Within the work of the GAIA initiative, the pivotal project “GAIA-Sat-IoT” focuses on the research of vultures as individuals and on the development of basic hardware and software for novel animal tags. In the “SyNaKI” project (Synergy of Natural and Artificial Intelligence in the Swarm), GAIA is making the leap from the individual animal, tag or communication module to the swarm and to the interaction of animals within a species and between species, as well as to the networking of microprocessors in digital, virtual swarms. Inspired by the swarm intelligence of vultures and their interaction with other carnivores, GAIA is developing a virtual swarm intelligence in a network of animal tags to enable more efficient data analysis through distributed artificial intelligence – so-called extreme edge computing. In addition to data collection and analysis, data transmission can also benefit from the spontaneous networks of animal tag and send valuable information even faster, more accurately and more reliably.
To achieve this, GAIA will virtually map a natural swarm intelligence in a network of microprocessors (digital swarm) with its own artificial intelligence. This digital swarm will be developed using a concrete application scenario of tagged vultures in cross-species association with collared carrion-eating land mammals (lions and hyenas). Complex algorithms such as the GAIA AIs for behaviour classification or image recognition are not processed centrally on a single device, but distributed on several devices in the vicinity of the Extreme Edge. For this purpose, ad-hoc networks are set up that connect the individual nodes in a network. Animal swarms operate in remote areas without terrestrial network coverage. Therefore, it is necessary to still connect these local networks via satellite. In this way, the information generated in this local AI network can be transmitted quickly and efficiently to the users. The intended result in the first phase of the SyNaKI project is a simulator consisting of a wireless network of distributed computing components for the execution of a dynamically distributed artificial intelligence.
As a basis for the technical and conceptual development work for a virtual swarm intelligence, GAIA is expanding the agenda of its wildlife research with the SyNaKI project. Firstly, the wildlife biologists are explicitly looking at the group and swarm behaviour of white-backed vultures and are researching their communication and interaction, for example connected to social foraging strategies. And secondly, they are also equipping individuals of other animal species with tags and collars with which the white-backed vultures share the habitat and with which they interact. These are predators or carrion-eating land mammals such as lions and hyenas. In this way, swarms of transmittered animals can also be built up across species boundaries in order to be able to read out and virtually map the advantages of biological swarm intelligence by means of AI. Through this extension, not only the group behaviour within the individual species can be analysed, but also the group behaviour of a “swarm” consisting of different species – a multi-modal network of cross-species biological measuring stations is created. This makes it possible to answer completely new biological and ecological questions and provides reference data for the development of the digital swarm.
The project “SyNaKI” is funded by the German Federal Ministry for Economic Affairs and Climate Action on the basis of a decision of the German Bundestag.
Consortium Partners: Leibniz Institute for Zoo and Wildlife Research (Leibniz-IZW) & Fraunhofer Institute for Integrated Circuits IIS
Duration: January 1, 2022 – June 30, 2024
Funding code: 50YB2202B
