Phoenix is an European H2020 project in FET-Open, a scheme for Future Emerging Technologies and cooperation projects for advanced and paradigm-changing innovation. It focusses on ultra-low power wireless sensor networks.
Technische Universiteit Eindhoven
Katholieke Universiteit Leuven
Antea Nederland BV
Vrije Universiteit Amsterdam
University of Groningen
University of Trento
Humans have been exploring the world from the depths of the oceans to the edges of the universe. Yet many environments remain inaccessible, even to modern cutting-edge technology. Therefore problems like exploring the status of waste water under the Fukushima reactor, or discover suitable sites for underground CO2 storage remain unsolved.
Objectives and Approach
The aim is to investigate a new line of technology that will enable the exploration of difficult-to-access environments exploiting a risky, highly-novel approach called Phoenix.
Phoenix will accomplish the exploration of inaccessible environments with physical agents that are extremely limited in size and resources, and can operate without direct control over software and hardware. Phoenix starts with processing a user question, then assesses available knowledge and initiates an evolutionary process involving two nested generational loops. In the outer loop Phoenix develops, deploys and retrieves physical agents capable of penetrating the inaccessible environment and gathering information. Based on this knowledge, a model of the unknown environment is developed and evaluated. This model is refined in the inner loop, where environmental models and abstract representations of the physical agents (virtual agents) co-evolve in a virtual world until an improved generation of physical agents is ready for deployment. The goal of this co-evolution is to maximize the information captured about the unknown environment by progressively optimized agents.
Phoenix is a radically new, high risk/high reward project. It also holds the promise to shed light on emergent properties of self-organization, local adaptation and division of labour in autonomous systems. The high societal benefits, foundational character and long-term focus make Phoenix a perfect fit for the FET programme.
Hallawa, A., De Roose, J., Andraud, M., Verhelst, M. and Ascheid, G.: Instinct-driven Dynamic Hardware Reconfiguration: Evolutionary Algorithm Optimized Compression for Autonomous Sensory Agents, in Proceedings of the Genetic and Evolutionary Computation Conference Companion(New York, NY, USA), pp. 1727--1734, ACM, Jul. 2017, ISBN: 978-1-45034-939-0, 10.1145/3067695.3084202