Dependable AI in Safe Autonomous Systems

Status:

active

Start date:

2022-01-01

End date:

2026-01-01

Data-driven development methods show great promise in producing accurate models for perception functions such as object detection and semantic segmentation, however, most of them lack a holistic view for being implemented in dependable systems. This project proposal aims at producing Machine Learning (ML) models of robust nature to meet and stay ahead of emerging certification requirements. A large part of the accuracy and robustness of a trained model is due to the data it was trained on, yet most research today focuses on model architecture development. It is the intention of this project to emphasize the dataset side of the problem, including novel methods of data augmentation e.g. neural augmentation. The expected outputs of the project would be to set the basis of a safety-conscious ML system and provide the methodology to iterate and refine such systems.

[Show all publications]

Evaluating the robustness of ML models to out-of-distribution data through similarity analysis (Sep 2023)
Joakim Lindén, Håkan Forsberg, Ingemar Söderquist , Masoud Daneshtalab
1st Workshop on Advanced AI Techniques for Data Management and Analytics (AIDMA)

Curating Datasets for Visual Runway Detection (Oct 2021)
Joakim Lindén, Håkan Forsberg, Josef Haddad , Emil Tagebrand , Erasmus Cedernaes , Emil Gustafsson Ek , Masoud Daneshtalab
The 40th Digital Avionics Systems Conference (DASC'2021)

PartnerType
Saab Industrial

Masoud Daneshtalab, Professor

Email: masoud.daneshtalab@mdh.se
Room:
Phone: +4621103111