Description du projet
S’appuyer sur la robotique et l’intelligence artificielle pour imiter les réseaux fongiques des plantes et atténuer le changement climatique
Les réseaux fongiques souterrains, surnommés Wood Wide Webs («réseau sauvage des bois»), relient les plantes entre elles, leur permettant d’échanger des nutriments et des informations et de maintenir des écosystèmes sains. Le projet I-Wood, financé par l’UE, étudiera les interactions plantes-champignons (mycorhizes) afin de les reconstituer en développant des modèles virtuels et des réseaux physiques robotisés. Ces systèmes imiteront les réseaux de plantes en utilisant des racines robotisées qui poussent et se ramifient en fonction de l’environnement, échangent des informations et adoptent des comportements collectifs inspirés des plantes. Testés dans un réseau social mixte à échelle réduite, ils interagiront avec de vraies plantes dans l’objectif de faciliter le développement de mycorhizes. I-Wood entend définir un nouveau paradigme en matière de robotique et d’intelligence artificielle, et apporter de nouvelles connaissances sur les communautés végétales, qui devraient revêtir une importance majeure pour la biodiversité et la protection du climat.
Objectif
Plants are connected to each other by an underground network of fungi that provide them with nutrients, help share resources, and extend their perception abilities. This mycorrhizal network, known as the Wood Wide Web, plays a crucial role in maintaining healthy natural ecosystems, and in limiting the global warming. Thus, it must be preserved in order to mitigate the speeding up of the carbon cycle and its effects on climate change. Robotics and Artificial Intelligence (AI) can offer concrete solutions for a deeper analysis of natural processes at the basis of this global change and for developing sustainable technologies. Based on that, I-Wood proposes a new paradigm of virtual and physical robotic networks inspired by the belowground fungus-mediated inter-plant communication and by the associated collective behaviours. Specifically, I-Wood will study, extract and formalize the rules of plant-fungus interaction mechanisms to develop: a plant-inspired perceptron-like model; and a new generation of plant-inspired robots able to explore soil using their roots with growing, ageing, branching, and elongating abilities in response to their network-augmented perception and implementing plant-inspired collective behaviours. By imitating plants, these distributed intelligent systems will co-develop morphology and behaviour in a dynamic environment. Impact and feasibility of the proposed approach will be tested in a mixed social network, scale-down in a confined environment, where robots will interact with real plants to facilitate the development of mycorrhizal networks. Grounded on a strong multi-disciplinary approach, I-Wood will pave the way for new paradigms in robotics and embodied AI, based on solutions that overcome the current animal-based or brain-based model, novel approaches for the use of robotics in biology and for new scientific knowledge on plants community with a major significance for biodiversity and climate protection.
Champ scientifique
- natural sciencescomputer and information sciencesartificial intelligence
- natural sciencesbiological sciencesecologyecosystems
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringrobotics
- natural sciencesearth and related environmental sciencesatmospheric sciencesclimatologyclimatic changes
- agricultural sciencesagriculture, forestry, and fisheriesforestry
Mots‑clés
Programme(s)
Régime de financement
ERC-COG - Consolidator GrantInstitution d’accueil
16163 Genova
Italie