Rigorous Safety and Reliability in Autonomous Systems via Formal Verification and Data-Driven Control
Explore how to develop mathematically rigorous methods ensuring safety and reliability in autonomous systems by integrating control theory, formal verification, and probabilistic approaches. Ideal for candidates eager to work across disciplines to tackle foundational challenges in trustworthy AI.
AI-generated overview
Project Description
Project Overview
This project focuses on the intersection of control theory, formal verification, probability, and data-driven methods to develop rigorous and principled approaches to ensuring safety and reliability in autonomous systems. The goal is to create theoretical foundations and practical techniques that provide robust guarantees for autonomous system behavior under uncertainty.
What You Will Do
You will undertake research building on and expanding formal methods and stochastic control, applying data-driven and probabilistic techniques to model and verify autonomous systems. You will explore how to integrate these methods for improved safety assurances, working across disciplinary boundaries in mathematics, computer science, and engineering.
Expected Outcomes
The expected outcomes include theoretical advances in formal synthesis and verification of stochastic systems, new algorithms for abstraction and control with safety guarantees, and practical frameworks applicable to autonomous systems. These will offer novel ways to handle uncertainty in cyber-physical and autonomous environments.
Why This Matters
Autonomous systems are increasingly deployed in safety-critical domains. Ensuring their reliability amidst uncertain and dynamic environments is vital for public trust and technological progress. This research addresses foundational challenges to create trustworthy autonomous technologies that meet stringent safety standards.
Entry Requirements
How to Apply
Eligibility
Supervisor Profile
Prof. Sadegh Soudjani is Chair in Cyber-Physical Systems at the University of Birmingham and associated with the Max Planck Institute. His research spans control theory, formal methods, model checking, and quantum verification, focusing on rigorous synthesis and verification of stochastic and hybrid systems. He is a leading figure known for pioneering approaches in formal abstractions and safety guarantees for complex stochastic systems.