WORKSHOP
“Autonomous Experimentation and Self-Driving Laboratories”
We bring together leading academic scientists and researchers!
November 27th, 2026 1pm - 5pm
Scope of the event
The convergence of Bayesian optimisation, robotic automation, and real-time machine learning analysis has produced a new class of experimental platform: the self-driving laboratory, which closes the loop between measurement and experimental design without human intervention. These systems promise to accelerate dis- covery by orders of magnitude, but their effective deployment requires careful integration of domain knowledge, uncertainty quantification, and experimental infrastructure.
This workshop examines the conceptual and practical foundations of autonomous experimentation, developing the design–measure–learn–decide cycle that underpins all closed-loop systems. Bayesian optimisation, intro- duced in Workshop 4, is revisited here as the decision engine that selects the next experiment based on surro- gate model predictions and uncertainty estimates. Multi-fidelity strategies that combine cheap computational models with expensive experimental measurements are examined as a route to efficient resource allocation.
The session reviews notable implementations in chemistry and materials science, including photocatalyst dis- covery campaigns, flow chemistry optimisation, and the self-driving laboratory platforms developed by the Aspuru-Guzik group and collaborators. The landmark closed-loop optimisation of battery fast-charging proto- cols provides an electrochemical case study of particular relevance. The workshop also addresses the practical challenges of infrastructure integration, data standards, reproducibility, and the respective roles of human-in- the-loop and fully autonomous approaches.
Extended Key Takeaways & Outputs
• Understanding of the closed-loop design–measure–learn–decide cycle
• Practical knowledge of Bayesian optimisation as a decision engine for experimental design
• Assessment of multi-fidelity strategies for combining computation and experiment
• Case studies from photocatalysis, flow chemistry, battery optimisation, and self-driving labs
• Guidance on infrastructure, data standards, and the role of human oversight
Agenda & Speakers
13:00–13:05 — Introduction & Objectives
Organizer
· From traditional experimentation to autonomous discovery systems
· The design–measure–learn–decide paradigm
· Workshop objectives: integrating AI, robotics, and scientific reasoning
13:05–13:35 — Foundations of Autonomous Experimentation
Speaker (Academia): N.N.
· Closed-loop experimentation and self-driving laboratory concepts
· Integration of machine learning with robotic platforms
· Role of domain knowledge in guiding automation
13:35–14:05 — Bayesian Optimisation as a Decision Engine
Speaker (Academia): N.N.
· Surrogate models and acquisition functions
· Exploration–exploitation trade-off in experimental design
· Applications to materials and chemical optimisation
14:05–14:35 — Multi-Fidelity and Hybrid Experimentation Strategies
Speaker (Academia): N.N.
· Combining simulations with experimental data
· Efficient allocation of experimental resources
· Hierarchical modelling approaches
14:35–14:45 — Break
14:45–15:15 — Industrial Deployment of Self-Driving Laboratories
Speaker (Industry): N.N.
· Autonomous experimentation platforms in real-world settings
· Integration with digital infrastructure and lab automation
· Scaling challenges and industrial use cases
15:15–15:45 — Case Studies: Chemistry, Materials, and Electrochemical Systems
Speaker (Industry): N.N.
· Photocatalyst discovery and reaction optimisation
· Flow chemistry and battery fast-charging optimisation
· Lessons learned from closed-loop experimental campaigns
15:45–16:15 — Infrastructure, Data Standards, and Human Oversight
Speaker (Policy/Applied Research): Representative, National Institute of Standards and Technology
· Data interoperability and reproducibility in autonomous labs
· Standards for experimental automation and AI integration
· Human-in-the-loop vs fully autonomous decision-making
16:15–16:55 — Panel Discussion & Strategic Alignment
All Speakers + Moderator
· How close are we to fully autonomous scientific discovery?
· Balancing automation with expert intuition and oversight
· Investment priorities: infrastructure vs algorithms
· Future outlook: scaling self-driving laboratories across disciplines
Concluding remarks
Registration
Deadlines:
Early-Bird: until July 15th, 2026
Registration : until September 5th, 2026
The registration takes place online by filling out the form.
The registration and access to the virtual room for workshop is effective only if the fees payment has been confirmed.
Please note that INVIRTA MEMBERS can purchase all our workshops and services with 10% discount . If you desire to get more information on our membership please press here .
Prices* :
Industry: 150 € (early bird**: 125 €)
Academy: 125 € (early bird**: 100 €)
Students***: 90 € (early bird**: 75 €)
* Note that prices are subject to VAT (for European countries, except Germany, provide the VAT number of your organisation to be within the VAT reverse framework payment).
** Until November 15th, 2020
*** Copy of the registration certificate (Ph.D, undergraduates)
Special price offers for Workshop packages
Our Workshop packages are valid for any workshops offered by our academy and can be used anytime. If you want to use one of our packages press here.
