SafeDeep: Dependable Deep Learning for Safety-Critical Airborne Embedded Systems

Status:

active

Start date:

2019-09-01

End date:

2022-12-31

Deep neural networks (DNNs) have shown to be very successful in several areas, e.g. for object detection in autonomous cars. DNNs may also be successful in airborne systems. One such possible application is guided landing. The enabling of safe landing in adverse weather conditions without full ground support from the instrument landing system, decreases aerospace greenhouse gas emissions as multiple landing attempts and aerospace congestion are mitigated. To land autonomously without support from ground infrastructure requires advanced airborne systems including algorithms for detecting the runway. These systems are safety-critical. 

This project addresses design methods for the use of DNNs in airborne safety-critical systems. DNNs cannot rely on traditional design assurance techniques described in documents from certification authorities or standardization bodies. In this project, the research focus is on mitigation techniques for design errors in both hardware and software and for adversarial effects which can lead to system failures. The expected results are design methodologies and fault tolerant architectures for airborne safety-critical applications using neural networks.

[Show all publications]

A software implemented comprehensive soft error detection method for embedded systems (Sep 2020)
Seyyed Amir Asghari , Mohammadreza Binesh Marvasti , Masoud Daneshtalab
Elsevier journal of Microprocessors and Microsystems (MICPRO)

NOM: Network-On-Memory for Inter-Bank Data Transfer in Highly-Banked Memories (May 2020)
Seyyed Hossein Seyyedaghaei Rezaei , Mehdi Modarressi, Rachata Ausavarungnirun , Mohammad Sadrosadati , Onur Mutlu , Masoud Daneshtalab
IEEE Computer Architecture Letters (CAL)

Computation reuse-aware accelerator for neural networks (May 2020)
Hoda Mahdiani , Alireza Khadem , Ali Yasoubi , Azam Ghanbari , Mehdi Modarressi, Masoud Daneshtalab
Institution of Engineering and Technology (IET)

Hardware Acceleration for Recurrent Neural Networks (May 2020)
Sima Sinaei, Masoud Daneshtalab
Institution of Engineering and Technology (IET)

Feedforward Neural Networks on Massively Parallel Architectures (May 2020)
Reza Hojabr , Ahmad Khonsari , Mehdi Modarressi, Masoud Daneshtalab
Institution of Engineering and Technology (IET)

Hardware Accelerators for Deep Learning (May 2020)
Masoud Daneshtalab, Mehdi Modarressi
Institution of Engineering and Technology (IET)

PartnerType
Saab AB, Avionics Systems Industrial

Håkan Forsberg, Senior Lecturer

Room: U1-081
Phone: +46-21-101381