Technologies such as batteries, biomaterials and heterogeneous catalysts have functions that are defined by mixtures of molecular and mesoscale components. As yet, this multi-length-scale complexity cannot be fully captured by atomistic simulations, and the design of such materials from first principles is still rare1,2,3,4,5. Likewise, experimental complexity scales exponentially with the number of variables, restricting most searches to narrow areas of materials space. Robots can assist in experimental searches6,7,8,9,10,11,12,13,14 but their widespread adoption in materials research is challenging because of the diversity of sample types, operations, instruments and measurements required. Here we use a mobile robot to search for improved photocatalysts for hydrogen production from water15. The robot operated autonomously over eight days, performing 688 experiments within a ten-variable experimental space, driven by a batched Bayesian search algorithm16,17,18. This autonomous search identified photocatalyst mixtures that were six times more active than the initial formulations, selecting beneficial components and deselecting negative ones. Our strategy uses a dexterous19,20 free-roaming robot21,22,23,24, automating the researcher rather than the instruments. This modular approach could be deployed in conventional laboratories for a range of research problems beyond photocatalysis.
The implementation of the liquid-dispensing station, photolysis station and the workflow, along with three-dimensional designs for labware developed in the project, are available at https://bitbucket.org/ben_burger/kuka_workflow, the code for the robot at and the Bayesian optimizer is available at https://github.com/Taurnist/kuka_workflow_tantalus and https://github.com/CooperComputationalCaucus/kuka_optimizer. Additional design details can be obtained from the authors upon request.
Kang, K., Meng, Y. S., Bréger, J., Grey, C. P. & Ceder, G. Electrodes with high power and high capacity for rechargeable lithium batteries. Science 311, 977–980 (2006).
Woodley, S. M. & Catlow, R. Crystal structure prediction from first principles. Nat. Mater. 7, 937–946 (2008).
Gómez-Bombarelli, R. et al. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach. Nat. Mater. 15, 1120–1127 (2016).
Collins, C. et al. Accelerated discovery of two crystal structure types in a complex inorganic phase field. Nature 546, 280–284 (2017).
Davies, D. W. et al. Computer-aided design of metal chalcohalide semiconductors: from chemical composition to crystal structure. Chem. Sci. 9, 1022–1030 (2018).
King, R. D. Rise of the robo scientists. Sci. Am. 304, 72–77 (2011).
Li, J. et al. Synthesis of many different types of organic small molecules using one automated process. Science 347, 1221–1226 (2015).
Dragone, V., Sans, V., Henson, A. B., Granda, J. M. & Cronin, L. An autonomous organic reaction search engine for chemical reactivity. Nat. Commun. 8, 15733 (2017).
Bédard, A.-C. et al. Reconfigurable system for automated optimization of diverse chemical reactions. Science 361, 1220–1225 (2018).
Granda, J. M., Donina, L., Dragone, V., Long, D.-L. & Cronin, L. Controlling an organic synthesis robot with machine learning to search for new reactivity. Nature 559, 377–381 (2018).
Tabor, D. P. et al. Accelerating the discovery of materials for clean energy in the era of smart automation. Nat. Rev. Mater. 3, 5–20 (2018).
Langner, S. et al. Beyond ternary OPV: high-throughput experimentation and self-driving laboratories optimize multi-component systems. Preprint at https://arxiv.org/abs/1909.03511 (2019).
MacLeod, B. P. et al. Self-driving laboratory for accelerated discovery of thin-film materials. Preprint at https://arxiv.org/abs/1906.05398 (2019).
Steiner, S. et al. Organic synthesis in a modular robotic system driven by a chemical programming language. Science 363, eaav2211 (2019).
Wang, Z., Li, C. & Domen, K. Recent developments in heterogeneous photocatalysts for solar-driven overall water splitting. Chem. Soc. Rev. 48, 2109–2125 (2019).
Shahriari, B., Swersky, K., Wang, Z., Adams, R. P. & Freitas, N. D. Taking the human out of the loop: a review of Bayesian optimization. Proc. IEEE 104, 148–175 (2016).
Häse, F., Roch, L. M., Kreisbeck, C. & Aspuru-Guzik, A. Phoenics: a Bayesian optimizer for chemistry. ACS Cent. Sci. 4, 1134–1145 (2018).
Roch, L. M. et al. ChemOS: orchestrating autonomous experimentation. Sci. Robot. 3, eaat5559 (2018).
Chen, C.-L., Chen, T.-R., Chiu, S.-H. & Urban, P. L. Dual robotic arm “production line” mass spectrometry assay guided by multiple Arduino-type microcontrollers. Sens. Actuat. B 239, 608–616 (2017).
Fleischer, H. et al. Analytical measurements and efficient process generation using a dual-arm robot equipped with electronic pipettes. Energies 11, 2567 (2018).
Liu, H., Stoll, N., Junginger, S. & Thurow, K. Mobile robot for life science automation. Int. J. Adv. Robot. Syst. 10, 288 (2013).
Liu, H., Stoll, N., Junginger, S. & Thurow, K. A fast approach to arm blind grasping and placing for mobile robot transportation in laboratories. Int. J. Adv. Robot. Syst. 11, 43 (2014).
Abdulla, A. A., Liu, H., Stoll, N. & Thurow, K. A new robust method for mobile robot multifloor navigation in distributed life science laboratories. J. Contrib. Sci. Eng. 2016, 3589395 (2016).
Dömel, A. et al. Toward fully autonomous mobile manipulation for industrial environments. Int. J. Adv. Robot. Syst. 14, https://doi.org/10.1177/1729881417718588 (2017).
Schweidtmann, A. M. et al. Machine learning meets continuous flow chemistry: automated optimization towards the Pareto front of multiple objectives. Chem. Eng. J. 352, 277–282 (2018).
Zhi, L. et al. Robot-accelerated perovskite investigation and discovery (RAPID): 1. Inverse temperature crystallization. Preprint at https://doi.org/10.26434/chemrxiv.10013090.v1 (2019).
Matsuoka, S. et al. Photocatalysis of oligo (p-phenylenes): photoreductive production of hydrogen and ethanol in aqueous triethylamine. J. Phys. Chem. 95, 5802–5808 (1991).
Shu, G., Li, Y., Wang, Z., Jiang, J.-X. & Wang, F. Poly(dibenzothiophene-S,S-dioxide) with visible light-induced hydrogen evolution rate up to 44.2 mmol h−1 g−1 promoted by K2HPO4. Appl. Catal. B 261, 118230 (2020).
Pellegrin, Y. & Odobel, F. Sacrificial electron donor reagents for solar fuel production. C. R. Chim. 20, 283–295 (2017).
Sakimoto, K. K., Zhang, S. J. & Yang, P. Cysteine–cystine photoregeneration for oxygenic photosynthesis of acetic acid from CO2 by a tandem inorganic–biological hybrid system. Nano Lett. 16, 5883–5887 (2016).
Wang, X. et al. Sulfone-containing covalent organic frameworks for photocatalytic hydrogen evolution from water. Nat. Chem. 10, 1180–1189 (2018).
Real Life. Real News. Real Voices
Help us tell more of the stories that matterBecome a founding member
Schwarze, M. et al. Quantification of photocatalytic hydrogen evolution. Phys. Chem. Chem. Phys. 15, 3466–3472 (2013).
Bai, Y. et al. Accelerated discovery of organic polymer photocatalysts for hydrogen evolution from water through the integration of experiment and theory. J. Am. Chem. Soc. 141, 9063–9071 (2019).
Zhang, J. et al. H-bonding effect of oxyanions enhanced photocatalytic degradation of sulfonamides by g-C3N4 in aqueous solution. J. Hazard. Mater. 366, 259–267 (2019).
Hutter, F., Hoos, H. H. & Leyton-Brown, K. Parallel Algorithm Configuration 55–70 (Springer, 2012).
Mynatt, C. R., Doherty, M. E. & Tweney, R. D. Confirmation bias in a simulated research environment: an experimental study of scientific inference. Q. J. Exp. Psychol. 29, 85–95 (1977).
King, R. D. et al. Functional genomic hypothesis generation and experimentation by a robot scientist. Nature 427, 247–252 (2004).
Pulido, A. et al. Functional materials discovery using energy–structure–function maps. Nature 543, 657–664 (2017).
Campbell, J. E., Yang, J. & Day, G. M. Predicted energy–structure–function maps for the evaluation of small molecule organic semiconductors. J. Mater. Chem. C 5, 7574–7584 (2017).
Fuentes-Pacheco, J., Ruiz-Ascencio, J. & Rendón-Mancha, J. M. Visual simultaneous localization and mapping: a survey. Artif. Intell. Rev. 43, 55–81 (2015).
Rasmussen, C. E. & Williams, C. K. I. Gaussian Processes for Machine Learning (MIT Press, 2006).
Matthews, A. G. G., Rowland, M., Hron, J., Turner, R. E. & Ghahramani, Z. Gaussian process behaviour in wide deep neural networks. Preprint at https://arxiv.org/abs/1804.11271 (2018).
Millman, K. J. & Aivazis, M. Python for scientists and engineers. Comput. Sci. Eng. 13, 9–12 (2011).
Sachs, M. et al. Understanding structure-activity relationships in linear polymer photocatalysts for hydrogen evolution. Nat. Commun. 9, 4968 (2018).
We acknowledge financial support from the Leverhulme Trust via the Leverhulme Research Centre for Functional Materials Design, the Engineering and Physical Sciences Research Council (EPSRC) (grant number EP/N004884/1), the Newton Fund (grant number EP/R003580/1), and CSols Ltd. X.W. and Y.B. thank the China Scholarship Council for a PhD studentship. We thank KUKA Robotics for help with gripper design and the initial implementation of the robot.