Mobilité en Environnement Enrichi par les Données et interprétées pour l'Autonomie de Navigation – MEEDIAN

The consortium associates Safran Electronics & Defense (SED) with the robotics laboratory (CAOR) of Mines Paris Science et Lettres. The project applies to the MOBILEX challenge call for proposals and addresses two fundamental points of autonomous mobile robotics : the mobility in unstructured areas disrupting the autonomous vehicle control. This results into uncertainty and unknowns in route planning, feasibility of trajectories, control and temporal or spatial uncertainty at different points on the trajectory. The semantic interpretation of the environment done by the vehicle (function equivalent to understanding a scene by humans), which the areas of machine learning, the perception functions and the proximal sensors (cameras, LIDAR) contribute to. Indeed, planning and control techniques are based on these representations by interpreting them in order to establish an intelligent behavior of navigation, maneuver and mobility.
The scientific approach consists in building and maintaining a representation of the interpretable environment and thus in deducing models that are essential for localization, computation of navigation plans and control strategies. In terms of automatic learning for geolocation, perception and cartography, the flexibility of the models gives the robot the expected level of autonomy, in interaction with an operator supervising the mission progress. Several technological breakthroughs are expected in order to meet the challenges of unstructured environments and disturbances such as the loss of GNSS or communications. The project uses the existing assets developed by SED and used in the scope of FURIOUS, COHOMA and iMUGS projects. This architecture provides an on-board computing framework and a set of software components. Thanks to CAOR research activities, the localization, perception and control functions will be enhanced with new methods addressing physical models hybridization with machine learning.
The project is structured around five work packages A: “Advanced Autonomous Functions” relating to research activities, work-package B “Engineering of the Autonomous System Architecture” ensures the evolution of the SED system, work-package C “Development and integration” includes development activities, and work-package D “Analysis and execution of the challenges” focuses on challenges activity. Finally, work-package E “Project management” includes all Project management activities. This project has a fundamental impact in the positioning of SED in France and in Europe on autonomous systems, including drones, by building an offer based on a suite of autonomy modules, integrating control/command, perception, navigation, artificial intelligence and dependability. For the CAOR, this project enables launching an effective team with a concrete research objective linked to the installation of its future unit in Satory.