The research hub wishes to actively contribute to the development of efficient, autonomous, reconfigurable and intelligent communication systems. 

ENSTA Bretagne researchers primarily contribute to the “Security, Intelligence and Integrity of Information” (SI3) team.  

“Security, intelligence and integrity of information” research areas

The team designs and develops methods, algorithms and solutions for securing the physical layer of future communications and transmission systems. 

Its contributions also involve testing the deployed standards and systems or carrying out the corresponding “reverse engineering” for our institutional defense or national regulatory partners. 

In this area, everything can be considered as a challenge, because most of the reception processing is generally performed blindly and/or with very severe operational constraints in terms of stealth, threshold of noise level, own or external interference, power consumption, spectral efficiency, security, etc.

These research topics are at the intersection of signal processing, mathematics, “classical” and quantum information theory, and require consideration of major criteria and constraints related to operational, confidential, secure and other hardware aspects of the considered applications.
 

APPLICATIONS

• Tactical communications in defense and aerospace, radio spectrum monitoring, Cognitive Radio, securing restricted access areas and critical systems, 
• Drones, the Internet of Things (IoT), Smart factory, autonomous cars and radars embedded in vehicles.
• Applications of advanced signal processing methods, wireless telecommunications techniques and artificial intelligence in the biomedical field.

COLLABORATIONS

• Institutions: DGA, ANFR, Brest Teaching Hospital (CHU), Brest Military Hospital, etc.
• Academia: Naval Academy, GIPSA, UBO, Université de Paul Sabatier Toulouse 3, AUCE (Beirut-Lebanon), SNCS (Tabuk – KSA), ISEN, AAMST (Cairo - Egypt), etc.
   

Expertise

• communications systems,
• information processing and protection, 
• information encoding and decoding, 
• algorithm-architecture matching,
• physical layer security, 
• artificial intelligence.

Research areas of the “propagation and multi-scale interaction” team

The research conducted at ENSTA Bretagne by this Lab-STICC team is primarily aimed at representing and understanding certain phenomena resulting from the interaction of electromagnetic waves with the environment.

The team is seeking to further integrate innovative concepts and artificial intelligence into systems for the acquisition and processing of observations from radar (whether airborne or satellites) or GPS-type geolocation systems.

3 complementary research themes:

• Multi-scale and multi-physics electromagnetic simulation and modeling – in near and far fields: tools, asymptotic methods, exact methods, empirical methods, hybrid methods, etc. (MOSEM).
• Modeling and characterization of the propagation channel – physical and statistical models, etc. (MOCAP).
• Systems and platforms / modeling and simulation – experimental and virtual systems (MOSSYP).

Experimental facilities:

• Anechoic chamber (2-18 GHz)
• Operational radar operating in the X band
• Experimental radar operating in the Ku band
• Several simulation platforms (high-performance servers)
• Specialized software: HFFS, FEKO, ADS, CST-MWS, MicroStripes, Winprop, IE3D, SolidWorks, OrCAD, etc.
   

APPLICATIONS

• Observation of the globe, earth and sea, by satellite (Remote sensing)
• Environmental monitoring
• Automated detection of offshore pollution and irregularities
• Defense: radar, electronic warfare, detection/recognition and tracking of targets
• Surveillance: maritime safety and security
• Autonomous vehicles (aircraft, drones, etc.), geolocation and navigation, etc.

Collaborations

• Companies: Thales, SAFRAN Electronics & defense, Diades Marine, Naval Group, CESTIM, Syrlinks
• Institutions: DGA, IFREMER
• Academia: CNAM Paris, ENSM, IMT Atlantique, UBO, Naval Academy, RMA

Research areas

The researchers develop approaches guided by mathematical and statistical models to study and represent natural phenomena, dynamic systems or sociotechnical systems, all of which generate data.

• Information is extracted using data mining or machine learning algorithms.
• This information can, in itself, represent an answer to the question raised, or act as a starting point for a decision-maker to reach informed or optimal decisions.
• To guide decision-makers, operational research or decision support techniques will be used.
• These decisions can then influence the underlying phenomena again, thereby closing this loop.

Applications

• Knowledge of the marine environment
• Environmental monitoring
• Management and security of offshore human activities
• Functioning of robots and large industrial systems
• Human behavior, etc.

Organzed into 2 research teams

• Models and AlgoriThms for pRocessIng and eXtracting information (MATRIX)

• DECision aid and Information DiscovEry (DECIDE)

ENSTA Bretagne contributes primarily to the Matrix team and, to a lesser extent, to Decide.

Research areas for protecting the marine environment

To meet the environmental challenges and support stakeholders (NGOs, policy makers, civil society and the private sector) in their actions to minimize the impact of human activity on the marine environment, considerable effort has been invested over recent decades in increasing observations of the marine environment. Accordingly, worldwide, more than 90% of environmental data has been generated in the last three years (signals, images and time series).

Against this backdrop, artificial intelligence (AI) techniques, not least data science and machine learning, have an instrumental role to play in analyzing and processing data relevant for measures protecting the marine environment.

The "OSE" research team has taken up this methodological research in signal processing and AI applied to the marine environment, by focusing more particularly on multimodal remote sensing:
 

• oceanic remote sensing (satellite images),
• monitoring of the marine environment (aerial images, GNSS, ARGOS or AIS data, etc.)
• and underwater monitoring (passive acoustics, underwater video images).

One of the team’s concerns is to improve the performance of AI algorithms through in-depth consideration of the nature of the phenomena we wish to find out more about.

Three aspects of the interface between AI and monitoring of the marine environment are addressed: AI & physics, AI & robustness and AI & inverse problems. The latter, for example, includes building AI strategies on the basis of large datasets to resolve environmental inverse problems (data interpolation, target recognition, geophysical signal inversion, information reduction, etc.). 
 

Examples of applications

• Geophysical dynamics at the ocean surface: by variational model and solver learning for data assimilation.
• Recognition of fish species in underwater video images.

Collaborations

• Companies: Thales, NavalGroup, CLS, Eodyn, Actimar, Hytech-imaging.
• Institutions: CNES, DGA, IFREMER, IUEM, INRIA, Météo France, Mercator Ocean, IRISPACE, EUR ISblue, SHOM, FEM.
• Academia: GIPSA, Marbec, Sorbonne Univ, UCLA (Computational and Applied Mathematics group), Univ. of Washington (Applied Phys. Lab., Applied Math. Dept), Australian Antarctic Division, Barcelona Supercomputer Center, NERSC, Univ. of Dalhousie (Institute of Big Data Analytics), IMEDEA (Spain), Univ. Laval (Canada), ETH Zurich, Univ. Buenos Aires (CIMA, Argentina).
• and the GDR ISIS research network (CNRS)

OSmOSE, a collaborative data analysis tool

To analyze underwater recordings, researchers are also harnessing the open-source data processing tools developed by the research group OSmOSE (which stands for Open Science meets the Ocean Sound Explorers; this is a project supported by the OFB). Launched by ENSTA Bretagne in 2018, its aim is to standardize and share the methods and findings of their research community to make it easier for research teams in the field of underwater acoustics to work together.

To date, the project has enabled development of a data storage and processing platform as well as a web app used for audio annotation. Dorian Cazau, a professor and the group coordinator, explains that “[t]he annotation stage is key for training automated algorithms to subsequently detect the sounds”. Both tools are hosted at France’s ocean science research institute, Ifremer.

To annotate a sound, and therefore characterize it in the algorithm, it must first be recognized. For that, it must be isolated from the other sounds and visually represented on a spectrogram (2D graph of the intensity of a sound at variable frequencies over time). Citizen scientists, i.e. amateurs, help to analyze the spectrograms. “By studying the deviations between the amateurs’ findings and the experts’ conclusions, we can understand in what way our annotation tasks are difficult to carry out, and adapt the development of our tools accordingly.”

Indeed, the group would ultimately like to provide user-friendly tools for training staff working at Iroise Marine Natural Park and the OFB for example.
OSmOSE will thus bring research developments more closely into line with ecology practitioners’ requirements.

Objectives and applications: design intelligent, autonomous robots for exploring the environment – particularly the marine environment

Mobile robotics has grown significantly, usually in structured and already mapped environments. In other situations – unknown and unstructured environments – such as distant planets, volcanoes, deep caves, irradiated areas, underground water veins, burning buildings or the sea depths – the nature of robotics changes.

Because it is difficult for humans to intervene safely in these circumstances, where remote operation is usually no longer possible, robotics becomes essential. Robots must therefore be equipped with maximum autonomy and intelligence to accomplish a mission. This is called "exploratory robotics", as the robot has to map its environment, make decisions, locate itself and be able to return home.
 

Research areas: design methodological tools of autonomous robotics for exploration

The ROBEX team seeks to develop methodological tools for designing intelligent algorithms which enable robots to accomplish an exploratory mission autonomously. Bearing certain hypotheses about the environment and dynamics of the robot in mind, the team endeavors to guarantee such properties as:

• avoidance of a forbidden zone, 
• compliance with constraints on the state of the system,
• integrity of the location 
• and the ability to return to the starting point.

The team strives to take any type of uncertainty into rigorous account, obtain theoretically elegant solutions and make convincing experimental validations.

Methodological Tools

The emphasis is on:

• set theory,
• abstract interpretation, 
• nonlinear robot control and Bayesian filtering. 

Collaborations

• Companies: Kopadia, Thales, Forssea, RT-sys, iXblue, ECA-robotics, Subsea-Tech, Orange-Labs, Pilgrim, Texys Marine, Oxxius.
• Institutions: DGA, DRASSM, Ifremer, EDF, Brittany Region, Shom.
• Laboratories: LIRMM, IRISA, Polytechnique, LS2N.
• Research networks: GDR Macs and GDR robotique.

Prof. Luc Jaulin, research professor at ENSTA Bretagne / Lab-STICC in robotics for exploration:

We seek to represent and propagate uncertainties as rigorously as possible without making uncontrolled approximations, such as those induced by linearization or discretization. Uncertain variables may be the environment map, sensor data, robot trajectory, past or future decision making, robot dynamics and human interventions. The modeling of these different types of uncertainty requires reflection and the development of tools capable of meeting our objectives.

Research areas

The scientific objective of the AI & Ocean Department takes the ocean into account as a complex system, with physical, biological and ecological interactions, as well as human activities (maritime traffic, coastal planning, marine resources, environmental monitoring, etc.). 

The AI & Ocean Department is organized around three specific research areas, to which the Department’s three research teams contribute: 

• AI & perception of marine environments (ROBEX, OSE and M3 teams), 
• AI & robotics for exploration (ROBEX team) 
• AI & ocean and marine data (M3 and OSE teams).

Applications

• Knowledge of the marine environment
• Environmental monitoring
• Management and safety of offshore human activities
• Maritime & coastal planning

Organized into 3 research teams 

ENSTA Bretagne contributes to the 3 teams:

• Marine Mapping & Metrology (M3)
• Robotics for exploration (ROBEX)
• Observations, Signal & Environnement (OSE)

Research areas for understanding the marine environment

With the increase in insightful, precise and heterogeneous information about the marine environment come efforts to improve the processing of these countless datasets from varied observation systems (underwater, marine and spatial). Only judicious, joint use of this metadata can enable a faithful description of the environment.

To that end, the team explores different aspects of marine data analysis:

• design of the observation system through the assembly of sensor bricks, 
• consideration of the physical reality of this system and its measurements,
• qualification, analysis, interpretation and representation of the data acquired.

Expertise harnessed for analyzing marine data

• marine acoustics 
• passive acoustics
• marine data processing
• marine imaging
• machine learning
• data science
• big data
• sensor systems

Collaborations

Here are some examples of partners with whom this research is conducted.

• Companies: Hytech Imaging, Naval Group, Thales, ECA-robotics, CIDCO, iXblue
• Institutions: DGA, Shom, IGN, Ifremer
• Academia: Université Laval, Woods Hole Oceanographic Institution, Centre de Géomatique du Québec

HOLI-D Blue: holistic engineering education scheme for understanding and addressing the maritime environmental and societal challenges

Building on the work of ENSTA Bretagne’s education and professionalization of engineers (FPI) research team, the HOLI-D Blue project is aimed at updating the sustainability education given to future engineers hired by businesses operating in the sea and coastal professions, through the practical uptake of its recent research findings, by designing a concrete process in the context of an engineering school (école d'ingénieurs).

One of the main objectives of this project is to improve the contribution that higher education curricula (at universities and graduate and postgraduate schools, grandes écoles) make to sustainability and social responsibility by empowering maritime engineering students to identify and better understand maritime environmental and societal issues and challenges, so as to tackle them and act in a socially relevant and responsible way through the acquisition of appropriate skills for addressing complex concerns.

With that in mind, the HOLI-D Blue project thus sets out to jointly develop a cross-cutting and interdisciplinary "Maritime and sustainability" option as part of the initial syllabus followed by students embarking on a doctorate in ISblue community institutions, starting with ENSTA Bretagne for the pilot scheme.

Background

Educating engineers capable of taking up the challenges shaping the ecological transition, in the framework of the sustainable development goals, is at once:

• An increasing expectation on the part of students joining an engineering school (école d’ingénieurs) 
• An increasing demand on the part of businesses, in terms of knowledge and skills
• An increasingly common objective in engineering courses worldwide
• An increasingly important criterion on the part of accrediting bodies
• An ambition of the institutions belonging to the ISblue community, not least as regards the maritime environmental challenges and social responsibility
• A strategic objective of ENSTA Bretagne, enshrined in its 2022-2026 Performance and Objectives Contract 

Challenges and aims

HOLI-D Blue is grounded in a cross-cutting educational framework linking all types and stages of education, both formal and non-formal, academic and non-academic, right across a course of study. The aim is to empower students with the intellectual tools and technical skills necessary to tackle these environmental and societal challenges of the maritime sphere, by first understanding the latter then taking action with greater awareness of the impact of their activities.

In that respect, the focus of HOLI-D Blue is the joint development of open and flexible educational approaches with all of the stakeholders involving in engineering education (lecturers and research professors, students, socio-economic partners including local businesses and student associations), which can be adapted to other contexts (engineering schools and partner universities), so as to:

• Make educational improvements to syllabus contents (increase technical, human and social skills and knowledge), both at course level (strengthening the relevance of the teaching, particularly by increasing interaction between the various modules and the academic and professional application of skills acquired) and at institution level (update practices and promote the institutions involved)
• Enable ENSTA Bretagne students who want to, to enhance their studies thanks to this option and, ultimately, to include all first-year students in the awareness stages.
• Provide partner educational institutions of the ISblue community with the results of this pilot scheme, help to roll it out in their courses and/or forge partnerships between several courses/institutions