Oliver Schön · Postdoc @ ETH Zürich

Towards Trustworthy
Physical AI

My research focuses on the development of algorithms that let autonomous systems cross from simulation into the real world with guarantees.

» As new legislation tightens the screws on AI in high-risk applications, we need tools that can provably certify that an AI-powered system is safe and trustworthy when deployed in the real world.

01 — Research

Research directions

A few of the research threads I'm interested in.

/01

Bridging sim-to-real

A probabilistic simulation framework so controllers proven safe in simulation transfer to the real world with quantified guarantees.

/02

Formal verification

Certifying black-box stochastic and learning-enabled systems from finite data — quantified safety where classical tools break down.

/03

Data-driven abstractions

Scalable abstractions of uncertain stochastic systems — like binary-tree Gaussian processes — built for efficient model checking.

02 — Projects

Selected projects

Each is a research line spanning several papers, tools, and collaborations.

Learning-enabled certification

LUCID

The first tool to establish quantified safety guarantees for black-box stochastic systems from a finite dataset of transitions.

4  papers · AAAI · JAIR · ACC
Controller synthesis

SySCoRe

Correct-by-design control for uncertain stochastic systems — infinite-horizon specs, non-Gaussian noise, tensor-scaled synthesis.

5+  papers · HSCC · CDC · TAC
Scalable abstraction

Binary-Tree Gaussian Processes

Data-driven abstractions that naturally partition the state space, simplifying error quantification for formal verification.

2  papers · IFAC ADHS
Multi-objective reasoning

Robust Multi-Objective Reasoning

Balancing competing objectives under uncertainty — from multi-objective physics-guided models of dynamical systems to spatiotemporal robustness of temporal-logic tasks.

2+  papers · CAV · IFAC ALCOS
03 — Contact

Let's build
trustworthy autonomy.

oschoen@ethz.ch

Open to collaborations, talks, and questions on formal verification, safe control, and learning-enabled systems.