Bayesian & AI driven Embedded Perception and Decision-making. Application to Autonomous Navigation in Complex, Dynamic, Uncertain and Human-populated Environments.Synoptic of Research Activity, Period 2004-20 and beyond

Robust perception & Decision-making for safe navigation in open and dynamic environments populated by human beings is an open and challenging scientific problem. Traditional approaches do not provide adequate solutions for these problems, mainly because these environments are partially unknown, open and subject to strong constraints to be satisfied (in particular high dynamicity and uncertainty). This means that the proposed solutions have to take simultaneously into account characteristics such as real-time processing, temporary occultation or false detections, dynamic changes in the scene, prediction of the future dynamic behaviors of the surrounding moving entities, continuous assessment of the collision risk, or decision-making for safe navigation. This research report presents how we have addressed this problem over the two last decades, as well as an outline of our Bayesian & IA approach for solving the Embedded Perception and Decision-making problems