Join us

Research

Research areas for the Self-Driving Chemistry Laboratory.

Our Approach

Closing the Gap Between Computation and Experiment

Our research seeks to understand, design and control chemical systems by combining molecular simulation, artificial intelligence and autonomous experimentation.

We investigate chemistry across multiple scales. At the molecular and atomic levels, Catalyst Design and ReaxFF reveal how structure, interactions and reaction dynamics determine chemical behavior. These computational insights are complemented by Inverse Design by AI, which transforms desired properties and performance targets into promising molecular structures, materials and synthesis conditions.

The Self-Driving Laboratory connects these predictions with physical experiments through automated synthesis, characterization and data-driven decision-making. Experimental results can then be used to refine computational models and guide subsequent design.

Through this tight integration of theory, computation and experiment, we aim to establish predictive and iterative approaches to chemical discovery—moving from understanding how chemical systems behave toward designing how they should behave.

RESEARCH TOPIC 01

Self-Driving Laboratory

We develop autonomous experimental platforms that integrate robotic experimentation, real-time characterization and AI-driven decision-making in a closed loop. These systems are designed to plan, execute and evaluate experiments with minimal human intervention.

By connecting synthesis, measurement and optimization, our platforms can efficiently explore complex chemical and materials spaces, identify promising conditions and continuously refine experimental strategies while maintaining traceability and reproducibility.

AutomationRoboticsOrchestration SystemAI
View research →
RESEARCH TOPIC 02

Inverse Design by AI

Inverse design identifies material structures from target properties. We use AI to model relationships between high-dimensional properties (e.g., DOS) and structures, enabling efficient exploration of materials space beyond traditional screening.

We also extend inverse design to synthesis routes and processing conditions for practical realization.

Generative AITarget-Driven DesignMaterials InformaticsSynthesis Design
View research →
RESEARCH TOPIC 03

Catalyst Design

We design catalysts using multiscale simulations that connect atomic-scale interactions with catalytic performance.

DFT calculations and molecular dynamics reveal reaction mechanisms and interfacial phenomena, while computational screening identifies promising catalysts for sustainable energy and chemical processes.

CatalysisDFTReaction MechanismsComputational Screening
View research →
RESEARCH TOPIC 04

ReaxFF

ReaxFF enables reactive molecular dynamics simulations of bond formation and dissociation at larger spatial and longer temporal scales than direct quantum-mechanical methods.

We use this approach to investigate structural evolution and reaction mechanisms in catalytic and chemical processes.

Reactive Force FieldMolecular DynamicsReaction MechanismsAtomistic Simulation
View research →
Collaboration

We welcome collaborators

We welcome academic and industry partnerships that combine complementary expertise, data or experimental capabilities. Contact us to discuss shared scientific questions and potential projects.

Contact us