The paper “Autonomous driving at intersections: Combining theoretical analysis with practical considerations” won a Best Paper Award at the ITS World Congress 2015 in Bordeaux.
The paper was written by Arnaud de La Fortelle (Director of the Robotics Centre and holder of the Chair Drive for You) and Xiangjun Qian (PhD student at the Robotics Centre) as part of the work on the European project Autonet 2030 and within the Chaire Drive for You.
The move towards automated driving is gaining impetus recently. This paper follows the approach of combining theoretical analysis with practical issues. It gives an insight of some practical problems that are encountered when running automated vehicles in real environments, using intersection crossing as a major example. The aim is not to try to be exhaustive but to show some criteria (safety, efficiency, reactivity, resilience, scalability…) for decision making in automated driving that have to be balanced before any mass deployment. In a second part we introduce mathematical tools that can help define algorithms and systems that improve current state of the art. We will also show some perspective for accommodating the hypotheses of these mathematical tools with real life constraints.
The mobile robot developed in the Center For Robotics at MINES Centre ParisTech was illustrated during the decade of the Carnot Institutes. The Carnot Institutes are composed of laboratory of excellence with lots of R&D activities.
The mobile robot his equipped by the CoreSLAM algorithm (developed in the Center for Robotics) to locate and mapping a previously unknown space, the robot can move autonomously in a room to perform various missions.
Tony Noël in charge of this mobile robot gave more information about the robot and its applications in a video made within the ten years of Carnot Institutes.
[Youtube id = “4uyef0byAQ0” width = “600” height = “350”]
The mobile robot also seen at “Usine Nouvelle“
The session SIS25 on “theoretical and technical challenges for automated” won the Best rated session award at ITS World Congress 2015 in Bordeaux.
This session has been the opportunity to present the theoretical and technical challenges for automated driving from different perspectives. Indeed the speakers were coming from all around the world, and with an academic or industrial focus.
The session has been organised and moderated by Arnaud de La Fortelle (MINES ParisTech, Center for robotics), in collaboration the following speakers:
The Chair Drive for You was well represented during this session (PSA Peugeot Citroën, Valeo, Shanghai Jiao Tong University, University of California at Berkeley and MINES ParisTech). This award is a strong encouragement for the research carried out in the Chair Drive for You.
Summary of the session:
We present a new dataset of annotations for aligning a Point Distribution Model onto the human body. The corresponding research is described in the paper O. Huynh and B.Stanciulescu, “Clustering and Classifying Deformations for Shape Regression applied to the Human Body”, in ISPA 2015. The InriaLHB uses the pedestrian images from the Inria Person Dataset. Annotated shapes correspond to a standing person in front or back view.
Etienne Servais is pleased to invite you to his Ph. D. defense entitled “Trajectory planning and control of collaborative systems: Application to trirotor UAVs” on Friday 18 septembre 2015 at 15:00 at Mines Paristech (60 bd St Michel, Paris VI, RER B – Luxembourg), in the amphitheater L 109.
This thesis is dedicated to the creation of a complete framework, from high-level to low-level, of trajectory generation for a group of independent dynamical systems. This framework, based for the trajectory generation, on the resolution of Burgers equation, is applied to a novel model of trirotor UAV and uses the flatness of the two levels of dynamical systems.
The first part of this thesis is dedicated to the generation of trajectories. Formal solutions to the heat equation are created using the differential flatness of this equation. These solutions are transformed into solutions to Burgers’ equation through Hopf-Cole transformation to match the desired formations. They are optimized to match specific requirements. Several examples of trajectories are given.
The second part is dedicated to the autonomous trajectory tracking by a trirotor UAV. This UAV is totally actuated and a nonlinear closed-loop controller is suggested. This controller is tested on the ground and in flight by tracking, rolling or flying, a trajectory. A model is presented and a control approach is suggested to transport a pendulum load.
Axel Barrau is pleased to invite you to his PhD. defense on Thursday, 15 September 2015 at 15:00 at MINES ParisTech 60 boulevard Saint-Michel 75006 Paris.
Mme Brigitte d’ANDREA-NOVEL, Professeur, Mines ParisTech (Examinateur),
M. Xavier BISSUEL, Expert en navigation inertielle, Sagem (Examinateur),
M. Silvère BONNABEL, Professeur, Mines Paristech (Examinateur, directeur de thèse),
M. Jay FARRELL, Professeur, UC Riverside (Examinateur),
M. Pascal MORIN, Professeur, UPMC (Rapporteur),
M. Christophe PRIEUR, Directeur de recherche, Gipsa-lab (Rapporteur),
M. Pierre ROUCHON, Professeur, MINES ParisTech (Examinateur).
The present thesis explores the use of non-linear state errors to devise extended Kalman filters (EKFs). First we depart from the theory of invariant observers on Lie groups and propose a more general yet simpler framework allowing to obtain non-linear error variables having the novel unexpected property of being governed by a (partially) linear differential equation. This result is leveraged to ensure local stability of the invariant EKF (IEKF) under standard observability assumptions, when extended to this class of (non-invariant) systems. Real applications to some industrial problems in partnership with the company SAGEM illustrate the remarkable performance gap over the conventional EKF. A second route we investigate is to turn the noise on and consider the invariant errors as stochastic processes. Convergence in law of the error to a fixed probability distribution, independent of the initialization, is obtained if the error with noise turned off is globally convergent, which in turn allows to assess gains in advance that minimize the error’s asymptotic dispersion. The last route consists in stepping back a little and exploring general EKFs (beyond the Lie group case) relying on a non-linear state error. Novel mathematical (global) properties are derived.
The chair Chaire elected unanimously Professor Arnaud de La Fortelle as the new holder. The professor is an expert in Fortelle intelligent transport systems (ITS) with a specialization in vehicle communications, cooperative systems and stochastic models.
His tenure is part of the revival of Chair FRELON, which aims to develop the operational and theoretical knowledge in the field of urban logistics, making the technological approach the common base of new projects while continuing capitalization operational experience of the partners.
The professor Fortelle seek to use the latest advances in automation and robotics, robotics developed in the center of MINES ParisTech, of which he is director, to provide the information, models, tools and experiments with themes Research addressed.
La startup YoGoKo, déjà lauréate du concours i-LAB en Emergence lors de l’édition 2012 et du concours OMTE de DIGITEO également en 2012, passe aujourd’hui à l’étape supérieure en devant lauréate du 17ème concours national d’aide à la création d’entreprises de technologies innovantes (i-LAB) décerné par le Ministère en charge de l’Enseignement Supérieur et de la Recherche, dans la catégorie Création & Développement.
YoGoKo a été fondée en juin 2014 par Thierry Ernst (chercheur à MINES ParisTech et anciennement Inria), Emmanuel Thierry (anciennement ingénieur à Télécom Bretagne), Jean-Marie Bonin (Professeur à Télécom Bretagne) et Arnaud de la Fortelle (Professeur à MINES ParisTech).
YoGoKo conçoit, déploie et met en œuvre un système de communication innovant spécifiquement adapté aux besoins de connectivité du transport routier. Ce système de communication associe des boîtiers de communication installés dans des équipements hétérogènes et distants (véhicules, infrastructure routière, mobilier urbain) à une plateforme Cloud de services et de gestion des communications vers et à partir de ces boîtiers.
Il permet aux véhicules, à l’infrastructure, aux centres de contrôle et aux équipements nomades d’échanger des informations de manière standardisée, en toute sécurité, en utilisant toutes les technologies d’accès disponibles (WiFi, 3G, satellite, courant porteur, etc.). Ces solutions permettent ensuite de déployer des services de gestion de parc d’équipements, de mise à jour logicielle, de localisation et de diagnostic à distance.
La technologie développée par YoGoKo repose sur les travaux de Télécom Bretagne, de l’Inria et de MINES ParisTech.
Pour plus d’informations : www.yogoko.fr
The logistics team from CAOR developed a serious game for the POMONA group.
The game allows to increase knowledge on logistics performance by identifying interactions between process variables associated to sales, buying and logistics.
For more information : simon.tamayo[at]mines-paristech.fr
The Chair Drive for You is pleased to invite you to a seminar on conflict resolution for automated cars. We have the honor to receive Alessandro Colombo and Gabriel Rodrigues De Campos from the Polytecnico di Milano (Italy).
The seminar will be held at MINES ParisTech room V334 on Monday, June 1 (from 14:00 to 16:30).
This seminar is public and free of charge.