Development framework for Adaptive Autonomous Robot Fleets (AARF)

Robot swarms typically consist of many individual, homogeneous or heterogeneous agents. They traditionally cooperate without any central control. Individual robots exhibit a behavior that is based on a local rule set which can range from a simple reactive mapping between sensor inputs and actuator outputs to elaborate local algorithms. Typically, these local behaviors incorporate interactions with the physical world, including the environment and other robots. Through such interactions a collective behavior that is able to solve complex tasks should emerge. Regarding the high cost and severe requirements to trustworthy autonomous systems, there is urgent need for new unifying concepts and development tools to build complex open trustworthy autonomous systems. The main obstacle here is the lack of rigorous common semantic framework for such systems. The development of an AARF methodology and related SW tools to support a unified approach to self- and context-awareness, adaptivity, and autonomy, as motivated above, will be supported through 6 work packages: - WP1: AARF cognitive framework - WP2: Programming and modeling framework - WP3: Computation platform (edge, fog, cloud, IoT, 5G) - WP4: Quality (safety, security) assurance - WP5: Applications covering 3 case studies - WP6: Management and dissemination. The consortium consists of academic institutions and companies from Estonia, Finland, Germany, Greece, and Norway. The project leader will be Prof. Juri vain, Tallinn Technical University, Estonia. From PROSA Security AS, 3 persons will take part in the EU project, if funded, namely Owe, Hagalisletto and Monshizadeh., and we have made plans to hire one more expert on modeling frameworks. Our contribution on the project will be 1 to 2 person year per year for the duration of the project.