Projects

Current Projects

· 

Proteus

• French National Research Agency (ANR) PRC Project, 2023-2026 (PI: Fabien Lotte)

• Title: Proteus: Measuring, understanding and tackling variabilities in Brain-Computer Interfacing

• Abstract: Whereas Brain-Computer Interfaces (BCI) are very promising for various applications, e.g., brain-based wheelchair control or plane pilots’ mental state monitoring, they are not reliable. Their reliability degrades even more when used across contexts (e.g., across days, for changing users’ states or applications used) due to various sources of variabilities. Unfortunately, such variabilities are 1) often ignored in the literature, as most BCIs are assessed in a single context and 2) poorly understood. Thus, for BCIs to fulfil their promises and be used outside laboratories, we need to make them robust to such variabilities. In project PROTEUS we propose to do so by 1) Systematically measuring BCI and brain signal variabilities across various contexts while sharing the collected databases; 2) Characterising, understanding and modelling the variability and their sources based on these new databases; and 3) Tackling these variabilities by designing new machine learning algorithms optimally invariant to them according to our models, and using the resulting BCIs for two practical applications affected by variabilities: tetraplegic BCI user training and auditory attention monitoring at home or in flight.

• Partners:

  • Inria center at the university of Bordeaux, France (Fabien Lotte)

  • LAMSADE, Paris, France (Florian Yger)

  • ISAE-SupAéro, Toulouse, France (Raphaëlle Roy)

  • Wisear, Paris, France (Alain Sirois)

BCI4IA

• French National Research Agency (ANR) PRC Project, 2023-2026 (PI: Claude Meistelman)

• Title: BCI4IA: a New BCI Paradigm To Detect Intraoperative Awareness During General Anesthesia

• Abstract: The BCI4IA project aims to design a brain-computer interface to enable reliable general anesthesia (GA) monitoring, in particular to detect intraoperative awareness. Currently, there is no satisfactory solution to do so whereas it causes severe post-traumatic stress disorder. "I couldn't breathe, I couldn't move or open my eyes, or even tell the doctors I wasn't asleep." This testimony shows that a patient's first reaction during an intraoperative awareness is usually to move to alert the medical staff. Unfortunately, during most surgery, the patient is curarized, which causes neuromuscular block and prevents any movement. To prevent intraoperative awareness, we propose to study motor brain activity under GA using electroencephalography (EEG) to detect markers of motor intention (MI) combined with general brain markers of consciousness. We will analyze a combination of MI markers (relative powers, connectivity) under the propofol anesthetics, with a brain-computer interface based on median nerve stimulation to amplify them. Doing so will also require to design new machine learning algorithms based on one-class (rest class) EEG classification, since no EEG examples of the patient's MI under GA are available to calibrate the BCI. Our preliminary results are very promising to bring an original solution to this problem which causes serious traumas.

• Partners:

  • CHRU Nancy, France (Claude Meistelman)

  • Inria center at the university of Bordeaux, Talence, France (Fabien Lotte)

  • LORIA, Nancy, France (Laurent Bougrain)

BeAware

• French National Research Agency (ANR) PRC Project, 2023-2025 (PI: Martin Hachet)

• Title: Be-Aware: Bringing environmental issues closer to the public with augmented reality

• Abstract: This project will explore how augmented reality (AR) systems can reduce the spatial and temporal distance between people’s choices and their environmental consequences, in order to reveal the impact of both individual habits and global policies. More concretely, we will design interactive visualizations that integrate concrete environmental consequences (e.g. waste accumulation, rare earth mining) directly into user's surroundings. This interdisciplinary research will be informed and validated by incentivized and controlled behavioral economics experiments based on game-theoretical models, and guided by real environmental scenarios.

• Partners:

  • Inria center at the university of Bordeaux, France (Martin Hachet)

  • LESSAC team at BSB Dijon, France (Angela Sutan)

  • CIRED, France (Thomas Le Gallic)

BITSCOPE

• CHIST-ERA European Project, 2022-2025 (PI: Tomas Ward)

• Title: Brain Integrated Tagging for Socially Curated Online Personalised Experiences

• Abstract: This project presents a vision for brain computer interfaces (BCI) which can enhance social relationships in the context of sharing virtual experiences. In particular we propose BITSCOPE, that is, Brain-Integrated Tagging for Socially Curated Online Personalised Experiences. We envisage a future in which attention, memorability and curiosity elicited in virtual worlds will be measured without the requirement of “likes” and other explicit forms of feedback. Instead, users of our improved BCI technology can explore online experiences leaving behind an invisible trail of neural data-derived signatures of interest. This data, passively collected without interrupting the user, and refined in quality through machine learning, can be used by standard social sharing algorithms such as recommender systems to create better experiences. Technically the work concerns the development of a passive hybrid BCI (phBCI). It is hybrid because it augments electroencephalography with eye tracking data, galvanic skin response, heart rate and movement in order to better estimate the mental state of the user. It is passive because it operates covertly without distracting the user from their immersion in their online experience and uses this information to adapt the application. It represents a significant improvement in BCI due to the emphasis on improved denoising facilitating operation in home environments and the development of robust classifiers capable of taking inter- and intra-subject variations into account. We leverage our preliminary work in the use of deep learning and geometrical approaches to achieve this improvement in signal quality. The user state classification problem is ambitiously advanced to include recognition of attention, curiosity, and memorability which we will address through advanced machine learning, Riemannian approaches and the collection of large representative datasets in co-designed user centred experiments.

• Partners:

  • Dublin City University, Ireland (Tomas Ward)

  • Inria Bordeaux Sud-Ouest, France (Fabien Lotte)

  • Univ. Polytechnic Valencia, Spain (Mariano Alcaniz)

  • Nicolas Copernicus University, Poland (Veslava Osinska)

NeuroPerf

• Labex BRAIN Clinical Research Project, 2017-2023 (PI: Jean-Arthur Micoulaud-Franchi)

• Title: NeuroPerf: Effectiveness of Neurofeedback on Cognitive Performance and Daytime Alterness in Controlled sleep restricted healthy subject 

• Abstract: In neurofeedback, brain activation is volitionally regulated through learning. In particular, neurofeedback has been used to self-regulate electroencephalography (EEG) amplitudes, which correlate with the degree of neuronal synchronization. Our team has confirmed the impact of repeated sleep restriction protocols (i.e., 4 to 6 hr of sleep per day, for 5 days) on daytime alertness level and on cognitive performance (in particular sustained-attention). Sleep restriction enhances brain homeostatic sleep pressure that can be measured in EEG signals by an augmentation of neuronal synchronization. Thus, targeting the neuronal synchronization underlying the daytime alertness level and cognitive performance is a relevant clinical and behavioral neuroscience grounded way of research to develop countermeasures to fight the effect of sleep restriction on brain function. The aim of this project is to target EEG synchronization using neurofeedback to teach the subject to self-regulate brain activity and to evaluate the impact of this training on the brain capacity to face repeated sleep restriction. Our hypothesis is that neurofeedback targeting EEG theta and beta spectral bands will teach the subject to desynchronize her/his brain activities in order to restore the daytime alertness level and the cognitive performance in a context of repeated mild sleep restriction. Neurofeedback will be designed to enhance the brain regulation learning. Daytime alertness level and cognitive performance will be measured with standardized tests for which it is well established that they change after sleep restriction periods. This study will offer additional insights into the neurophysiological mechanism of neurofeedback protocol on the daytime alertness level.

• Partners: SANSPY – University of Bordeaux – Bordeaux Hospital Pellegrin

Past Projects

BrainConquest

• ERC Starting Grant, 2017-2022 (PI: Fabien Lotte)

• Title: BrainConquest: Boosting Brain-Computer Communication with High Quality User Training 

• Abstract: Brain-Computer Interfaces (BCIs) are communication systems that enable users to send commands to computers through brain signals only, by measuring and processing these signals. Making computer control possible without any physical activity, BCIs have promised to revolutionize many application areas, notably assistive technologies, e.g., for wheelchair control, and man-machine interaction. Despite this promising potential, BCIs are still barely used outside laboratories, due to their current poor reliability. For instance, BCIs only using two imagined hand movements as mental commands decode, on average, less than 80% of these commands correctly, while 10 to 30% of users cannot control a BCI at all. 

A BCI should be considered a co-adaptive communication system: its users learn to encode commands in their brain signals (with mental imagery) that the machine learns to decode using signal processing. Most research efforts so far have been dedicated to decoding the commands. However, BCI control is a skill that users have to learn too. Unfortunately how BCI users learn to encode the commands is essential but is barely studied, i.e., fundamental knowledge about how users learn BCI control is lacking. Moreover standard training approaches are only based on heuristics, without satisfying human learning principles. Thus, poor BCI reliability is probably largely due to highly suboptimal user training.

In order to obtain a truly reliable BCI we need to completely redefine user training approaches. To do so, I propose to study and statistically model how users learn to encode BCI commands. Then, based on human learning principles and this model, I propose to create a new generation of BCIs which ensure that users learn how to successfully encode commands with high signal-to-noise ratio in their brain signals, hence making BCIs dramatically more reliable. Such a reliable BCI could positively change man-machine interaction as BCIs have promised but failed to do so far.

• Webpage: http://team.inria.fr/potioc/collaborative-projects/brainconquest/

REBEL

• ANR Jeune Chercheur Jeune Chercheuse Project, 2016-2019 (PI: Fabien Lotte)

• Title: REBEL: REdefining Brain-Computer Interfaces to Enable their users to achieve controL mastery 

• Abstract: Brain-Computer Interfaces (BCI) are communication systems that enable their users to send commands to computers through brain activity only. While BCI are very promising for assistive technologies or human-computer interaction (HCI), they are barely used outside laboratories, due to a poor reliability. Designing a BCI requires 1) its user to learn to produce distinct brain activity patterns and 2) the machine to recognize these patterns using signal processing. Most research efforts focused on signal processing. However, BCI user training is as essential but is only scarcely studied and based on heuristics that do not satisfy human learning principles. Thus, currently poor BCI reliability is probably due to suboptimal user training. Thus, we propose to create a new generation of BCI that apply human learning principles in their design to ensure the users can learn high quality control skills, hence making BCI reliable. This could change HCI as BCI have promised but failed to do so far.

• Partners: Inria Bordeaux Sud-Ouest, team Potioc, Laboratoire Handicap & Systèmes Nerveux Bordeaux

• Webpage: http://team.inria.fr/potioc/rebel/

BCI-LIFT

• Inria Project Lab (IPL): 2015-2018 (PI: Maureen Clerc)

• Title: BCI-LIFT: BCI, Learning, Interaction, Feedback Training

• BCI-LIFT is a large-scale 4-year research initiative whose aim is to reach a next generation of non-invasive Brain-Computer Interfaces (BCI), more specifically BCI that are easier to appropriate, more efficient, and suit a larger number of people. With this concern of usability as our driving objective, we will build non-invasive systems that benefit from advanced signal processing and machine learning methods, from smart interface design, and where the user immediately receives supportive feedback. What drives this project is the concern that a substantial proportion of human participants is currently categorized “BCI-illiterate” because of their apparent inability to communicate through BCI. Through this project we aim at making it easier for people to learn to use the BCI, by implementing appropriate machine learning methods and developping user training scenarios.

• Partners: Athena project-team (Sophia Antipolis),Demar project-team (Montpellier),Hybrid project-team (Rennes), Mjolnir project-team (Lille), Neurosys project-team (Nancy), Potioc project-team (Bordeaux), Université de Rouen, Dycog team, Centre de Recherche en Neurosciences de Lyon

• Official website: http://bci-lift.inria.fr/

Assessing and Optimising Human-Machine Symbiosis through Neural signals for Big Data Analytics

• DGA-DSTL project, 2014-2018 (PIs: UK: Damien Coyle, FR: Fabien Lotte)

• This project objective is to design new tools for Big Data analysis, and in particular visual analytics tools that tap onto human cognitive skills as well as on Brain-Computer Interfaces. The goal is to enable the user to identify and select relevant information much faster than what can be achieved by using automatic tools or traditional human-computer interfaces. More specifically, this project will aim at identifying in a passive way various mental states (e.g., different kinds of attention, mental workload, relevant stimulus perception, etc.) in order to optimize the display, the arrangement of the selection of relevant information.

• Partners: Ulster University (Northern Ireland, UK), Inria Bordeaux Sud-Ouest (France)

OpenViBE-X

• Inria ADT (Technological Development Support) project, 2014-2016 (PI: Maureen Clerc)

• This project is located in the framework of the Inria Project-Lab BCI-LIFT, and is the sequel to the ADT project OpenViBE-NT. The opensource OpenViBE software, developped by Inria since 2005, is among the main mature software to design and study Brain Computer Interfaces (BCI) worldwide, and is at the heart of BCI research at Inria. This project aims at providing OpenViBE with engineer resources to extent the functionalities of OpenViBE on the one hand, in order to contribute to the research works from IPL BCI-LIFT, and, on the other hand, to contribute to its maintenance and necessary upgrades, to be up-to-date with software and hardware evolutions, as well to work on new OpenViBE releases for the community.

• Partners: Inria teams Athéna (Nice, project leader), Hybrid (Rennes) et Potioc (Bordeaux)

OpenViBE-NT

• ADT-Inria project, 2012-2014 (PI: Anatole Lécuyer)

• OpenViBE (http://openvibe.inria.fr) is an open-source software platform to design Brain-Computer Interfaces (BCI). This software is currently used by numerous users all over the world (more than 10000 downloads since 2009), in the fields of BCI, real-time neurosciences, and even human computer-interfaces and virtual reality. Since its creation in 2005, new usages of OpenViBE appeared as well as new limitations. Over the years, we have identified some lack of functionalities or drawbacks that impact its widespread use and long-term viability. The aim of this project is to further develop OpenViBE, notably in order to (1) make the software evolve towards a new version that fits better current and future needs from its users, (2) to offer new and original functionalities and (3) to keep ensuring OpenViBE support and dissemination. The final objective is to further increase OpenViBE usability and appeal, in order to strengthen the users’ community surrounding the software and enable us to make it as viable and useful as possible, on the long term. The developments will also enable the Inria teams involved (Potioc, Hybrid, Neurosys and Athena) to explore new research directions on BCI, such as adaptive BCI, hybrid BCI, that combines EEG with other physiological sensors (e.g., heart rate, galvanic skin response, gaze, etc.), or new coupling between BCI and virtual reality in order to improve human training for BCI, thanks to new immersive feedback types.

• Partners : team Hybrid (Inria Rennes Bretagne Atlantique), team Athéna (Inria Sophia-Antipolis Méditerranée), team Neurosys (Inria Nancy Grand-Est), team Potioc (Inria Bordeaux Sud-Ouest) Duration : 2 years (2012-2014) Coordinator : Anatole Lécuyer (Inria Rennes Bretagne Atlantique) funded by Inria (Technological Development Project)

OpenViBE 2

• ANR funded project, 2009-2012 (PI: Anatole Lécuyer)

• The second OpenViBE project gathers academic partners and video games industrials. It aims at studying the automatic adaptation of the content and interaction with virtual environments (VE) based on the user’s mental states, as measured from scalp-EEG signals, with a special focus on videogame applications. Being “consumer world” oriented, the project faces several difficult challenges: robustness, preserving user’s comfort, and adaptability to a large number of users with their own EEG signature, etc. As compared to previous BCI approaches (e.g., previous OpenViBE1 project), our goal is to use EEG signals not only as a direct input for mental command, but also as complementary means to adapt the interaction protocol and the content of the virtual world. Thus, a main challenging objective is to combine brain-computer interaction with usual mouse or gamepad motor interaction within the same set-up. To sum up, OpenViBE2 covers 3 major innovative aspects: (1) the complex and challenging videogame context; (2) the possibility for the user to keep using other interaction devices such as joysticks, gamepads, etc; and (3) the development of real-time techniques adapting VE interaction and content from mental state measures.

• Official website.

• Partners: Inria, Inserm, Gipsa-lab, CEA, Ubisoft, Blaksheep studio, CHART, CLARTE, Kylotonn entertainment

OpenViBE

• ANR funded project, 2006-2009 (PI: Anatole Lécuyer)

• This project was pioneer in France in the field of Brain-Computer Interfaces. One of the main results of the project was the release of the OpenViBE software. The aim of the OpenViBE project is to develop an open-source software environment enclosing novel and efficient techniques for Brain-Computer Interfaces, Neurofeedback and Virtual Reality. Brain-Computer Interfaces are novel interfaces that measure the cerebral activity of the user (using for instance EEG acquisition machines) and give Neurofeedback to the user or translate it into a command for a computer or another system (robot, machine, car, etc). The two main innovations which the OpenViBE project focuses on:

  • new techniques for processing and identification of cerebral data based on neurophysiological experimentations that will identify the best physiological indicators

  • new techniques to send back information to the user of the BCI about his/her mental activity using Virtual Reality technologies, which could then be used to improve the learning and the control of the mental activity.

• Official website.

• Partners: Inria, Inserm, France Telecom, Gipsa-lab, CEA, AFM