RECOLTE (2021/2024)

Embedded agent architecture for adjustable autonomy

This work is carried out in the framework of a collaboration between the International Unit of Mathematical Modeling and Complex-Systems (UMMISCO) - attached to Sorbonne University and the Research Institute for Development (IRD), the Gastin Berger University from Saint-Louis in Senegal and the Multi-Agent System (MAS) group of LIP6.

The objective of this project is - building on previous work - to propose, design and implement a decisional architecture able to adapt the degree of autonomy of an artificial entity over time. In addition to the development of an architecture supporting the different modes mentioned, particular attention will be paid to the form that the transition from one mode (autonomous, semi-autonomous, remotely operated) to the other takes.

The platform, equipped with a set of embedded sensors (GPS, inertial unit, altimeter,..), a camera, a high performance camera and an M2M communication system, will have to evolve in a spatialized and geometrically constrained context in order to detect, identify, characterize and follow periodically and semi-automatically the targets present in the concerned area. The platform will have to be able to adapt dynamically to the elements encountered from an initial route provided off-line and to be able to switch, on-line, from an autonomous mode to a semi-autonomous or remotely operated mode (and vice versa) in a context of shared authority with a low-skilled operator.

Associate Professor of Artificial Intelligence

My research interests include long-term autonomy, coordination, learning and decision making.