Verifiable and Safe AI for Autonomous Systems

Project: Research

Project Details

Description

The rapidly growing application of machine learning techniques in cyber-physical systems leads to better solutions and products in terms of adaptability, performance, efficiency, functionality and usability.
However, cyber-physical systems are often safety critical, e.g., self-driving cars or medical devices, and the need for verification against potentially fatal accidents is of key importance.
Together with industrial partners, this project aims to develop methods and tools that will enable industry to automatically synthesize correct-by-construction and near-optimal controllers for safety critical systems within a variety of domains.
Short titleDIREC P7
AcronymDIREC
StatusActive
Effective start/end date01/03/202130/09/2025

Collaborative partners

  • IT University of Copenhagen
  • Aalborg University (Project partner) (lead)
  • Grundfos (Project partner)
  • Aarhus Vand (Project partner)
  • Seluxit (Project partner)
  • Hofor (Project partner)

Funding

  • IFD - Innovation Fund Denmark: DKK3,729,054.00

Keywords

  • Verifiable AI
  • Safety
  • Reinforcement learning
  • Urban water management

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.