The chair team intends to study human-AI interactions with the optimization of human-technology teaming as ultimate goal. Indeed, the development of artificial intelligence-based technology (e.g. automated cars, aircraft, virtual assistants) are becoming increasingly present in a wide variety of operational contexts and in everyday life situations.

Most scientific and technical efforts have focused on the implementation of AI and smart sensors. However, these developments are generally achieved without questioning the integration of the human in the control/decision loop.

Safety analyses in many critical domains (e.g. aviation, nuclear power plant, high frequency trading) highlight that human-artificial agent interactions breakdown represents one major contributive factor to recent industrial disasters. A promising avenue to deal with these issues is to consider that humans and artificial agents have complementary skills/abilities and are likely to provide better performance when joined efficiently than when used separately.

A first step to enhance human-AI interactions is to design monitoring technology to “sense” the cognitive state of the human (e.g. degraded attentional abilities).  To that end, we will implement passive Brain Computer Interfaces (pBCIs) dedicated to monitoring brain activity while performing complex real-life tasks. We will especially focus on the use of advanced artificial intelligence techniques dedicated to better understand brain dynamics and  measure one and/or multiple users’ brains while interacting with each other and with artificial agents.  The outputs of this mental state estimator will feed a decision system to close the loop.

We will then develop a decisional unit that considers uncertainties on actions, partially observable states (e.g. states of the humans and states/failures of the artificial agent) or potentially non-deterministic human behavior. Such decision-making system will be governed by a policy to adapt and to enhance human-machine teaming. One originality of this Chair will be to examine such human-technology interaction with (i) multiple agents and (ii) in increasingly naturalistic settings representative of work and in everyday life situations.

Programme : IA collaborative
Thèmes : Neuroscience et IA, Robotique et IA

Porteur : Frédéric Dehais, PR ISAE-Supaero

Raphaëlle Roy
Caroline Chanel
Nicolas Drougard
Fabien Lotte
Bertille Somon
Xiaoqi Xu’s
Giorgio Angelotti


Dehais, F., Rida, I., Roy, R. N., Iversen, J., Mullen, T., & Callan, D. (2019, October). A pBCI to predict attentional error before it happens in real flight conditions. In  IEEE International Conference on Systems, Man and Cybernetics (SMC) (pp. 4155-4160). IEEE. (Best paper – IEEE Brain Initiative).

Angelotti, G., Drougard, N. & Chanel, C.  (2020). Offline Learning for Planning: A Summary.   The 30th International Conference on Automated Planning and Scheduling (ICAPS) , Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL)

Somon, B., Chanel C.P.C., & Dehais, F. (2020). Open science for better AI. [Abstract]. LiveMEEG 2020 conference (October 2020)


Angelotti, G., Drougard, N. & Chanel, C. 2020. Offline Model Learning with Importance Sampling  The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)

Roy, R.,  Drougard, N. Gateau,  T., Dehais, F. & Chanel, C. (in revision) How Can Physiological Computing Benefit Human-Robot Interaction? » Frontiers in Robotics and AI

Xu, X., Roy, R.,  Drougard, N. Spatial analysis of EEG signals via the Laplace-Beltrami operator – Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020)

The team

Frédéric Dehais is a full professor at ISAE-SUPAERO. His research deals with the understanding of the neural correlates of failure of attention and decision making and the implementation of Brain Computer Interface (BCI) out of the lab. –

Raphaëlle Roy is an associate professor at ISAE-SUPAERO with an expertise in cognitive science and physiological computing. Her research deals with. –

Caroline Chanel is an associate professor at ISAE-SUPAERO with an expertise in Artificial Intelligence/Sequential Decision-Making. Her research deals with the development of decisional control models considering uncertainties and partial observability. –

Nicolas Drougard is an associate professor at ISAE-SUPAERO with an expertise in Artificial Intelligence/Machine Learning. His research deals with uncertainty theories, human-machine interaction, and machine learning for planning and for brain-computer interfaces.

Fabien Lotte (Dr, HDR Non-local Permanent researcher scientist), INRIA Bordeaux Sud Ouest/LaBRI. His an international renowned research in the field of Brain Computer Interfaces. –

Bertille Somon (Dr., Post Doctoral Fellow) aims at combining cognitive neuroscience measures and inverse reinforcement learning. She intends to develop more accurate monitoring and prediction algorithms thanks to the definition of optimal policies based on ideal expert’s reward function definition through features extracted from experts’ brain data analyses. –

Xiaoqi Xu’s (Phd student) research is concerned with the implementation of a robust pipeline by applying cutting-edge machine learning techniques to process physiological data for the purpose of monitoring mental workload of pilots.

Giorgio Angelotti (PhD student) work in the field of offline model learning for planning endeavouring an automated and efficient application to the improvement of performances of teams involving Human Robot Interaction ». –