Self-driving laboratory platform for many-objective self-optimisation of polymer nanoparticle synthesis with cloud-integrated machine learning and orthogonal online analytics
Stephen T. Knox, Kai E. Wu, Nazrul Islam, Róisín A. O’Connell, Peter M. Pittaway, Kudakwashe E. Chingono, John Oluwagbemiga Oyekan, George Panoutsos, Thomas W. Chamberlain, Richard A. Bourne, Nicholas J. Warren · Polymer Chemistry · 2025
simulations using a range of algorithms - Thompson sampling efficient multi-objective optimisation (TSEMO), radial basis function neural network/reference vector evolutionary algorithm (RBFNN/RVEA) and multi objective particle swarm optimisation, hybridised with an evolutionary algorithm (EA-MOPSO), which were then applied to in-lab optimisations. This approach accounts for an unprecedented number of objectives for closed-loop optimisation of a synthetic polymerisation; and enabled the use of algorithms operated from different geographical locations to the reactor platform.