brianletort.ai
← Library

University of Liverpool

Verified evidenceAutonomous + backstop

Mobile robotic chemist with Bayesian experiment selection

A robot can automate researcher-facing lab work when search and safety are bounded.

Engineering design · United Kingdom

An editorial scene for University of Liverpool contrasts chooses formulations, prepares samples, operates instruments, records results, and decides the next experiment. with selects the next batch from prior measured outcomes. in the mobile robotic chemist with bayesian experiment selection workflow.

Executive brief

The operating-model shift, in one view.

The operating-model hinge is linking experiment choice, physical execution, measurement, and fault handling.

AI value · Autonomous search

Verified

688 experiments in eight days; best mixture six times more active

Laboratory proof of concept, not a production deployment; 11 results were discarded.

Before

Chooses formulations, prepares samples, operates instruments, records results, and decides the next experiment. → Interprets results and updates the experimental plan.

After

Selects the next batch from prior measured outcomes. → Navigates the lab, dispenses materials, runs photolysis and chromatography, and returns measurements.

Human boundary

Researchers set the problem and safety envelope; the system selects and executes experiments within it.

Why it matters

A robot can automate researcher-facing lab work when search and safety are bounded.

How the work changed

Before

How the work ran before the change.

  1. Step 1 of 2

    Human chemist

    Chooses formulations, prepares samples, operates instruments, records results, and decides the next experiment.

    ControlLaboratory safety and researcher judgment; authors describe manual search as constrained but provide no measured manual baseline.

  2. Step 2 of 2

    Human researcher

    Interprets results and updates the experimental plan.

    ControlManual trial-and-error across a ten-variable space.

What changed

A robot can automate researcher-facing lab work when search and safety are bounded.

Decision rightAI acts within a human backstop

After

How the same work runs now.

  1. Step 1 of 2

    Batched Bayesian search algorithm

    Selects the next batch from prior measured outcomes.

    ControlTen-variable bounded search; oxygen and workflow checks discard faulty results.

  2. Step 2 of 2

    Mobile robot

    Navigates the lab, dispenses materials, runs photolysis and chromatography, and returns measurements.

    ControlCollaborative-robot safety standards; 11 results discarded for workflow errors or high oxygen.

Process model built from the published workflow evidence for University of Liverpool. Every step, actor, and control appears in full below.
Every step, actor, and control

Exception path

Faulty seals, high oxygen, workflow errors, or hardware issues are flagged/discarded for human attention.

Work removed

  • Repetitive sample handling
  • Manual instrument transfers
  • Manual next-experiment scheduling

Decision authority

Researchers set the problem and safety envelope; the system selects and executes experiments within it.

Before

  1. 01

    Human chemist

    Chooses formulations, prepares samples, operates instruments, records results, and decides the next experiment.

    Control: Laboratory safety and researcher judgment; authors describe manual search as constrained but provide no measured manual baseline.

  2. 02

    Human researcher

    Interprets results and updates the experimental plan.

    Control: Manual trial-and-error across a ten-variable space.

After

  1. 01

    Batched Bayesian search algorithm

    Selects the next batch from prior measured outcomes.

    Control: Ten-variable bounded search; oxygen and workflow checks discard faulty results.

  2. 02

    Mobile robot

    Navigates the lab, dispenses materials, runs photolysis and chromatography, and returns measurements.

    Control: Collaborative-robot safety standards; 11 results discarded for workflow errors or high oxygen.

Work that left the path

  • Repetitive sample handling
  • Manual instrument transfers
  • Manual next-experiment scheduling

Human role before

Researchers perform repetitive preparation, movement, analysis, and next-experiment selection.

Human role after

Researchers define the objective and supervise a robot that executes and searches continuously.

AI roleSelects experiment batches and controls a mobile robot across laboratory stations.

Outcomes

Autonomous search

Verified

Initial catalyst formulations688 experiments in eight days; best mixture six times more active

172 operating hours across eight days · Ten-variable photocatalyst search; 319 moves and 6,500 manipulations

Laboratory proof of concept, not a production deployment; 11 results were discarded.

What leaders can reuse

Anti-pattern

Do not generalize one autonomous experiment to unsupervised general chemistry.

Questions

  1. 01Where is the operating threshold set and who can override it?
  2. 02What measured result would trigger rollback or retraining?
  3. 03Which residual decisions must remain human-owned?

Portability conditions

  • Machine-readable objective
  • Instrument interfaces
  • Lab safety
  • Fault detection

Reputation risk

high

Evidence and authority

What the public record supports.

Current · updated

1 peer reviewed, 1 primary; publication outcomes are verified.

Bundle 1.0.0 · reviewed 2026-08-23 · stable ID 535dcf1aea9a1411

Related transformations

More in Engineering design

Sources

Read the evidence, freshness, caveat, and version policy.