Multi-stage Bayesian optimisation for dynamic decision-making in self-driving labs

2025-12-17

AI Summary

Bayesian optimization (BO) in self-driving laboratories (SDLs) struggles to adapt to dynamic, multi-stage experimental workflows due to its reliance on fixed protocols and terminal-only observations. Method: This paper introduces the first multi-stage BO framework, explicitly incorporating intermediate surrogate measurements into Gaussian process modeling and uncertainty-aware acquisition function design. It integrates multi-fidelity surrogate modeling with sequential decision theory to enable real-time path adaptation and sequential decision-making under asynchronous, variable-length experimental processes. Contribution/Results: Across diverse experimental domains, the framework reduces time-to-optimal-solution by 2.3× on average, improves objective values by 17–41%, and enables closed-loop coupling between simulation and physical experimentation—thereby overcoming key limitations of conventional BO in SDLs.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Self-driving laboratories (SDLs) are combining recent technological advances in robotics, automation, and machine learning based data analysis and decision-making to perform autonomous experimentation toward human-directed goals without requiring any direct human intervention. SDLs are successfully used in materials science, chemistry, and beyond, to optimise processes, materials, and devices in a systematic and data-efficient way. At present, the most widely used algorithm to identify the most informative next experiment is Bayesian optimisation. While relatively simple to apply to a wide range of optimisation problems, standard Bayesian optimisation relies on a fixed experimental workflow with a clear set of optimisation parameters and one or more measurable objective functions. This excludes the possibility of making on-the-fly decisions about changes in the planned sequence of operations and including intermediate measurements in the decision-making process. Therefore, many real-world experiments need to be adapted and simplified to be converted to the common setting in self-driving labs. In this paper, we introduce an extension to Bayesian optimisation that allows flexible sampling of multi-stage workflows and makes optimal decisions based on intermediate observables, which we call proxy measurements. We systematically compare the advantage of taking into account proxy measurements over conventional Bayesian optimisation, in which only the final measurement is observed. We find that over a wide range of scenarios, proxy measurements yield a substantial improvement, both in the time to find good solutions and in the overall optimality of found solutions. This not only paves the way to use more complex and thus more realistic experimental workflows in autonomous labs but also to smoothly combine simulations and experiments in the next generation of SDLs.

Problem

• Extends Bayesian optimization for multi-stage workflows in self-driving labs
• Enables on-the-fly decisions using intermediate proxy measurements
• Improves solution speed and optimality over conventional fixed workflows

Innovation

• Multi-stage Bayesian optimization for dynamic decision-making
• Flexible sampling using proxy measurements in workflows
• Improves solution optimality and time efficiency