CAB- Cockpit and Bidirectional Assistant
Providing support in augmented decision making for complex steering systems
Managing critical systems (aircraft, car, train, etc.) or sensitive networks (transport, electricity, telecoms, etc.) means that the operator is required to manage a large amount of data originating from the system to be piloted, linked to its environment and the complexity of the situation in which he finds itself. This leads to a significant increase in its cognitive work load. Automation and the provision of virtual assistants are commonly used in situations where the final decision is made by the human. The quality of cooperation and the complementarity of learning between the human and his virtual assistant are essential.
The objective of the CAB project, launched in July 2020 for a period of four years within the framework of the IA2 programme (Artificial Intelligence and Augmented Engineering), is the development and prototyping of a bi-directional virtual assistant – open in terms of industrial applications – in which it will be possible to evaluate the forms of exchange between the Human expert and an AI that continuously learns both from the information flows received and from the decisions made by man. The explanatory aspect of AI recommendations is central to this project to give added value to the operator in his decision making. The virtual assistant will be able to determine the profile of the operator, his cognitive work load level, and adapt the information flows uploaded to the operator in order to manage a complex and/or atypical situation in the best conditions.
4 use cases will be studied in the framework of the CAB project:
- Dassault Aviation : to offer assistance to aircraft crews in view of the increasing complexity of missions, while consolidating safety.
- Orange : to benefit from a bi-directional wizard that groups together measures to check that telecom applications and infrastructures are operational and efficient, warn in the event of a current or anticipated malfunction, and display measures that have reached a critical threshold in order to identify and repair the cause of the malfunction.
- RTE : to offer operators a learning assistant who adapts to their level of expertise and the criticality of the situation, to help with decision-making in the context of operating electrical networks in anticipation and in real time and to facilitate cooperation within the control room, between different trades and when handing over from one team to another in 3/8. Objective: guarantee the continuity of service of particularly critical and complex systems.
- SNCF : design a proof of concept of a bidirectional virtual agent allowing to increase in real time the capacities of the operators (Operation Center Supervision and/or Driver) facing complex and/or atypical situations under strong time constraint.
At the end of the project, the following will be developed/proposed: an open intelligent cockpit demonstrator to address various use cases, datasets and algorithms relevant to the hybridization of AI with multimodal HMIs.
|Data Science and IA|
Doctoral theses supervised within the framework of the project
Co-adaptive instruments for Smart Cockpits