News

PhD Defense: “Learning-based algorithms for real-time visual localization of mobile robots”

The Centre for Robotics is proud to announce that the PhD Defense of Arthur MOREAU will take place on Thursday, April 27th at MINES PARIS.

The subject of the work is:

“Learning-based algorithms for real-time visual localization of mobile robots”

This research is the result of a collaboration between our Centre and Huawei France.

The PhD has been directed by Arnaud de La Fortelle, and supervized by Bogdan Stanciulescu.

 

To attend:
MINES PARIS
60, Saint-Michel boulevard, Paris.

 

Jury members:

Valérie GOUET-BRUNET, Research Director, LASTIG – National Institute for Geographical and Forest Information (IGN)

Patric JANSFELT, Full Professor, KTH Royal Institute of Technology, Sweden

Vincent LEPETIT, Research Director, École des ponts ParisTech

Bogdan STANCIULESCU, Associate Professor, MINES PARIS

Arnaud de La Fortelle, HDR, CEO Heex Technologies

Dzmitry TSISHKOU, PhD, Huawei Technologies France

 

Abstract:

This PhD investigates visual-based algorithms for real-time localization of mobile robots. The core objective is to provide a reliable solution to the vehicle relocalization problem in large urban environments using camera images as input. Thanks to computer vision progress and low cost sensors, visual-based localization is an appealing solution, where the best performing methods use structure-based pipelines with high computational cost and memory footprint. On the other hand, learning-based approaches connect images and camera poses in an end-to-end fashion, matching real time embedded processing requirements. This PhD aims to push forward learning-based methods on several aspects: localization accuracy, uncertainty quantification, robustness to real-world conditions and easier adaptation to unseen maps. These limitations can be addressed in many ways: using Bayesian Deep Learning tools to provide uncertainty quantification of the model outputs; adapting the spatial and visual distribution of the training examples to increase robustness and reliability of the learned models; designing better model architecture to take in account geometrical clues within the learning process in order to reach state of the art accuracy for a tiny fraction of the computational cost of classical geometric pipelines. The resulting system is intended to be used as a scalable and reliable localization system for automated vehicles.

PhD Defense: “Smart vehicule trajectory prediction in various autonomous driving scenarios”

Image showing autonomous cars on a roundabout with their trajectories

The Centre for Robotics is proud to announce that the PhD Defense of Thomas GILLES will take place on Friday, April 21st at MINES PARIS.

The subject of the work is:

“Smart vehicule trajectory prediction in various autonomous driving scenarios”

This research is the result of a collaboration between our Centre and Huawei France.

The PhD has been directed by Fabien Moutarde, and supervized by Bogdan Stanciulescu.

 

To attend:
MINES PARIS
60, Saint-Michel boulevard, Paris.

 

Jury members:

Alexandre ALAHI, Assistant Professor, EPFL

Fawzi NASHASHIBI, Research Director, National Institute for Research in Digital Science and Technology (Inria)

David FILLIAT, Full Professor, ENSTA Paris

Anne SPALANZANI, Full Professor, Université Grenoble Alpes (UGA) / National Institute for Research in Digital Science and Technology (Inria)

John FOLKESSON, Associate Professor, KTH Royal Institute of Technology, Sweden

Dzmitry TSISHKOU, PhD, Huawei Technologies France

Fabien MOUTARDE, Full Professor, MINES PARIS

Bogdan STANCIULESCU, Associate Professor, MINES PARIS

 

Abstract:

Recent advances in machine learning methods have enabled tremendous progress in autonomous driving, namely through the perception step thanks to deep learning and deep neural networks, combined with all-around progress in sensors, mapping and proprioception techniques. The focus is now therefore shifting towards the next steps in the autonomous pipeline, where prediction plays an important role. Once the surrounding road agents have been detected and tracked, the driving system needs to predict their future trajectory and plan accordingly to have a collision-less course.
This trajectory prediction must follow multiple requirements. First, it should obviously be accurate and trustworthy, so that its output can be reliably used in the following processes. The future can present multiple possibilities, from which it may not always be possible to disambiguate solely based on past historical data. The forecast must therefore be multimodal, by predicting multiple simultaneous probable futures. Since the prediction is to be made on all surrounding agents, and these agents behaviors are very much influenced by their interactions with each other, the model should take these interactions into account, and its multimodal predictions should be coherent with each other. Finally, for safety and reliability, the trajectory prediction should be easy to interpret, extensively evaluated, able to provide confidence evaluates and designed with its final use in the pipeline in mind.
In the first part of this dissertation, after recapitulating existing non-learning methods for trajectory forecasting, we study different existing representations and approaches for learning-based motion forecasting. We then propose to tackle the trajectory prediction problem using probability heatmaps to facilitate multimodality. We design three different ways of generating these heatmaps and evaluate them against each other and the existing state-of-the-art. We also provide a complete sampling method to extract actual trajectories from these heatmaps, and study the pro and cons of these heatmap methods compared to other commonly used frameworks. In the next chapter, we focus on multi-agent prediction, and more specifically consistent scene-level outputs, for these type of heatmap models through sampling and learned post-processing. Finally, we explore different ways of expanding prediction model evaluation by uncertainty assessment, calibration and cross-dataset generalizability analysis.

Seminar on 3D Vision on Thursday March 16

https://www.caor.minesparis.psl.eu/wp-content/uploads/2022/12/pointclouds-2-800x200.png

We are organizing a seminar on 3D Point Clouds which will take place face-to-face only on Thursday March 16 from 2p.m. to 5p.m.

This seminar will be on the representations and analysis of 3D point clouds.

The place of the seminar is the Auditorium of Paris Santé Campus (2-10 Rue d’Oradour-sur-Glane, 75015 Paris)

Detailed program in the attached poster:
https://cloud.minesparis.psl.eu/index.php/s/DfQnUn0JmA8n9xe

Free but mandatory registration (due to the limited number of places) by filling out the Google Form:
https://docs.google.com/forms/d/e/1FAIpQLScBz2Gf014kzxTilbMl2cpgq2NMwnrQMKu_8W844ytCAEIJMw/viewform?usp=sf_link

#pointcloud #lidar #autonomousdriving

Paper accepted at ICRA2023 – COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets

https://www.caor.minesparis.psl.eu/wp-content/uploads/2023/02/1674205575126-500x400.jpg

Congratulations to Jules Sanchez for his paper accepted at #ICRA2023

How to improve 3D semantic segmentation performance using more 3D data? Pre-training with “coarse” labels. This requires fewer raw data than typical contrastive pre-training approaches and can really boost performance when the target dataset has few annotations!

Paper on arXiv: https://arxiv.org/pdf/2202.06884.pdf

#lidar #semanticsegmentation #pretrain #autonomousdriving #ICRA2023

PhD defense of Jean Pierre RICHA on “Urban Scene Modeling From 3D Point Clouds and Massive LiDAR Simulation for Autonomous Vehicles”

This thesis was realized in collaboration between Mines Paris – PSL and Ansys under the direction of François Goulette and Jean-Emmanuel Deschaud of the Center of Robotics of Mines Paris – PSL, as well as Nicolas Dalmasso, Nassim Jibai, and David Ganieux from Ansys.

The defense took place on Thursday 08 December 2022 at Mines Paris – PSL.

https://www.caor.minesparis.psl.eu/wp-content/uploads/2022/12/MDPI-full-pipeline-new-900x400.png

Summary of the PhD thesis: development of autonomous vehicles and testing can be achieved by simulating the different sensors in a virtual environment. However, manually handcrafted virtual environments fail to generalize to real-world scenes, due to the over-simplified models used in such environments. In this thesis, we propose to reduce this domain gap by leveraging real-world scans of urban scenes in the form of 3D point clouds acquired using a LiDAR sensor mounted on a mobile mapping system. Toward this end, we propose an automatic simulation pipeline. The pipeline introduces an accurate scene modeling method based on semantic adaptive splatting to create the virtual environment and a real-time LiDAR simulation.

Congratulations to Jean-Pierre !!!

https://www.caor.minesparis.psl.eu/wp-content/uploads/2022/12/IMG_20221208_141421-scaled-300x200.jpg
https://www.caor.minesparis.psl.eu/wp-content/uploads/2022/12/IMG_20221208_163230-scaled-300x200.jpg
https://www.caor.minesparis.psl.eu/wp-content/uploads/2022/12/IMG_20221208_173925-scaled-300x200.jpg

Silvère Bonnabel wins the 2021 European Control Prize

Silvère Bonnabel, associate researcher at the Robotics Center, and Professor at MINES ParisTech since 2009, has just won the “European Control Award”, a prestigious European prize for young researcher in automatic control. The purpose of this prize is to distinguish each year a researcher under the age of 40 with exceptional contributions in the field of automatic control and systems, and working in a European higher education or research establishment.

“I am particularly pleased to win this award, and to join the prestigious list of previous recipients. I would also like to thank Robert Mahony of the Australian National University (ANU) for his assistance in the nomination process,” said Silvère. He was invited to present his work during a plenary conference at the major European conference in the field “European Control Conference”, where the award ceremony was also held.