No abstract

In this paper, we argue that PDDL-based real-time planning can be achieved for today's video-games. PDDL is an expressive language which offers to represent many planning knowledge while freeing from the plan search algorithms. We present two case studies where we connected a PDDL-based AI Planner to a video-game. In each case, we report on the engineering decisions which turned out to be crucial to achieve real-time playability.

Digitalization of the whole society changes the way Systems-of-Systems have to be considered. Remaining independently operated and managed, SoS increase their collaboration skills using shared or cooperated information systems. People can be seen as particular digital subsystems due to smart equipments they can use. Military operations, which are considered as typical SoS, are no exception to this fact. New operational doctrines have to be created to take advantage of those new capabilities. In this paper, we propose to develop methods and tools inspired by software engineering to create new automated capabilities in battlefield engineering. More precisely, we explain the direction which should be considered in the area of battlefield engineering in order to deal with those new capabilities. Inspired from Model-Based Engineering, we realized a proof-of-concept showing how to change textual operation orders with graphical ones. The latter can be exported in a common standardized format, that enables digital interpretation. We present the OPORD-ML language which is based on a metamodel inspired from a NATO operation order standard. It is supported by an automatically generated tool.

No abstract

Relevant sounds such as alarms are sometimes involuntarily ignored, a phenomenon called inattentional deafness. This phenomenon occurs under specific conditions including high workload (i.e., multitasking) and/or cognitive fatigue. In the context of aviation, such an error can have drastic consequences on flight safety. This study uses an oddball paradigm in which participants had to detect rare sounds in an ecological context of simulated flight. Cognitive fatigue and cognitive load were manipulated to trigger inattentional deafness, and brain activity was recorded via electroencephalography (EEG). Our results showed that alarm omission and alarm detection can be classified based on time-frequency analysis of brain activity. We reached a maximum accuracy of 76.4% when the algorithm was trained on all participants and a maximum of 90.5%, on one participant, when the algorithm was trained individually. This method can benefit from explainable artificial intelligence to develop efficient and understandable passive brain–computer interfaces, improve flight safety by detecting such attentional failures in real time, and give appropriate feedback to pilots, according to our ambitious goal, providing them with reliable and rich human/machine interactions.