POST-DOC/CDD X-ray tomography reconstruction based on Deep-Learning methods
CEA-LIST is developing the CIVA software platform, a benchmark for the simulation of non-destructive testing processes. In particular, it offers tools for X-ray and tomographic inspection which, for a given inspection, can simulate all radiographies, taking into account various associated physical phenomena, as well as the corresponding tomographic reconstruction. CEA-LIST also has an experimental platform for robotized X-ray tomography inspection.
The proposed work is part of the laboratory's contribution to a bilateral French-German ANR project involving academic and industrial partners, focusing on the inspection of large-scale objects using the robotized platform. A sufficient number of X-rays must be taken in order to carry out a 3D reconstruction of the object. In many situations, some angles of view cannot be acquired due to the dimensions of the object and/or the motion limitations of the robots used, resulting in a loss of quality in the 3D reconstruction.
Expected contributions focus on the use of Deep-Learning methods, to complete missing projections on the one hand, and reduce reconstruction artifacts on the other. This work includes the CIVA-based steps of building a simulated database and evaluating the obtained results using POD (Probability Of Detection) measurements.
The candidate will have access to the facilities of the Paris Saclay research center and will be expected to promote his/her results in the form of scientific communications (international conferences, publications).
PhD in data processing or artificial intelligence.
Fluent English (oral presentations, scientific publications).
Previous knowledge of X-ray physics and tomographic reconstruction methods would be appreciated.
X-ray tomography reconstruction based on analytical methods and Deep-Learning
CEA-LIST develops the CIVA software platform, a reference for the simulation of non-destructive testing processes. In particular, it proposes tools for X-ray and tomographic inspection, which allow, for a given tomographic testing, to simulate all the radiographic projections (or sinogram) taking into account various associated physical phenomena, as well as the corresponding tomographic reconstruction.
The proposed work is part of the laboratory's contribution to a European project on tomographic testing of freight containers with inspection systems using high-energy sources. The spatial constraints of the projection acquisition stage (the trucks carrying the containers pass through an inspection gantry) imply an adaptation of the geometry of the source/detector system and consequently of the corresponding reconstruction algorithm. Moreover, the system can only generate a reduced number of projections, which makes the problem ill-posed in the context of inversion.
The expected contributions concern two distinct aspects of the reconstruction methodology from the acquired data. On the one hand, it is a question of adapting the analytical reconstruction methods to the specific acquisition geometry of this project, and on the other hand, to work on methods allowing to overcome the lack of information related to the limited number of radiographic projections. In this objective, supervised learning methods, more specifically by Deep-Learning, will be used both to complete the sinogram, and to reduce the reconstruction artifacts caused by the small number of projections available. A constraint of adequacy to the data and the acquisition system will also be introduced in order to generate physically coherent projections.
Development of a digital twin of complex processes
The current emergence of new digital technologies is opening up new opportunities for industry, making production more efficient, safer, more flexible and more reliable than ever. The application of these technologies to the vitrification processes could improve the knowledge of the processes, optimise their operation, train operators, help with predictive maintenance and assist in the management of the process.
The SOSIE project aims at providing a first proof of concept for the implementation of digital technologies in the field of vitrification processes, by integrating virtual reality, augmented reality, IoT (Internet of Things) and Artificial Intelligence.
This project, carried out in collaboration between the CEA and the SME GAMBI-M, is a READYNOV project. GAMBI-M is a company specialised in the reconstruction of complex environments and in digital engineering. The work will be carried out in close collaboration with the CEA teams developing the vitrification processes for nuclear waste.
The project consists of developing a digital twin of 2 vitrification processes, and will be implemented on 2 platforms in parallel, one in a conventional zone, the other in a high activity zone. The first step will be to develop a visual digital twin, the virtual 3D model of each cell, which will allow the user to visit the cells and access any point virtually. Based on this reconstructed model, an "augmented" twin will be developed and connected to the supervisory controller. Finally, the last step will be to develop the "intelligent twin" by exploiting existing databases on the operation of the process. By training machine learning algorithms on these data, a predictive model of nominal operation will be generated.
Publications are expected on the implementation of virtual reality and augmented reality tools on shielded chain operations, as well as on the development of deep learning methods for the assistance to the control of such complex processes.
Elaboration of a common robot/human action space
This post-doc aims at establishing by artificial intelligence methods (e.g. signal processing on graphs), the mapping of an industrial task performed by a human operator, and acquired by visual sensors, in order to be interpretable and exploitable by a robot. It is part of a project aiming at designing a demonstrator in which a robot will learn to reproduce by observation a task performed by a human. The platform has been deployed at CEA Tech and is currently operated by an engineer.
The objective of this post-doc is mainly to study and develop a set of methods to build a mapping between the actions performed by a human operator and perceived through visual sensors and the actions performed by the robot. These methods and the work of the related theses will then be implemented in the demonstrator in order to test them experimentally.
Due to the central position of the subject of this post-doc, under the triple supervision of the PACCE and IPI teams of LS2N and CEA, you will have to collaborate closely with the two PhD students already involved in the project. You will have to conceptualize and formalize the methods and representations on the one hand by synthesizing the existing literature on the subject and on the other hand by establishing a common framework encompassing the two thesis works.
High precision robotic manipulation with reinforcement learning and Sim2Real
High precision robotic assembly that handles high product variability is a key part of an agile and a flexible manufacturing automation system. To date however, most of the existing systems are difficult to scale with product variability since they need precise models of the environment dynamics in order to be efficient. This information is not always easy to get.
Reinforcement learning based methods can be of interest in this situation. They do not rely on the environment dynamics and only need sample data from the system to learn a new manipulation skill. The main caveat is the efficiency of the data generation process.
In this post-doc, we propose to investigate the use of reinforcement learning based algorithms to solve high precision robotic assembly tasks. To handle the problem of sample generation we leverage the use of simulators and adopt a sim2real approach. The goal is to build a system than can solve tasks such as those proposed in the World Robot Challenge and tasks that the CEA’s industrial partners will provide.
Numerical Meta-modelization based study of the propagation of ultrasonic waves in piping system with corroded area
The aim of the ANR project PYRAMID (http://www.agence-nationale-recherche.fr/Projet-ANR-17-CE08-0046) is to develop some technics of detection and quantification of the wall thinning due to flow accelerated corrosion in piping system. In the framework of this project involving French and Japanese laboratories, CEA LIST develops new numerical tools based on finite elements dedicated to the modelling of an ultrasonic guided wave diffracted by the corrosion in an elbow pipe. These solutions support the design of an inspection process based on electromagnetic-acoustic transduction (EMAT). To this end, the ability of CEA LIST to adapt meta-modeling tools of its physical models will be the key asset to allow intensive use of the simulation.