task or object at hand. Our approach, thus, takes the form of a pipeline to sense the shape of deformable objects.

To validate the proposed pipeline, we implemented three dierent applications. Two applications focused exclusively on estimating the object's deformation using either tactile or force data, and the third application consisted in controlling the deformation of an object. An evaluation of the pipeline, performed on a set of elastic objects for all three applications, shows promising results for an approach that makes no use of visual information and hence, it could greatly be improved by the addition of this modality.

17/05/19 : Seminar "Intelligent Vehicles and Machines"

The challenge "Intelligent Vehicles and Machines" of LabEx IMobS³ organizes its annual seminar to take stock of current actions.

Date : Friday, May 17, 2019 from 8:45 am to 1:30 pm

Location : Amphi Lagrange, SIGMA-Clermont, Campus des Cézeaux, 63170 AUBIERE

16/05/19 : PhD Defense - Yizhen Lao

On Thursday 16^th May at 13:30, Mr. Yizhen Lao will publicly support his doctoral thesis entitled:

"3D Vision Geometry for Rolling Shutter Cameras"

Place: Amphi 9109 of Pôle Physique, Campus des Cézeaux, 63170 AUBIERE

RESUME

Many modern CMOS cameras are equipped with Rolling Shutter (RS) sensors which are considered as low cost, low consumption and fast cameras. In this acquisition mode, the pixel rows are exposed sequentially from the top to the bottom of the image. Therefore, images captured by moving RS cameras produce distortions (e.g. wobble and skew) which make the classic algorithms at best less precise, at worst unusable due to singularities or degeneracies. The goal of this thesis is to propose a general framework for modelling and solving structure from motion (SfM) with RS cameras. Our approach consists in addressing each sub-task of the SfM pipe-line (namely image correction, absolute and relative pose estimation and bundle adjustment) and proposing improvements.

The first part of this manuscript presents a novel RS correction method which uses line features. Unlike existing methods, which uses iterative solutions and make Manhattan World (MW) assumption, our method R4C computes linearly the camera instantaneous-motion using few image features. Besides, the method was integrated into a RANSAC-like framework which enables us to detect curves that correspond to actual 3D straight lines and reject outlier curves making image correction more robust and fully automated.

The second part revisits Bundle Adjustment (BA) for RS images. It deals with a limitation of existing RS bundle adjustment methods in case of close read-out directions among RS views which is a common configuration in many real-life applications. In contrast, we propose a novel camera-based RS projection algorithm and incorporate it into RSBA to calculate reprojection errors. We found out that this new algorithm makes SfM survive the degenerate configuration mentioned above.

The third part proposes a new RS Homography matrix based on point correspondences from an RS pair. Linear solvers for the computation of this matrix are also presented. Specifically, a practical solver with 13 point correspondences is proposed. In addition, we present two essential applications in computer vision that use RS homography: plane-based RS relative pose estimation and RS image stitching.

The last part of this thesis studies absolute camera pose problem (PnP) and SfM which handle RS effects by drawing analogies with non-rigid vision, namely Shape-from-Template (SfT) and Non-rigid SfM (NRSfM) respectively. Unlike all existing methods which perform 3D-2D registration after augmenting the Global Shutter (GS) projection model with the velocity parameters under various kinematic models, we propose to use local differential constraints. The proposed methods outperform stat-of-the-art and handles configurations that are critical for existing methods.

07/02/19 : Cooperative robotics for transit

The LabEx IMobS³, the ViaMéca competitiveness cluster, the I-SITE CAP 20-25 and the Coboteam regional cluster propose this year to dedicate their event to innovative robotic solutions in the service of transit.

Date : Thursday, February 7, 2019 from 8:30 am to 5 pm

Location : Polytech Clermont, Common Pole, Amphi 3, Campus des Cézeaux, 63170 AUBIERE

Detailed program and Registration

18/12/18 : PhD Denfense - François de La Bourdonnaye

On Tuesday 18^th December at 2pm, Mr. François de La Bourdonnaye will publicly support his doctoral thesis entitled:

"Learning sensori-motor mappings using little knowledge: application to manipulation robotics"

Place: Amphi 9109 of Pôle Physique, Campus des Cézeaux, 63170 AUBIERE

Langues

SIDO2019

Clermont Innovation Week 2019

LabEx IMobS3 extension for 5 years

Cooperative robotics for transit

What is the Mobility DOMEX?

Scientific challenges

Challenge 1

Challenge 2

Challenge 3

Langues

SIDO2019

Clermont Innovation Week 2019

LabEx IMobS3 extension for 5 years

Cooperative robotics for transit

What is the Mobility DOMEX?

Scientific challenges

Challenge 1

Challenge 2

Challenge 3

Login Form